Explainable AI in Healthcare Predictions

DOI

10.2991/978-94-6239-674-6_15How to use a DOI?

Keywords

Explainable AI; XAI; SHAP; LIME; healthcare prediction; clinical decision support

Abstract

This study aims to show how Explainable Artificial Intelligence (XAI) can increase clinician trust, boost hospital adoption of predictive systems, and improve the accuracy and accountability of AI-assisted diagnostics. The system created predicts the status of three diseases - heart disease, breast cancer and diabetes, and generates an understandable explanation for each of the predictions it makes. The interpretability framework is composed of two layers, namely, SHAP and LIME. SHAP recognizes and provides the importance of global features related to the dataset, while LIME provides a detailed local explanation for specific patients. According to experimental results, interpretable models such as Logistic Regression and Decision Trees succeeded in generating instant clarity and dependability, and black-box models such as XGBoost and Random Forest succeeded in achieving the best predictive performance. The study focuses on the three diseases and generates a comparative basis to access the performance of algorithms by comparing their predictive power and transparency in the task of predicting these diseases.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ankit Kumar Soni
AU  - Krishna Kumar
AU  - Vansh Choudhary
AU  - Arav Gupta
AU  - Sandeep Kaur Gill
PY  - 2026
DA  - 2026/05/28
TI  - Explainable AI in Healthcare Predictions
BT  - Proceedings of the International Conference on Sustainable Computing and Artificial Intelligence (ICSCAI 2025)
PB  - Atlantis Press
SP  - 169
EP  - 181
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-674-6_15
DO  - 10.2991/978-94-6239-674-6_15
ID  - Soni2026
ER  -