1 |
Study of Pre-trained Language Models for Named Entity Recognition in Clinical Trial Eligibility Criteria from Multiple Corpora |
10.1109/ICHI52183.2021.00095 |
CT parsing |
NER |
PRF |
Covance, ELilE, Chia |
1700.0 |
|
internal, ClinicalTrials.gov |
|
|
normalization |
|
BERT, SpanBERT, BlueBERT, BioBERT, PubMedBERT, SciBERT |
|
evaluation |
2 |
Accuracy of an Artificial Intelligence System for Cancer Clinical Trial Eligibility Screening: Retrospective Pilot Study |
10.2196/27767 |
patient CT matching |
not specified |
accuracy, sensitivity, specificity, PPV, NPV |
not specified |
4.0 |
|
internal, ClinicalTrials.gov |
|
manual |
|
|
|
|
evaluation |
3 |
Extending the Query Language of a Data Warehouse for Patient Recruitment |
10.3233/978-1-61499-808-2-152 |
patient CT matching |
IR |
recall |
internal |
|
|
|
EHR |
manual |
regex, negation detection |
|
|
|
evaluation |
4 |
An Evaluation of Pretrained BERT Models for Comparing Semantic Similarity Across Unstructured Clinical Trial Texts |
10.3233/SHTI210848 |
CT similarity |
STS |
similarity |
not specified |
689.0 |
|
internal, ClinicalTrials.gov |
|
manual |
|
cosine similarity |
BERT, BioBERT, BlueBERT, ClinicalBioBERT, SciBERT, PubMedBERT, CODER |
|
evaluation |
5 |
Automated classification of eligibility criteria in clinical trials to facilitate patient-trial matching for specific patient populations |
10.1093/jamia/ocw176 |
patient CT matching |
classification |
PRF, AUC |
not specified |
3462.0 |
|
ClinicalTrials.gov |
|
manual |
TF-IDF, term normalization, negation detection |
SVM |
|
|
method |
6 |
A Unified Machine Reading Comprehension Framework for Cohort Selection |
10.1109/JBHI.2021.3095478 |
CT design |
QA |
F1 |
i2b2/n2c2 |
|
26.0 |
|
|
manual |
normalization, keyword filtering |
|
BERT, RoBERTa, BioBERT, word2vec, Glove, FastText, BiLSTM, BiDAF |
|
method |
7 |
ASCOT: A text mining-based web-service for efficient search and assisted creation of clinical trials |
10.1186/1472-6947-12-S1-S3 |
CT design |
NER |
|
not specified |
|
|
|
|
|
keyword filtering, term normalization |
|
|
|
evaluation |
8 |
Cohort selection for clinical trials using deep learning models |
10.1093/jamia/ocz139 |
n2c2 challenge |
not specified |
F1 |
i2b2/n2c2 |
|
13.0 |
|
|
|
|
|
word2vec, CNN, GRU, FCFF |
|
method |
9 |
EliIE: An open-source information extraction system for clinical trial eligibility criteria |
10.1093/jamia/ocx019 |
CT parsing |
NER, RE, normalization |
F1, accuracy |
not specified |
230.0 |
|
ClinicalTrials.gov |
|
manual |
normalization, negation detection |
SVM, CRF |
|
|
protocol |
10 |
Classifying Eligibility Criteria in Clinical Trials Using Active Deep Learning |
10.1109/ICMLA.2018.00052 |
patient CT matching |
classification |
error rate |
not specified |
9762.0 |
209441.0 |
NCI |
|
|
|
|
|
|
method |
11 |
Protocol Feasibility Workflow Using an Automated Multi-country Patient Cohort System |
10.3233/978-1-61499-432-9-985 |
patient CT matching |
not specified |
not specified |
not specified |
|
|
|
|
|
|
|
|
|
method |
12 |
Assessing clinical trial eligibility with logic expression queries |
10.1016/j.datak.2007.07.005 |
patient CT matching |
IR, normalization |
PRF |
not specified |
100.0 |
1545.0 |
