Coupled Hidden Markov Model with Binomial and Truncated Geometric Copula to Investigate Hypertension and Diabetes Multimorbidity Progression

This study aims to investigate the relationship between hypertension and diabetes, two chronic diseases with significant public health implications. While the association between these two diseases has been well-established, the underlying pathogenic mechanisms remain unclear. The authors propose to use a recently developed model for studying multimorbidity, which considers the interactions between risk factors for each disease. We use a coupled hidden Markov model (CHMM) with binomial and truncated geometric copulas to analyze hospital appointment data from a private hospital between January 2015 and December 2020. The results suggest that the CHMM with discrete copulas is an effective tool for examining disease multimorbidity, particularly when clinical data is scarce. The study contributes to our understanding of the complex relationship between hypertension and diabetes, and highlights the importance of considering the interdependence of risk factors in the development of chronic diseases.