Track genomics, neuroscience and molecular biology.
Search papers, labs, and topics across Lattice.
This paper introduces LifeLong Digital Twin, an event-driven modeling paradigm that unifies diverse lifelong health data into a cumulative Health Context, enabling whole-person health state trajectory modeling. An Agent Harness extends this by incorporating multimodal evidence beyond language model text. Evaluation on 25 disease endpoints demonstrates significant improvements in disease trajectory forecasting and risk ranking, with model-averaged F1 scores increasing by up to 22.0%.
A single digital twin framework can now unify lifelong health data, from genetics to environment, to accurately predict disease trajectories and risks across a person's life.
Human health is a continuous, dynamic trajectory shaped by the cumulative interplay of biological processes, clinical events, behaviors and environmental exposures across the life course. Unifying the full breadth of lifelong health information, including longitudinal records, genetic variation, molecular profiles and environmental histories, is essential for whole-person modeling and remains a major challenge. We introduce LifeLong Digital Twin, a unified, event-driven modeling paradigm that organizes Life Events into daily Health States and accumulates them into Lifelong Health Context. An accompanying Agent Harness incorporates multimodal evidence beyond the language model's textual context. We evaluate four language models across 25 disease endpoints on three tasks: Disease Trajectory Forecasting, Disease Risk Ranking and Multi-horizon Disease Prediction. The approach yields marked gains over the reference condition: model-averaged F1 increases by 22.0% for disease identification in trajectory forecasting and 18.3% for five-year disease outcomes; thyroid-disease F1 reaches 0.669. The framework provides a foundation for whole-person digital twins and research on personalized lifelong disease prevention.