Explainable diabetes classification using hybrid Bayesian-optimized TabNet architecture. (December 2022)

• Record Type: Journal Article
• Authors: Joseph, Lionel P.; Joseph, Erica A.; Prasad, Ramendra
• Is Part Of: Computers in biology and medicine. Volume 151:Part A(2022)
• Publication Date: 2022-12
• Subjects: Attention mechanism -- Bayesian optimization -- "Black-box" models -- Diabetes classification -- eXplainable artificial intelligence (XAI) -- Interpretability -- TabNet; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2022.106178
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Diabetes is a deadly chronic disease that occurs when the pancreas is not able to produce ample insulin or when the body cannot use insulin effectively. If undetected, it may lead to a host of health complications. Hence, accurate and explainable early-stage detection of diabetes is essential for the proper administration of treatment options in leading a healthy and productive life. For this, we developed an interpretable TabNet model tuned via Bayesian optimization (BO). To achieve model-specific interpretability, the attention mechanism of TabNet architecture was used, which offered the local and global model explanations on the influence of the attributes on the outcomes. The model was further explained locally and globally using more robust model-agnostic LIME and SHAP eXplainable Artificial Intelligence (XAI) tools. The proposed model outperformed all benchmarked models by obtaining high accuracy of 92.2% and 99.4% using the Pima Indians diabetes dataset (PIDD) and the early-stage diabetes risk prediction dataset (ESDRPD), respectively. Based on the XAI results, it was clear that the most influential attribute for diabetes classification using PIDD and ESDRPD were Insulin and Polyuria, respectively. The feature importance values registered for insulin was 0.301 (PIDD) and for polyuria 0.206 was registered (ESDRPD). The high accuracy and ancillary interpretability of our objective model is expected to increase end-users trust and confidence in early-stage detection of diabetes. Graphical abstract: Image 1 Highlights: A robust deep learning model for tabular data – "TabNet" for early detection of diabetes. Bayesian optimization is applied to tune the hyperparameters of the TabNet model. The proposed model is tested on two separate datasets obtaining 92.2% and 99.4% accuracy. Model-specific local and global model interpretability is achieved via the sequential attention mechanism of TabNet. Local interpretability achieved by LIME XAI while SHAP XAI provided global interpretability.