TY  - JOUR
T1  - Health State Clustering and Prediction Based on Bayesian HMM
AU  - Sin, Bong-Kee 
JO  - Journal of KIISE, JOK
PY  - 2017
DA  - 2017/1/14
DO  - 10.5626/JOK.2017.44.10.1026
KW  - health clinic data
KW  - health state
KW  - hierarchical Dirichlet process
KW  - hidden Markov model
KW  - prediction
AB  - In this paper a Bayesian modeling and duration-based prediction method is proposed for health clinic time series data using the Hierarchical Dirichlet Process Hidden Markov Model (HDP-HMM). HDP-HMM is a Bayesian extension of HMM which can find the optimal number of health states, a number which is highly uncertain and even difficult to estimate under the context of health dynamics. Test results of HDP-HMM using simulated data and real health clinic data have shown interesting modeling behaviors and promising prediction performance over the span of up to five years. The future of health change is uncertain and its prediction is inherently difficult, but experimental results on health clinic data suggests that practical long-term prediction is possible and can be made useful if we present multiple hypotheses given dynamic contexts as defined by HMM states.