Datasets
Models
Downloads: 1
3444 lines (3443 with data), 146.4 kB
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Same as feature_engineering in /notebooks folder"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {},
"outputs": [],
"source": [
"import pandas as pd\n",
"import warnings\n",
"warnings.filterwarnings('ignore')\n"
]
},
{
"cell_type": "code",
"execution_count": 4,
"metadata": {},
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th></th>\n",
" <th>label</th>\n",
" <th>scc</th>\n",
" <th>race</th>\n",
" <th>marital</th>\n",
" <th>ethnic</th>\n",
" <th>gender</th>\n",
" <th>state</th>\n",
" <th>age</th>\n",
" <th>Pain severity - 0-10 verbal numeric rating [Score] - Reported</th>\n",
" <th>Influenza seasonal injectable preservative free</th>\n",
" <th>...</th>\n",
" <th>Parainfluenza virus 1 RNA [Presence] in Respiratory specimen by NAA with probe detection</th>\n",
" <th>Influenza virus B RNA [Presence] in Respiratory specimen by NAA with probe detection</th>\n",
" <th>Influenza virus A RNA [Presence] in Respiratory specimen by NAA with probe detection</th>\n",
" <th>Adenovirus A+B+C+D+E DNA [Presence] in Respiratory specimen by NAA with probe detection</th>\n",
" <th>SARS-CoV-2 RNA Pnl Resp NAA+probe</th>\n",
" <th>Hydroxychloroquine Sulfate 200 MG Oral Tablet</th>\n",
" <th>1 ML denosumab 60 MG/ML Prefilled Syringe</th>\n",
" <th>Fexofenadine hydrochloride 60 MG Oral Tablet</th>\n",
" <th>Leronlimab 700 MG Injection</th>\n",
" <th>Lenzilumab 200 MG IV</th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>0</td>\n",
" <td>113</td>\n",
" <td>white</td>\n",
" <td>m</td>\n",
" <td>hispanic</td>\n",
" <td>m</td>\n",
" <td>massachusetts</td>\n",
" <td>50t70</td>\n",
" <td>abnormal</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>1</th>\n",
" <td>0</td>\n",
" <td>100</td>\n",
" <td>white</td>\n",
" <td>s</td>\n",
" <td>nonhispanic</td>\n",
" <td>f</td>\n",
" <td>massachusetts</td>\n",
" <td>50t70</td>\n",
" <td>abnormal</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>2</th>\n",
" <td>0</td>\n",
" <td>106</td>\n",
" <td>other</td>\n",
" <td>m</td>\n",
" <td>nonhispanic</td>\n",
" <td>f</td>\n",
" <td>massachusetts</td>\n",
" <td>30t50</td>\n",
" <td>normal</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>3</th>\n",
" <td>1</td>\n",
" <td>74</td>\n",
" <td>hawaiian</td>\n",
" <td>m</td>\n",
" <td>nonhispanic</td>\n",
" <td>m</td>\n",
" <td>massachusetts</td>\n",
" <td>gt70</td>\n",
" <td>abnormal</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" <tr>\n",
" <th>4</th>\n",
" <td>0</td>\n",
" <td>112</td>\n",
" <td>white</td>\n",
" <td>m</td>\n",
" <td>nonhispanic</td>\n",
" <td>f</td>\n",
" <td>massachusetts</td>\n",
" <td>50t70</td>\n",
" <td>abnormal</td>\n",
" <td>True</td>\n",
" <td>...</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" <td>NaN</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"<p>5 rows × 783 columns</p>\n",
"</div>"
],
"text/plain": [
" label scc race marital ethnic gender state age \\\n",
"0 0 113 white m hispanic m massachusetts 50t70 \n",
"1 0 100 white s nonhispanic f massachusetts 50t70 \n",
"2 0 106 other m nonhispanic f massachusetts 30t50 \n",
"3 1 74 hawaiian m nonhispanic m massachusetts gt70 \n",
"4 0 112 white m nonhispanic f massachusetts 50t70 \n",
"\n",
" Pain severity - 0-10 verbal numeric rating [Score] - Reported \\\n",
"0 abnormal \n",
"1 abnormal \n",
"2 normal \n",
"3 abnormal \n",
"4 abnormal \n",
"\n",
" Influenza seasonal injectable preservative free ... \\\n",
"0 True ... \n",
"1 True ... \n",
"2 True ... \n",
"3 True ... \n",
"4 True ... \n",
"\n",
" Parainfluenza virus 1 RNA [Presence] in Respiratory specimen by NAA with probe detection \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" Influenza virus B RNA [Presence] in Respiratory specimen by NAA with probe detection \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" Influenza virus A RNA [Presence] in Respiratory specimen by NAA with probe detection \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" Adenovirus A+B+C+D+E DNA [Presence] in Respiratory specimen by NAA with probe detection \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" SARS-CoV-2 RNA Pnl Resp NAA+probe \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" Hydroxychloroquine Sulfate 200 MG Oral Tablet \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" 1 ML denosumab 60 MG/ML Prefilled Syringe \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
" Fexofenadine hydrochloride 60 MG Oral Tablet Leronlimab 700 MG Injection \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"\n",
" Lenzilumab 200 MG IV \n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 NaN \n",
"4 NaN \n",
"\n",
"[5 rows x 783 columns]"
]
},
"execution_count": 4,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df = pd.read_csv('../validation_data/validation_data.csv')\n",
"df = df.drop('ptnum', axis=1)\n",
"df.drop(columns=['C-20565-8'], inplace=True)\n",
"df_codes = pd.read_csv('../data/codes.csv')\n",
"code_to_name = df_codes.set_index('code')['name'].to_dict()\n",
"df = df.rename(columns=code_to_name)\n",
"df2 = df.copy()\n",
"df.head()"
]
},
{
"cell_type": "code",
"execution_count": 5,
"metadata": {},
"outputs": [],
"source": [
"X = pd.read_csv('../transformed_data/X_train.csv')\n",
"train_cols = X.columns.to_list()"
]
},
{
"cell_type": "code",
"execution_count": 6,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"\n",
"DataFrame after combining columns with the same name:\n",
" Mammography (procedure) Amputation of right leg \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 True NaN \n",
"... ... ... \n",
"3874 NaN NaN \n",
"3875 NaN NaN \n",
"3876 True NaN \n",
"3877 NaN NaN \n",
"3878 NaN NaN \n",
"\n",
" History of amputation of foot (situation) Vasectomy \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"3874 NaN NaN \n",
"3875 NaN NaN \n",
"3876 NaN NaN \n",
"3877 NaN NaN \n",
"3878 NaN NaN \n",
"\n",
" 2 ML Ondansetron 2 MG/ML Injection Psychiatric follow-up \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"3874 NaN NaN \n",
"3875 NaN NaN \n",
"3876 NaN NaN \n",
"3877 NaN NaN \n",
"3878 NaN NaN \n",
"\n",
" Evaluation of uterine fundal height Impacted molars \\\n",
"0 NaN NaN \n",
"1 True NaN \n",
"2 True NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"3874 NaN NaN \n",
"3875 NaN NaN \n",
"3876 NaN NaN \n",
"3877 NaN NaN \n",
"3878 True NaN \n",
"\n",
" Unhealthy alcohol drinking behavior (finding) \\\n",
"0 NaN \n",
"1 NaN \n",
"2 NaN \n",
"3 True \n",
"4 True \n",
"... ... \n",
"3874 True \n",
"3875 True \n",
"3876 True \n",
"3877 NaN \n",
"3878 NaN \n",
"\n",
" Nitroglycerin 0.4 MG/ACTUAT Mucosal Spray ... \\\n",
"0 NaN ... \n",
"1 NaN ... \n",
"2 NaN ... \n",
"3 NaN ... \n",
"4 NaN ... \n",
"... ... ... \n",
"3874 True ... \n",
"3875 NaN ... \n",
"3876 NaN ... \n",
"3877 NaN ... \n",
"3878 NaN ... \n",
"\n",
" Percutaneous coronary intervention ethnic Osteoarthritis of knee \\\n",
"0 NaN hispanic NaN \n",
"1 NaN nonhispanic True \n",
"2 NaN nonhispanic NaN \n",
"3 NaN nonhispanic NaN \n",
"4 NaN nonhispanic NaN \n",
"... ... ... ... \n",
"3874 True nonhispanic NaN \n",
"3875 NaN nonhispanic NaN \n",
"3876 NaN nonhispanic NaN \n",
"3877 NaN nonhispanic NaN \n",
"3878 NaN nonhispanic NaN \n",
"\n",
" Alteplase 100 MG Injection Heart rate Simvastatin 20 MG Oral Tablet \\\n",
"0 NaN normal NaN \n",
"1 NaN normal NaN \n",
"2 NaN normal NaN \n",
"3 NaN normal NaN \n",
"4 NaN normal NaN \n",
"... ... ... ... \n",
"3874 NaN normal True \n",
"3875 NaN normal NaN \n",
"3876 NaN normal NaN \n",
"3877 NaN normal NaN \n",
"3878 NaN normal NaN \n",
"\n",
" Concussion with loss of consciousness Leucovorin 100 MG Injection \\\n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"3874 NaN NaN \n",
"3875 NaN NaN \n",
"3876 NaN NaN \n",
"3877 NaN NaN \n",
"3878 NaN NaN \n",
"\n",
" Naproxen 500 MG Oral Tablet Died in hospice (finding) \n",
"0 NaN NaN \n",
"1 NaN NaN \n",
"2 NaN NaN \n",
"3 NaN NaN \n",
"4 NaN NaN \n",
"... ... ... \n",
"3874 NaN NaN \n",
"3875 NaN NaN \n",
"3876 NaN NaN \n",
"3877 NaN NaN \n",
"3878 NaN NaN \n",
"\n",
"[3879 rows x 779 columns]\n"
]
}
],
"source": [
"columns = df.columns\n",
"unique_columns = list(set(columns)) # Get unique column names\n",
"\n",
"# Create a new DataFrame with combined columns\n",
"df_combined = pd.DataFrame()\n",
"\n",
"# Iterate over the unique columns to combine and merge appropriately\n",
"for col in unique_columns:\n",
" if list(columns).count(col) > 1: # If the column name is duplicated\n",
" # Find all columns with this name and combine them, e.g., with first non-null\n",
" combined_series = df[[col]].bfill(axis=1).iloc[:, 0] # Backfill to combine\n",
" df_combined[col] = combined_series\n",
" else:\n",
" df_combined[col] = df[col] # If it's unique, just copy the column\n",
"\n",
"print(\"\\nDataFrame after combining columns with the same name:\")\n",
"print(df_combined)"
]
},
{
"cell_type": "code",
"execution_count": 7,
"metadata": {},
"outputs": [],
"source": [
"df2 = df_combined.copy()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Creating new features"
]
},
{
"cell_type": "code",
"execution_count": 8,
"metadata": {},
"outputs": [],
"source": [
"respiratory_disorders_columns = [\n",
" 'Acute bacterial sinusitis (disorder)',\n",
" 'Acute bronchitis (disorder)',\n",
" 'Acute respiratory distress syndrome (disorder)',\n",
" 'Acute viral pharyngitis (disorder)',\n",
" 'Asthma',\n",
" 'Asthma screening',\n",
" 'Bacterial infectious disease (disorder)',\n",
" 'COVID-19',\n",
" 'Chronic obstructive bronchitis (disorder)',\n",
" 'Cough (finding)',\n",
" 'Dyspnea (finding)',\n",
" 'Fever (finding)',\n",
" 'Hemoptysis (finding)',\n",
" 'Hypoxemia (disorder)',\n",
" 'Measurement of respiratory function (procedure)',\n",
" 'NDA020503 200 ACTUAT Albuterol 0.09 MG/ACTUAT Metered Dose Inhaler',\n",
" 'Nasal congestion (finding)',\n",
" 'Nasal sinus endoscopy (procedure)',\n",
" 'Otitis media',\n",
" 'Oxygen Therapy',\n",
" 'Pneumococcal conjugate PCV 13',\n",
" 'Pneumonia (disorder)',\n",
" 'Pulmonary emphysema (disorder)',\n",
" 'Respiratory distress (finding)',\n",
" 'Sore throat symptom (finding)',\n",
" 'Sputum examination (procedure)',\n",
" 'Sputum finding (finding)',\n",
" 'Streptococcal sore throat (disorder)',\n",
" 'Streptococcus pneumoniae group B antigen test',\n",
" 'Throat culture (procedure)',\n",
" 'Total knee replacement',\n",
" 'Transfer to stepdown unit (procedure)',\n",
" 'Transplant of lung (procedure)',\n",
" 'Viral sinusitis (disorder)',\n",
" 'House dust mite (organism)',\n",
" 'Mold (organism)',\n",
" 'Grass pollen (substance)',\n",
" 'Tree pollen (substance)',\n",
" 'Animal dander (substance)',\n",
" 'Wheezing (finding)'\n",
"]\n",
"\n",
"df2['Respiratory Disorders'] = df2[respiratory_disorders_columns].sum(axis=1)\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"metadata": {},
"outputs": [],
"source": [
"heart_and_cardiovascular_diseases_columns = [\n",
" 'Acute deep venous thrombosis (disorder)',\n",
" 'Acute pulmonary embolism (disorder)',\n",
" 'Atrial Fibrillation',\n",
" 'Blindness due to type 2 diabetes mellitus (disorder)',\n",
" 'Chronic congestive heart failure (disorder)',\n",
" 'Coronary Heart Disease',\n",
" 'Diabetes',\n",
" 'Diabetic renal disease (disorder)',\n",
" 'Diabetic retinopathy associated with type II diabetes mellitus (disorder)',\n",
" 'Hyperglycemia (disorder)',\n",
" 'Hypertension',\n",
" 'Hyperlipidemia',\n",
" 'Hypertriglyceridemia (disorder)',\n",
" 'Myocardial Infarction',\n",
" 'Stroke',\n",
" 'Heart failure (disorder)'\n",
"]\n",
"\n",
"\n",
"df2['Heart and Cardiovascular Diseases'] = df2[heart_and_cardiovascular_diseases_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 10,
"metadata": {},
"outputs": [],
"source": [
"metabolic_and_endocrine_disorders_columns = [\n",
" 'Alcoholism',\n",
" 'Anemia (disorder)',\n",
" 'Body mass index 30+ - obesity (finding)',\n",
" 'Chronic kidney disease stage 1 (disorder)',\n",
" 'Chronic kidney disease stage 2 (disorder)',\n",
" 'Chronic kidney disease stage 3 (disorder)',\n",
" 'Fatigue (finding)',\n",
" 'Gout',\n",
" 'Hyperlipidemia',\n",
" 'Hypertension',\n",
" 'Hypertriglyceridemia (disorder)',\n",
" 'Hypoxemia (disorder)',\n",
" 'Idiopathic atrophic hypothyroidism',\n",
" 'Loss of taste (finding)',\n",
" 'Macular edema and retinopathy due to type 2 diabetes mellitus (disorder)',\n",
" 'Metabolic syndrome X (disorder)',\n",
" 'Microalbuminuria due to type 2 diabetes mellitus (disorder)',\n",
" 'Neuropathy due to type 2 diabetes mellitus (disorder)',\n",
" 'Nonproliferative diabetic retinopathy due to type 2 diabetes mellitus (disorder)',\n",
" 'Osteoarthritis of hip',\n",
" 'Osteoarthritis of knee',\n",
" 'Osteoporosis (disorder)',\n",
" 'Pathological fracture due to osteoporosis (disorder)',\n",
" 'Prediabetes',\n",
" 'Proteinuria due to type 2 diabetes mellitus (disorder)',\n",
" 'Protracted diarrhea',\n",
" 'Rheumatoid arthritis',\n",
" 'Secondary malignant neoplasm of colon',\n",
" 'Stress (finding)',\n",
" 'Unhealthy alcohol drinking behavior (finding)',\n",
" 'Whiplash injury to neck',\n",
" 'Proliferative diabetic retinopathy due to type II diabetes mellitus (disorder)'\n",
"]\n",
"\n",
"df2['Metabolic and Endocrine Disorders'] = df2[metabolic_and_endocrine_disorders_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 11,
"metadata": {},
"outputs": [],
"source": [
"neurological_disorders_columns = [\n",
" 'Alzheimer\\'s disease (disorder)',\n",
" 'Brain damage - traumatic',\n",
" 'Chronic intractable migraine without aura',\n",
" 'Chronic low back pain (finding)',\n",
" 'Chronic neck pain (finding)',\n",
" 'Chronic pain',\n",
" 'Chronic paralysis due to lesion of spinal cord',\n",
" 'Chronic sinusitis (disorder)',\n",
" 'Epilepsy',\n",
" 'Familial Alzheimer\\'s disease of early onset (disorder)',\n",
" 'Fibromyalgia (disorder)',\n",
" 'Lupus erythematosus',\n",
" 'Male infertility due to cystic fibrosis (disorder)',\n",
" 'Malignant neoplasm of breast (disorder)',\n",
" 'Malignant tumor of colon',\n",
" 'Seizure disorder',\n",
" 'Sepsis (disorder)',\n",
" 'Sepsis caused by virus (disorder)',\n",
