TECHNICAL NOTE | doi:10.20944/preprints201911.0073.v1
Subject: Computer Science And Mathematics, Probability And Statistics Keywords: deep behavioral covariates; clinical informatics; predictive modeling; electronic medical records; machine-learning; data-mining
Online: 7 November 2019 (09:25:04 CET)
Deep behavioral covariates (DBCs) introduced in this perspective form a new class of covariates that have the potential to enhance the performance of predictive models and improve analytics in clinical decision support applications. DBCs can measure how engaged a patient tends to be and how he or she tends to respond to events, and they may be highly predictive of the patient’s outcomes for a planned treatment. DBCs may potentially serve as a standard to measure patient engagement and activation and may form highly efficient mechanisms for improving patient outcomes.