Artificial Intelligence–Driven Risk-Based Monitoring Framework for Phase I–III Clinical Trials
Main Article Content
Abstract
As have rapidly developed electronic health records and artificial intelligence, we are presented with new opportunities for enhancing the efficiency and accuracy of clinical trial monitoring. This research presents a Recurrent Neural Networks (RNN)-based, AI-enabled risk-based monitoring system using MIMIC-III data. This section comprises various preprocessing stages, such as handling missing values, one-hot encoding, and min-max scaling, followed by train-test splitting and model implementation. The RNN model is structured to learn the time-dependent relationship of clinical data to predict risk. Experimental results show improved performance, with accuracy (acc) of 92.08, precision (prec) of 94.8, recall (rec) of 96.6, F1-score (F1) of 95.7, and AUC of 0.98. The comparative analysis reveals that the proposed model outperforms conventional machine learning techniques, including MLP, XGBoost, and SVM. The results indicate that the suggested method can be successfully used to enhance the efficiency of early risk identification and patient safety during clinical trials and could serve as a potential solution for real-time AI-based monitoring systems.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
References
R. Liu, H. Liu, L. Li, Z. Wang, and Y. Li, “Predicting in-hospital mortality for MIMIC-
III patients: A nomogram combined with SOFA score,” Medicine (Baltimore)., vol. 101, no. 42, p. e31251, Oct. 2022, doi: 10.1097/MD.0000000000031251.
R. Snehamrutha, “Patient Engagement Strategies in Community Pharmacies and their
Effect on Vaccination Uptake and Medication Synchronizations,” ESP J. Eng. Technol. Adv., vol. 3, no. 3, pp. 163–173, 2023, doi: 10.56472/25832646/JETA-V3I7P120.
J. A. Kachhia, “Healthcare Predictive Analytics based on Machine Techniques for Identifying Cardiovascular Risks Screening,” Int. J. Curr. Eng. Technol., vol. 13, no. 6, pp. 635–642, 2023, doi: 10.14741/ijcet/v.13.6.17.
Z. He, A. Erdengasileng, X. Luo, A. Xing, N. Charness, and J. Bian, “How the clinical research community responded to the COVID-19 pandemic: An analysis of the COVID19 clinical studies in ClinicalTrials.gov,” JAMIA Open, 2021, doi: 10.1093/jamiaopen/ooab032.
K. Larson et al., “COVID-19 interventional trials: Analysis of data sharing intentions during a time of pandemic,” Contemp. Clin. Trials, vol. 115, p. 106709, Apr. 2022, doi: 10.1016/j.cct.2022.106709.