Whole-body Representation Learning For Competing Preclinical Disease Risk Assessment
This work addresses the problem of early disease risk prediction for public healthcare by providing a more effective screening tool, though it appears incremental as it builds on existing self-supervised and competing risk modeling approaches.
The paper tackles preclinical disease risk assessment by proposing a whole-body self-supervised representation learning method that outperforms whole-body radiomics in predicting multiple diseases, including cardiovascular disease, type 2 diabetes, COPD, and chronic kidney disease, with further improvements for CVD subgroups when combined with cardiac MRI.
Reliable preclinical disease risk assessment is essential to move public healthcare from reactive treatment to proactive identification and prevention. However, image-based risk prediction algorithms often consider one condition at a time and depend on hand-crafted features obtained through segmentation tools. We propose a whole-body self-supervised representation learning method for the preclinical disease risk assessment under a competing risk modeling. This approach outperforms whole-body radiomics in multiple diseases, including cardiovascular disease (CVD), type 2 diabetes (T2D), chronic obstructive pulmonary disease (COPD), and chronic kidney disease (CKD). Simulating a preclinical screening scenario and subsequently combining with cardiac MRI, it sharpens further the prediction for CVD subgroups: ischemic heart disease (IHD), hypertensive diseases (HD), and stroke. The results indicate the translational potential of whole-body representations as a standalone screening modality and as part of a multi-modal framework within clinical workflows for early personalized risk stratification. The code is available at https://github.com/yayapa/WBRLforCR/