On the Problem of Latent Temporal Modulation in Diagnostic Decision-Making

Abstract

Modern diagnostic systems increasingly rely on longitudinal and multimodal data, yet they typically assume a stable relation between observations and disease risk. We introduce latent temporal modulation (LTM) as a conceptual framework for a class of problems in which the relation (i.e., the mapping between observations and risk) evolves over time due to temporally structured, non-observable factors. We formalise LTM and show that it is not explicitly represented within standard dynamic or latent-state modelling frameworks. In such settings, diagnostically relevant information is encoded in the evolving relation between observations and disease risk rather than in observed variables alone. This perspective has implications for the design of diagnostic decision systems operating on temporal medical data. In particular, LTM shifts the focus of diagnostic modelling from analysing temporal data alone to analysing how their interpretation evolves over time.