Application of Explainable AI for Diagnosis of Coronary Heart Disease


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 :

  1. Lundberg, S. M., & Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. Advances in Neural Information Processing Systems.
  2. Prokhorenkova, L., et al. (2018). CatBoost: Unbiased Boosting with Categorical Features. Advances in Neural Information Processing Systems.
  3. Benjamin, E. J., et al. (2019). Heart Disease and Stroke Statistics—2019 Update: A Report From the American Heart Association. Circulation.
  4. 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
  5. 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
  6. Unveiling the black box: imperative for explainable AI in cardiovascular disease prevention Wu, Yanyi , The Lancet Regional Health – Western Pacific, Volume 48, 101145
  7. 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.
  8. 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.

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe