A Semi-Markov Switching Linear Gaussian Model for Censored Physiological Data
This work addresses the need for timely ICU transfers in regular wards, offering a novel risk assessment tool for patient monitoring, though it is incremental as it builds on existing switching linear models.
The authors tackled the problem of predicting clinical deterioration in critically ill patients by developing a Semi-Markov Switching Linear Gaussian Model (SSLGM) for physiological data, which significantly outperformed existing risk scores like Rothman index, MEWS, SOFA, and APACHE in experiments on 6,094 patients.
Critically ill patients in regular wards are vulnerable to unanticipated clinical dete- rioration which requires timely transfer to the intensive care unit (ICU). To allow for risk scoring and patient monitoring in such a setting, we develop a novel Semi- Markov Switching Linear Gaussian Model (SSLGM) for the inpatients' physiol- ogy. The model captures the patients' latent clinical states and their corresponding observable lab tests and vital signs. We present an efficient unsupervised learn- ing algorithm that capitalizes on the informatively censored data in the electronic health records (EHR) to learn the parameters of the SSLGM; the learned model is then used to assess the new inpatients' risk for clinical deterioration in an online fashion, allowing for timely ICU admission. Experiments conducted on a het- erogeneous cohort of 6,094 patients admitted to a large academic medical center show that the proposed model significantly outperforms the currently deployed risk scores such as Rothman index, MEWS, SOFA and APACHE.