" 'Septic shock (disorder)',\n",
" 'Shock (disorder)',\n",
" 'Sinusitis (disorder)',\n",
" 'Streptococcal sore throat (disorder)',\n",
" 'Suspected COVID-19',\n",
" 'Transformed migraine (disorder)',\n",
" 'Victim of intimate partner abuse (finding)',\n",
" 'Viral sinusitis (disorder)',\n",
" 'Seizure Count Cerebral Cortex Electroencephalogram (EEG)',\n",
" 'Headache (finding)',\n",
" 'Primary fibromyalgia syndrome'\n",
"]\n",
"\n",
"\n",
"df2['Neurological Disorders'] = df2[neurological_disorders_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 12,
"metadata": {},
"outputs": [],
"source": [
"orthopedic_injuries_columns = [\n",
" 'Admission to orthopedic department',\n",
" 'Ankle X-ray',\n",
" 'Bone immobilization',\n",
" 'Brain damage - traumatic',\n",
" 'Bullet wound',\n",
" 'Burn injury(morphologic abnormality)',\n",
" 'Chronic kidney disease stage 1 (disorder)',\n",
" 'Clavicle X-ray',\n",
" 'Closed fracture of hip',\n",
" 'Concussion injury of brain',\n",
" 'Concussion with loss of consciousness',\n",
" 'Concussion with no loss of consciousness',\n",
" 'Facial laceration',\n",
" 'Fracture of ankle',\n",
" 'Fracture of clavicle',\n",
" 'Fracture of forearm',\n",
" 'Fracture of rib',\n",
" 'Fracture of the vertebral column with spinal cord injury',\n",
" 'Fracture of vertebral column without spinal cord injury',\n",
" 'Fracture subluxation of wrist',\n",
" 'History of amputation of foot (situation)',\n",
" 'History of lower limb amputation (situation)',\n",
" 'Hypertriglyceridemia (disorder)',\n",
" 'Impacted molars',\n",
" 'Injury of anterior cruciate ligament',\n",
" 'Injury of heart (disorder)',\n",
" 'Injury of kidney (disorder)',\n",
" 'Injury of medial collateral ligament of knee',\n",
" 'Injury of tendon of the rotator cuff of shoulder',\n",
" 'Joint pain (finding)',\n",
" 'Laceration of foot',\n",
" 'Laceration of hand',\n",
" 'Laceration of thigh',\n",
" 'Localized primary osteoarthritis of the hand',\n",
" 'Muscle pain (finding)',\n",
" 'Rupture of appendix',\n",
" 'Rupture of patellar tendon',\n",
" 'Second degree burn',\n",
" 'Sprain of ankle',\n",
" 'Sprain of wrist',\n",
" 'Surgical manipulation of joint of knee',\n",
" 'Surgical manipulation of shoulder joint',\n",
" 'Tear of meniscus of knee',\n",
" 'Total knee replacement',\n",
" 'Whiplash injury to neck',\n",
" 'Third degree burn'\n",
"]\n",
"\n",
"df2[\"Orthopedic Injuries\"] = df2[orthopedic_injuries_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 13,
"metadata": {},
"outputs": [],
"source": [
"mental_health_columns = [\n",
" 'Alcoholism',\n",
" 'At risk for suicide (finding)',\n",
" 'Brief general examination (procedure)',\n",
" 'Care regimes assessment (procedure)',\n",
" 'Comprehensive interview and evaluation (procedure)',\n",
" 'Concussion with no loss of consciousness',\n",
" 'Depression screening (procedure)',\n",
" 'Depression screening using Patient Health Questionnaire Nine Item score (procedure)',\n",
" 'Depression screening using Patient Health Questionnaire Two-Item score (procedure)',\n",
" 'Died in hospice (finding)',\n",
" 'Drug overdose',\n",
" 'Evaluation of psychiatric state of patient',\n",
" 'Has a criminal record (finding)',\n",
" 'Homeless (finding)',\n",
" 'Limited social contact (finding)',\n",
" 'Mental health Outpatient Note',\n",
" 'Mental health Telehealth Note',\n",
" 'Mental health screening (procedure)',\n",
" 'Misuses drugs (finding)',\n",
" 'Nausea (finding)',\n",
" 'Not in labor force (finding)',\n",
" 'Part-time employment (finding)',\n",
" 'Passive conjunctival congestion (finding)',\n",
" 'Posttraumatic stress disorder',\n",
" 'Psychiatric follow-up',\n",
" 'Refugee (person)',\n",
" 'Reports of violence in the environment (finding)',\n",
" 'Severe anxiety (panic) (finding',\n",
" 'Social isolation (finding)',\n",
" 'Stress (finding)',\n",
" 'Suicide risk assessment (procedure)',\n",
" 'Victim of intimate partner abuse (finding)',\n",
" 'Attempted suicide - cut/stab',\n",
" 'Attempted suicide - suffocation',\n",
" 'Opioid abuse (disorder)',\n",
" 'Assessment of anxiety (procedure)'\n",
"]\n",
"\n",
"df2['Mental Health'] = df2[mental_health_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 14,
"metadata": {},
"outputs": [],
"source": [
"reproductive_and_pregancy_columns = [\n",
" '1 ML medroxyPROGESTERone acetate 150 MG/ML Injection',\n",
" '168 HR Ethinyl Estradiol 0.00146 MG/HR / norelgestromin 0.00625 MG/HR Transdermal System',\n",
" 'Antenatal RhD antibody screening',\n",
" 'Antepartum eclampsia',\n",
" 'Augmentation of labor',\n",
" 'Auscultation of the fetal heart',\n",
" 'Bilateral tubal ligation',\n",
" 'Blighted ovum',\n",
" 'Camila 28 Day Pack',\n",
" 'Counseling for termination of pregnancy',\n",
" 'Cytopathology procedure preparation of smear genital source',\n",
" 'Episiotomy',\n",
" 'Errin 28 Day Pack',\n",
" 'Estrostep Fe 28 Day Pack',\n",
" 'Etonogestrel 68 MG Drug Implant',\n",
" 'Evaluation of uterine fundal height',\n",
" 'Excision of fallopian tube and surgical removal of ectopic pregnancy',\n",
" 'Fetal anatomy study',\n",
" 'Fetus with unknown complication',\n",
" 'Gonorrhea infection test',\n",
" 'Hyperlipidemia',\n",
" 'Induced termination of pregnancy',\n",
" 'Insertion of intrauterine contraceptive device',\n",
" 'Insertion of subcutaneous contraceptive',\n",
" 'Instrumental delivery',\n",
" 'Jolivette 28 Day Pack',\n",
" 'Kyleena 19.5 MG Intrauterine System',\n",
" 'Leronlimab 700 MG Injection',\n",
" 'Levonorgestrel 0.00354 MG/HR Drug Implant',\n",
" 'Levora 0.15/30 28 Day Pack',\n",
" 'Liletta 52 MG Intrauterine System',\n",
" 'Medical induction of labor',\n",
" 'Mestranol / Norethynodrel [Enovid]',\n",
" 'Methotrexate injection into tubal pregnancy',\n",
" 'Mirena 52 MG Intrauterine System',\n",
" 'Miscarriage in first trimester',\n",
" 'Natazia 28 Day Pack',\n",
" 'Norinyl 1+50 28 Day Pack',\n",
" 'NuvaRing 0.12/0.015 MG per 24HR 21 Day Vaginal Ring',\n",
" 'Ortho Tri-Cyclen 28 Day Pack',\n",
" 'Preeclampsia',\n",
" 'Pregnancy termination care',\n",
" 'Premature birth of newborn',\n",
" 'Removal of intrauterine device',\n",
" 'Removal of subcutaneous contraceptive',\n",
" 'Replacement of contraceptive intrauterine device',\n",
" 'RhD passive immunization',\n",
" 'Screening for chromosomal aneuploidy in prenatal amniotic fluid',\n",
" 'Spontaneous breech delivery',\n",
" 'Standard pregnancy test',\n",
" 'Tubal pregnancy',\n",
" 'Ultrasonography of abdomen right upper quadrant and epigastrium',\n",
" 'Ultrasonography of bilateral breasts (procedure)',\n",
" 'Ultrasound scan for fetal viability',\n",
" 'Vaccination for diphtheria pertussis and tetanus',\n",
" 'Vasectomy' \n",
"]\n",
"\n",
"df2['Reproductive and Pregnancy'] = df2[reproductive_and_pregancy_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 15,
"metadata": {},
"outputs": [],
"source": [
"pain_relievers_and_analesics_columns = [\n",
" '10 ML Alfentanil 0.5 MG/ML Injection',\n",
" '10 ML Fentanyl 0.05 MG/ML Injection',\n",
" '12 HR Hydrocodone Bitartrate 10 MG Extended Release Oral Capsule',\n",
" '5 ML SUFentanil 0.05 MG/ML Injection',\n",
" '72 HR Fentanyl 0.025 MG/HR Transdermal System',\n",
" 'Abuse-Deterrent 12 HR Oxycodone Hydrochloride 10 MG Extended Release Oral Tablet [Oxycontin]',\n",
" 'Abuse-Deterrent 12 HR Oxycodone Hydrochloride 15 MG Extended Release Oral Tablet',\n",
" 'Acetaminophen 325 MG / oxyCODONE Hydrochloride 2.5 MG Oral Tablet',\n",
" 'Acetaminophen 325 MG / oxyCODONE Hydrochloride 5 MG Oral Tablet',\n",
" 'Acetaminophen 500 MG Oral Tablet',\n",
" 'Acetaminophen 300 MG / Hydrocodone Bitartrate 5 MG Oral Tablet',\n",
" 'Acetaminophen 325 MG / HYDROcodone Bitartrate 7.5 MG Oral Tablet',\n",
" 'Acetaminophen 325 MG / Oxycodone Hydrochloride 10 MG Oral Tablet [Percocet]',\n",
" 'Acetaminophen 325 MG Oral Tablet',\n",
" 'Acetaminophen/Hydrocodone',\n",
" 'Aspirin',\n",
" 'Aspirin 81 MG Oral Tablet',\n",
" 'Carbamazepine[Tegretol]',\n",
" 'Chlorpheniramine Maleate 4 MG Oral Tablet',\n",
" 'Clopidogrel 75 MG Oral Tablet',\n",
" 'Colchicine 0.6 MG Oral Tablet',\n",
" 'Cyclophosphamide 1000 MG Injection',\n",
" 'Diazepam 5 MG Oral Tablet',\n",
" 'Diazepam 5 MG/ML Injectable Solution',\n",
" 'Doxycycline Monohydrate 100 MG Oral Tablet',\n",
" 'Ibuprofen',\n",
" 'Ibuprofen 200 MG Oral Tablet',\n",
" 'Ibuprofen 400 MG Oral Tablet [Ibu]',\n",
" 'Lorazepam 2 MG/ML Injectable Solution',\n",
" 'Meperidine Hydrochloride 50 MG Oral Tablet',\n",
" 'Muscle pain (finding)',\n",
" 'Naproxen 500 MG Oral Tablet',\n",
" 'Naproxen sodium 220 MG Oral Tablet',\n",
" 'Nitroglycerin 0.4 MG/ACTUAT Mucosal Spray',\n",
" 'Phenazopyridine hydrochloride 100 MG Oral Tablet',\n",
" 'Sulfamethoxazole / Trimethoprim',\n",
" 'buprenorphine 2 MG / naloxone 0.5 MG Sublingual Tablet',\n",
" 'diphenhydrAMINE Hydrochloride 25 MG Oral Tablet',\n",
" 'duloxetine 20 MG Delayed Release Oral Capsule',\n",
" 'methadone hydrochloride 10 MG Oral Tablet',\n",
" 'tramadol hydrochloride 50 MG Oral Tablet',\n",
" 'clonazePAM 0.25 MG Oral Tablet',\n",
" 'Midazolam 1 MG/ML Injectable Solution',\n",
" 'Rocuronium bromide 10 MG/ML Injectable Solution',\n",
" 'Epidural anesthesia',\n",
"]\n",
"\n",
"df2['Pain Relievers and Analesics'] = df2[pain_relievers_and_analesics_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 16,
"metadata": {},
"outputs": [],
"source": [
"cardiovascular_and_blood_pressure_medications_columns = [\n",
" '0.3 ML Enoxaparin sodium 100 MG/ML Prefilled Syringe',\n",
" '0.4 ML Enoxaparin sodium 100 MG/ML Prefilled Syringe',\n",
" '1 ML Enoxaparin sodium 150 MG/ML Prefilled Syringe',\n",
" '1 ML heparin sodium porcine 5000 UNT/ML Injection',\n",
" '3 ML Amiodarone hydrocholoride 50 MG/ML Prefilled Syringe',\n",
" '4 ML norepinephrine 1 MG/ML Injection',\n",
" 'Acute deep venous thrombosis (disorder)',\n",
" 'Acute pulmonary embolism (disorder)',\n",
" 'Alteplase 100 MG Injection',\n",
" 'Assessment using New York Heart Association Classification (procedure)',\n",
" 'Atorvastatin 80 MG Oral Tablet',\n",
" 'Atropine Sulfate 1 MG/ML Injectable Solution',\n",
" 'Captopril 25 MG Oral Tablet',\n",
" 'Cardiac Arrest',\n",
" 'Cardiovascular stress testing (procedure)',\n",
" 'Catheter ablation of tissue of heart',\n",
" 'Coronary artery bypass grafting',\n",
" 'Digoxin 0.125 MG Oral Tablet',\n",
" 'Echocardiography (procedure)',\n",
" 'Electrical cardioversion',\n",
" 'Electrocardiographic procedure',\n",
" 'Furosemide 40 MG Oral Tablet',\n",
" 'History of myocardial infarction (situation)',\n",
" 'Hydrochlorothiazide 25 MG Oral Tablet',\n",
" 'Implantation of left ventricular assist device (procedure)',\n",
" 'Insertion of biventricular implantable cardioverter defibrillator',\n",
" 'Lisinopril',\n",
" 'Myocardial Infarction',\n",
" 'Nitrofurantoin 5 MG/ML Oral Suspension',\n",
" 'Peripheral blood smear interpretation',\n",
" 'Referral to hypertension clinic',\n",
" 'Shock (disorder)',\n",
" 'Stroke',\n",
" 'Transplantation of heart (procedure)',\n",
" 'Verapamil Hydrochloride 40 MG',\n",
" 'Warfarin Sodium 5 MG Oral Tablet',\n",
" 'carvedilol 25 MG Oral Tablet',\n",
" 'lisinopril 10 MG Oral Tablet',\n",
" 'lisinopril 20 MG Oral Tablet',\n",
" 'losartan potassium 25 MG Oral Tablet',\n",
" 'losartan potassium 50 MG Oral Tablet',\n",
" 'sacubitril 97 MG / valsartan 103 MG Oral Tablet',\n",
" 'remifentanil 2 MG Injection',\n",
" 'pregabalin 100 MG Oral Capsule'\n",
"]\n",
"\n",
"df2['Cardiovascular and Blood Pressure'] = df2[cardiovascular_and_blood_pressure_medications_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 17,
"metadata": {},
"outputs": [],
"source": [
"injection_medications_columns = [\n",
" '10 ML Doxorubicin Hydrochloride 2 MG/ML Injection',\n",
" '10 ML oxaliplatin 5 MG/ML Injection',\n",
" '1 ML DOCEtaxel 20 MG/ML Injection',\n",
" '1 ML Epinephrine 1 MG/ML Injection',\n",
" '1 ML Morphine Sulfate 5 MG/ML Injection',\n",
" '1 ML Vasopressin (USP) 20 UNT/ML Injection',\n",
" '10 ML Fluorouracil 50 MG/ML Injection',\n",
" '10 ML Pamidronate Disodium 3 MG/ML Injection',\n",
" '100 ML Epirubicin Hydrochloride 2 MG/ML Injection',\n",
" '100 ML Propofol 10 MG/ML Injection',\n",
" '100 ML zoledronic acid 0.04 MG/ML Injection',\n",
" '150 ML vancomycin 5 MG/ML Injection',\n",
" '2 ML Ondansetron 2 MG/ML Injection',\n",
" '20 ML tocilizumab 20 MG/ML Injection',\n",
" '5 ML hyaluronidase-oysk 2000 UNT/ML / trastuzumab 120 MG/ML Injection',\n",
" 'pneumococcal polysaccharide vaccine 23 valent',\n",
" 'remdesivir 100 MG Injection',\n",
" 'zoster',\n",
" 'Aztreonam 2000 MG Injection',\n",
" 'cefdinir', \n",
" 'Cefdinir',\n",
" 'doxycycline hyclate 100 MG',\n",
" 'Ampicillin 100 MG/ML Injectable Solution',\n",
" 'Penicillin G 375 MG/ML Injectable Solution',\n",
" 'Penicillin V',\n",
" 'Paclitaxel 100 MG Injection',\n",
" 'Piperacillin 4000 MG / tazobactam 500 MG Injection',\n",
" 'Leucovorin 100 MG Injection',\n",
" 'Influenza seasonal injectable preservative free',\n",
" 'Syphilis infection test',\n",
" 'Skin test for tuberculosis',\n",
" 'Urine culture'\n",
"]\n",
"\n",
"\n",
"df2['Injection Medications'] = df2[injection_medications_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 18,
"metadata": {},
"outputs": [],
"source": [
"oral_medications_columns = [\n",
" '12 HR Cefaclor 500 MG Extended Release Oral Tablet',\n",
" '24 HR Donepezil hydrochloride 10 MG / Memantine hydrochloride 28 MG Extended Release Oral Capsule',\n",
" '24 HR Metformin hydrochloride 500 MG Extended Release Oral Tablet',\n",
" 'Acetaminophen 300 MG / Codeine Phosphate 15 MG Oral Tablet',\n",
" 'Acetaminophen 325 MG Oral Tablet [Tylenol]',\n",
" 'Alendronic acid 10 MG Oral Tablet',\n",
" 'Allopurinol 100 MG Oral Tablet',\n",
" 'Amlodipine 5 MG Oral Tablet',\n",
" 'Amoxicillin 250 MG / Clavulanate 125 MG Oral Tablet',\n",
" 'Amoxicillin 250 MG Oral Capsule',\n",
" 'Aspirin 81 MG Oral Tablet',\n",
" 'Astemizole 10 MG Oral Tablet',\n",
" 'Atorvastatin 80 MG Oral Tablet',\n",
" 'Azithromycin 250 MG Oral Tablet',\n",
" 'Azithromycin 250mg',\n",
" 'Cefuroxime 250 MG Oral Tablet',\n",
" 'Chlorpheniramine Maleate 4 MG Oral Tablet',\n",
" 'Clopidogrel 75 MG Oral Tablet',\n",
" 'Colchicine 0.6 MG Oral Tablet',\n",
