Analyzing Patient Trajectories With Artificial Intelligence
Patient data recorded over time form unique patient histories that can predict future disease progression and thereby facilitate effective care. However, digital medicine often uses limited health events data from a single or small number of time points, ignoring additional information encoded in patient trajectories. This paper provides an overview of recent efforts to develop AI solutions that incorporate trajectories, with a particular focus on the implications for developing disease models from patient trajectories in the context of the typical AI workflow, and concludes with a discussion of how such AI solutions will enable the development of robust models for personalized risk assessment, subtyping, and disease pathway discovery.
See Allam et al., JMIR