analiza aiqbench
The paper proposes CHDT, a generative model that simulates full patient-state trajectories under different interventions, with an explicit component for irregular visit intervals. Its reported gains come mainly from that time-conditioning, which is a modeling choice that could transfer to other sparse longitudinal datasets. The evaluation covers one real cohort (ADNI) and one simulator-generated cohort (ALPACA), so claims about clinical-trial utility remain preliminary.
Intervention-Conditioned Counterfactual Human Digital Twin Generator
arXiv:2610.40664v1 Announce Type: cross Abstract: Chronic diseases evolve through long, heterogeneous trajectories shaped by interacting mediators, confounders, and treatment histories. Estimating long-term patient trajectories under alternative interventions is essential for in silico clinical trial design. However, most existing models overlook irregular visit intervals and cross-mediator dependencies, both of which are crucial for reliable long-term longitudinal prediction. Moreover, these models typically focus on outcome prediction rather than generating complete patient-state trajectories. To address these challenges, we propose CHDT, an intervention-conditioned Human Digital Twin generator under standard identification assumptions for multimodal longitudinal trajectory estimation. Its main empirical advantage arises from explicit modeling of irregular visit intervals, while cross-mediator refinement provides additional gains in selected intervention-conditioned settings. Across real-world ADNI and simulator-generated ALPACA cohorts, CHDT shows improved long-horizon patient-state fidelity relative to competing baselines. Ablation results indicate that irregular-time conditioning provides the primary empirical gain, and cross-mediator refinement provides additional improvements.
Abstract:Chronic diseases evolve through long, heterogeneous trajectories shaped by interacting mediators, confounders, and treatment histories. Estimating long-term patient trajectories under alternative interventions is essential for in silico clinical trial design. However, most existing models overlook irregular visit intervals and cross-mediator dependencies, both of which are crucial for reliable long-term longitudinal prediction. Moreover, these models typically focus on outcome prediction rather than generating complete patient-state trajectories. To address these challenges, we propose CHDT, an intervention-conditioned Human Digital Twin generator under standard identification assumptions for multimodal longitudinal trajectory estimation. Its main empirical advantage arises from explicit modeling of irregular visit intervals, while cross-mediator refinement provides additional gains in selected intervention-conditioned settings. Across real-world ADNI and simulator-generated ALPACA cohorts, CHDT shows improved long-horizon patient-state fidelity relative to competing baselines. Ablation results indicate that irregular-time conditioning provides the primary empirical gain, and cross-mediator refinement provides additional improvements.
Quantitative Methods (q-bio.QM); Machine Learning (cs.LG)
arXiv:2610.40664 [q-bio.QM]
(or arXiv:2610.40664v1 [q-bio.QM] for this version)
https://doi.org/10.48550/arXiv.2610.40664 Focus to learn more arXiv-issued DOI via DataCite
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.
Text integral sub licența deschisă a publicației · 238 cuvinte