Machine learning prediction of increased healthcare utilization in colectomy for inflammatory bowel disease.

PURPOSE: Healthcare spending for patients with inflammatory bowel disease (IBD) has steadily increased over the past few decades. While some of the increase is due to the rise in the use of biologics, surgery and postoperative care contribute significantly to healthcare spending. We aimed to analyze the preoperative factors associated with increased healthcare resource utilization (HRU) by developing and internally validating machine learning prediction models for increased HRU. METHODS: We analyzed the ACS-NSQIP database from 2018 to 2022 to identify preoperative factors that could predict increased HRU in patients undergoing non-emergent colectomy for Crohn's disease or ulcerative colitis. Increased HRU was defined as a composite of either (a) discharge destination other than home, (b) readmission within 30 days of surgery, or (c) prolonged length of stay. A total of six machine learning algorithms were utilized to find the best-performing model determined by area under the curve. Models were internally validated with an 80:20 training and testing split. RESULTS: A total of 7535 patients were analyzed. The overall rate of increased HRU was 33%. The best-performing model was the random forest, achieving an AUC of 0.75, an accuracy of 0.73, and an F1 of 0.82. The most important preoperative variables for model accuracy were albumin, hematocrit, and creatinine. CONCLUSION: Machine learning may assist in identifying IBD patients at risk for increased healthcare resource utilization. Here, we propose a predictive model in the preoperative setting that may allow targeted perioperative planning to optimize outcomes and resource use.