An Explainable AI Data Pipeline for Multi-Level Survival Prediction of Breast Cancer Patients Using Electronic Medical Records and Social Determinants of Health Data

Authors

• Soheil Hashtarkhani, The University of Tennessee Health Science Center College of Medicine
• Shelley White-Means, University of Tennessee Health Science Center
• Sam Li, University of Tennessee Health Science Center
• Rezaur Rashid, The University of Tennessee Health Science Center College of Medicine
• Fekede Kumsa, The University of Tennessee Health Science Center College of Medicine
• Cindy Lemon, University of Tennessee Health Science Center
• Lluvia Chipman, University of Tennessee Health Science Center
• Jill Dapremont, University of Memphis
• Brianna White, The University of Tennessee Health Science Center College of Medicine
• Arash Shaban-Nejad, The University of Tennessee Health Science Center College of Medicine

Abstract

This study introduces an innovative explainable AI (XAI) pipeline designed to predict breast cancer survival by integrating clinical, socioeconomic, and geographic data. Using data from 10,172 patients treated at hospitals in the Memphis, Tennessee metropolitan area, the pipeline identifies key survival determinants and reveals significant survival disparities affecting Black women. Advanced machine learning models combined with SHapley Additive exPlanations (SHAP) provide actionable and interpretable insights into the role of tumor stage, socioeconomic conditions, and access to preventive care. This framework facilitates personalized survival predictions and targeted equity-focused interventions, demonstrating the potential of multi-source data integration to address health inequities and improve patient outcomes.

Publication Title

Proceedings 2024 IEEE International Conference on Big Data Bigdata 2024

Recommended Citation

Hashtarkhani, S., White-Means, S., Li, S., Rashid, R., Kumsa, F., Lemon, C., Chipman, L., Dapremont, J., White, B., & Shaban-Nejad, A. (2024). An Explainable AI Data Pipeline for Multi-Level Survival Prediction of Breast Cancer Patients Using Electronic Medical Records and Social Determinants of Health Data. Proceedings 2024 IEEE International Conference on Big Data Bigdata 2024, 8661-8664. https://doi.org/10.1109/BigData62323.2024.10825044