Modeling sepsis progression using hidden Markov models
This work addresses sepsis risk stratification for personalized treatment, but it is incremental as it builds on existing diagnostic criteria.
The authors tackled the problem of characterizing sepsis progression by introducing a hidden Markov model that accounts for patient heterogeneity, providing a tool to uncover latent trajectories and identify high-risk patients.
Characterizing a patient's progression through stages of sepsis is critical for enabling risk stratification and adaptive, personalized treatment. However, commonly used sepsis diagnostic criteria fail to account for significant underlying heterogeneity, both between patients as well as over time in a single patient. We introduce a hidden Markov model of sepsis progression that explicitly accounts for patient heterogeneity. Benchmarked against two sepsis diagnostic criteria, the model provides a useful tool to uncover a patient's latent sepsis trajectory and to identify high-risk patients in whom more aggressive therapy may be indicated.