" 'Diazepam 5 MG Oral Tablet',\n",
" 'Digoxin 0.125 MG Oral Tablet',\n",
" 'Donepezil hydrochloride 10 MG Oral Tablet',\n",
" 'Donepezil hydrochloride 23 MG Oral Tablet',\n",
" 'Doxycycline Monohydrate 100 MG Oral Tablet',\n",
" 'Fexofenadine hydrochloride 60 MG Oral Tablet',\n",
" 'Furosemide 40 MG Oral Tablet',\n",
" 'Galantamine 4 MG Oral Tablet',\n",
" 'Hydrochlorothiazide 25 MG Oral Tablet',\n",
" 'Levothyroxine Sodium 0.075 MG Oral Tablet',\n",
" 'Loratadine 10 MG Oral Tablet',\n",
" 'Methotrexate 2.5 MG Oral Tablet',\n",
" 'Milnacipran hydrochloride 100 MG Oral Tablet',\n",
" 'Nitrofurantoin 5 MG/ML Oral Suspension',\n",
" 'Penicillin V Potassium 500 MG Oral Tablet',\n",
" 'Phenazopyridine hydrochloride 100 MG Oral Tablet',\n",
" 'Sertraline 100 MG Oral Tablet',\n",
" 'Simvastatin 10 MG Oral Tablet',\n",
" 'Simvastatin 20 MG Oral Tablet',\n",
" 'Tacrine 10 MG Oral Capsule',\n",
" 'Tamoxifen 10 MG Oral Tablet',\n",
" 'Terfenadine 60 MG Oral Tablet',\n",
" 'Verapamil Hydrochloride 40 MG',\n",
" 'Verzenio 100 MG Oral Tablet',\n",
" 'Warfarin Sodium 5 MG Oral Tablet',\n",
" 'palbociclib 100 MG Oral Capsule',\n",
" 'predniSONE 20 MG Oral Tablet',\n",
" 'ribociclib 200 MG Oral Tablet',\n",
" 'neratinib 40 MG Oral Tablet',\n",
" 'Hydroxychloroquine Sulfate 200 MG Oral Tablet',\n",
" 'chloroquine phosphate 500 MG Oral Tablet',\n",
" 'Naltrexone hydrochloride 50 MG Oral Tablet',\n",
" 'lapatinib 250 MG Oral Tablet',\n",
" 'cetirizine hydrochloride 10 MG Oral Tablet',\n",
" 'cycloSPORINE modified 100 MG Oral Capsule',\n",
" 'letrozole 2.5 MG Oral Tablet',\n",
" 'exemestane 25 MG Oral Tablet',\n",
" 'ferrous sulfate 325 MG Oral Tablet'\n",
" \n",
"]\n",
"\n",
"df2['Oral Medications'] = df2[oral_medications_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 19,
"metadata": {},
"outputs": [],
"source": [
"other_medications_columns = [\n",
" '0.25 ML Leuprolide Acetate 30 MG/ML Prefilled Syringe',\n",
" '1 ML Epoetin Alfa 4000 UNT/ML Injection [Epogen]',\n",
" '1 ML denosumab 60 MG/ML Prefilled Syringe',\n",
" '10 ML Furosemide 10 MG/ML Injection',\n",
" '3 ML liraglutide 6 MG/ML Pen Injector',\n",
" '5 ML fulvestrant 50 MG/ML Prefilled Syringe',\n",
" '12 HR Cefaclor 500 MG Extended Release Oral Tablet',\n",
" '120 ACTUAT Fluticasone propionate 0.044 MG/ACTUAT Metered Dose Inhaler',\n",
" '60 ACTUAT Fluticasone propionate 0.25 MG/ACTUAT / salmeterol 0.05 MG/ACTUAT Dry Powder Inhaler',\n",
" 'Acetaminophen 21.7 MG/ML / Dextromethorphan Hydrobromide 1 MG/ML / doxylamine succinate 0.417 MG/ML Oral Solution',\n",
" 'Chlamydia antigen test',\n",
" 'Hepatitis B Surface Antigen Measurement',\n",
" 'Hepatitis C antibody test',\n",
" 'Human immunodeficiency virus antigen test',\n",
" 'Insulin Lispro 100 UNT/ML Injectable Solution [Humalog]',\n",
" 'Jolivette 28 Day Pack',\n",
" 'Measurement of Varicella-zoster virus antibody',\n",
" 'Memantine hydrochloride 2 MG/ML Oral Solution',\n",
" 'NDA020503 200 ACTUAT Albuterol 0.09 MG/ACTUAT Metered Dose Inhaler',\n",
" 'NDA020800 0.3 ML Epinephrine 1 MG/ML Auto-Injector',\n",
" 'NITROFURANTOIN MACROCRYSTALS 50 MG Oral Capsule',\n",
" 'Ortho Tri-Cyclen 28 Day Pack',\n",
" 'Pneumococcal conjugate PCV 13',\n",
" 'Pulmozyme (Dornase Alfa)',\n",
" 'SARS-COV-2 (COVID-19) vaccine mRNA spike protein LNP preservative free 100 mcg/0.5mL dose',\n",
" 'SARS-COV-2 (COVID-19) vaccine mRNA spike protein LNP preservative free 30 mcg/0.3mL dose',\n",
" 'SARS-COV-2 (COVID-19) vaccine vector non-replicating recombinant spike protein-Ad26 preservative free 0.5 mL',\n",
" 'Seasonique 91 Day Pack',\n",
" 'Td (adult) preservative free',\n",
" 'Trinessa 28 Day Pack',\n",
" 'Vaccination for diphtheria pertussis and tetanus',\n",
" 'Vitamin B 12 5 MG/ML Injectable Solution',\n",
" 'Vomiting symptom (finding)',\n",
" 'Yaz 28 Day Pack',\n",
" 'ado-trastuzumab emtansine 100 MG Injection',\n",
" 'albuterol 5 MG/ML Inhalation Solution',\n",
" 'amLODIPine 2.5 MG Oral Tablet',\n",
" 'anastrozole 1 MG Oral Tablet',\n",
" 'baricitinib 2 MG Oral Tablet',\n",
" 'buprenorphine 2 MG / naloxone 0.5 MG Sublingual Tablet',\n",
" 'carvedilol 25 MG Oral Tablet',\n",
" 'sevoflurane 1000 MG/ML Inhalant Solution',\n",
" 'Latex (substance)',\n",
" 'desflurane 1000 MG/ML Inhalation Solution',\n",
" 'Isoflurane 999 MG/ML Inhalant Solution',\n",
" 'Hydrocortisone 10 MG/ML Topical Cream',\n",
" 'Lenzilumab 200 MG IV',\n",
" 'remifentanil 2 MG Injection',\n",
" 'Carboplatin 10 MG/ML Injectable Solution',\n",
" 'chloroquine phosphate 500 MG Oral Tablet',\n",
" 'Naltrexone hydrochloride 50 MG Oral Tablet',\n",
" 'lapatinib 250 MG Oral Tablet',\n",
" 'Sodium Chloride 9 MG/ML Injectable Solution',\n",
" 'insulin human isophane 70 UNT/ML / Regular Insulin Human 30 UNT/ML Injectable Suspension [Humulin]'\n",
"]\n",
"\n",
"df2['Other Medications'] = df2[other_medications_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 20,
"metadata": {},
"outputs": [],
"source": [
"therapies_and_regimes_columns = [\n",
" '24hr nicotine transdermal patch',\n",
" 'Assessment of health and social care needs (procedure)',\n",
" 'Assessment of substance use (procedure)',\n",
" 'Assessment using Alcohol Use Disorders Identification Test - Consumption (procedure)',\n",
" 'Assessment using Morse Fall Scale (procedure)',\n",
" 'Cognitive and behavioral therapy (regime/therapy)',\n",
" 'Combined chemotherapy and radiation therapy (procedure)',\n",
" 'Comprehensive interview and evaluation (procedure)',\n",
" 'Construction of diverting colostomy',\n",
" 'Controlled ventilation procedure and therapy initiation and management (procedure)',\n",
" 'Coordination of care plan (procedure)',\n",
" 'Home health aide service (regime/therapy)',\n",
" 'Hospice care (regime/therapy)',\n",
" 'Interstitial brachytherapy (procedure)',\n",
" 'Intracavitary brachytherapy (procedure)',\n",
" 'Monitoring of patient (regime/therapy)',\n",
" 'Movement therapy (regime/therapy)',\n",
" 'Nursing care/supplementary surveillance (regime/therapy)',\n",
" 'Occupational therapy (regime/therapy)',\n",
" 'Physical examination',\n",
" 'Physical therapy procedure (regime/therapy)',\n",
" 'Professional / ancillary services care (regime/therapy)',\n",
" 'Psychosocial care (regime/therapy)',\n",
" 'Pulmonary rehabilitation (regime/therapy)',\n",
" 'Radiation oncology AND/OR radiotherapy (procedure)',\n",
" 'Radiation therapy care (regime/therapy)',\n",
" 'Referral to home health care service (procedure)',\n",
" 'Referral to hypertension clinic',\n",
" 'Social case work (regime/therapy)',\n",
" 'Speech and language therapy regime (regime/therapy',\n",
" 'Subcutaneous immunotherapy',\n",
" 'Teleradiotherapy procedure (procedure)',\n",
" 'Transplant of lung (procedure)',\n",
" 'Transplantation of heart (procedure)',\n",
" 'Weaning from mechanically assisted ventilation (procedure)',\n",
" 'Microbial culture (procedure)',\n",
" 'Chemotherapy (procedure)'\n",
"]\n",
"\n",
"\n",
"df2['Therapies and Regimes'] = df2[therapies_and_regimes_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 21,
"metadata": {},
"outputs": [],
"source": [
"diagnostic_procedures_columns = [\n",
" 'Biopsy of breast (procedure)',\n",
" 'Biopsy of colon',\n",
" 'Biopsy of prostate',\n",
" 'Blood typing RH typing',\n",
" 'Bone density scan (procedure)',\n",
" 'Chlamydia antigen test',\n",
" 'Clavicle X-ray',\n",
" 'Colonoscopy',\n",
" 'Digital examination of rectum',\n",
" 'Echocardiography (procedure)',\n",
" 'Electrocardiographic procedure',\n",
" 'Human epidermal growth factor receptor 2 gene detection by fluorescence in situ hybridization (procedure)',\n",
" 'Human epidermal growth factor receptor 2 gene detection by immunohistochemistry (procedure)',\n",
" 'Human immunodeficiency virus antigen test',\n",
" 'Initial patient assessment (procedure)',\n",
" 'Knee X-ray',\n",
" 'Magnetic resonance imaging of breast (procedure)',\n",
" 'Mammogram - symptomatic (procedure)',\n",
" 'Mammography (procedure)',\n",
" 'Manual pelvic examination (procedure)',\n",
" 'Measurement of Varicella-zoster virus antibody',\n",
" 'Measurement of respiratory function (procedure)',\n",
" 'Nasal sinus endoscopy (procedure)',\n",
" 'Pelvis X-ray',\n",
" 'Plain chest X-ray (procedure)',\n",
" 'Screening for domestic abuse (procedure)',\n",
" 'Screening for drug abuse (procedure)',\n",
" 'Screening for occult blood in feces (procedure)',\n",
" 'Screening mammography (procedure)',\n",
" 'Sentinel lymph node biopsy (procedure)',\n",
" 'Spirometry (procedure)',\n",
" 'Throat culture (procedure)',\n",
" 'Upper arm X-ray',\n",
" 'X-ray or wrist',\n",
" 'Seizure Count Cerebral Cortex Electroencephalogram (EEG)',\n",
" 'Allergy screening test',\n",
" 'Alpha-fetoprotein test',\n",
" 'Bilirubin.total [Presence] in Urine by Test strip',\n",
" 'Urine screening for glucose',\n",
" 'Urine screening test for diabetes',\n",
" 'Urine protein test',\n",
" 'Hemoglobin / Hematocrit / Platelet count',\n",
" 'Assessment of anxiety (procedure)',\n",
" 'Urine culture'\n",
"]\n",
"\n",
"\n",
"df2['Diagnostic Procedures'] = df2[diagnostic_procedures_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 22,
"metadata": {},
"outputs": [],
"source": [
"surgerical_interventions_columns = [\n",
" 'Admission to burn unit',\n",
" 'Admission to long stay hospital',\n",
" 'Admission to neurosurgical department',\n",
" 'Admission to trauma surgery department',\n",
" 'Admit to ICU (procedure)',\n",
" 'Amputation of right foot',\n",
" 'Amputation of right leg',\n",
" 'Appendectomy',\n",
" 'Artificial respiration (procedure)',\n",
" 'Brachytherapy of breast (procedure)',\n",
" 'Catheter ablation of tissue of heart',\n",
" 'Coronary artery bypass grafting',\n",
" 'Excision of axillary lymph node (procedure)',\n",
" 'Excision of breast tissue (procedure)',\n",
" 'Excision of sentinel lymph node (procedure)',\n",
" 'Extraction of wisdom tooth',\n",
" 'Implantation of left ventricular assist device (procedure)',\n",
" 'Induced termination of pregnancy',\n",
" 'Insertion of biventricular implantable cardioverter defibrillator',\n",
" 'Insertion of endotracheal tube (procedure)',\n",
" 'Instrumental delivery',\n",
" 'Intubation',\n",
" 'Laparoscopic Removal of Gall Bladder',\n",
" 'Lumpectomy of breast (procedure)',\n",
" 'Lung volume reduction surgery (procedure)',\n",
" 'Open Removal of Gall Bladder',\n",
" 'Partial resection of colon',\n",
" 'Percutaneous coronary intervention',\n",
" 'Percutaneous mechanical thrombectomy of portal vein using fluoroscopic guidance',\n",
" 'Prostatectomy',\n",
" 'Rectal polypectomy',\n",
" 'Removal of endotracheal tube (procedure)',\n",
" 'Removal of subcutaneous contraceptive',\n",
" 'Surgical manipulation of joint of knee',\n",
" 'Surgical manipulation of shoulder joint',\n",
" 'Suture open wound',\n",
" 'Tear of meniscus of knee',\n",
" 'Transplantation of heart (procedure)'\n",
"]\n",
"df2['Surgical Interventions'] = df2[surgerical_interventions_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 23,
"metadata": {},
"outputs": [],
"source": [
"patient_care_management_columns = [\n",
" 'Assessment of health and social care needs (procedure)',\n",
" 'Bleeding from anus',\n",
" 'Bullet wound',\n",
" 'Chronic low back pain (finding)',\n",
" 'Contact dermatitis',\n",
" 'Cystitis',\n",
" 'Diarrhea symptom (finding)',\n",
" 'Escherichia coli urinary tract infection',\n",
" 'Evaluation of psychiatric state of patient',\n",
" 'Facial laceration',\n",
" 'First degree burn',\n",
" 'Heart failure education (procedure)',\n",
" 'Hemodialysis (procedure)',\n",
" 'Hep A adult',\n",
" 'History AND physical examination (procedure)',\n",
" 'History of amputation of foot (situation)',\n",
" 'History of appendectomy',\n",
" 'History of cardiac arrest (situation)',\n",
" 'History of lower limb amputation (situation)',\n",
" 'History of single seizure (situation)',\n",
" 'Hospital admission short-term 24 hours',\n",
" 'Information gathering (procedure)',\n",
" 'Injection of tetanus antitoxin',\n",
" 'Intramuscular injection',\n",
" 'Intravenous blood transfusion of packed cells (procedure)',\n",
" 'Intravenous injection (procedure)',\n",
" 'Laceration of foot',\n",
" 'Laceration of forearm',\n",
" 'Laceration of hand',\n",
" 'Laceration of thigh',\n",
" 'Medication Reconciliation (procedure)',\n",
" 'Movement therapy (regime/therapy)',\n",
" 'Notifications (procedure)',\n",
" 'Oxygen administration by mask (procedure)',\n",
" 'Patient discharge (procedure)',\n",
" 'Placing subject in prone position (procedure)',\n",
" 'Postoperative procedure education (procedure)',\n",
" 'Pre-discharge assessment (procedure)',\n",
" 'Radiation oncology AND/OR radiotherapy (procedure)',\n",
" 'Referral to home health care service (procedure)',\n",
" 'Referral to hypertension clinic',\n",
" 'Renal dialysis (procedure)',\n",
" 'Resuscitation using intravenous fluid (procedure)',\n",
" 'Review of systems (procedure)',\n",
" 'Rubella screening',\n",
" 'Screening mammography (procedure)',\n",
" 'Subcutaneous immunotherapy',\n",
" 'Teleradiotherapy procedure (procedure)',\n",
" 'Transfer to stepdown unit (procedure)',\n",
" 'Transfusion of plasma (procedure)',\n",
" 'Weaning from mechanically assisted ventilation (procedure)',\n",
" 'piperacillin 2000 MG / tazobactam 250 MG Injection',\n",
" 'vancomycin 1000 MG Injection',\n",
" 'Recurrent urinary tract infection',\n",
" 'Acquired coagulation disorder (disorder)',\n",
" 'Primary malignant neoplasm of colon',\n",
" 'Pyelonephritis',\n",
" 'Chill (finding)',\n",
" 'Acute Cholecystitis',\n",
" 'Cholelithiasis',\n",
" 'Appendicitis',\n",
" 'Metastasis from malignant tumor of prostate (disorder)',\n",
" 'Overlapping malignant neoplasm of colon',\n",
" 'Polyp of colon',\n",
" 'Neoplasm of prostate',\n",
" 'Carcinoma in situ of prostate (disorder)',\n",
" 'Recurrent rectal polyp',\n",
" 'Discharge from skilled nursing facility (procedure)',\n",
" 'Certification procedure (procedure)',\n",
" 'Development of individualized plan of care (procedure)'\n",
"]\n",
"\n",
"df2['Patient Care Management'] = df2[patient_care_management_columns].sum(axis=1)"
]
},
{
"cell_type": "code",
"execution_count": 24,
"metadata": {},
"outputs": [],
