Predictive Modeling of Anesthesia Types and Their Associations with Clinical Outcomes Using the MIMIC-IV Database

Abstract

Background: Perioperative management plays a pivotal role in reducing complications and improving patient outcomes. The choice of anesthesia can significantly influence postoperative trajectories; however, current clinical practice lacks data-driven tools to support personalized selection. With the emergence of machine learning (ML) and access to large clinical databases, new opportunities have arisen to optimize anesthesia selection and predict patient outcomes. Methods: This retrospective study utilized the MIMIC-IV database (version 3.1), which comprises data from over 364,000 patients. After feature selection and preprocessing, 28 demographic, clinical, and laboratory variables were used to model four types of anesthesia (general, regional, local, and sedation) in 31,821 patients. Supervised models [random forest, logistic regression, support vector machine (SVM), k-nearest neighbors (KNN), decision tree, gradient boosting, and extreme gradient boosting (XGBoost)] were trained to predict anesthesia type; synthetic minority oversampling technique (SMOTE) was applied within training to address class imbalance. Performance was evaluated on a held-out test set using accuracy and macro-F1. Associations between anesthesia type and short-term outcomes (in-hospital mortality, 30-day readmission, postoperative infection, and length of stay) were examined through observational comparisons. Results: Boosting-based models achieved the highest predictive performance, with XGBoost and gradient boosting reaching approximately 83% accuracy on the test set (macro-F1 for XGBoost ≈ 0.45). Across anesthesia groups, regional anesthesia was associated with more favorable outcomes than general anesthesia — namely lower in-hospital mortality, fewer infections, shorter hospital and intensive care unit (ICU) stays, and reduced 30-day readmission — although estimates for the regional group were less precise due to small sample size and residual confounding is possible. Conclusions: Anesthesia type was associated with short-term clinical outcomes in this large, single-center cohort, and boosting models demonstrated strong predictive performance for anesthesia type. These findings suggest a potential role for predictive analytics in perioperative planning, while underscoring that observed differences are associations rather than causal effects. Prospective multicenter studies and randomized trials, with longer-term patient-reported outcomes, are warranted. Predictive models require external validation and calibration before they can be used clinically.