Ferdowsi, Sohrab; Knafou, Julien; Borissov, Nikolay; Vicente Alvarez, David; Mishra, Rahul; Amini, Poorya; Teodoro, Douglas (2023). Deep learning-based risk prediction for interventional clinical trials based on protocol design: A retrospective study. Patterns, 4(3), p. 100689. Cell Press 10.1016/j.patter.2023.100689
|
Text
1-s2.0-S266638992300020X-main.pdf - Published Version Available under License Creative Commons: Attribution-Noncommercial-No Derivative Works (CC-BY-NC-ND). Download (5MB) | Preview |
Success rate of clinical trials (CTs) is low, with the protocol design itself being considered a major risk factor. We aimed to investigate the use of deep learning methods to predict the risk of CTs based on their protocols. Considering protocol changes and their final status, a retrospective risk assignment method was proposed to label CTs according to low, medium, and high risk levels. Then, transformer and graph neural networks were designed and combined in an ensemble model to learn to infer the ternary risk categories. The ensemble model achieved robust performance (area under the receiving operator characteristic curve [AUROC] of 0.8453 [95% confidence interval: 0.8409-0.8495]), similar to the individual architectures but significantly outperforming a baseline based on bag-of-words features (0.7548 [0.7493-0.7603] AUROC). We demonstrate the potential of deep learning in predicting the risk of CTs from their protocols, paving the way for customized risk mitigation strategies during protocol design.
Item Type: |
Journal Article (Original Article) |
|---|---|
Division/Institute: |
04 Faculty of Medicine > Pre-clinic Human Medicine > Department of Clinical Research (DCR) |
UniBE Contributor: |
Borissov, Nikolay, Amini, Poorya |
Subjects: |
600 Technology > 610 Medicine & health |
ISSN: |
2666-3899 |
Publisher: |
Cell Press |
Funders: |
[198] Innosuisse - Swiss Innovation Agency |
Language: |
English |
Submitter: |
Pubmed Import |
Date Deposited: |
27 Mar 2023 10:38 |
Last Modified: |
20 Feb 2024 14:15 |
Publisher DOI: |
10.1016/j.patter.2023.100689 |
PubMed ID: |
36960445 |
Uncontrolled Keywords: |
clinical trials deep learning graph neural networks neural language models risk prediction text classification text mining transformer-based language models |
BORIS DOI: |
10.48350/180643 |
URI: |
https://boris.unibe.ch/id/eprint/180643 |
Actions (login required)
 |
Edit item |