"source": [
"categories = ['Respiratory Disorders', 'Heart and Cardiovascular Diseases', 'Metabolic and Endocrine Disorders', 'Neurological Disorders', 'Orthopedic Injuries', 'Mental Health', 'Reproductive and Pregnancy', 'Pain Relievers and Analesics', 'Cardiovascular and Blood Pressure', 'Injection Medications', 'Oral Medications', 'Other Medications', 'Therapies and Regimes', 'Diagnostic Procedures', 'Surgical Interventions', 'Patient Care Management']"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Type of these column is object, we will convert them to int."
]
},
{
"cell_type": "code",
"execution_count": 25,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Column: Mammography (procedure)\n",
"Data Type: object\n",
"Column: Amputation of right leg\n",
"Data Type: float64\n",
"Column: History of amputation of foot (situation)\n",
"Data Type: object\n",
"Column: Vasectomy\n",
"Data Type: object\n",
"Column: 2 ML Ondansetron 2 MG/ML Injection\n",
"Data Type: object\n",
"Column: Psychiatric follow-up\n",
"Data Type: object\n",
"Column: Evaluation of uterine fundal height\n",
"Data Type: object\n",
"Column: Impacted molars\n",
"Data Type: object\n",
"Column: Unhealthy alcohol drinking behavior (finding)\n",
"Data Type: object\n",
"Column: Nitroglycerin 0.4 MG/ACTUAT Mucosal Spray\n",
"Data Type: object\n",
"Column: Antenatal RhD antibody screening\n",
"Data Type: object\n",
"Column: Excision of fallopian tube and surgical removal of ectopic pregnancy\n",
"Data Type: object\n",
"Column: Recurrent urinary tract infection\n",
"Data Type: object\n",
"Column: Chronic low back pain (finding)\n",
"Data Type: object\n",
"Column: Colchicine 0.6 MG Oral Tablet\n",
"Data Type: object\n",
"Column: diphenhydrAMINE Hydrochloride 25 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Lactate [Mass/volume] in Blood\n",
"Data Type: object\n",
"Column: Posttraumatic stress disorder\n",
"Data Type: object\n",
"Column: Sertraline 100 MG Oral Tablet\n",
"Data Type: object\n",
"Column: 5 ML SUFentanil 0.05 MG/ML Injection\n",
"Data Type: object\n",
"Column: Postoperative procedure education (procedure)\n",
"Data Type: object\n",
"Column: Clarity of Urine\n",
"Data Type: object\n",
"Column: Hemoglobin / Hematocrit / Platelet count\n",
"Data Type: object\n",
"Column: Movement therapy (regime/therapy)\n",
"Data Type: object\n",
"Column: Allopurinol 100 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Evaluation of psychiatric state of patient\n",
"Data Type: object\n",
"Column: Diazepam 5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Headache (finding)\n",
"Data Type: object\n",
"Column: Injection of tetanus antitoxin\n",
"Data Type: object\n",
"Column: Acute bronchitis (disorder)\n",
"Data Type: object\n",
"Column: Cytopathology procedure preparation of smear genital source\n",
"Data Type: object\n",
"Column: Radiation therapy care (regime/therapy)\n",
"Data Type: object\n",
"Column: Removal of endotracheal tube (procedure)\n",
"Data Type: object\n",
"Column: Body temperature\n",
"Data Type: object\n",
"Column: Chlamydia antigen test\n",
"Data Type: object\n",
"Column: History of single seizure (situation)\n",
"Data Type: object\n",
"Column: Not in labor force (finding)\n",
"Data Type: object\n",
"Column: History of upper limb amputation (situation)\n",
"Data Type: float64\n",
"Column: Drug overdose\n",
"Data Type: object\n",
"Column: 20 ML tocilizumab 20 MG/ML Injection\n",
"Data Type: object\n",
"Column: Objective assessment of cardiovascular disease NYHA\n",
"Data Type: object\n",
"Column: 72 HR Fentanyl 0.025 MG/HR Transdermal System\n",
"Data Type: object\n",
"Column: Cystic Fibrosis\n",
"Data Type: float64\n",
"Column: Iron [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Ortho Tri-Cyclen 28 Day Pack\n",
"Data Type: object\n",
"Column: Lactate dehydrogenase [Enzymatic activity/volume] in Serum or Plasma by Lactate to pyruvate reaction\n",
"Data Type: float64\n",
"Column: Prediabetes\n",
"Data Type: object\n",
"Column: Proliferative diabetic retinopathy due to type II diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: Sputum Culture\n",
"Data Type: float64\n",
"Column: Chloride [Moles/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Nasal sinus endoscopy (procedure)\n",
"Data Type: object\n",
"Column: Total Bilirubin (Elevated)\n",
"Data Type: float64\n",
"Column: Progesterone receptor Ag [Presence] in Breast cancer specimen by Immune stain\n",
"Data Type: object\n",
"Column: Cardiac Arrest\n",
"Data Type: object\n",
"Column: Phenazopyridine hydrochloride 100 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Polyp size greatest dimension by CAP cancer protocols\n",
"Data Type: object\n",
"Column: Cholelithiasis\n",
"Data Type: object\n",
"Column: Mestranol / Norethynodrel [Enovid]\n",
"Data Type: object\n",
"Column: Epilepsy\n",
"Data Type: object\n",
"Column: Erythrocyte distribution width [Ratio] by Automated count\n",
"Data Type: object\n",
"Column: Acute viral pharyngitis (disorder)\n",
"Data Type: object\n",
"Column: Assessment using New York Heart Association Classification (procedure)\n",
"Data Type: object\n",
"Column: White Blood Cell (Elevated)\n",
"Data Type: float64\n",
"Column: Atropine Sulfate 1 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: Mirena 52 MG Intrauterine System\n",
"Data Type: object\n",
"Column: Nitrofurantoin 5 MG/ML Oral Suspension\n",
"Data Type: object\n",
"Column: Antepartum eclampsia\n",
"Data Type: object\n",
"Column: Fibrin D-dimer FEU [Mass/volume] in Platelet poor plasma\n",
"Data Type: float64\n",
"Column: Drugs of abuse 5 panel - Urine by Screen method\n",
"Data Type: object\n",
"Column: Hydroxychloroquine Sulfate 200 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Facial laceration\n",
"Data Type: object\n",
"Column: Information gathering (procedure)\n",
"Data Type: object\n",
"Column: Piperacillin 4000 MG / tazobactam 500 MG Injection\n",
"Data Type: object\n",
"Column: Open Removal of Gall Bladder\n",
"Data Type: object\n",
"Column: Brachytherapy of breast (procedure)\n",
"Data Type: object\n",
"Column: Carbon dioxide [Partial pressure] in Arterial blood\n",
"Data Type: float64\n",
"Column: Sinusitis (disorder)\n",
"Data Type: object\n",
"Column: Neoplasm of prostate\n",
"Data Type: object\n",
"Column: Mold (organism)\n",
"Data Type: object\n",
"Column: Assessment using Morse Fall Scale (procedure)\n",
"Data Type: object\n",
"Column: High Density Lipoprotein Cholesterol\n",
"Data Type: object\n",
"Column: Surgical manipulation of shoulder joint\n",
"Data Type: object\n",
"Column: Treatment status Cancer\n",
"Data Type: object\n",
"Column: Color of Urine\n",
"Data Type: object\n",
"Column: Homeless (finding)\n",
"Data Type: object\n",
"Column: Weaning from mechanically assisted ventilation (procedure)\n",
"Data Type: object\n",
"Column: Controlled ventilation procedure and therapy initiation and management (procedure)\n",
"Data Type: object\n",
"Column: History AND physical examination (procedure)\n",
"Data Type: object\n",
"Column: Lymphocytes/100 leukocytes in Blood by Automated count\n",
"Data Type: float64\n",
"Column: ferrous sulfate 325 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Excision of axillary lymph node (procedure)\n",
"Data Type: object\n",
"Column: Eosinophils [#/volume] in Blood by Automated count\n",
"Data Type: float64\n",
"Column: Estrostep Fe 28 Day Pack\n",
"Data Type: object\n",
"Column: Screening for domestic abuse (procedure)\n",
"Data Type: object\n",
"Column: Calcium\n",
"Data Type: object\n",
"Column: Chemotherapy (procedure)\n",
"Data Type: object\n",
"Column: Part-time employment (finding)\n",
"Data Type: object\n",
"Column: age\n",
"Data Type: object\n",
"Column: pregabalin 100 MG Oral Capsule\n",
"Data Type: object\n",
"Column: Iron binding capacity [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Galantamine 4 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Gout\n",
"Data Type: object\n",
"Column: Macular edema and retinopathy due to type 2 diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: Resuscitation using intravenous fluid (procedure)\n",
"Data Type: object\n",
"Column: Oxygen Saturation\n",
"Data Type: object\n",
"Column: Sepsis caused by Pseudomonas (disorder)\n",
"Data Type: float64\n",
"Column: Atrial Fibrillation\n",
"Data Type: object\n",
"Column: Fracture of ankle\n",
"Data Type: object\n",
"Column: Fever (finding)\n",
"Data Type: object\n",
"Column: Acetaminophen 325 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Monocytes/100 leukocytes in Blood by Automated count\n",
"Data Type: float64\n",
"Column: 1 ML denosumab 60 MG/ML Prefilled Syringe\n",
"Data Type: float64\n",
"Column: Excision of breast tissue (procedure)\n",
"Data Type: object\n",
"Column: Psychosocial care (regime/therapy)\n",
"Data Type: object\n",
"Column: Pyelonephritis\n",
"Data Type: object\n",
"Column: race\n",
"Data Type: object\n",
"Column: Camila 28 Day Pack\n",
"Data Type: object\n",
"Column: Human immunodeficiency virus antigen test\n",
"Data Type: object\n",
"Column: Levonorgestrel 0.00354 MG/HR Drug Implant\n",
"Data Type: object\n",
"Column: Admission to burn unit\n",
"Data Type: object\n",
"Column: Fracture of vertebral column without spinal cord injury\n",
"Data Type: object\n",
"Column: Escherichia coli urinary tract infection\n",
"Data Type: object\n",
"Column: Sodium Chloride 9 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: Acute deep venous thrombosis (disorder)\n",
"Data Type: object\n",
"Column: Acute pulmonary embolism (disorder)\n",
"Data Type: object\n",
"Column: Percutaneous mechanical thrombectomy of portal vein using fluoroscopic guidance\n",
"Data Type: object\n",
"Column: Male infertility due to cystic fibrosis (disorder)\n",
"Data Type: float64\n",
"Column: Left ventricular Ejection fraction\n",
"Data Type: object\n",
"Column: Fracture of clavicle\n",
"Data Type: object\n",
"Column: Oral Glucose Tolerance Test\n",
"Data Type: float64\n",
"Column: Skin test for tuberculosis\n",
"Data Type: object\n",
"Column: Norinyl 1+50 28 Day Pack\n",
"Data Type: object\n",
"Column: Amlodipine 5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: 3 ML Amiodarone hydrocholoride 50 MG/ML Prefilled Syringe\n",
"Data Type: object\n",
"Column: Acetaminophen/Hydrocodone\n",
"Data Type: object\n",
"Column: Bilateral tubal ligation\n",
"Data Type: object\n",
"Column: Hemoglobin.gastrointestinal [Presence] in Stool by Immunologic method\n",
"Data Type: object\n",
"Column: Catheter ablation of tissue of heart\n",
"Data Type: object\n",
"Column: Whiplash injury to neck\n",
"Data Type: object\n",
"Column: Normal pregnancy\n",
"Data Type: object\n",
"Column: Interleukin 6 [Mass/volume] in Serum or Plasma\n",
"Data Type: float64\n",
"Column: Red Blood Cell\n",
"Data Type: float64\n",
"Column: Take blood sample\n",
"Data Type: float64\n",
"Column: Glucose [Presence] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Liletta 52 MG Intrauterine System\n",
"Data Type: object\n",
"Column: Fracture of rib\n",
"Data Type: object\n",
"Column: sevoflurane 1000 MG/ML Inhalant Solution\n",
"Data Type: object\n",
"Column: Primary malignant neoplasm of colon\n",
"Data Type: object\n",
"Column: Injury of anterior cruciate ligament\n",
"Data Type: object\n",
"Column: 4 ML norepinephrine 1 MG/ML Injection\n",
"Data Type: object\n",
"Column: Familial Alzheimer's disease of early onset (disorder)\n",
"Data Type: object\n",
"Column: Tumor marker Cancer\n",
"Data Type: object\n",
"Column: Cefdinir\n",
"Data Type: object\n",
"Column: Procalcitonin [Mass/volume] in Serum or Plasma\n",
"Data Type: float64\n",
"Column: Total Cholesterol\n",
"Data Type: object\n",
"Column: Prothrombin time (PT)\n",
"Data Type: float64\n",
"Column: 1 ML DOCEtaxel 20 MG/ML Injection\n",
"Data Type: object\n",
"Column: Sprain of ankle\n",
"Data Type: object\n",
"Column: Vancomycin 50 MG/ML Injectable Solution\n",
"Data Type: float64\n",
"Column: Spirometry (procedure)\n",
"Data Type: object\n",
"Column: Initial patient assessment (procedure)\n",
"Data Type: object\n",
"Column: Albumin\n",
"Data Type: object\n",
"Column: albuterol 5 MG/ML Inhalation Solution\n",
"Data Type: object\n",
"Column: Cat dander IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Abuse-Deterrent 12 HR Oxycodone Hydrochloride 15 MG Extended Release Oral Tablet\n",
"Data Type: object\n",
"Column: HIV status\n",
"Data Type: object\n",
"Column: Miscarriage in first trimester\n",
"Data Type: object\n",
"Column: Lumpectomy of breast (procedure)\n",
"Data Type: object\n",
"Column: Levora 0.15/30 28 Day Pack\n",
"Data Type: object\n",
"Column: Colonoscopy\n",
"Data Type: object\n",
"Column: Hematocrit [Volume Fraction] of Blood by Automated count\n",
"Data Type: object\n",
"Column: Depression screening using Patient Health Questionnaire Nine Item score (procedure)\n",
"Data Type: object\n",
"Column: ribociclib 200 MG Oral Tablet\n",
"Data Type: object\n",
"Column: letrozole 2.5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Joint pain (finding)\n",
"Data Type: object\n",
"Column: Epidural anesthesia\n",
"Data Type: object\n",
"Column: Chronic obstructive bronchitis (disorder)\n",
"Data Type: object\n",
"Column: Burn injury(morphologic abnormality)\n",
"Data Type: object\n",
"Column: Sputum examination (procedure)\n",
"Data Type: object\n",
"Column: Second degree burn\n",
"Data Type: object\n",
"Column: Nitrite [Presence] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Hypertension\n",
"Data Type: object\n",
"Column: Anemia (disorder)\n",
"Data Type: object\n",
"Column: 100 ML Epirubicin Hydrochloride 2 MG/ML Injection\n",
"Data Type: object\n",
"Column: Osteoarthritis of hip\n",
"Data Type: object\n",
"Column: Passive conjunctival congestion (finding)\n",
"Data Type: object\n",
"Column: Acute Cholecystitis\n",
"Data Type: object\n",
"Column: Measurement of Varicella-zoster virus antibody\n",
"Data Type: object\n",
"Column: Stress (finding)\n",
"Data Type: object\n",
"Column: Chronic intractable migraine without aura\n",
"Data Type: object\n",
"Column: MCV\n",
"Data Type: float64\n",
