Explainable Artificial Intelligence (XAI) for Early Detection and Transparent Diagnosis in Healthcare
This chapter presents an Explainable Artificial Intelligence (XAI) framework for healthcare diagnosis. While traditional machine learning models achieve high accuracy, they act as black-box models and doctors cannot trust them. This work uses SHAP and LIME to explain model predictions, improve transparency, and support clinical decision-making. The proposed model is evaluated on a healthcare dataset and achieves high accuracy while providing clear, interpretable explanations for each prediction. The results show that XAI can bridge the gap between AI performance and clinical trust, making AI systems safer and more acceptable for real hospitals
Authors
- R Shravan Kumar Reddy
- M Sandeep
- Beevi Hairunesa
- D Kaviyaadharshani
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2026-11-17
- DOI
- https://doi.org/10.5281/zenodo.24314301
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 0.00