Probabilistic Modelling of Multiple Long-Term Condition Onset Times

TL;DR

This paper introduces ProMOTe, a probabilistic model for clustering and forecasting the onset times of multiple long-term conditions, effectively handling incomplete health record data and revealing meaningful disease progression patterns.

Contribution

ProMOTe is a novel probabilistic approach that models disease onset times, enabling clustering and forecasting of multimorbidity trajectories from incomplete health data.

Findings

Identified 50 disease clusters consistent with prior studies

Demonstrated effective forecasting of disease progression

Handled incomplete and unreliable health records

Abstract

The co-occurrence of multiple long-term conditions (MLTC), or multimorbidity, in an individual can reduce their lifespan and severely impact their quality of life. Exploring the longitudinal patterns, e.g. clusters, of disease accrual can help better understand the genetic and environmental drivers of multimorbidity, and potentially identify individuals who may benefit from early targeted intervention. We introduce $\textit{probabilistic modelling of onset times}$, or $\texttt{ProMOTe}$, for clustering and forecasting MLTC trajectories. $\texttt{ProMOTe}$ seamlessly learns from incomplete and unreliable disease trajectories that is commonplace in Electronic Health Records but often ignored in existing longitudinal clustering methods. We analyse data from 150,000 individuals in the UK Biobank and identify 50 clusters showing patterns of disease accrual that have also been reported by some recent studies. We further discuss the forecasting capabilities of the model given the history of disease accrual.