Learning from Clinical Judgments: Semi-Markov-Modulated Marked Hawkes Processes for Risk Prognosis
This work addresses the critical need for accurate risk prognosis in hospitalized patients to prevent adverse events, representing an incremental improvement over current methods.
The authors tackled the problem of predicting deterioration in critically ill patients by developing a novel continuous-time probabilistic model that incorporates clinical judgments and physiological data, resulting in significantly outperforming existing medical risk scores and baseline machine learning algorithms on a 3-year patient cohort.
Critically ill patients in regular wards are vulnerable to unanticipated adverse events which require prompt transfer to the intensive care unit (ICU). To allow for accurate prognosis of deteriorating patients, we develop a novel continuous-time probabilistic model for a monitored patient's temporal sequence of physiological data. Our model captures "informatively sampled" patient episodes: the clinicians' decisions on when to observe a hospitalized patient's vital signs and lab tests over time are represented by a marked Hawkes process, with intensity parameters that are modulated by the patient's latent clinical states, and with observable physiological data (mark process) modeled as a switching multi-task Gaussian process. In addition, our model captures "informatively censored" patient episodes by representing the patient's latent clinical states as an absorbing semi-Markov jump process. The model parameters are learned from offline patient episodes in the electronic health records via an EM-based algorithm. Experiments conducted on a cohort of patients admitted to a major medical center over a 3-year period show that risk prognosis based on our model significantly outperforms the currently deployed medical risk scores and other baseline machine learning algorithms.