Marrying Generative Model of Healthcare Events with Digital Twin of Social Determinants of Health for Disease Reasoning

Despite the central role of sensor-derived measurements such as imaging traits and plasma biomarkers in biomedical research and clinical practice, existing generative models for disease prediction largely depend on event-level representations from hospital and registry data. Given the multi-factorial nature of human disease, the absence of explicit modeling of social determinants of health (SDoH) limits the capacity for personalized disease modeling and clinical decision support. To address this limitation, we propose a generative model with ICD-coded proxies of SDoH for \textit{in silico} modeling of disease reasoning, a conditioned latent diffusion framework that establishes the connection between multi-organ sensor data with tokenized healthcare events. Specifically, we introduce a novel geometric diffusion model to characterize the temporal evolution of complex data representation such as brain networks (region-to-region connectivity encoded in a graph), in parallel with diffusion models for tabular data from other organ systems. Together, we integrate the generative model with digitalized SDoH proxies (coined **DiffDT**) for simulated intervention and reasoning of future disease trajectories. We conduct extensive experiments on the UK Biobank (UKB) dataset, which contains organ-specific imaging traits, including brain (44,834), heart (23,987), liver (28,722), and kidney (32,155), along with nearly 500k medical history sequences (age range: 25$\sim$89 years). Our **DiffDT** achieves significant improvements over state-of-the-art human disease autoregressive models and imaging trait generative baselines.

Predicting Future Health Risks by Combining Organ Scans and Social Factors The Problem: Current AI models for predicting disease trajectories mostly rely on basic hospital records. They often ignore crucial organ-specific data (like brain or heart scans) and vital social determinants of health, such as a patient's living environment and economic background. The Solution: We developed DiffDT, a new generative AI framework that combines multi-organ scans (brain, heart, liver, and kidney) with social health factors and medical histories from half a million participants. It uses advanced digital modeling to simulate how complex body networks, like brain connectivity, change over time. The Impact: By successfully mapping these diverse data points together, DiffDT allows doctors to run virtual interventions and accurately forecast a patient's future health. This paves the way for highly personalized medicine and better clinical decision support before diseases progress.