ClinicalTrials.gov |
|
manual |
normalization, custom transformations |
|
|
|
method |
13 |
Improving the efficiency of clinical trial recruitment using electronic health record data, natural language processing, and machine learning |
10.1002/art.41108 |
patient CT matching |
NER |
sensitivity, PPV, custom |
internal |
|
15.0 |
|
|
manual |
|
RF, logistic regression |
|
UMLS |
method |
14 |
Automatic trial eligibility surveillance based on unstructured clinical data |
10.1016/j.ijmedinf.2019.05.018 |
patient CT matching |
NER, classification, EL |
recall, precision, AUC, MAP |
internal |
3.0 |
24.0 |
ClinicalTrials.gov |
EHR |
manual |
normalization, term normalization, custom transformations, regex |
SVM, cosine similarity, custom rules |
|
|
method |
15 |
Information Extraction from Free Text in Clinical Trials with Knowledge-based Distant Supervision |
10.1109/COMPSAC.2019.00158 |
CT parsing |
normalization |
accuracy, recall |
not specified |
100.0 |
386.0 |
ClinicalTrials.gov |
|
|
|
|
|
UMLS, Wikipedia, OHDSI |
method |
16 |
ETACTS: A method for dynamically filtering clinical trial search results |
10.1016/j.jbi.2013.07.014 |
patient CT matching |
STS |
custom |
internal |
141291.0 |
|
ClinicalTrials.gov |
synthetic EHR |
|
POS, keyword filtering, term normalization |
jaccard similarity, custom rules |
|
|
evaluation |
17 |
A practical method for transforming free-text eligibility criteria into computable criteria |
10.1016/j.jbi.2010.09.007 |
CT parsing |
normalization |
custom |
not specified |
|
|
ClinicalTrials.gov |
|
manual |
keyword filtering, custom transformations |
dependency parsing |
|
UMLS |
method |
18 |
Evaluation of an artificial intelligence clinical trial matching system in Australian lung cancer patients |
10.1093/jamiaopen/ooaa002 |
patient CT matching |
not specified |
accuracy, precision, recall, PPV, NPV |
internal |
10.0 |
11467.0 |
internal, ClinicalTrials.gov |
EHR |
manual |
|
|
|
|
evaluation |
19 |
Increasing the efficiency of trial-patient matching: automated clinical trial eligibility Pre-screening for pediatric oncology patients |
10.1186/s12911-015-0149-3 |
patient CT matching |
IR |
precision, recall, NPV, specificity |
internal |
55.0 |
|
ClinicalTrials.gov |
EHR |
manual |
keyword filtering, negation detection, regex, sentence segmentation |
custom rules |
|
UMLS, SNOMED, RxNORM |
method |
20 |
An eligibility criteria query language for heterogeneous data warehouses |
10.3414/ME13-02-0027 |
patient CT matching |
IR, EL |
custom |
internal |
17.0 |
208.0 |
|
|
|
|
|
|
CCR, HL7 RIM |
method |
21 |
DeepEnroll: Patient-Trial Matching with Deep Embedding and Entailment Prediction |
10.1145/3366423.3380181 |
patient CT matching |
NLI |
F1, AUC |
IQVIA |
794.0 |
12445.0 |
ClinicalTrials.gov |
IQVIA, Synthea |
manual |
numerical normalization, BOW |
|
MLP, ClinicalBERT |
|
method |
22 |
Improving Clinical Trial Participant Prescreening With Artificial Intelligence (AI): A Comparison of the Results of AI-Assisted vs Standard Methods in 3 Oncology Trials |
10.1177/2168479018815454 |
patient CT matching |
NLI |
custom, precision |
not specified |
3.0 |
|
CBCC |
|
manual |
OCR |
|
Mendel.ai |
SNOMED, ICD |
method |
23 |