"Column: Bilirubin.total [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Paclitaxel 100 MG Injection\n",
"Data Type: object\n",
"Column: Triglycerides\n",
"Data Type: object\n",
"Column: Chloride\n",
"Data Type: object\n",
"Column: Screening for occult blood in feces (procedure)\n",
"Data Type: object\n",
"Column: Body mass index 30+ - obesity (finding)\n",
"Data Type: object\n",
"Column: Trinessa 28 Day Pack\n",
"Data Type: object\n",
"Column: Interstitial brachytherapy (procedure)\n",
"Data Type: object\n",
"Column: Protracted diarrhea\n",
"Data Type: object\n",
"Column: Echocardiography (procedure)\n",
"Data Type: object\n",
"Column: buprenorphine 2 MG / naloxone 0.5 MG Sublingual Tablet\n",
"Data Type: object\n",
"Column: Urine screening for glucose\n",
"Data Type: object\n",
"Column: Acetaminophen 325 MG / Oxycodone Hydrochloride 10 MG Oral Tablet [Percocet]\n",
"Data Type: object\n",
"Column: Sentinel lymph node biopsy (procedure)\n",
"Data Type: object\n",
"Column: Alanine aminotransferase [Enzymatic activity/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Protein [Presence] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Astemizole 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Brain damage - traumatic\n",
"Data Type: object\n",
"Column: Transformed migraine (disorder)\n",
"Data Type: object\n",
"Column: Amputation of right foot\n",
"Data Type: object\n",
"Column: Admission to neurosurgical department\n",
"Data Type: float64\n",
"Column: Closed fracture of hip\n",
"Data Type: object\n",
"Column: Social isolation (finding)\n",
"Data Type: object\n",
"Column: Mammogram - symptomatic (procedure)\n",
"Data Type: object\n",
"Column: INR in Platelet poor plasma by Coagulation assay\n",
"Data Type: float64\n",
"Column: Laceration of foot\n",
"Data Type: object\n",
"Column: Lisinopril\n",
"Data Type: object\n",
"Column: Codfish IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Bilirubin.total [Presence] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Auscultation of the fetal heart\n",
"Data Type: object\n",
"Column: ado-trastuzumab emtansine 100 MG Injection\n",
"Data Type: float64\n",
"Column: Influenza virus B RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: History of disarticulation at wrist (situation)\n",
"Data Type: float64\n",
"Column: tramadol hydrochloride 50 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Kyleena 19.5 MG Intrauterine System\n",
"Data Type: object\n",
"Column: Creatine kinase [Enzymatic activity/volume] in Serum or Plasma\n",
"Data Type: float64\n",
"Column: duloxetine 20 MG Delayed Release Oral Capsule\n",
"Data Type: object\n",
"Column: Hyperglycemia (disorder)\n",
"Data Type: object\n",
"Column: Bilirubin.total [Mass/volume] in Urine by Test strip\n",
"Data Type: object\n",
"Column: MCH [Entitic mass] by Automated count\n",
"Data Type: object\n",
"Column: losartan potassium 50 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Acetaminophen 325 MG Oral Tablet [Tylenol]\n",
"Data Type: object\n",
"Column: Naltrexone hydrochloride 50 MG Oral Tablet\n",
"Data Type: object\n",
"Column: 10 ML Pamidronate Disodium 3 MG/ML Injection\n",
"Data Type: object\n",
"Column: Biopsy of colon\n",
"Data Type: object\n",
"Column: Latex IgE Ab in Serum\n",
"Data Type: object\n",
"Column: methadone hydrochloride 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Acetaminophen 325 MG / oxyCODONE Hydrochloride 2.5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Prostatectomy\n",
"Data Type: object\n",
"Column: Sepsis (disorder)\n",
"Data Type: object\n",
"Column: Cesarean section\n",
"Data Type: object\n",
"Column: Intravenous blood transfusion of packed cells (procedure)\n",
"Data Type: object\n",
"Column: Vitamin B 12 5 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: Prostate specific Ag [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Teleradiotherapy procedure (procedure)\n",
"Data Type: object\n",
"Column: Thyrotropin [Units/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Gram positive blood culture panel by Probe in Positive blood culture\n",
"Data Type: object\n",
"Column: SARS-CoV-2 RNA Pnl Resp NAA+probe\n",
"Data Type: object\n",
"Column: Digital examination of rectum\n",
"Data Type: object\n",
"Column: Heart failure education (procedure)\n",
"Data Type: object\n",
"Column: Fracture of the vertebral column with spinal cord injury\n",
"Data Type: object\n",
"Column: Has a criminal record (finding)\n",
"Data Type: object\n",
"Column: Patient discharge (procedure)\n",
"Data Type: object\n",
"Column: Leukocytes [#/volume] in Blood by Automated count\n",
"Data Type: object\n",
"Column: Medication Reconciliation (procedure)\n",
"Data Type: object\n",
"Column: Assessment using Alcohol Use Disorders Identification Test - Consumption (procedure)\n",
"Data Type: object\n",
"Column: Recurrent rectal polyp\n",
"Data Type: object\n",
"Column: Mental health Telehealth Note\n",
"Data Type: float64\n",
"Column: Tobacco smoking status NHIS\n",
"Data Type: object\n",
"Column: Parainfluenza virus 1 RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: Ankle X-ray\n",
"Data Type: object\n",
"Column: Secondary malignant neoplasm of colon\n",
"Data Type: object\n",
"Column: desflurane 1000 MG/ML Inhalation Solution\n",
"Data Type: object\n",
"Column: Throat culture (procedure)\n",
"Data Type: object\n",
"Column: Attempted suicide - cut/stab\n",
"Data Type: float64\n",
"Column: Face mask (physical object)\n",
"Data Type: object\n",
"Column: Polyp of colon\n",
"Data Type: object\n",
"Column: Premature birth of newborn\n",
"Data Type: object\n",
"Column: Penicillin V\n",
"Data Type: object\n",
"Column: Anion Gap\n",
"Data Type: float64\n",
"Column: pH of Arterial blood\n",
"Data Type: float64\n",
"Column: Hyperlipidemia\n",
"Data Type: object\n",
"Column: 10 ML Furosemide 10 MG/ML Injection\n",
"Data Type: object\n",
"Column: Rubella screening\n",
"Data Type: object\n",
"Column: Glucose [Mass/volume] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Incision of trachea (procedure)\n",
"Data Type: float64\n",
"Column: Td (adult) preservative free\n",
"Data Type: object\n",
"Column: Yaz 28 Day Pack\n",
"Data Type: object\n",
"Column: Chronic kidney disease stage 2 (disorder)\n",
"Data Type: object\n",
"Column: Physical therapy procedure (regime/therapy)\n",
"Data Type: object\n",
"Column: RhD passive immunization\n",
"Data Type: object\n",
"Column: Cyclophosphamide 1000 MG Injection\n",
"Data Type: object\n",
"Column: RBC Distribution Width\n",
"Data Type: float64\n",
"Column: Lymphocytes [#/volume] in Blood by Automated count\n",
"Data Type: float64\n",
"Column: Plain chest X-ray (procedure)\n",
"Data Type: object\n",
"Column: Ketones [Presence] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Suicidal deliberate poisoning\n",
"Data Type: object\n",
"Column: Transplant of lung (procedure)\n",
"Data Type: object\n",
"Column: Otitis media\n",
"Data Type: object\n",
"Column: X-ray or wrist\n",
"Data Type: object\n",
"Column: HER2 [Presence] in Breast cancer specimen by FISH\n",
"Data Type: object\n",
"Column: Shock (disorder)\n",
"Data Type: object\n",
"Column: Estrogen+Progesterone receptor Ag [Presence] in Tissue by Immune stain\n",
"Data Type: object\n",
"Column: Hemoptysis (finding)\n",
"Data Type: object\n",
"Column: Transport problems (finding)\n",
"Data Type: object\n",
"Column: Body Mass Index\n",
"Data Type: object\n",
"Column: Respiratory distress (finding)\n",
"Data Type: object\n",
"Column: remdesivir 100 MG Injection\n",
"Data Type: float64\n",
"Column: Rectal polypectomy\n",
"Data Type: object\n",
"Column: Renal dialysis (procedure)\n",
"Data Type: object\n",
"Column: Glucose [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: 0.3 ML Enoxaparin sodium 100 MG/ML Prefilled Syringe\n",
"Data Type: object\n",
"Column: Parainfluenza virus 3 RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: 1 ML Epoetin Alfa 4000 UNT/ML Injection [Epogen]\n",
"Data Type: object\n",
"Column: Assessment of health and social care needs (procedure)\n",
"Data Type: object\n",
"Column: Transfusion of plasma (procedure)\n",
"Data Type: object\n",
"Column: Asthma screening\n",
"Data Type: object\n",
"Column: Erythrocyte distribution width [Entitic volume] by Automated count\n",
"Data Type: object\n",
"Column: Occupational therapy (regime/therapy)\n",
"Data Type: object\n",
"Column: Penicillin V Potassium 500 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Induced termination of pregnancy\n",
"Data Type: object\n",
"Column: Laceration of hand\n",
"Data Type: object\n",
"Column: Laceration of thigh\n",
"Data Type: object\n",
"Column: Biopsy of prostate\n",
"Data Type: object\n",
"Column: 12 HR Cefaclor 500 MG Extended Release Oral Tablet\n",
"Data Type: object\n",
"Column: Mental health Outpatient Note\n",
"Data Type: float64\n",
"Column: Mean blood pressure\n",
"Data Type: object\n",
"Column: Excision of sentinel lymph node (procedure)\n",
"Data Type: object\n",
"Column: Verzenio 100 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Respiratory syncytial virus RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: Intravenous injection (procedure)\n",
"Data Type: object\n",
"Column: Glomerular filtration rate/1.73 sq M.predicted\n",
"Data Type: object\n",
"Column: Episiotomy\n",
"Data Type: object\n",
"Column: Infection caused by Staphylococcus aureus\n",
"Data Type: float64\n",
"Column: Acetaminophen 325 MG / oxyCODONE Hydrochloride 5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Digoxin 0.125 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Alcoholism\n",
"Data Type: object\n",
"Column: Proteinuria due to type 2 diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: MCHC [Mass/volume] by Automated count\n",
"Data Type: object\n",
"Column: Methotrexate injection into tubal pregnancy\n",
"Data Type: object\n",
"Column: Stroke\n",
"Data Type: object\n",
"Column: Human epidermal growth factor receptor 2 gene detection by immunohistochemistry (procedure)\n",
"Data Type: object\n",
"Column: Hydrochlorothiazide 25 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Fexofenadine hydrochloride 60 MG Oral Tablet\n",
"Data Type: object\n",
"Column: NDA020800 0.3 ML Epinephrine 1 MG/ML Auto-Injector\n",
"Data Type: object\n",
"Column: Azithromycin 250 MG Oral Tablet\n",
"Data Type: float64\n",
"Column: label\n",
"Data Type: int64\n",
"Column: Assessment of anxiety (procedure)\n",
"Data Type: object\n",
"Column: Social case work (regime/therapy)\n",
"Data Type: object\n",
"Column: Loratadine 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Ibuprofen\n",
"Data Type: float64\n",
"Column: pH of Urine by Test strip\n",
"Data Type: object\n",
"Column: Potassium\n",
"Data Type: object\n",
"Column: Leronlimab 700 MG Injection\n",
"Data Type: float64\n",
"Column: Platelets [#/volume] in Blood by Automated count\n",
"Data Type: object\n",
"Column: History of cardiac arrest (situation)\n",
"Data Type: object\n",
"Column: Idiopathic atrophic hypothyroidism\n",
"Data Type: object\n",
"Column: Surgical manipulation of joint of knee\n",
"Data Type: object\n",
"Column: Verapamil Hydrochloride 40 MG\n",
"Data Type: object\n",
"Column: Bone immobilization\n",
"Data Type: object\n",
"Column: Seizure disorder\n",
"Data Type: object\n",
"Column: 120 ACTUAT Fluticasone propionate 0.044 MG/ACTUAT Metered Dose Inhaler\n",
"Data Type: object\n",
"Column: Electrocardiographic procedure\n",
"Data Type: object\n",
"Column: Errin 28 Day Pack\n",
"Data Type: object\n",
"Column: Contact dermatitis\n",
"Data Type: object\n",
"Column: Isoflurane 999 MG/ML Inhalant Solution\n",
"Data Type: object\n",
"Column: Hep A adult\n",
"Data Type: object\n",
"Column: Urine protein test\n",
"Data Type: object\n",
"Column: Cardiovascular stress testing (procedure)\n",
"Data Type: object\n",
"Column: Diastolic Blood Pressure\n",
"Data Type: object\n",
"Column: Aspirin\n",
"Data Type: object\n",
"Column: Nasal congestion (finding)\n",
"Data Type: object\n",
"Column: zoster\n",
"Data Type: object\n",
"Column: Concussion injury of brain\n",
"Data Type: object\n",
"Column: cycloSPORINE modified 100 MG Oral Capsule\n",
"Data Type: object\n",
"Column: Coronary artery bypass grafting\n",
"Data Type: object\n",
"Column: Levothyroxine Sodium 0.075 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Etonogestrel 68 MG Drug Implant\n",
"Data Type: object\n",
"Column: Eosinophils/100 leukocytes in Blood by Automated count\n",
"Data Type: float64\n",
"Column: baricitinib 2 MG Oral Tablet\n",
"Data Type: float64\n",
"Column: Insertion of biventricular implantable cardioverter defibrillator\n",
"Data Type: object\n",
"Column: Ultrasonography of abdomen right upper quadrant and epigastrium\n",
"Data Type: object\n",
"Column: Reports of violence in the environment (finding)\n",
"Data Type: object\n",
"Column: Hepatitis C antibody test\n",
"Data Type: object\n",
"Column: Tree pollen (substance)\n",
"Data Type: object\n",
"Column: Gonorrhea infection test\n",
"Data Type: object\n",
"Column: Intracavitary brachytherapy (procedure)\n",
"Data Type: object\n",
"Column: 10 ML Doxorubicin Hydrochloride 2 MG/ML Injection\n",
"Data Type: object\n",
"Column: Medical induction of labor\n",
"Data Type: object\n",
"Column: Smokes tobacco daily\n",
"Data Type: object\n",
"Column: Housing status\n",
"Data Type: object\n",
"Column: Chronic pain\n",
"Data Type: object\n",
"Column: 12 HR Hydrocodone Bitartrate 10 MG Extended Release Oral Capsule\n",
"Data Type: object\n",
"Column: Lack of access to transportation (finding)\n",
"Data Type: object\n",
"Column: Opioid abuse (disorder)\n",
"Data Type: object\n",
"Column: Syphilis infection test\n",
"Data Type: object\n",
"Column: Limited social contact (finding)\n",
"Data Type: object\n",
"Column: Subcutaneous immunotherapy\n",
"Data Type: object\n",
"Column: Donepezil hydrochloride 23 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Acquired coagulation disorder (disorder)\n",
"Data Type: object\n",
"Column: Fetal anatomy study\n",
"Data Type: object\n",
"Column: Myocardial Infarction\n",
"Data Type: object\n",
"Column: insulin human isophane 70 UNT/ML / Regular Insulin Human 30 UNT/ML Injectable Suspension [Humulin]\n",
