Authors :
Rishabh Jha; Amrita Singh; Dr. Anju Bhandari Gandhi
Volume/Issue :
Volume 9 - 2024, Issue 12 - December
Google Scholar :
https://tinyurl.com/ycy97dep
Scribd :
https://tinyurl.com/3ba8s84r
DOI :
https://doi.org/ 10.5281/zenodo.14575931
Abstract :
Coronary heart disease (CHD) is a leading
global health challenge, necessitating early and accurate
diagnostic methods to prevent adverse outcomes. This
research explores the application of Explainable
Artificial Intelligence (XAI) to enhance the diagnostic
process. Leveraging CatBoost, a high-performing
gradient boosting algorithm, this study achieves the
maximum performance, minimizing false negatives and
ensuring all potential CHD cases are identified.
Furthermore, SHAP (SHapley Additive exPlanations)
values are utilized to provide transparency in the
model's decision-making process, addressing the opacity
often associated with machine learning systems. The
combination of high predictive performance and
explainability demonstrates the feasibility of deploying
AI systems in clinical decision-making for CHD.
References :
- Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems.
- Prokhorenkova, L., et al. (2018). CatBoost: Unbiased Boosting with Categorical Features. Advances in Neural Information Processing Systems.
- Benjamin, E. J., et al. (2019). Heart Disease and Stroke Statistics—2019 Update: A Report From the American Heart Association. Circulation.
- Titti, R., Pukkella, S. & Radhika, T. (2024). Augmenting heart disease prediction with explainable AI: A study of classification models. Computational and Mathematical Biophysics, 12(1), 20240004. https://doi.org/10.1515/cmb-2024-0004
- El-Sofany, H., Bouallegue, B. & El-Latif, Y.M.A. A proposed technique for predicting heart disease using machine learning algorithms and an explainable AI method. Sci Rep 14, 23277 (2024). https://doi.org/10.1038/s41598-024-74656-2
- Unveiling the black box: imperative for explainable AI in cardiovascular disease prevention Wu, Yanyi , The Lancet Regional Health – Western Pacific, Volume 48, 101145
- M.U. Sreeja, Abin Oommen Philip, M.H. Supriya, Towards explainability in artificial intelligence frameworks for heartcare: A comprehensive survey, Journal of King Saud University - Computer and Information Sciences, Volume 36, Issue 6, 2024, 102096, ISSN 1319-1578, https://doi.org/10.1016/j.jksuci.2024.102096.
- Jha, R., & Singh, A. (n.d.). Early diagnosis of cyanotic congenital heart disease using deep learning. In Advances in artificial intelligence for healthcare ( Taylor & Francis, USA) https://doi.org/10.1201/9781003493570-3.
Coronary heart disease (CHD) is a leading
global health challenge, necessitating early and accurate
diagnostic methods to prevent adverse outcomes. This
research explores the application of Explainable
Artificial Intelligence (XAI) to enhance the diagnostic
process. Leveraging CatBoost, a high-performing
gradient boosting algorithm, this study achieves the
maximum performance, minimizing false negatives and
ensuring all potential CHD cases are identified.
Furthermore, SHAP (SHapley Additive exPlanations)
values are utilized to provide transparency in the
model's decision-making process, addressing the opacity
often associated with machine learning systems. The
combination of high predictive performance and
explainability demonstrates the feasibility of deploying
AI systems in clinical decision-making for CHD.