ExaCT: automatic extraction of clinical trial characteristics from journal publications |
10.1186/1472-6947-10-56 |
CT parsing |
IR |
precision, recall |
not specified |
182.0 |
|
PubMed |
|
manual |
BOW, keyword filtering, normalization, regex, sentence segmentation |
SVM |
|
|
evaluation |
24 |
Building a specialized lexicon for breast cancer clinical trial subject eligibility analysis |
10.1177/1460458221989392 |
patient CT matching |
IR, EL |
custom |
NCI dictionary, breastcancer.org, emedicinehealth.org |
378.0 |
|
ClinicalTrials.gov |
NCI dictionary, ACS website, breastcancer.org |
|
TF-IDF |
|
|
SNOMED |
protocol |
25 |
An OMOP CDM-Based Relational Database of Clinical Research Eligibility Criteria |
10.3233/978-1-61499-830-3-950 |
CT parsing |
NER, normalization, RE |
PRF |
not specified |
1587.0 |
|
ClinicalTrials.gov |
|
manual |
POS, negation detection, term normalization, sentence segmentation |
SVM |
|
SNOMED, ICD |
method |
26 |
An Ensemble Learning Strategy for Eligibility Criteria Text Classification for Clinical Trial Recruitment: Algorithm Development and Validation |
10.2196/17832 |
CT parsing |
classification |
accuracy, PRF |
not specified |
|
38341.0 |
internal |
|
manual |
regex, normalization |
GBM |
BERT, BERNIE, XLNet, RoBERTa |
|
method |
27 |
Chia, a large annotated corpus of clinical trial eligibility criteria |
10.1038/s41597-020-00620-0 |
dataset building |
not specified |
PRF, Cohen kappa |
Chia |
1000.0 |
12409.0 |
ClinicalTrials.gov |
|
manual |
|
|
|
|
dataset |
28 |
Cohort selection for clinical trials using multiple instance learning |
10.1016/j.jbi.2020.103438 |
patient CT matching |
classification |
F1 |
i2b2/n2c2 |
13.0 |
|
|
|
benchmark dataset |
term normalization, regex, negation detection, TF-IDF |
SVM, KNN, custom rules |
|
|
method |
29 |
Learning Eligibility in Cancer Clinical Trials Using Deep Neural Networks |
10.3390/app8071206 |
patient CT matching |
classification |
PRF, Cohen kappa |
not specified |
49201.0 |
6186572.0 |
ClinicalTrials.gov |
|
protocol text |
BOW, custom transformations, normalization, sentence segmentation |
SVM, KNN |
word2vec, CNN |
|
method |
30 |
Valx: A System for Extracting and Structuring Numeric Lab Test Comparison Statements from Text |
10.3414/ME15-01-0112 |
CT parsing |
IR, normalization |
PRF |
not specified |
4383.0 |
|
ClinicalTrials.gov |
|
manual |
normalization, regex, custom transformations |
|
|
UMLS |
evaluation |
31 |
EMR2vec: Bridging the gap between patient data and clinical trial |
10.1016/j.cie.2021.107236 |
patient CT matching |
classification, NER, STS, EL |
PRF, p@k |
i2b2/n2c2 |
31500.0 |
|
ClinicalTrials.gov |
|
manual |
term normalization, negation detection |
SVM, CRF, custom rules |
CNN, LSTM, BioBERT, word2vec, BiLSTM, BiLSTM-CRF, BioBERT-CRF |
|
method |
32 |
How the clinical research community responded to the COVID-19 pandemic: an analysis of the COVID-19 clinical studies in ClinicalTrials.gov |
10.1093/jamiaopen/ooab032 |
CT parsing |
IR |
precision, recall |
not specified |
3765.0 |
|
ClinicalTrials.gov |
|
manual |
term normalization, TF-IDF, PCA |
k-means, custom rules |
|
MeSH |
method |
33 |
DQueST: dynamic questionnaire for search of clinical trials |
10.1093/jamia/ocz121 |
