A binary hidden Markov model on spatial network for amyotrophic lateral sclerosis disease spreading pattern analysis

Amyotrophic lateral sclerosis (ALS) is a neurological disease that starts at focal point and gradually spreads to other parts of the nervous system. One main clinical symptoms ALS muscle weakness. To study spreading patterns weakness, we analyze spatiotemporal binary strength data, which indicates whether observed strengths are impaired or healthy. We propose hidden Markov model-based approach assumes status depends on two latent states. The model enables us estimate incidence rate probability state transition. Specifically, latter modeled by logistic autoregression in spatial network susceptible muscles follows process. proposed flexible allow both historical conditions their relationships be included analysis. parameters, provide an iterative algorithm maximize sparse-penalized likelihood with bias correction, use Viterbi label apply patients' data from EMPOWER Study.