"Data Type: object\n",
"Column: Oxygen [Partial pressure] in Arterial blood\n",
"Data Type: float64\n",
"Column: Hypoxemia (disorder)\n",
"Data Type: object\n",
"Column: Discharge from skilled nursing facility (procedure)\n",
"Data Type: object\n",
"Column: Chlorpheniramine Maleate 4 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Dyspnea (finding)\n",
"Data Type: object\n",
"Column: Assessment of substance use (procedure)\n",
"Data Type: object\n",
"Column: Iron saturation [Mass Fraction] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Suicide risk assessment (procedure)\n",
"Data Type: object\n",
"Column: Chill (finding)\n",
"Data Type: object\n",
"Column: Microbial culture (procedure)\n",
"Data Type: object\n",
"Column: 10 ML Alfentanil 0.5 MG/ML Injection\n",
"Data Type: object\n",
"Column: Depression screening using Patient Health Questionnaire Two-Item score (procedure)\n",
"Data Type: object\n",
"Column: 150 ML vancomycin 5 MG/ML Injection\n",
"Data Type: object\n",
"Column: Measurement of respiratory function (procedure)\n",
"Data Type: object\n",
"Column: Fibromyalgia (disorder)\n",
"Data Type: object\n",
"Column: Tamoxifen 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Full-time employment (finding)\n",
"Data Type: object\n",
"Column: 100 ML Propofol 10 MG/ML Injection\n",
"Data Type: object\n",
"Column: Screening for drug abuse (procedure)\n",
"Data Type: object\n",
"Column: Suture open wound\n",
"Data Type: object\n",
"Column: DXA [T-score] Bone density\n",
"Data Type: object\n",
"Column: 24hr nicotine transdermal patch\n",
"Data Type: object\n",
"Column: Atorvastatin 80 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Insertion of endotracheal tube (procedure)\n",
"Data Type: object\n",
"Column: Victim of intimate partner abuse (finding)\n",
"Data Type: object\n",
"Column: Meperidine Hydrochloride 50 MG Oral Tablet\n",
"Data Type: object\n",
"Column: History of myocardial infarction (situation)\n",
"Data Type: object\n",
"Column: Vomiting symptom (finding)\n",
"Data Type: object\n",
"Column: Cough (finding)\n",
"Data Type: object\n",
"Column: Osteoporosis (disorder)\n",
"Data Type: object\n",
"Column: Fatigue (finding)\n",
"Data Type: object\n",
"Column: FEV1/FVC\n",
"Data Type: object\n",
"Column: exemestane 25 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Captopril 25 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Asthma\n",
"Data Type: object\n",
"Column: 1 ML Enoxaparin sodium 150 MG/ML Prefilled Syringe\n",
"Data Type: object\n",
"Column: Wheat IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Carbon Dioxide\n",
"Data Type: object\n",
"Column: Development of individualized plan of care (procedure)\n",
"Data Type: object\n",
"Column: Protein [Mass/volume] in Urine by Test strip\n",
"Data Type: object\n",
"Column: SARS-COV-2 (COVID-19) vaccine mRNA spike protein LNP preservative free 30 mcg/0.3mL dose\n",
"Data Type: object\n",
"Column: Oxygen Therapy\n",
"Data Type: object\n",
"Column: Basophils [#/volume] in Blood by Automated count\n",
"Data Type: float64\n",
"Column: Honey bee IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Placing subject in prone position (procedure)\n",
"Data Type: object\n",
"Column: Carcinoma in situ of prostate (disorder)\n",
"Data Type: object\n",
"Column: Monitoring of patient (regime/therapy)\n",
"Data Type: object\n",
"Column: COVID-19\n",
"Data Type: object\n",
"Column: 5 ML hyaluronidase-oysk 2000 UNT/ML / trastuzumab 120 MG/ML Injection\n",
"Data Type: object\n",
"Column: sacubitril 97 MG / valsartan 103 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Allergy screening test\n",
"Data Type: object\n",
"Column: Insulin Lispro 100 UNT/ML Injectable Solution [Humalog]\n",
"Data Type: object\n",
"Column: Azithromycin 250mg\n",
"Data Type: object\n",
"Column: Referral to home health care service (procedure)\n",
"Data Type: object\n",
"Column: 5 ML fulvestrant 50 MG/ML Prefilled Syringe\n",
"Data Type: object\n",
"Column: Fracture of forearm\n",
"Data Type: object\n",
"Column: Spontaneous breech delivery\n",
"Data Type: object\n",
"Column: Respiratory rate\n",
"Data Type: object\n",
"Column: Diabetic retinopathy associated with type II diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: Bullet wound\n",
"Data Type: object\n",
"Column: Professional / ancillary services care (regime/therapy)\n",
"Data Type: object\n",
"Column: 24 HR Metformin hydrochloride 500 MG Extended Release Oral Tablet\n",
"Data Type: object\n",
"Column: Childbirth\n",
"Data Type: object\n",
"Column: Injury of kidney (disorder)\n",
"Data Type: object\n",
"Column: Construction of diverting colostomy\n",
"Data Type: object\n",
"Column: Fetus with unknown complication\n",
"Data Type: object\n",
"Column: Admit to ICU (procedure)\n",
"Data Type: object\n",
"Column: Lorazepam 2 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: Admission to trauma surgery department\n",
"Data Type: object\n",
"Column: Blighted ovum\n",
"Data Type: object\n",
"Column: Platelet mean volume [Entitic volume] in Blood by Automated count\n",
"Data Type: object\n",
"Column: Cow milk IgE Ab in Serum\n",
"Data Type: object\n",
"Column: 1 ML Morphine Sulfate 5 MG/ML Injection\n",
"Data Type: object\n",
"Column: Laparoscopic Removal of Gall Bladder\n",
"Data Type: object\n",
"Column: Aztreonam 2000 MG Injection\n",
"Data Type: object\n",
"Column: Screening for chromosomal aneuploidy in prenatal amniotic fluid\n",
"Data Type: object\n",
"Column: Sputum finding (finding)\n",
"Data Type: object\n",
"Column: Pelvis X-ray\n",
"Data Type: object\n",
"Column: predniSONE 20 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Pre-discharge assessment (procedure)\n",
"Data Type: object\n",
"Column: Urine screening test for diabetes\n",
"Data Type: object\n",
"Column: Ferritin [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Estrogen receptor Ag [Presence] in Breast cancer specimen by Immune stain\n",
"Data Type: object\n",
"Column: Lung volume reduction surgery (procedure)\n",
"Data Type: object\n",
"Column: Sepsis caused by Staphylococcus aureus\n",
"Data Type: float64\n",
"Column: Soybean IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Blood typing RH typing\n",
"Data Type: object\n",
"Column: Jolivette 28 Day Pack\n",
"Data Type: object\n",
"Column: Bee venom (substance)\n",
"Data Type: float64\n",
"Column: Total knee replacement\n",
"Data Type: object\n",
"Column: Walnut IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Thyroxine (T4) free [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Certification procedure (procedure)\n",
"Data Type: object\n",
"Column: Viral sinusitis (disorder)\n",
"Data Type: object\n",
"Column: Third degree burn\n",
"Data Type: object\n",
"Column: Cystitis\n",
"Data Type: object\n",
"Column: Social migrant (finding)\n",
"Data Type: float64\n",
"Column: Chronic neck pain (finding)\n",
"Data Type: object\n",
"Column: 0.67 ML anakinra 149 MG/ML Prefilled Syringe\n",
"Data Type: float64\n",
"Column: Sore throat symptom (finding)\n",
"Data Type: object\n",
"Column: Removal of subcutaneous contraceptive\n",
"Data Type: object\n",
"Column: Amoxicillin 250 MG Oral Capsule\n",
"Data Type: object\n",
"Column: Cefuroxime 250 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Latex (substance)\n",
"Data Type: float64\n",
"Column: Coordination of care plan (procedure)\n",
"Data Type: object\n",
"Column: Alendronic acid 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Intravenous infusion (procedure)\n",
"Data Type: float64\n",
"Column: Hypertriglyceridemia (disorder)\n",
"Data Type: object\n",
"Column: Ultrasonography of bilateral breasts (procedure)\n",
"Data Type: object\n",
"Column: 10 ML Fluorouracil 50 MG/ML Injection\n",
"Data Type: object\n",
"Column: Clopidogrel 75 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Influenza virus A RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: Primary fibromyalgia syndrome\n",
"Data Type: object\n",
"Column: Intubation\n",
"Data Type: object\n",
"Column: SARS-COV-2 (COVID-19) vaccine mRNA spike protein LNP preservative free 100 mcg/0.5mL dose\n",
"Data Type: object\n",
"Column: Diarrhea symptom (finding)\n",
"Data Type: object\n",
"Column: pneumococcal polysaccharide vaccine 23 valent\n",
"Data Type: object\n",
"Column: Appearance of Urine\n",
"Data Type: object\n",
"Column: Chronic congestive heart failure (disorder)\n",
"Data Type: object\n",
"Column: 1 ML Epinephrine 1 MG/ML Injection\n",
"Data Type: object\n",
"Column: Sweat Test\n",
"Data Type: float64\n",
"Column: Pulmonary emphysema (disorder)\n",
"Data Type: object\n",
"Column: Ampicillin 100 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: clonazePAM 0.25 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Diabetes from Cystic Fibrosis\n",
"Data Type: float64\n",
"Column: NDA020503 200 ACTUAT Albuterol 0.09 MG/ACTUAT Metered Dose Inhaler\n",
"Data Type: object\n",
"Column: Vaccination for diphtheria pertussis and tetanus\n",
"Data Type: object\n",
"Column: Rupture of patellar tendon\n",
"Data Type: object\n",
"Column: Ibuprofen 200 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Penicillin G 375 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: Simvastatin 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Acetaminophen 325 MG / HYDROcodone Bitartrate 7.5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Are you covered by health insurance or some other kind of health care plan [PhenX]\n",
"Data Type: object\n",
"Column: Amoxicillin 250 MG / Clavulanate 125 MG Oral Tablet\n",
"Data Type: object\n",
"Column: remifentanil 2 MG Injection\n",
"Data Type: object\n",
"Column: Artificial respiration (procedure)\n",
"Data Type: object\n",
"Column: Tear of meniscus of knee\n",
"Data Type: object\n",
"Column: 100 ML zoledronic acid 0.04 MG/ML Injection\n",
"Data Type: object\n",
"Column: Pregnancy termination care\n",
"Data Type: object\n",
"Column: Urea Nitrogen\n",
"Data Type: object\n",
"Column: Fracture subluxation of wrist\n",
"Data Type: object\n",
"Column: Electrical cardioversion\n",
"Data Type: object\n",
"Column: Pulmonary rehabilitation (regime/therapy)\n",
"Data Type: object\n",
"Column: Hemoglobin [Presence] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Sulfamethoxazole / Trimethoprim\n",
"Data Type: object\n",
"Column: Human epidermal growth factor receptor 2 gene detection by fluorescence in situ hybridization (procedure)\n",
"Data Type: object\n",
"Column: Chronic paralysis due to lesion of spinal cord\n",
"Data Type: object\n",
"Column: Depression screening (procedure)\n",
"Data Type: object\n",
"Column: Influenza virus A Ag [Presence] in Nasopharynx by Rapid immunoassay\n",
"Data Type: object\n",
"Column: Pathological fracture due to osteoporosis (disorder)\n",
"Data Type: object\n",
"Column: Acetaminophen 300 MG / Codeine Phosphate 15 MG Oral Tablet\n",
"Data Type: object\n",
"Column: gender\n",
"Data Type: object\n",
"Column: Instrumental delivery\n",
"Data Type: object\n",
"Column: Rupture of appendix\n",
"Data Type: object\n",
"Column: Admission to orthopedic department\n",
"Data Type: object\n",
"Column: Mental health screening (procedure)\n",
"Data Type: object\n",
"Column: Peripheral blood smear interpretation\n",
"Data Type: object\n",
"Column: Alkaline phosphatase [Enzymatic activity/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Leukocyte esterase [Presence] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Care regimes assessment (procedure)\n",
"Data Type: object\n",
"Column: Magnesium [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: 168 HR Ethinyl Estradiol 0.00146 MG/HR / norelgestromin 0.00625 MG/HR Transdermal System\n",
"Data Type: object\n",
"Column: Influenza virus B Ag [Presence] in Nasopharynx by Rapid immunoassay\n",
"Data Type: object\n",
"Column: House dust mite (organism)\n",
"Data Type: object\n",
"Column: 0.25 ML Leuprolide Acetate 30 MG/ML Prefilled Syringe\n",
"Data Type: object\n",
"Column: Microalbuminuria due to type 2 diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: Neutrophils [#/volume] in Blood by Automated count\n",
"Data Type: float64\n",
"Column: Influenza seasonal injectable preservative free\n",
"Data Type: object\n",
"Column: Metastasis from malignant tumor of prostate (disorder)\n",
"Data Type: object\n",
"Column: 3 ML liraglutide 6 MG/ML Pen Injector\n",
"Data Type: object\n",
"Column: palbociclib 100 MG Oral Capsule\n",
"Data Type: object\n",
"Column: Terfenadine 60 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Shrimp IgE Ab in Serum\n",
"Data Type: object\n",
"Column: US Guidance for biopsy of Prostate\n",
"Data Type: object\n",
"Column: cetirizine hydrochloride 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Intramuscular injection\n",
"Data Type: object\n",
"Column: Hospital admission short-term 24 hours\n",
"Data Type: object\n",
"Column: marital\n",
"Data Type: object\n",
"Column: Nonproliferative diabetic retinopathy due to type 2 diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: 1 ML medroxyPROGESTERone acetate 150 MG/ML Injection\n",
"Data Type: object\n",
"Column: Non-low risk pregnancy\n",
"Data Type: float64\n",
"Column: 60 ACTUAT Fluticasone propionate 0.25 MG/ACTUAT / salmeterol 0.05 MG/ACTUAT Dry Powder Inhaler\n",
"Data Type: object\n",
"Column: Bacterial infectious disease (disorder)\n",
"Data Type: object\n",
"Column: Blindness due to type 2 diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: White oak IgE Ab in Serum\n",
"Data Type: object\n",
"Column: History of lower limb amputation (situation)\n",
"Data Type: object\n",
"Column: Calcium [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Alpha-fetoprotein test\n",
"Data Type: object\n",
"Column: Manual pelvic examination (procedure)\n",
"Data Type: object\n",
"Column: 20 Gene mutation test\n",
"Data Type: float64\n",
"Column: Sprain of wrist\n",
"Data Type: object\n",
"Column: Appendicitis\n",
"Data Type: object\n",
"Column: Furosemide 40 MG Oral Tablet\n",
"Data Type: object\n",
"Column: carvedilol 25 MG Oral Tablet\n",
"Data Type: object\n",
"Column: MCV [Entitic volume] by Automated count\n",
