Keywords: clinical trial, predictive model, machine learning, analytics, quality
Lack of insight to proactively predict, in a data-driven and objective manner, which clinical trials are at risk of experiencing Good Clinical Practice (GCP) quality issue is a problem in clinical development. We develop a predictive model that predicts the risk of experiencing possible poor-quality outcomes for a given clinical trial based on information that’s typically available at approved protocol stage to address this problem. The model is based on the historical data from clinical trials and utilizes machine learning techniques to achieve high accuracy. It has been demonstrated to reflect potential quality risk. Providing this capability increases awareness of the risk level associated with the study. It also helps to drive risk-based planning and oversight. In this poster, we will share our approach to solve this problem, and the methodology that we used.