Open Conference Systems, 50th Scientific meeting of the Italian Statistical Society

Font Size: 
Hidden Markov Models for disease progression
Andrea Martino, Andrea Ghiglietti, Giuseppina Guatteri, Anna Maria Paganoni

Last modified: 2018-05-18


Disease progression models are a powerful tool for understanding and predicting the development of a disease, given some longitudinal measurements obtained from a sample of patients. These models are able to give some insights about the disease progression through the analysis of patients histories and could be also used to predict the future course of the disease in an individual. In particular, Hidden Markov Models (HMMs) are a useful tool for disease modeling since they allow to model situations where the state of the disease is not observable, by giving the possibility to incorporate some priors and constraints. We applied our models to a simulated dataset by considering a generalization of HMMs with continuous time and multivariate outcome.


1. Cox DR, Miller HD. The Theory of Stochastic Processes. Chapman and Hall; London: 1965.
2. Jackson CH. Multi-state models for panel data: the msm package for R. Journal of Statistical Software. 2011; 38 (no. 8)
3. Y.Y. Liu, S. Li, F. Li, L. Song, J.M. Rehg, Efficient Learning of Continuous-Time Hidden Markov Models for Disease Progression, Advances in Neural Information Processing Systems, 3599-3607
4. R Core Team (2017). R: A language and environment for statistical computing. R Foundation for StatisticalComputing, Vienna, Austria. URL
5. L. R. Rabiner, A tutorial on hidden Markov models and selected applications in speech recognition, Proc. IEEE, 77, 257-285 (1989)

Full Text: PDF