Predicting-ICU-Admission-COVID19

The COVID-19 pandemic has shown us the unpreparedness of our current healthcare system and services. We need to optimize the allocation of medical resources to maximize the utilization. We are preparing this Machine Learning model based on the clinical data of confirmed COVID-19 cases. This will help us to predict the need of ICU for a patient in advance. By this information hospitals can plan the flow of operations and take critical decisions like shifting patient to another hospital or arrangement of resources within the time so that the lives of patients can be saved.

About Project

If you want to know about the project details, open the file Predicting_ICU_Admission_of_Confirmed_COVID19_Cases_Presentation.pdf. It contains all the details about the implementation.

How to Run Code

It is recommended to use the jupyter notebook or google colab for best experience.

Dependencies

asgiref==3.2.10
certifi==2020.6.20
chardet==3.0.4
cycler==0.10.0
Django==3.0.7
django-multiselectfield==0.1.12
h5py==2.10.0
idna==2.10
joblib==0.16.0
kiwisolver==1.2.0
matplotlib==3.3.1
nnfs==0.5.1
numpy==1.19.1
panda==0.3.1
pandas==1.1.2
Pillow==7.2.0
pyparsing==2.4.7
python-dateutil==2.8.1
pytz==2020.1
requests==2.24.0
scikit-learn==0.23.2
scipy==1.5.2
seaborn==0.11.0
selenium==3.141.0
six==1.15.0
sklearn==0.0
sqlparse==0.3.1
threadpoolctl==2.1.0
urllib3==1.25.10
wget==3.2

Instructions

1. Download the source code using git clone.
2. If you are using Google colab upload the .ipynb file and press Ctrl+F9
3. If you are using terminal, install dependencies by running command "pip -r install 'requirements.txt'"
4. Run the python code by executing command "python3 covid19_icu_prediction.py"

About Code

The code is well documented. Every section has been marked with headings and sub headings. Read the comments if you face any difficulty in understanding the code.