Early Stratification of Patients at Risk for Postoperative Complications after Elective Colectomy
This work addresses the need for real-time risk stratification of patients after elective colectomy to reduce adverse events, representing an incremental improvement over existing static risk calculators.
The researchers tackled the problem of early detection of postoperative complications after elective colectomy by developing a Hidden Markov Model sequence classifier that analyzes patients' postoperative temperature sequences and incorporates time-invariant characteristics. Their method improved classification performance compared to 8 other machine learning classifiers using full temperature sequences and achieved close performance within 44 hours after surgery.
Stratifying patients at risk for postoperative complications may facilitate timely and accurate workups and reduce the burden of adverse events on patients and the health system. Currently, a widely-used surgical risk calculator created by the American College of Surgeons, NSQIP, uses 21 preoperative covariates to assess risk of postoperative complications, but lacks dynamic, real-time capabilities to accommodate postoperative information. We propose a new Hidden Markov Model sequence classifier for analyzing patients' postoperative temperature sequences that incorporates their time-invariant characteristics in both transition probability and initial state probability in order to develop a postoperative "real-time" complication detector. Data from elective Colectomy surgery indicate that our method has improved classification performance compared to 8 other machine learning classifiers when using the full temperature sequence associated with the patients' length of stay. Additionally, within 44 hours after surgery, the performance of the model is close to that of full-length temperature sequence.