patient CT matching |
NER, IR, EL |
custom |
internal |
252330.0 |
|
ClinicalTrials.gov |
|
manual |
BOW, negation detection, numerical normalization, custom transformations, term normalization, sentence segmentation |
custom rules, clustering, CRF |
|
OHDSI |
evaluation |
34 |
Conflict discovery and analysis for clinical trials |
10.1145/3079452.3079494 |
CT parsing |
IR |
custom |
not specified |
134.0 |
|
ClinicalTrials.gov |
|
|
normalization |
custom rules |
|
UMLS |
method |
35 |
COVID-19 trial graph: a linked graph for COVID-19 clinical trials |
10.1093/jamia/ocab078 |
CT design |
IR, normalization |
precision, recall |
not specified |
3392.0 |
|
ClinicalTrials.gov |
|
manual |
normalization |
SVM, RF, GBM, logistic regression |
GNN, t-SNE, node2vec |
OMOP CDM |
dataset |
36 |
Identifying the status of genetic lesions in cancer clinical trial documents using machine learning |
10.1186/1471-2164-13-S8-S21 |
CT parsing |
NER, IR, EL |
accuracy |
internal |
250.0 |
1143.0 |
NCI |
|
manual |
POS, negation detection, keyword filtering |
SVM |
|
|
method |
37 |
Parsing clinical trial eligibility criteria for cohort query by a multi-input multi-output sequence labeling model |
10.1101/2021.11.18.21266533 |
patient CT matching |
NER, IR |
PRF, AUC |
not specified |
|
13.0 |
ClinicalTrials.gov |
|
manual |
POS, normalization |
|
BERT, BioRoBERTa |
|
evaluation |
38 |
Transformer-Based Named Entity Recognition for Parsing Clinical Trial Eligibility Criteria |
10.1145/3459930.3469560 |
CT parsing |
NER |
PRF |
not specified |
4314.0 |
|
ClinicalTrials.gov |
MIMIC-III |
manual |
|
|
BERT, RoBERTa, ELECTRA, ALBERT |
|
method |
39 |
Cohort Selection for Clinical Trials From Longitudinal Patient Records: Text Mining Approach |
10.2196/15980 |
patient CT matching |
STS |
F1 |
not specified |
|
13.0 |
n2c2 |
|
benchmark dataset |
custom transformations, normalization, BOW, keyword filtering, sentence segmentation |
SVM, logistic regression, NBC, GTB |
|
|
method |
40 |
Medical knowledge infused convolutional neural networks for cohort selection in clinical trials |
10.1093/jamia/ocz128 |
patient CT matching |
RL |
PRF |
not specified |
|
13.0 |
n2c2 |
|
benchmark dataset |
term normalization, normalization, keyword filtering, sentence segmentation |
|
CNN, word2vec |
|
method |
41 |
Semantic categorization of Chinese eligibility criteria in clinical trials using machine learning methods |
10.1186/s12911-021-01487-w |
patient CT matching |
RL |
PRF |
not specified |
272.0 |
|
ChiCTR |
|
manual |
normalization, custom transformations |
logistic regression, NBC, KNN, SVM |
CNN, RNN, FastText, BERT, ERNIE |
UMLS |
method |
42 |
Building an OMOP common data model-compliant annotated corpus for COVID-19 clinical trials |
10.1016/j.jbi.2021.103790 |
CT parsing |
NER, IR |
Cohen kappa |
not specified |
700.0 |
11710.0 |
ClinicalTrials.gov |
|
manual |
regex, normalization |
|
|
OMOP CDM |
dataset |
43 |
Improving Disease Named Entity Recognition for Clinical Trial Matching |
10.1109/BIBM47256.2019.8983421 |
CT parsing |
NER |
PRF |
not specified |
|
7500.0 |
NCBI, TREC |
|
|
|
|
BiLSTM-CRF, ELMO, Glove |
UMLS, SNOMED, MEDICS |
method |
44 |
Analysis of eligibility criteria representation in industry-standard clinical trial protocols |
