Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{196380,
        author = {Smita Gavkar and Sujata Tirpude and Sonali Patil},
        title = {Explainable AI Approach for Heart Disease Risk Prediction Using Feature Importance Analysis},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {2743-2747},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=196380},
        abstract = {The increasing availability of healthcare data has enabled the application of machine learning techniques for early disease prediction. However, many predictive models function as “black boxes,” making it difficult for medical professionals to understand the reasoning behind predictions. This study proposes an explainable machine learning framework for predicting the risk of heart disease using patient health and lifestyle data. The dataset includes multiple clinical and behavioral attributes such as age, gender, blood pressure, cholesterol level, body mass index (BMI), smoking habits, stress level, and exercise patterns.
A predictive model was developed using the Random Forest algorithm implemented through scikit-learn. To enhance model transparency and interpretability, explainable artificial intelligence (XAI) techniques were applied to identify the most influential factors affecting heart disease prediction. Feature importance analysis was performed to determine the contribution of each attribute in the model’s decision-making process. Additionally, data exploration techniques such as correlation analysis and visualization were used to analyze relationships between health indicators.
Experimental results indicate that features such as cholesterol level, blood pressure, body mass index, and smoking habits significantly influence the prediction of heart disease risk. The integration of explainable AI methods provides meaningful insights into model behavior, making the predictive system more transparent and trustworthy for healthcare applications. The proposed approach demonstrates how interpretable machine learning models can support medical decision-making and early diagnosis, ultimately contributing to improved patient care and preventive healthcare strategies.},
        keywords = {Data mining in health care, Explainable Artificial Intelligence (XAI), Feature importance, Healthcare data analytics, Predictive Modeling},
        month = {April},
        }