A Machine Learning Approach in Predicting Mortality Following Emergency General Surgery

Background There is a significant mortality burden associated with emergency general surgery (EGS) procedures. The objective of this study was to develop and validate the use of a machine learning approach to predict mortality following EGS. Methods The American College of Surgeons National Surgical Quality Improvement Program database was queried for patients who underwent EGS between 2012 and 2017. We developed a machine learning algorithm to predict mortality following EGS and compared its performance with existing risk-prediction models of American Society of Anesthesiologists (ASA) classification, American College of Surgeon Surgical Risk Calculator (ACS-SRC), and the modified frailty index (mFI) using the area under receiver operative curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Results The machine learning algorithm had a very high performance for predicting mortality following EGS, and it had superior performance compared to the ASA classification, ACS-SRC, and the mFI, as measured by the AUC, sensitivity, specificity, PPV, and NPV. Discussion Machine learning approaches may be a promising tool to predict outcomes for EGS, aiding clinicians in surgical decision-making and counseling of patients and family, improving clinical outcomes by identifying modifiable risk factors than can be optimized, and decreasing treatment costs through resource allocation.