Transparent AI: Developing an Explainable Interface for Predicting Postoperative Complications
This addresses the need for transparent AI in healthcare to improve risk assessment for surgical patients, but it is incremental as it builds on existing XAI techniques.
The authors tackled the problem of uninterpretable AI tools for predicting postoperative complications by developing an explainable AI framework with an interface prototype, which provided initial insights into its explanatory potential for clinical use.
Given the sheer volume of surgical procedures and the significant rate of postoperative fatalities, assessing and managing surgical complications has become a critical public health concern. Existing artificial intelligence (AI) tools for risk surveillance and diagnosis often lack adequate interpretability, fairness, and reproducibility. To address this, we proposed an Explainable AI (XAI) framework designed to answer five critical questions: why, why not, how, what if, and what else, with the goal of enhancing the explainability and transparency of AI models. We incorporated various techniques such as Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive exPlanations (SHAP), counterfactual explanations, model cards, an interactive feature manipulation interface, and the identification of similar patients to address these questions. We showcased an XAI interface prototype that adheres to this framework for predicting major postoperative complications. This initial implementation has provided valuable insights into the vast explanatory potential of our XAI framework and represents an initial step towards its clinical adoption.