Longitudinal Modeling of Glaucoma Progression Using 2-Dimensional Continuous-Time Hidden Markov Model

摘要: We propose a 2D continuous-time Hidden Markov Model (2D CT-HMM) for glaucoma progression modeling given longitudinal structural and functional measurements. CT-HMM is suitable medical data consisting of visits at arbitrary times, state structure more appropriate since the time courses degeneration are usually different. The learned model not only corroborates clinical findings that evident than in early opposite observed advanced stages, but also reveals exact stages where trend reverses. A method to detect segments fast proposed. Our results show this detector can effectively identify patients with rapid degeneration. derived be value monitoring.