10.1016/j.jbi.2013.06.001 |
CT parsing |
normalization, RL, STS |
custom |
not specified |
32.0 |
|
internal, ClinicalTrials.gov |
|
manual |
keyword filtering, term normalization, custom transformations, sentence segmentation |
cosine similarity, custom rules |
|
UMLS |
method |
45 |
Syntactic and Semantic Knowledge-Aware Paraphrase Detection for Clinical Data |
10.1007/978-981-16-2937-2_13 |
patient CT matching |
STS, classification |
PRF |
MSRP, TREC 2018 |
|
3160.0 |
ClinicalTrials.gov |
MSRP |
manual |
char-level embedding |
|
ClinicalBERT, word2vec, CliNER, FCFF, LSTM |
UMLS, DrugBank, CTD |
method |
46 |
Criteria2Query: A natural language interface to clinical databases for cohort definition |
10.1093/jamia/ocy178 |
CT design |
NER |
PRF, accuracy |
not specified |
407.0 |
|
ClinicalTrials.gov |
|
manual |
regex, normalization, custom transformations, negation detection, sentence segmentation |
CRF |
|
UMLS |
evaluation |
47 |
Textual inference for eligibility criteria resolution in clinical trials |
10.1016/j.jbi.2015.09.008 |
patient CT matching |
NLI |
F1 |
i2b2/n2c2, internal |
5054.0 |
4.0 |
ClinicalTrials.gov |
EHR |
manual |
keyword filtering, normalization, custom transformations, sentence segmentation |
custom rules |
|
UMLS |
method |
48 |
Inferring appropriate eligibility criteria in clinical trial protocols without labeled data |
10.1145/2390068.2390074 |
CT design |
STS, classification, topic modeling |
similarity |
not specified |
44203.0 |
462459.0 |
ClinicalTrials.gov |
|
CT.gov structured data |
BOW, keyword filtering, normalization |
LDA, logistic regression, custom rules, cosine similarity |
|
|
method |
49 |
Formulating queries for assessing clinical trial eligibility |
10.1007/11765448_8 |
patient CT matching |
IR |
custom |
internal |
25000.0 |
|
ClinicalTrials.gov |
EHR |
manual |
custom transformations, regex, sentence segmentation |
custom rules |
|
SNOMED |
method |
50 |
Numerical Eligibility Criteria in Clinical Protocols: Annotation, Automatic Detection and Interpretation |
10.1007/978-3-319-59758-4_22 |
patient CT matching |
NER |
Cohen kappa |
not specified |
211438.0 |
2000000.0 |
ClinicalTrials.gov |
|
manual |
custom transformations |
CRF |
|
|
method |
51 |
Automated learning of domain taxonomies from text using background knowledge |
10.1016/j.jbi.2016.09.002 |
dataset building |
IR, RE |
PRF, silhouette, purity |
|
|
455773.0 |
ClinicalTrials.gov |
|
manual |
term normalization, normalization, sentence segmentation |
jaccard similarity, HAC |
|
UMLS, SNOMED, DBPedia, MEDLINE |
method |
52 |
Feasibility of Feature-based Indexing, Clustering, and Search of Clinical Trials |
10.3414/ME12-01-0092 |
CT parsing |
clustering |
Cohen kappa |
not specified |
80.0 |
|
ClinicalTrials.gov |
|
manual |
term normalization, custom transformations, sentence segmentation |
HAC, custom rules |
|
UMLS |
method |
53 |
Predictive modeling of clinical trial terminations using feature engineering and embedding learning |
10.1038/s41598-021-82840-x |
CT design |
RL |
accuracy, F1, AUC |
not specified |
68999.0 |
|
ClinicalTrials.gov |
|
|
custom transformations |
RF, XGB, logistic regression |
MLP |
|
method |
