Clinical Trials and Machine Learning: Regulatory Approach Review

Abstract

: Machine Learning, a fast-growing technology, is an application of Artificial Intelligence that has significantly contributed to drug discovery and clinical development. In the last few years, the number of clinical applications based on Machine Learning has constantly been growing. Moreover, it is now also impacting National Competent Authorities during the assessment of most recently submitted Clinical Trials that are designed, managed, or generating data deriving from the use of Machine Learning or Artificial Intelligence technologies. We review current information available on the regulatory approach to Clinical Trials and Machine Learning. We also provide inputs for further reasoning and potential indications, including six actionable proposals for regulators to proactively drive the upcoming evolution of Clinical Trials within a strong regulatory framework, focusing on patient safety, health protection, and fostering immediate access to effective treatments.

Predicting Phase 1 Lymphoma Clinical Trial Durations Using Machine Learning: An In-Depth Analysis and Broad Application Insights

“…Using Python 3.9.7, we selected eight distinct machine learning models/classifiers to predict the duration of lymphoma clinical trials. Our choices were informed using previous research in oncology clinical trial predictions [ 4 , 6 , 16 , 17 , 18 , 19 , 20 , 21 , 22 , 23 , 24 ] and the inherent strengths of each model. These models are Logistic Regression (LR), K-Nearest Neighbor (KNN), Decision Tree (DT), Random Forest (RF), XGBoost (XGB), Linear Discriminative Analysis (LDA), Gaussian Naïve Bayes (Gaussian NB), and Multi-Layer Perceptron Classifier (MLP).…”

“…Furthermore, this foresight enables organizations to make informed decisions about trial prioritization, resource allocation, and initiation timelines [ 3 , 4 ]; Patient Involvement and Safety: estimating trial durations provides patients with clarity on their commitment, which safeguards their well-being and promotes informed participation [ 5 ]; Transparent Relations with Regulators: Providing predictions on trial durations, whether below or above the average, fosters open communication with regulatory authorities. This strengthens compliance, builds trust, and establishes transparent relationships among all stakeholders [ 6 ]. …”

“…Transparent Relations with Regulators: Providing predictions on trial durations, whether below or above the average, fosters open communication with regulatory authorities. This strengthens compliance, builds trust, and establishes transparent relationships among all stakeholders [ 6 ].…”

“…A wealth of studies also exist on outcome predictions using machine learning, from predicting treatment responses [ 21 ] to forecasting outcomes based on patient profiles [ 22 ] to predicting negative outcomes, with an emphasis on mortality events [ 23 ]. In regulatory compliance, machine learning has been used to automate clinical research classification [ 24 ] and recommend regulatory strategies [ 6 ].…”

Regulatory Considerations on the use of Machine Learning based tools in Clinical Trials

“…The need to test the ability of ML methods to identify data that may support with the interpretation of healthcare data together with real-world data (RWD), in a clinical trial setting, is clearly identified by EMA in the recent regulatory science research needs publication [ 13 ]. The application of ML in CTs may widely vary, from patient recruitment to study design, to the definition of endpoints or to perform a more accurate diagnosis; in any case the assessment of these technologies is impacting the activities of RAs involved in the authorization of clinical studies [ 14 ]. From a regulatory point of view, the lack of dedicated guidelines and harmonized approaches brings uncertainty among applicants and RAs [ 15 ], making it difficult to frame these tools, that sometimes according to the stated intended use, may be used within a trial for instance in the selection of patients to be enrolled, with the aim to just save resources in time consuming processes, and so they may not meet the definition of medical device.…”