Explainable artificial intelligence for Healthcare applications using Random Forest Classifier with LIME and SHAP

Abstract: With the advances in computationally efficient artificial Intelligence (AI) techniques and its numerous applications in our every day's life, there is a pressing need to understand the computational details hidden in black box AI techniques such as: most popular machine learning and deep learning techniques; through more detailed explanations. The origin of explainable AI (xAI) is coined from these challenges and recently gained more attentions by the researchers by adding explainability comprehensively in traditional AI systems. This leads to develop an appropriate framework for successful applications of xAI in real life scenarios with respect to innovations, risk mitigation, ethical issues and logical values to the users. In this book chapter, an in-depth analysis of several xAI frameworks and methods including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations) are provided. Random Forest Classifier as black box AI is used on a publicly available Diabetes symptoms dataset with LIME and SHAP for better interpretations. The results obtained are interesting in terms of transparency, valid and trustworthiness in diabetes disease prediction. Introduction In the recent past, applications of artificial intelligence techniques have seen exponential growth in every sphere of life, be it Computer vision, natural language processing, precision medicine, smart agriculture, or autonomous driving to name a few, despite its poor transparency and interpretability. The emerging deep learning architectures are posing even more complexity in interpreting and explaining the inner details of the black box approaches what they adopt.