XAI–reduct: accuracy preservation despite dimensionality reduction for heart disease classification using explainable AI

Abstract

Machine learning (ML) has been used for classification of heart diseases for almost a decade, although understanding of the internal working of the black boxes, i.e., non-interpretable models, remain a demanding problem. Another major challenge in such ML models is the curse of dimensionality leading to resource intensive classification using the comprehensive set of feature vector (CFV). This study focuses on dimensionality reduction using explainable artificial intelligence, without negotiating on accuracy for heart disease classification. Four explainable ML models, using SHAP, were used for classification which reflected the feature contributions (FC) and feature weights (FW) for each feature in the CFV for generating the final results. FC and FW were taken into account in generating the reduced dimensional feature subset (FS). The findings of the study are as follows: (a) XGBoost classifies heart diseases best with explanations, with an increase in 2% in model accuracy over existing best proposals, (b) explainable classification using FS exhibits better accuracy than most of the literary proposals, and (c) with the increase in explainability, accuracy can be preserved using XGBoost classifier for classifying heart diseases, and (d) the top four features responsible for diagnosis of heart disease have been exhibited which have common occurrences in all the explanations reflected by the five explainable techniques used on XGBoost classifier based on feature contributions. To the best of our knowledge, this is first attempt to explain XGBoost classification for diagnosis of heart diseases using five explainable techniques.

Analysis of hematological indicators via explainable artificial intelligence in the diagnosis of acute heart failure: a retrospective study

“…contribution of each input variable to the model's predictions, allowing for a better understanding of the model's decisionmaking process. In the context of medical diagnosis, SHAP can help identify which hematological indicators are most influential in predicting acute heart failure such as the work recently done in(28)(29)(30).…”

XAI‐driven model for crop recommender system for use in precision agriculture

“…Similarly, the XAI technology is used in intrusion detection systems as experimented by Patil et al 34 using the LIME‐based analysis over classification algorithms like DT, RF, and SVM. Another similar study using XGBoost is used in intrusion detection over SHAP‐based analysis and obtained an accuracy of 93.28% as experimented by Barnard et al 35 There are numerous applications of XAI in feature analysis and explainability of the algorithms in the healthcare domain, Das et al 36 have experimented with XAI technology feature contributions and feature weights using SHAP for heart disease classification. Shad et al 37 have experimented with XAI Alzheimer's disease prediction over the different neural networks models like Resnet50, VGG16, and Inception v3, using LIME analysis, and the models have obtained an accuracy of 82%, 86%, 82% respectively.…”

A Comprehensive Survey of ArtificialIntelligence in Precision Healthcare:Shedding Light on Interpretability

“…Explainability methods are compared on different machine learning model. Five explainable models are used to show top features contributing in diagnosing heart diseases [71]. Pneumonia infection classification using transfer learning and explainability using LIME for chest X-ray images are performed.…”