Early Stratification of Patients at Risk for Postoperative Complications after Elective Colectomy

TL;DR

This paper introduces a Hidden Markov Model-based method for real-time postoperative complication detection using temperature sequences, outperforming existing classifiers and enabling early risk stratification after elective colectomy.

Contribution

The study develops a novel Hidden Markov Model that incorporates patient-specific data for dynamic, real-time postoperative complication prediction, improving over existing static risk calculators.

Findings

Outperforms 8 other machine learning classifiers with full temperature data.

Achieves near-optimal performance within 44 hours post-surgery.

Enhances early detection of postoperative complications.

Abstract

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.