54 |
Automated clinical trial eligibility prescreening: increasing the efficiency of patient identification for clinical trials in the emergency department |
10.1136/amiajnl-2014-002887 |
patient CT matching |
IR |
F1, MAP, custom |
not specified |
|
13.0 |
not specified |
|
manual |
normalization, BOW, negation detection, TF-IDF, custom transformations, sentence segmentation |
custom rules |
|
UMLS, SNOMED, RxNORM |
method |
55 |
Supporting Patient Screening to Identify Suitable Clinical Trials |
10.3233/978-1-61499-432-9-823 |
patient CT matching |
NER |
custom |
not specified |
|
|
internal |
|
|
|
custom rules |
|
SNOMED, LOINC |
method |
56 |
Attention-Based LSTM Network for COVID-19 Clinical Trial Parsing |
10.1109/BigData50022.2020.9378451 |
CT design |
NER |
PRF |
CTP |
2998.0 |
27352.0 |
ClinicalTrials.gov |
|
manual |
term normalization |
custom rules |
BiLSTM, word2vec |
MeSH |
method |
57 |
Patterns for conflict identification in clinical trial eligibility criteria |
10.1109/HealthCom.2016.7749519 |
patient CT matching |
IR |
custom |
not specified |
56.0 |
1588.0 |
ClinicalTrials.gov |
|
|
normalization, term normalization, sentence segmentation |
custom rules |
|
UMLS |
method |
58 |
Artificial Intelligence Tool for Optimizing Eligibility Screening for Clinical Trials in a Large Community Cancer Center |
10.1200/CCI.19.00079 |
patient CT matching |
not specified |
accuracy, sensitivity, specificity, PPV, NPV |
not specified |
4.0 |
218.0 |
ClinicalTrials.gov |
|
manual |
POS, negation detection, normalization |
|
|
|
evaluation |
59 |
Clinical Trial Information Extraction with BERT |
10.1109/ICHI52183.2021.00092 |
CT design |
NER |
PRF |
CTP, Criteria2Query |
10.0 |
45483.0 |
ClinicalTrials.gov |
|
benchmark dataset |
normalization |
|
CRF, BiLSTM, BERT, BioBERT, BlueBERT, ClinicalBERT |
|
method |
60 |
A knowledge base of clinical trial eligibility criteria |
10.1016/j.jbi.2021.103771 |
CT parsing |
NER, IR, RE |
custom |
not specified |
352110.0 |
3647567.0 |
ClinicalTrials.gov |
|
manual |
|
|
|
OMOP CDM, SNOMED, RxNORM |
dataset |
61 |
Classification And Extraction Of Medical Clinical Trial Screening Standard Texts Based On Bi-Lstm And Attention Mechanism |
10.1088/1755-1315/632/5/052088 |
patient CT matching |
classification |
PRF |
not specified |
|
|
not specified |
|
|
|
|
word2vec, BiLSTM |
|
method |
62 |
Understanding Common Key Indicators Of Successful And Unsuccessful Cancer Drug Trials Using A Contrast Mining Framework On Clinicaltrials.Gov |
10.1016/j.jbi.2023.104321 |
CT design |
RL |
support, growth, PRF |
not specified |
18304.0 |
|
ClinicalTrials.gov |
|
CT.gov structured data |
term normalization |
RF, logistic regression |
|
UMLS, DrugBank |
method |
63 |
A Comparative Study Of Pre-Trained Language Models For Named Entity Recognition In Clinical Trial Eligibility Criteria From Multiple Corpora |
10.1186/s12911-022-01967-7 |
CT parsing |
NER |
PRF |
Covance, ELilE, Chia |
1700.0 |
|
internal, ClinicalTrials.gov |
|
benchmark dataset |
normalization |
|
BERT, SpanBERT, PubMedBERT, BioBERT, BlueBERT, SciBERT |
|
method |
64 |
Improving Clinical Trial Design Using Interpretable Machine Learning Based Prediction Of Early Trial Termination |