"Data Type: object\n",
"Column: Lung Transplant\n",
"Data Type: float64\n",
"Column: scc\n",
"Data Type: int64\n",
"Column: Grass pollen (substance)\n",
"Data Type: float64\n",
"Column: Peanut IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Hepatitis B Surface Antigen Measurement\n",
"Data Type: object\n",
"Column: piperacillin 2000 MG / tazobactam 250 MG Injection\n",
"Data Type: object\n",
"Column: Concussion with no loss of consciousness\n",
"Data Type: object\n",
"Column: Localized primary osteoarthritis of the hand\n",
"Data Type: object\n",
"Column: lapatinib 250 MG Oral Tablet\n",
"Data Type: float64\n",
"Column: Hemoglobin [Mass/volume] in Blood\n",
"Data Type: object\n",
"Column: 1 ML heparin sodium porcine 5000 UNT/ML Injection\n",
"Data Type: object\n",
"Column: Suspected COVID-19\n",
"Data Type: object\n",
"Column: Wheezing (finding)\n",
"Data Type: object\n",
"Column: Aspirin 81 MG Oral Tablet\n",
"Data Type: object\n",
"Column: neratinib 40 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Lenzilumab 200 MG IV\n",
"Data Type: float64\n",
"Column: Acute respiratory distress syndrome (disorder)\n",
"Data Type: object\n",
"Column: Hospice care (regime/therapy)\n",
"Data Type: object\n",
"Column: Injury of tendon of the rotator cuff of shoulder\n",
"Data Type: object\n",
"Column: Pneumonia (disorder)\n",
"Data Type: object\n",
"Column: Extraction of wisdom tooth\n",
"Data Type: object\n",
"Column: Specific gravity of Urine by Test strip\n",
"Data Type: object\n",
"Column: Aspartate aminotransferase [Enzymatic activity/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Heart failure (disorder)\n",
"Data Type: object\n",
"Column: Ketones [Mass/volume] in Urine by Test strip\n",
"Data Type: object\n",
"Column: Hemoglobin A1c/Hemoglobin.total in Blood\n",
"Data Type: object\n",
"Column: Augmentation of labor\n",
"Data Type: object\n",
"Column: Hemodialysis (procedure)\n",
"Data Type: object\n",
"Column: Implantation of left ventricular assist device (procedure)\n",
"Data Type: object\n",
"Column: Physical examination\n",
"Data Type: object\n",
"Column: Review of systems (procedure)\n",
"Data Type: object\n",
"Column: Bleeding from anus\n",
"Data Type: object\n",
"Column: Brief general examination (procedure)\n",
"Data Type: object\n",
"Column: Admission to long stay hospital\n",
"Data Type: object\n",
"Column: state\n",
"Data Type: object\n",
"Column: Urea nitrogen [Mass/volume] in Serum or Plasma\n",
"Data Type: object\n",
"Column: Chronic sinusitis (disorder)\n",
"Data Type: object\n",
"Column: Urine culture\n",
"Data Type: object\n",
"Column: Warfarin Sodium 5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Partial resection of colon\n",
"Data Type: object\n",
"Column: Bicarbonate [Moles/volume] in Arterial blood\n",
"Data Type: float64\n",
"Column: Coronary Heart Disease\n",
"Data Type: object\n",
"Column: Screening mammography (procedure)\n",
"Data Type: object\n",
"Column: Troponin I.cardiac [Mass/volume] in Serum or Plasma by High sensitivity method\n",
"Data Type: object\n",
"Column: Midazolam 1 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: Acetaminophen 500 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Transfer to stepdown unit (procedure)\n",
"Data Type: object\n",
"Column: Muscle pain (finding)\n",
"Data Type: object\n",
"Column: lisinopril 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Functional capacity NYHA\n",
"Data Type: object\n",
"Column: Standard pregnancy test\n",
"Data Type: object\n",
"Column: Malignant tumor of colon\n",
"Data Type: object\n",
"Column: NT-proBNP\n",
"Data Type: object\n",
"Column: Injury of heart (disorder)\n",
"Data Type: object\n",
"Column: Human metapneumovirus RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: Streptococcal sore throat (disorder)\n",
"Data Type: object\n",
"Column: Appendectomy\n",
"Data Type: object\n",
"Column: canagliflozin 100 MG Oral Tablet\n",
"Data Type: float64\n",
"Column: Septic shock (disorder)\n",
"Data Type: object\n",
"Column: Biopsy of breast (procedure)\n",
"Data Type: object\n",
"Column: 10 ML Fentanyl 0.05 MG/ML Injection\n",
"Data Type: object\n",
"Column: Seizure Count Cerebral Cortex Electroencephalogram (EEG)\n",
"Data Type: object\n",
"Column: Abuse Status [OMAHA]\n",
"Data Type: object\n",
"Column: Oxygen saturation in Arterial blood\n",
"Data Type: object\n",
"Column: Pain severity - 0-10 verbal numeric rating [Score] - Reported\n",
"Data Type: object\n",
"Column: Combined chemotherapy and radiation therapy (procedure)\n",
"Data Type: object\n",
"Column: Parainfluenza virus 2 RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: Oxygen/Inspired gas setting [Volume Fraction] Ventilator\n",
"Data Type: float64\n",
"Column: History of appendectomy\n",
"Data Type: object\n",
"Column: Diazepam 5 MG/ML Injectable Solution\n",
"Data Type: float64\n",
"Column: Overlapping malignant neoplasm of colon\n",
"Data Type: object\n",
"Column: Seasonique 91 Day Pack\n",
"Data Type: object\n",
"Column: losartan potassium 25 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Acute bacterial sinusitis (disorder)\n",
"Data Type: object\n",
"Column: Referral to hypertension clinic\n",
"Data Type: object\n",
"Column: amLODIPine 2.5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Knee X-ray\n",
"Data Type: object\n",
"Column: Carbamazepine[Tegretol]\n",
"Data Type: object\n",
"Column: Ibuprofen 400 MG Oral Tablet [Ibu]\n",
"Data Type: object\n",
"Column: Lupus erythematosus\n",
"Data Type: float64\n",
"Column: Upper arm X-ray\n",
"Data Type: object\n",
"Column: Stage group.clinical Cancer\n",
"Data Type: object\n",
"Column: Clavicle X-ray\n",
"Data Type: object\n",
"Column: Hydrocortisone 10 MG/ML Topical Cream\n",
"Data Type: object\n",
"Column: Nursing care/supplementary surveillance (regime/therapy)\n",
"Data Type: object\n",
"Column: Rocuronium bromide 10 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: SARS-COV-2 (COVID-19) vaccine vector non-replicating recombinant spike protein-Ad26 preservative free 0.5 mL\n",
"Data Type: object\n",
"Column: Oxygen administration by mask (procedure)\n",
"Data Type: object\n",
"Column: Preeclampsia\n",
"Data Type: object\n",
"Column: NITROFURANTOIN MACROCRYSTALS 50 MG Oral Capsule\n",
"Data Type: object\n",
"Column: Basophils/100 leukocytes in Blood by Automated count\n",
"Data Type: float64\n",
"Column: Response to cancer treatment\n",
"Data Type: object\n",
"Column: Carboplatin 10 MG/ML Injectable Solution\n",
"Data Type: object\n",
"Column: American house dust mite IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Pancreatin 600 MG Oral Tablet\n",
"Data Type: float64\n",
"Column: Diabetic renal disease (disorder)\n",
"Data Type: object\n",
"Column: Counseling for termination of pregnancy\n",
"Data Type: object\n",
"Column: lisinopril 20 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Cladosporium herbarum IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Memantine hydrochloride 2 MG/ML Oral Solution\n",
"Data Type: object\n",
"Column: Doxycycline Monohydrate 100 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Acetaminophen 21.7 MG/ML / Dextromethorphan Hydrobromide 1 MG/ML / doxylamine succinate 0.417 MG/ML Oral Solution\n",
"Data Type: object\n",
"Column: At risk for suicide (finding)\n",
"Data Type: object\n",
"Column: Animal dander (substance)\n",
"Data Type: object\n",
"Column: 1 ML Vasopressin (USP) 20 UNT/ML Injection\n",
"Data Type: object\n",
"Column: Intravenous antibiotic therapy\n",
"Data Type: float64\n",
"Column: Chronic kidney disease stage 3 (disorder)\n",
"Data Type: object\n",
"Column: Refugee (person)\n",
"Data Type: object\n",
"Column: Egg white IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Body mass index 40+ - severely obese (finding)\n",
"Data Type: object\n",
"Column: NuvaRing 0.12/0.015 MG per 24HR 21 Day Vaginal Ring\n",
"Data Type: object\n",
"Column: Malignant neoplasm of breast (disorder)\n",
"Data Type: object\n",
"Column: Attempted suicide - suffocation\n",
"Data Type: float64\n",
"Column: Bone density scan (procedure)\n",
"Data Type: object\n",
"Column: Donepezil hydrochloride 10 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Acetaminophen 300 MG / Hydrocodone Bitartrate 5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Milnacipran hydrochloride 100 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Tubal pregnancy\n",
"Data Type: object\n",
"Column: Rheumatoid arthritis\n",
"Data Type: object\n",
"Column: Platelet Count\n",
"Data Type: float64\n",
"Column: Loss of taste (finding)\n",
"Data Type: object\n",
"Column: Streptococcus pneumoniae group B antigen test\n",
"Data Type: object\n",
"Column: First degree burn\n",
"Data Type: object\n",
"Column: 0.4 ML Enoxaparin sodium 100 MG/ML Prefilled Syringe\n",
"Data Type: object\n",
"Column: Transplantation of heart (procedure)\n",
"Data Type: object\n",
"Column: Common Ragweed IgE Ab in Serum\n",
"Data Type: object\n",
"Column: Sepsis caused by virus (disorder)\n",
"Data Type: object\n",
"Column: Radiation oncology AND/OR radiotherapy (procedure)\n",
"Data Type: object\n",
"Column: Laceration of forearm\n",
"Data Type: object\n",
"Column: Misuses drugs (finding)\n",
"Data Type: object\n",
"Column: Speech and language therapy regime (regime/therapy\n",
"Data Type: object\n",
"Column: Notifications (procedure)\n",
"Data Type: object\n",
"Column: Insertion of subcutaneous contraceptive\n",
"Data Type: object\n",
"Column: Pulmozyme (Dornase Alfa)\n",
"Data Type: float64\n",
"Column: Comprehensive interview and evaluation (procedure)\n",
"Data Type: object\n",
"Column: vancomycin 1000 MG Injection\n",
"Data Type: object\n",
"Column: Abuse-Deterrent 12 HR Oxycodone Hydrochloride 10 MG Extended Release Oral Tablet [Oxycontin]\n",
"Data Type: object\n",
"Column: Diabetes\n",
"Data Type: object\n",
"Column: chloroquine phosphate 500 MG Oral Tablet\n",
"Data Type: float64\n",
"Column: Monocytes [#/volume] in Blood by Automated count\n",
"Data Type: float64\n",
"Column: Rhinovirus RNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: Hematocrit [Volume Fraction] of Blood\n",
"Data Type: object\n",
"Column: Naproxen sodium 220 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Capillary refill [Time] of Nail bed\n",
"Data Type: object\n",
"Column: Nausea (finding)\n",
"Data Type: object\n",
"Column: Microalbumin Creatinine Ratio\n",
"Data Type: object\n",
"Column: Tacrine 10 MG Oral Capsule\n",
"Data Type: object\n",
"Column: Cognitive and behavioral therapy (regime/therapy)\n",
"Data Type: object\n",
"Column: Systolic Blood Pressure\n",
"Data Type: object\n",
"Column: 24 HR Donepezil hydrochloride 10 MG / Memantine hydrochloride 28 MG Extended Release Oral Capsule\n",
"Data Type: object\n",
"Column: Globulin [Mass/volume] in Serum by calculation\n",
"Data Type: object\n",
"Column: Neutrophils/100 leukocytes in Blood by Automated count\n",
"Data Type: float64\n",
"Column: Total replacement of hip\n",
"Data Type: object\n",
"Column: Glucose\n",
"Data Type: object\n",
"Column: Ultrasound scan for fetal viability\n",
"Data Type: object\n",
"Column: Erythrocytes [#/volume] in Blood by Automated count\n",
"Data Type: object\n",
"Column: Natazia 28 Day Pack\n",
"Data Type: object\n",
"Column: doxycycline hyclate 100 MG\n",
"Data Type: object\n",
"Column: Injury of medial collateral ligament of knee\n",
"Data Type: object\n",
"Column: Pneumococcal conjugate PCV 13\n",
"Data Type: object\n",
"Column: Metabolic syndrome X (disorder)\n",
"Data Type: object\n",
"Column: Low Density Lipoprotein Cholesterol\n",
"Data Type: object\n",
"Column: Sodium\n",
"Data Type: object\n",
"Column: anastrozole 1 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Creatinine\n",
"Data Type: object\n",
"Column: 10 ML oxaliplatin 5 MG/ML Injection\n",
"Data Type: object\n",
"Column: Alzheimer's disease (disorder)\n",
"Data Type: object\n",
"Column: Adenovirus A+B+C+D+E DNA [Presence] in Respiratory specimen by NAA with probe detection\n",
"Data Type: object\n",
"Column: Magnetic resonance imaging of breast (procedure)\n",
"Data Type: object\n",
"Column: cefdinir\n",
"Data Type: object\n",
"Column: Insertion of intrauterine contraceptive device\n",
"Data Type: object\n",
"Column: HER2 [Presence] in Breast cancer specimen by Immune stain\n",
"Data Type: object\n",
"Column: Neuropathy due to type 2 diabetes mellitus (disorder)\n",
"Data Type: object\n",
"Column: Home health aide service (regime/therapy)\n",
"Data Type: object\n",
"Column: Replacement of contraceptive intrauterine device\n",
"Data Type: object\n",
"Column: Severe anxiety (panic) (finding\n",
"Data Type: object\n",
"Column: Chronic kidney disease stage 1 (disorder)\n",
"Data Type: object\n",
"Column: Methotrexate 2.5 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Removal of intrauterine device\n",
"Data Type: object\n",
"Column: C reactive protein [Mass/volume] in Serum or Plasma\n",
"Data Type: float64\n",
"Column: Percutaneous coronary intervention\n",
"Data Type: object\n",
"Column: ethnic\n",
"Data Type: object\n",
"Column: Osteoarthritis of knee\n",
"Data Type: object\n",
"Column: Alteplase 100 MG Injection\n",
"Data Type: object\n",
"Column: Heart rate\n",
"Data Type: object\n",
"Column: Simvastatin 20 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Concussion with loss of consciousness\n",
"Data Type: object\n",
"Column: Leucovorin 100 MG Injection\n",
"Data Type: object\n",
"Column: Naproxen 500 MG Oral Tablet\n",
"Data Type: object\n",
"Column: Died in hospice (finding)\n",
"Data Type: object\n",
"Column: Respiratory Disorders\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Heart and Cardiovascular Diseases\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Metabolic and Endocrine Disorders\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Neurological Disorders\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Orthopedic Injuries\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Mental Health\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Reproductive and Pregnancy\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Pain Relievers and Analesics\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Cardiovascular and Blood Pressure\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Injection Medications\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Oral Medications\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Other Medications\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Therapies and Regimes\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Diagnostic Procedures\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Surgical Interventions\n",
