Search papers, labs, and topics across Lattice.
This paper introduces a novel framework for early disease risk prediction that integrates survival analysis with classification techniques using EMR data. By re-engineering survival analysis methods for classification, the approach aims to create a more comprehensive tool for disease risk surveillance. Experiments on real-world EMR data demonstrate that the performance of the survival models is comparable to or better than state-of-the-art models like LightGBM and XGBoost, while also providing clinically validated explanations.
Survival analysis, traditionally used for time-to-event prediction, can be re-engineered to outperform standard classification models in chronic disease risk prediction while also providing clinically validated explanations.
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.
