3:35 p.m. CT Monday, June 15
A key trend in current medical research is a shift from a one-size-fits-all to precision treatment strategies, where the focus is on identifying narrow subgroups of the population that would benefit from a given intervention. Within precision medicine, artificial intelligence can provide algorithms and accessible tools that clinicians can use to identify such subgroups and to generate novel inferences about the patient population they are treating. In many medical fields, especially in those requiring long-term care such as Type 2 Diabetes, complexity and variability of patients’ trajectories pose significant challenges. Longitudinal analytics methods, their exploitation in the context of clinical decisions, and their translation into clinical practice through accessible tools represent a potential for enabling precision health care. Algorithms such as Topological data analysis and Careflow mining are able to stratify large cohorts of patients on the basis of the heterogeneous digital health data registered during the course of the disease, and to provide indications regarding the underpinning mechanisms of the disease’s evolution. Such algorithms can be integrated Learning Health Systems, which are aimed at improving health service delivery while learning from processes extracted from digital data, care pathways captured from patients-level metrics, and multivariate process patterns.