A kNN based machine learning approach to automating causality assessment of adverse events

This paper introduces a machine learning classifier designed to automate causality assessment in Individual Case Safety Reports (ICSRs), utilizing the principle of event similarity. The classifier’s effectiveness was evaluated using adverse events from six marketed products. Furthermore, we incorporated an augmentation tool to efficiently manage the classification of ‘unassessable’ adverse events. To enhance medical review oversight, we developed a web-based application serving as a reliable decision-support tool for medical reviewers. The outcomes obtained from our model were highly encouraging, emphasizing the potential advantages of utilizing such a model in ICSR causality assessment.