AI-Driven Quality Assurance Frameworks for Decentralized Clinical Trials
DOI:
https://doi.org/10.63282/3050-9262.IJAIDSML-V6I4P131Keywords:
AI-Driven Quality Assurance Framework, Machine Learning (ML), Electronic Clinical Outcome Assessment (eCOA), Artificial Intelligence (AI), Decentralized Clinical Trials (DCTs), Risk-Based Quality Management (RBQM), Defect Prediction, PreventionAbstract
Traditional quality assurance (QA) processes used in electronic Clinical Outcome Assessment (eCOA), and Decentralized Clinical Trial (DCT) platforms rely on a variety of manual, reactive approaches with many regulatory risk elements. The purpose of this research is to introduce an AI-powered Predictive Quality Assurance (PQA) system that uses Ensemble Machine Learning Models to predict problems with the DCT platform or eCOA application prior to their release into production. Using simulated and anonymized QA data sets, the PQA system will implement Supervised Learning, Deep Learning and Hybrid models to generate Risk Scores at the Module Level as well as Optimize Regression Test Coverage in Real Time. The evaluation outcomes showed improvements in defect prediction accuracy and reductions in Defect Leakage post Release, and thus the use of AI-Driven QA can enhance the dependability of software applications, prepare the software applications for Regulatory Audits, and help enable the Digital Transformation of Clinical Research Systems.
References
[1] Iqra Batool and Tamim Ahmed Khan, “Software fault prediction using deep learning techniques,” Software quality journal, vol. 31, no. 4, pp. 1241–1280, Jun. 2023, doi: https://doi.org/10.1007/s11219-023-09642-4 .
[2] Y. Shin, M. Lee, Y. Lee, K. Kim, and T. Kim, “Artificial Intelligence-Powered Quality Assurance: Transforming Diagnostics, Surgery, and Patient Care—Innovations, Limitations, and Future Directions,” Life, vol. 15, no. 4, p. 654, Apr. 2025, doi: https://doi.org/10.3390/life15040654 .
[3] M. Jorayeva, A. Akbulut, C. Catal, and A. Mishra, “Machine Learning-Based Software Defect Prediction for Mobile Applications: A Systematic Literature Review,” Sensors, vol. 22, no. 7, p. 2551, Jan. 2022, doi: https://doi.org/10.3390/s22072551 .
[4] N. Stansbury et al., “Risk-Based Quality Management: A Case for Centralized Monitoring,” Therapeutic Innovation & Regulatory Science, Dec. 2024, doi: https://doi.org/10.1007/s43441-024-00719-1 .
[5] J. Geraci et al., “Current Opportunities for the Integration and Use of Artificial Intelligence and Machine Learning in Clinical Trials: Good Clinical Practice Perspectives,” Journal of the Society for Clinical Data Management, vol. 5, no. 2, Jun. 2025, doi: https://doi.org/10.47912/jscdm.426 .
[6] S. Gordon et al., “Best Practice Recommendations: User Acceptance Testing for Systems Designed to Collect Clinical Outcome Assessment Data Electronically,” Therapeutic Innovation & Regulatory Science, vol. 56, no. 3, pp. 442–453, Mar. 2022, doi: https://doi.org/10.1007/s43441-021-00363-z .
[7] M. Sendak et al., “Development and Validation of ML-DQA -- a Machine Learning Data Quality Assurance Framework for Healthcare,” arXiv.org, 2022. https://arxiv.org/abs/2208.02670
[8] M. C. Vaghela et al., “Leveraging AI and Machine Learning in Six-Sigma Documentation for Pharmaceutical Quality Assurance,” Chinese Journal of Applied Physiology, vol. 40, p. e20240005, 2024, doi: https://doi.org/10.62958/j.cjap.2024.005 .
[9] D. A. Patel, “The Application of Deep Learning in Quality Assurance for U.S. Manufacturing,” African Journal of Artificial Intelligence and Sustainable Development, vol. 4, no. 2, pp. 158–178, 2024, Available: https://africansciencegroup.com/index.php/AJAISD/article/view/158
[10] M. S. Bari et al., “Toward an Adaptive AI/ML-Based QA Framework with HRM Integration for Inclusive and Secure Healthcare Solutions in Edge Environments,” Journal of Neonatal Surgery, vol. 14, no. 32S, pp. 7612–7620, Aug. 2025, doi: https://doi.org/10.63682/jns.v14i32s.8917 .