"Data Type: object\n",
"Data Type: int64\n",
"Column: Patient Care Management\n",
"Data Type: object\n",
"Data Type: int64\n"
]
}
],
"source": [
"for col in df2.columns:\n",
" # print data type of column\n",
" print(f\"Column: {col}\") \n",
" print(f\"Data Type: {df2[col].dtype}\")\n",
" if col in categories:\n",
" # change data type to numeric\n",
" df2[col] = pd.to_numeric(df2[col], errors='coerce')\n",
" print(f\"Data Type: {df2[col].dtype}\")"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Dropping unnecessary columns"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Not important columns"
]
},
{
"cell_type": "code",
"execution_count": 26,
"metadata": {},
"outputs": [],
"source": [
"unimportant_columns = ['race', 'ethnic', 'state', 'Social migrant (finding)', 'Lack of access to transportation (finding)', 'Transport problems (finding)', 'Full-time employment (finding)', 'Face mask (physical object)', 'Childbirth', 'Cesarean section', 'Normal pregnancy', 'Non-low risk pregnancy']\n",
"df2.drop(columns=unimportant_columns, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Columns used in new features"
]
},
{
"cell_type": "code",
"execution_count": 27,
"metadata": {},
"outputs": [],
"source": [
"used_columns = respiratory_disorders_columns + heart_and_cardiovascular_diseases_columns + metabolic_and_endocrine_disorders_columns + neurological_disorders_columns + orthopedic_injuries_columns + mental_health_columns + reproductive_and_pregancy_columns + pain_relievers_and_analesics_columns + cardiovascular_and_blood_pressure_medications_columns + injection_medications_columns + oral_medications_columns + other_medications_columns + therapies_and_regimes_columns + diagnostic_procedures_columns + surgerical_interventions_columns + patient_care_management_columns\n",
"df2.drop(columns=used_columns, inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Columns with only null values"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Encoding"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Age "
]
},
{
"cell_type": "code",
"execution_count": 28,
"metadata": {},
"outputs": [],
"source": [
"df_one_hot = pd.get_dummies(df2['age'], prefix='age')\n",
"df2 = pd.concat([df2, df_one_hot], axis=1)\n",
"df2['age_30t50'] = df2['age_30t50'].astype(int)\n",
"df2['age_50t70'] = df2['age_50t70'].astype(int)\n",
"df2['age_gt70'] = df2['age_gt70'].astype(int)\n",
"df2.drop(columns=['age'], inplace=True)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"#### Columns with normal/abnormal values"
]
},
{
"cell_type": "code",
"execution_count": 29,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Alanine aminotransferase [Enzymatic activity/volume] in Serum or Plasma\n",
"Albumin\n",
"Alkaline phosphatase [Enzymatic activity/volume] in Serum or Plasma\n",
"American house dust mite IgE Ab in Serum\n",
"Aspartate aminotransferase [Enzymatic activity/volume] in Serum or Plasma\n",
"Bilirubin.total [Mass/volume] in Serum or Plasma\n",
"Bilirubin.total [Mass/volume] in Urine by Test strip\n",
"Body Mass Index\n",
"Body temperature\n",
"Calcium\n",
"Calcium [Mass/volume] in Serum or Plasma\n",
"Carbon Dioxide\n",
"Cat dander IgE Ab in Serum\n",
"Chloride\n",
"Chloride [Moles/volume] in Serum or Plasma\n",
"Cladosporium herbarum IgE Ab in Serum\n",
"Codfish IgE Ab in Serum\n",
"Common Ragweed IgE Ab in Serum\n",
"Cow milk IgE Ab in Serum\n",
"Creatinine\n",
"DXA [T-score] Bone density\n",
"Diastolic Blood Pressure\n",
"Egg white IgE Ab in Serum\n",
"Erythrocyte distribution width [Entitic volume] by Automated count\n",
"Erythrocyte distribution width [Ratio] by Automated count\n",
"Erythrocytes [#/volume] in Blood by Automated count\n",
"FEV1/FVC\n",
"Ferritin [Mass/volume] in Serum or Plasma\n",
"Globulin [Mass/volume] in Serum by calculation\n",
"Glomerular filtration rate/1.73 sq M.predicted\n",
"Glucose\n",
"Glucose [Mass/volume] in Serum or Plasma\n",
"Glucose [Mass/volume] in Urine by Test strip\n",
"Heart rate\n",
"Hematocrit [Volume Fraction] of Blood\n",
"Hematocrit [Volume Fraction] of Blood by Automated count\n",
"Hemoglobin A1c/Hemoglobin.total in Blood\n",
"Hemoglobin [Mass/volume] in Blood\n",
"Hemoglobin.gastrointestinal [Presence] in Stool by Immunologic method\n",
"High Density Lipoprotein Cholesterol\n",
"Honey bee IgE Ab in Serum\n",
"Iron [Mass/volume] in Serum or Plasma\n",
"Iron binding capacity [Mass/volume] in Serum or Plasma\n",
"Iron saturation [Mass Fraction] in Serum or Plasma\n",
"Lactate [Mass/volume] in Blood\n",
"Latex IgE Ab in Serum\n",
"Left ventricular Ejection fraction\n",
"Leukocytes [#/volume] in Blood by Automated count\n",
"Low Density Lipoprotein Cholesterol\n",
"MCH [Entitic mass] by Automated count\n",
"MCHC [Mass/volume] by Automated count\n",
"MCV [Entitic volume] by Automated count\n",
"Magnesium [Mass/volume] in Serum or Plasma\n",
"Mean blood pressure\n",
"Microalbumin Creatinine Ratio\n",
"NT-proBNP\n",
"Oxygen Saturation\n",
"Oxygen saturation in Arterial blood\n",
"Pain severity - 0-10 verbal numeric rating [Score] - Reported\n",
"Peanut IgE Ab in Serum\n",
"Platelet mean volume [Entitic volume] in Blood by Automated count\n",
"Platelets [#/volume] in Blood by Automated count\n",
"Polyp size greatest dimension by CAP cancer protocols\n",
"Potassium\n",
"Prostate specific Ag [Mass/volume] in Serum or Plasma\n",
"Protein [Mass/volume] in Urine by Test strip\n",
"Respiratory rate\n",
"Shrimp IgE Ab in Serum\n",
"Sodium\n",
"Soybean IgE Ab in Serum\n",
"Specific gravity of Urine by Test strip\n",
"Systolic Blood Pressure\n",
"Thyrotropin [Units/volume] in Serum or Plasma\n",
"Thyroxine (T4) free [Mass/volume] in Serum or Plasma\n",
"Total Cholesterol\n",
"Triglycerides\n",
"Troponin I.cardiac [Mass/volume] in Serum or Plasma by High sensitivity method\n",
"US Guidance for biopsy of Prostate\n",
"Urea Nitrogen\n",
"Urea nitrogen [Mass/volume] in Serum or Plasma\n",
"Walnut IgE Ab in Serum\n",
"Wheat IgE Ab in Serum\n",
"White oak IgE Ab in Serum\n",
"pH of Urine by Test strip\n"
]
}
],
"source": [
"n_abn_columns = []\n",
"for col in df2.columns:\n",
" if df2[col].isin(['normal', 'abnormal']).any():\n",
" n_abn_columns.append(col)\n",
"n_abn_columns.sort()\n",
"for col in n_abn_columns:\n",
" print(col)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Rest of them will be encoded using get_dummies."
]
},
{
"cell_type": "code",
"execution_count": 30,
"metadata": {},
"outputs": [],
"source": [
"df2 = pd.get_dummies(df2, columns=n_abn_columns, prefix_sep='_', dtype=int)"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"Other non-numeric columns will be encoded using get_dummies."
]
},
{
"cell_type": "code",
"execution_count": 31,
"metadata": {},
"outputs": [],
"source": [
"columns_to_encode = [\n",
" 'HER2 [Presence] in Breast cancer specimen by FISH',\n",
" 'Parainfluenza virus 1 RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'Estrogen+Progesterone receptor Ag [Presence] in Tissue by Immune stain',\n",
" 'Ketones [Mass/volume] in Urine by Test strip',\n",
" 'marital',\n",
" 'Abuse Status [OMAHA]',\n",
" 'Interleukin 6 [Mass/volume] in Serum or Plasma',\n",
" 'Progesterone receptor Ag [Presence] in Breast cancer specimen by Immune stain',\n",
" 'Influenza virus A RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'Parainfluenza virus 2 RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'Response to cancer treatment',\n",
" 'Estrogen receptor Ag [Presence] in Breast cancer specimen by Immune stain',\n",
" 'Hemoglobin [Presence] in Urine by Test strip',\n",
" 'Housing status',\n",
" 'Influenza virus B RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'Objective assessment of cardiovascular disease NYHA',\n",
" 'Drugs of abuse 5 panel - Urine by Screen method',\n",
" 'Leukocyte esterase [Presence] in Urine by Test strip',\n",
" 'Adenovirus A+B+C+D+E DNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'Protein [Presence] in Urine by Test strip',\n",
" 'Appearance of Urine',\n",
" 'Capillary refill [Time] of Nail bed',\n",
" 'Treatment status Cancer',\n",
" 'Gram positive blood culture panel by Probe in Positive blood culture',\n",
" 'Glucose [Presence] in Urine by Test strip',\n",
" 'Respiratory syncytial virus RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'Functional capacity NYHA',\n",
" 'Color of Urine',\n",
" 'Nitrite [Presence] in Urine by Test strip',\n",
" 'Tumor marker Cancer',\n",
" 'Tobacco smoking status NHIS',\n",
" 'gender',\n",
" 'HIV status',\n",
" 'Are you covered by health insurance or some other kind of health care plan [PhenX]',\n",
" 'Human metapneumovirus RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'Ketones [Presence] in Urine by Test strip',\n",
" 'Clarity of Urine',\n",
" 'Stage group.clinical Cancer',\n",
" 'Rhinovirus RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'HER2 [Presence] in Breast cancer specimen by Immune stain',\n",
" 'Smokes tobacco daily',\n",
" 'Parainfluenza virus 3 RNA [Presence] in Respiratory specimen by NAA with probe detection',\n",
" 'SARS-CoV-2 RNA Pnl Resp NAA+probe',\n",
" 'Influenza virus A Ag [Presence] in Nasopharynx by Rapid immunoassay',\n",
" 'Influenza virus B Ag [Presence] in Nasopharynx by Rapid immunoassay'\n",
"]\n",
"\n",
"df2 = pd.get_dummies(df2, columns=columns_to_encode, prefix_sep='_', dtype=int)"
]
},
{
"cell_type": "code",
"execution_count": 32,
"metadata": {},
"outputs": [],
"source": [
"to_drop = {'Adenovirus A+B+C+D+E DNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Appearance of Urine_cloudy',\n",
" 'Body Mass Index_normal',\n",
" 'Clarity of Urine_cloudy',\n",
" 'Clarity of Urine_translucent',\n",
" 'Color of Urine_brown',\n",
" 'Color of Urine_reddish',\n",
" 'Diastolic Blood Pressure_normal',\n",
" 'Ferritin [Mass/volume] in Serum or Plasma_abnormal',\n",
" 'Glucose [Presence] in Urine by Test strip_2+',\n",
" 'Gram positive blood culture panel by Probe in Positive blood culture_positive',\n",
" 'HER2 [Presence] in Breast cancer specimen by Immune stain_negative',\n",
" 'HER2 [Presence] in Breast cancer specimen by Immune stain_positive',\n",
" 'Heart rate_normal',\n",
" 'High Density Lipoprotein Cholesterol_normal',\n",
" 'Human metapneumovirus RNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Influenza virus A RNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Influenza virus B RNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Iron [Mass/volume] in Serum or Plasma_normal',\n",
" 'Iron saturation [Mass Fraction] in Serum or Plasma_normal',\n",
" 'Ketones [Mass/volume] in Urine by Test strip_low',\n",
" 'Ketones [Presence] in Urine by Test strip_3+',\n",
" 'Ketones [Presence] in Urine by Test strip_trace',\n",
" 'Leukocyte esterase [Presence] in Urine by Test strip_negative',\n",
" 'Low Density Lipoprotein Cholesterol_normal',\n",
" 'MCV [Entitic volume] by Automated count_normal',\n",
" 'Magnesium [Mass/volume] in Serum or Plasma_normal',\n",
" 'NT-proBNP_abnormal',\n",
" 'Nitrite [Presence] in Urine by Test strip_negative',\n",
" 'Pain severity - 0-10 verbal numeric rating [Score] - Reported_normal',\n",
" 'Parainfluenza virus 2 RNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Parainfluenza virus 3 RNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Polyp size greatest dimension by CAP cancer protocols_abnormal',\n",
" 'Polyp size greatest dimension by CAP cancer protocols_normal',\n",
" 'Respiratory syncytial virus RNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Rhinovirus RNA [Presence] in Respiratory specimen by NAA with probe detection_negative',\n",
" 'Sodium_normal',\n",
" 'Specific gravity of Urine by Test strip_abnormal',\n",
" 'Systolic Blood Pressure_abnormal',\n",
" 'Systolic Blood Pressure_normal',\n",
" 'Tobacco smoking status NHIS_never',\n",
" 'Total Cholesterol_normal',\n",
" 'Urea Nitrogen_normal',\n",
" 'Urea nitrogen [Mass/volume] in Serum or Plasma_normal',\n",
" 'gender_m',\n",
" 'marital_s',\n",
" 'pH of Urine by Test strip_normal'}"
]
},
{
"cell_type": "code",
"execution_count": 33,
"metadata": {},
"outputs": [],
"source": [
"df2.drop(columns=to_drop, inplace=True)"
]
},
{
"cell_type": "code",
"execution_count": 34,
"metadata": {},
"outputs": [
{
"data": {
"text/plain": [
"['Interleukin 6 [Mass/volume] in Serum or Plasma_5.33',\n",
" 'Ketones [Presence] in Urine by Test strip_2+']"
]
},
"execution_count": 34,
"metadata": {},
"output_type": "execute_result"
}
],
"source": [
"df2_cols = df2.columns\n",
"diff = [col for col in train_cols if col not in df2_cols]\n",
"diff"
]
},
{
"cell_type": "code",
"execution_count": 35,
"metadata": {},
"outputs": [],
"source": [
"df2['Interleukin 6 [Mass/volume] in Serum or Plasma_5.33'] = 0\n",
"df2['Ketones [Presence] in Urine by Test strip_2+'] = 0"
]
},
{
"cell_type": "code",
"execution_count": 36,
"metadata": {},
"outputs": [],
"source": [
"df2 = df2.fillna(df2.median())"
]
},
{
"cell_type": "code",
"execution_count": 37,
"metadata": {},
"outputs": [],
"source": [
"X_val = df2.drop('label', axis=1)\n",
"y_val = df2['label']"
]
},
{
"cell_type": "code",
"execution_count": 38,
"metadata": {},
"outputs": [],
"source": [
"X_val = X_val[train_cols]"
]
},
{
"cell_type": "code",
"execution_count": 39,
"metadata": {},
"outputs": [],
"source": [
"# save x_val and y_val to csv\n",
"X_val.to_csv('../validation_data/X_val.csv', index=False)\n",
"y_val.to_csv('../validation_data/y_val.csv', index=False)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": []
}
],
"metadata": {
"kernelspec": {
"display_name": "base",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.9.12"
}
},
"nbformat": 4,
"nbformat_minor": 2
}