aiqbench analysis
This research proposes a unified, event-driven modeling paradigm using large language models to construct lifelong digital twins for personalized disease prevention. By integrating multimodal evidence beyond standard text contexts, the framework demonstrates significant improvements in forecasting disease trajectories and ranking risks across 25 endpoints. The work advances the application of AI agents in managing complex, longitudinal health data to enable whole-person modeling.
LifeLong Digital Twin: A Unified Modeling Paradigm and Agent Harness for Event-Driven Lifelong Health State Trajectories
arXiv:2610.05566v1 Announce Type: new 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.
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.
15 pages, 5 figures, 2 tables. Technical report
Artificial Intelligence (cs.AI); Quantitative Methods (q-bio.QM)
arXiv:2610.05566 [cs.AI]
(or arXiv:2610.05566v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2610.05566 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 264 words
Related coverage
Guardian Angels: LLM Personalization for Productivity and Security
LessWrong · Jun 17, 2026
Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · Sep 25, 2026
Autonomous heterogeneous catalyst discovery with a self-evolving multi-agent digital twin
arXiv · Jun 8, 2026