10.1038/s41598-023-27416-7 |
CT design |
NER |
accuracy, F1, AUC |
Chia |
112647.0 |
|
ClinicalTrials.gov |
|
CT.gov structured data |
custom transformations |
logistic regression, RF, XGB, SHAP, custom rules |
|
|
dataset |
65 |
Combining Human And Machine Intelligence For Clinical Trial Eligibility Querying |
10.1093/jamia/ocac051 |
CT design |
NER, EL |
accuracy, PRF |
internal |
1015.0 |
|
ClinicalTrials.gov |
EHR |
manual |
POS, normalization, numerical normalization, regex |
|
BERT, PubMedBERT |
|
method |
66 |
A Scalable Ai Approach For Clinical Trial Cohort Optimization |
10.1007/978-3-030-93733-1_36 |
CT design |
NER |
|
Optum database |
125.0 |
3572.0 |
ClinicalTrials.gov |
EHR |
|
keyword filtering |
|
CT-BERT |
|
method |
67 |
The Leaf Clinical Trials Corpus: A New Resource For Query Generation From Clinical Trial Eligibility Criteria |
10.1038/s41597-022-01521-0 |
patient CT matching |
NER, RE |
F1 |
Chia, LCT |
1006.0 |
|
ClinicalTrials.gov |
|
manual |
|
|
BiLSTM-CRF, BERT, PubMedBERT, SciBERT |
|
dataset |
68 |
Piloting An Automated Clinical Trial Eligibility Surveillance And Provider Alert System Based On Artificial Intelligence And Standard Data Models |
10.1186/s12874-023-01916-6 |
patient CT matching |
IR, NER |
PRF |
MUSC warehouse |
5.0 |
|
|
EHR |
manual |
regex |
SVM, custom rules, cosine similarity |
|
|
method |
69 |
Hint: Hierarchical Interaction Network For Clinical-Trial-Outcome Predictions |
10.1016/j.patter.2022.100445 |
CT classification |
RL |
AUC, F1 |
internal |
12500.0 |
|
ClinicalTrials.gov |
drug-related datasets |
CT.gov structured data |
|
|
GNN, CNN, ClinicalBERT |
DrugBank, ICD |
method |
70 |
Predicting Publication Of Clinical Trials Using Structured And Unstructured Data: Model Development And Validation Study |
10.2196/38859 |
CT classification |
RL |
AUC, F1 |
|
75000.0 |
|
ClinicalTrials.gov |
|
MEDLINE |
TF-IDF |
RF |
FCFF, BERT, SciBERT |
MEDLINE |
method |
71 |
Growth In Eligibility Criteria Content And Failure To Accrue Among National Cancer Institute (Nci)-Affiliated Clinical Trials |
10.1002/cam4.5276 |
CT design |
IR, NER, RL |
AUC, R2 |
not specified |
1197.0 |
|
ClinicalTrials.gov |
|
CT.gov structured data |
normalization, custom transformations |
custom rules, XGB, logistic regression |
SciSpaCy |
|
method |
72 |
Utilizing Large Language Models For Enhanced Clinical Trial Matching: A Study On Automation In Patient Screening |
10.7759/cureus.60044 |
patient CT matching |
classification, RAG |
accuracy, recall, precision, F1, specificity |
i2b2/n2c2 |
|
13.0 |
n2c2 |
|
benchmark dataset |
|
|
GPT-3.5-turbo, GPT-4, ada-002 |
|
method |
73 |
Autocriteria: A Generalizable Clinical Trial Eligibility Criteria Extraction System Powered By Large Language Models |
10.1093/jamia/ocad218 |
CT parsing |
IR |
precision, recall, F1, accuracy |
internal |
432.0 |
|
ClinicalTrials.gov |
|
manual |
regex |
|
GPT-4, Davinci-003 |
|
method |
74 |
Automatic Assessment Of Patient Eligibility By Utilizing Nlp And Rule-Based Analysis |
10.1109/EMBC40787.2023.10340494 |
patient CT matching |
classification, STS |
precision, recall |
internal |
1.0 |
|
direct protocol |
EHR |
manual |
keyword filtering, term normalization, regex, custom transformations |
