Survival Meets Classification: A Novel Framework for Early Risk Prediction Models of Chronic Diseases

2026-03-12

AI Summary

This study addresses the limitation of existing chronic disease risk prediction models, which typically rely solely on either survival analysis or classification methods and thus struggle to simultaneously capture temporal dynamics and achieve high discriminative accuracy. To overcome this, we propose a unified framework that, for the first time, reformulates survival analysis models for high-accuracy classification tasks while integrating clinically interpretable mechanisms. The approach enables early risk prediction for five major chronic conditions, including diabetes and hypertension. Evaluated on large-scale real-world electronic health records, our method matches or exceeds state-of-the-art models such as LightGBM and XGBoost in terms of accuracy, F1 score, and AUROC. Furthermore, the interpretability outputs of the model were validated and endorsed by three clinical experts.

Technology Category

• Machine Learning: Classification and Regression
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models
• Reasoning under Uncertainty: Graphical Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Chronic diseases are long-lasting conditions that require lifelong medical attention. Using big EMR data, we have developed early disease risk prediction models for five common chronic diseases: diabetes, hypertension, CKD, COPD, and chronic ischemic heart disease. In this study, we present a novel approach for disease risk models by integrating survival analysis with classification techniques. Traditional models for predicting the risk of chronic diseases predominantly focus on either survival analysis or classification independently. In this paper, we show survival analysis methods can be re-engineered to enable them to do classification efficiently and effectively, thereby making them a comprehensive tool for developing disease risk surveillance models. The results of our experiments on real-world big EMR data show that the performance of survival models in terms of accuracy, F1 score, and AUROC is comparable to or better than that of prior state-of-the-art models like LightGBM and XGBoost. Lastly, the proposed survival models use a novel methodology to generate explanations, which have been clinically validated by a panel of three expert physicians.

Problem

• chronic disease
• risk prediction
• survival analysis
• classification
• early detection

Innovation

• survival analysis
• classification
• chronic disease prediction
• explainable AI
• electronic medical records