JMIR Publications

ABSTRACT

In digital medicine, patient data typically record health events over time (e.g., through electronic health records, wearables, or other sensing technologies) and thus form unique patient trajectories. Patient trajectories are highly prognostic of the future course of diseases and therefore facilitate effective care. However, digital medicine often uses only limited patient data, consisting of health events from only a single or a small number of time points while ignoring additional information encoded in patient trajectories. To leverage patient trajectories in digital medicine, new artificial intelligence (AI) solutions are needed, with implications for clinical practice across problem definition, data processing, modeling, evaluation, and interpretation. The development of these AI solutions will allow the field to build robust models of diseases that are optimized to work with the data heterogeneity typically seen in patient trajectories, thereby enabling the extraction of insights for personalized risk scoring, subgrouping, and pathway discovery.