custom rules, cosine similarity |
BioSentVec |
ICD |
method |
75 |
Characterisation Of Digital Therapeutic Clinical Trials: A Systematic Review With Natural Language Processing |
10.1016/S2589-7500(23)00244-3 |
CT analysis |
topic modeling |
accuracy |
internal |
449.0 |
|
ClinicalTrials.gov |
|
manual |
sentence segmentation |
|
BERTopic, SciSpaCy |
|
method |
76 |
Sociotechnical Feasibility Of Natural Language Processing-Driven Tools In Clinical Trial Eligibility Prescreening For Alzheimer'S Disease And Related Dementias |
10.1093/jamia/ocae032 |
patient CT matching |
IR |
ICC, custom |
internal |
2.0 |
|
direct protocol |
EHR |
manual |
|
|
|
|
evaluation |
77 |
A Self-Learning Resource-Efficient Re-Ranking Method For Clinical Trials Search |
10.1145/3583780.3615174 |
patient CT matching |
classification, ranking |
P@10, RR, NDCG@10 |
TREC 2021, TREC 2022 |
375580.0 |
|
ClinicalTrials.gov |
|
benchmark dataset |
|
custom rules, BM25 |
SciBERT, monoBERT |
|
method |
78 |
Automated Matching Of Patients To Clinical Trials: A Patient-Centric Natural Language Processing Approach For Pediatric Leukemia |
10.1200/CCI.23.00009 |
patient CT matching |
classification |
accuracy, precision, recall, time |
internal |
216.0 |
5251.0 |
ClinicalTrials.gov |
synthetic EHR |
manual |
regex, custom transformations, sentence segmentation |
SVM, custom rules |
FastText |
|
method |
79 |
Effective Matching Of Patients To Clinical Trials Using Entity Extraction And Neural Re-Ranking |
10.1016/j.jbi.2023.104444 |
patient CT matching |
NER, classification, ranking |
P@10, RR, NDCG@10, NDCG@5 |
TREC 2021, TREC 2022 |
375580.0 |
|
ClinicalTrials.gov |
|
benchmark dataset |
custom transformations, negation detection, keyword filtering, sentence segmentation |
BM25 |
monoBERT, traditionalRR, SciSpaCy, medSpaCy, BERT, BioBERT, ClinicalBERT |
|
|
80 |
Distilling Large Language Models For Matching Patients To Clinical Trials |
10.1093/jamia/ocae073 |
patient CT matching |
classification, ranking |
NDCG@10, P@10, AUROC, precision, recall, F1, custom |
SIGIR, TREC 2021, TREC 2022, internal |
23280.0 |
|
ClinicalTrials.gov |
|
GPT-created |
|
|
GPT-3.5-turbo, GPT-4, LLAMA-2-7B, LLAMA-2-13B, LLAMA-2-70B |
|
dataset, evaluation |
81 |
Named Entity Recognition and Normalization for Alzheimer's Disease Eligibility Criteria |
10.1109/ICHI57859.2023.00100 |
CT parsing |
NER, normalization |
precision, recall, F1 |
internal |
1508.0 |
|
ClinicalTrials.gov |
|
manual |
custom transformations |
custom rules, CRF |
SapBERT |
UMLS |
method |
82 |
Criteria2Query 3.0: Leveraging Generative Large Language Models For Clinical Trial Eligibility Query Generation |
10.1016/j.jbi.2024.104649 |
CT parsing |
NER, normalization |
precision, recall, F1 |
not specified |
20.0 |
|
ClinicalTrials.gov |
|
manual |
|
|
GPT-4, GPT-3.5 |
OMOP CDM |
method |
83 |
Treement: Interpretable Patient-Trial Matching Via Personalized Dynamic Tree-Based Memory Network |
10.1145/3584371.3612998 |
patient CT matching |
RL, classification, normalization |
F1, accuracy |
internal |
590.0 |
12445.0 |
ClinicalTrials.gov |
EHR |
manual |
normalization |
beam search |
MLP, Tree-MemNN, ClinicalBERT, Transformer Encoder |
USC |
method |