Journal DOI 10.68956/journal.human-performance-futures

Creative Commons source reading · Explainable decision support

An explainable artificial intelligence framework for ischemic heart disease prediction using enhanced squirrel search feature selection

D. Cenitta; N. Arul; R. Vijaya Arjunan; Krishnaraj Chadaga; J. Andrew

Originally published in Sci Rep · 2026-04-01

From the article

Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.

Abstract

Clinical decision-making depends on the ability to anticipate ischemic heart disease (IHD) accurately and interpretably. Despite their excellent accuracy, machine learning models are not often accepted in medical applications due to their black-box nature. To diagnose IHD, this study suggests an Explainable Artificial Intelligence (XAI) architecture that combines explainable models with the Enhanced Squirrel Search Optimization (ESSO) method for feature selection. The proposed Enhanced Squirrel Search Optimization (ESSO) introduces adaptive exploration mechanisms to efficiently identify an optimal subset of clinically relevant features. By integrating ESSO-based feature selection with Random Forest classification and explainable AI techniques (SHAP and LIME), the framework simultaneously improves predictive performance and provides…

Discussion

The proposed ISSO-RF-XAI framework successfully addresses key challenges in medical AI: dimensionality, accuracy, and interpretability. Although the deep learning models might be used as a reason to procure high performance, they tend to be black boxes. By contrast, we are able to match the accuracy in our framework with explainability, which is an essential attribute in clinical practice. This model, as well as predict disease, also enables the clinician to know why he or she has made that decision by picking such a minimal number of features and providing post-hoc explanations. Such a dual orientation reinforces its real-time usability in risk stratification and decision support of cardiovascular diagnostics.

Conclusion

This paper developed a new framework that is interpretable in predicting the ischemic heart disease (IHD) through the integration of the improved squirrel search optimization (ISSO) feature selection algorithm, Random Forest classifier, SHAP and LIME algorithms to interpret the model. High dimensionality was effectively addressed by the ISSO algorithm that provided a minimal set of highly informative clinical features with a major reduction in the number of dimensions, and which retained the accuracy of predictivity. Random Forest classifier with the optimized subset was trained successfully, and it performed with a great degree of accuracy of 96.4%, F1-score of 0.96, and an AUC of 0.98 compared to other traditional feature selection methods. Noteworthy, the explainable AI techniques allow having significant insights into the…

Editorial reading guide

  • What data created and tested the model, and was evaluation independent?
  • What is the cost of a false positive, false negative or out-of-distribution decision?