Machine Learning Prediction of Postoperative Mortality in Older Emergency Surgery Patients.

INTRODUCTION: The older adult population account for 35% of emergency general surgery (EGS) admissions and have an increased risk-adjusted odds of mortality compared to their younger counterparts. We aimed to create a machine learning tool utilizing deep mixture of neural networks (DMNN) to predict postoperative mortality in the older adult requiring EGS. METHODS: The American College of Surgeons National Surgical Quality Improvement Program (NSQIP) 2023 database was queried with approximately one million patient records. Patients aged ≥55 y who underwent EGS were included. A DMNN model to predict postoperative mortality from patient clinical data and biomarkers was performed. Model performance was assessed using the area under the receiver operating characteristic curve, confusion matrices, and Shapley additive explanations. RESULTS: A total of 91,058 patients were included of which 49,363 (54%) were females with a mean age of 71.7 y. A total of 91,058 patients were included. In the held-out test set (n=1,000; mortality rate 5.9%), the DMNN achieved an area under the receiver operating characteristic curve of 0.910 (95% confidence interval 0.878-0.938) compared with 0.936 (95% confidence interval 0.911-0.959) for the NSQIP calculator (DeLong p=0.0039). At the 0.5 probability threshold, the DMNN demonstrated substantially higher sensitivity (0.542 versus 0.119) while maintaining high specificity (0.943 versus 0.997). This resulted in fewer missed deaths (27 versus 52 false negatives) at the cost of more false positives (54 versus 3). Multithreshold and decision-curve analyses showed that relative performance is threshold-dependent. The DMNN offered advantages in sensitivity at higher thresholds, while NSQIP showed modestly higher net benefit at several lower-to-moderate risk thresholds. CONCLUSIONS: Our DMNN model consisting of clinical variables performed adjunctively with the American College of Surgeons NSQIP risk calculator in perioperative mortality risk prediction for older adults undergoing EGS. This model could be further trained and utilized for improved accuracy and prediction of adverse outcomes in older EGS patients.