A Retrospective Study of Mortality for Perioperative Cardiac Arrests Towards Personalized Treatment

Abstract

Background Perioperative cardiac arrest (POCA) is associated with a high mortality rate. This work aims to study its prognostic factors for risk mitigation by means of care management and planning. Methods A database of 380,919 surgeries was reviewed and 150 POCAs were curated. The main outcome is the mortality prior to hospital discharge. Patient demographics, medical history, and clinical characteristics (anesthesia and surgery) were main features. Six ML algorithms were explored: LR, SVC, RF, GBM, AdaBoost, and VotingClassifier. The last one is an ensemble of the beginning five ones. k-fold cross-validation and bootstrapping minimized the prediction bias and variance, respectively. Explainers (SHAP and LIME) were used to interpret the predictions. Results The ensemble provided the most accurate and robust predictions (AUC=0.90 [95% CI, 0.78-0.98]) across various age groups. The risk factors were identified by order of importance. Surprisingly, the comorbidity of hypertension was found to have a protective effect on survival, which was reported by a recent study (Alnabelsi T. et. al. 2020) for the first time to our knowledge. Conclusions The validated ensemble classifier in aid of the explainers improved the predictive differentiation, deepening our understanding of POCA prognostication. It offers a holistic model-based approach for personalized anesthesia and surgical treatment.