Explainable Automated Non-linear Computation scoring system for Health (EACH) score : a Machine Learning based Explainable Automated Nonlinear Computation scoring system for Health and an application for prediction of perioperative stroke (Preprint)

Abstract

Machine learning (ML) has the potential to enhance performance by capturing nonlinear interactions. However, ML-based models have some limitations in terms of interpretability.

To address this, we developed and validated a more comprehensible and efficient ML-based scoring system using SHapley Additive exPlanations (SHAP) values.

We developed and validated the Explainable Automated nonlinear Computation for Health (EACH) framework score. We developed CatBoost based prediction model, identified key features, and automatically detected the top five steepest slope change points based on SHAP plots. Subsequently, we developed a scoring system (EACH) and normalized the score. Finally, the EACH score was used to predict perioperative stroke.

When applied for perioperative stroke prediction among 44,901 patients undergoing noncardiac surgery, the EACH score achieved an area under the curve (AUC) of 0.829 [95% CI, 0.753-0.892]. In the external validation, the EACH score demonstrated superior predictive performance with an AUC of 0.784 [95% CI, 0.694-0.871] compared to a traditional score (AUC of 0.528 [95% CI, 0.457-0.619]) and another ML-based scoring generator (AUC of 0.784 [95% CI, 0.694-0.871]).

The EACH score is a more precise, explainable ML-based risk tool, proven effective in real-world data, outperforming traditional scoring system.