Feature allocation approach for multimorbidity trajectory modelling

Conference item

A multimorbidity trajectory charts the time-dependent acquisition of disease conditions in an individual. This is important for understanding and managing patients who have a complex array of multiple chronic conditions, particularly later in life. We construct a novel probabilistic generative model for multimorbidity acquisition within a Bayesian framework of latent feature allocation, which allows an individual’s morbidity profile to be driven by multiple latent factors and allows the modelling of age-dependent multimorbidity trajectories. We demonstrate the utility of our model in applications to both simulated data and disease event data from patient electronic health records. In each setting, we show our model can reconstruct clinically meaningful latent multimorbidity patterns and their age-dependent prevalence trajectories.

Authors: Kim, W; Jenkins, PA; Yau, C

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: PMLR
• Host title: Proceedings of the 2nd Machine Learning for Health symposium
• Pages: 103-119
• Series: Proceedings of Machine Learning Research
• Series number: 193
• Publication date: 2022-11-22
• Acceptance date: 2022-10-22
• Event title: Machine Learning for Health (ML4H) 2022
• Event location: New Orleans, Lousiana, USA
• Event website: https://ml4h.cc/2022/index.html
• Event start date: 2022-11-28
• Event end date: 2022-11-28
• EISSN: 2640-3498
• ISSN: 2640-3498
• Language: English
• Keywords: Bayesian feature allocation model; Markov chain Monte Carlo; multimorbidity analysis