Machine learning to predict patient engagement and retention in clinical trials and increase compliance with study aims

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for conditional monitoring using different groups of remote devices. In some implementations, a system accesses data indicating characteristics for a monitoring program that involves data collection from a plurality of remote devices over a communication network. The system identifies a group of candidates for the monitoring program and, based on outcomes of other monitoring programs, the system generates a prediction for a level of compliance of the group with the requirements of the monitoring program. The system generates one or more scores indicative of whether the monitoring program will satisfy one or more predetermined conditions needed for successful completion of the monitoring program. Based on the generated one or more scores, the system provides a notification over the communication network that is indicative of whether the monitoring program will satisfy one or more predetermined conditions.