Problem
Research questions and friction points this paper is trying to address.
Lifelong Digital Twin
Whole-person Modeling
Health State Trajectories
Disease Prediction
LifeLong Digital Twin: A Unified Modeling Paradigm and Agent Harness for Event-Driven Lifelong Health State Trajectories
🤖 AI Summary
This study addresses the challenges of integrating lifespan health data and enabling personalized disease prediction by proposing a lifelong digital twin framework. Methodologically, it establishes a unified event-driven modeling paradigm that transforms discrete life events into daily health states, which are cumulatively aggregated into a lifelong context. The framework integrates large language models, multimodal fusion agents, and longitudinal data analysis techniques to facilitate collaborative reasoning across multi-source evidence. Experimental results demonstrate that the proposed approach improves the F1 score for disease trajectory prediction by 22.0% and enhances five-year prognostic prediction by 18.3%. Notably, it achieves an F1 score of 0.669 in thyroid disease prediction, significantly outperforming existing baselines.
📝 Abstract
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.
Innovation
Methods, ideas, or system contributions that make the work stand out.
LifeLong Digital Twin
Event-Driven Modeling
Agent Harness
Multimodal Evidence
Disease Trajectory Forecasting
🔎 Similar Papers
No similar papers found.
