الملخص
Electronic health records provide irregular observations of latent patient states that evolve continuously over time. Recent autoregressive models condition on clinical histories to forecast future events as sequences of discrete observations. Conversely, multi-marginal flow matching provides a continuous-time formulation, but using multiple observations to supervise training paths does not itself give the learned dynamics access to preceding patient history. We introduce EHRFlow, a multi-marginal flow-matching framework that conditions on encoded patient history, thereby allowing future dynamics to depend on the patient's prior clinical trajectory. Our proposed framework accommodates irregular observation times and supports forecasting at arbitrary horizons. Across controlled synthetic benchmarks, EHRFlow improves clinical-code forecasting and latent-state recovery. On real-world clinical datasets comprising more than one million patients, including an independent external validation cohort, EHRFlow improves horizon-averaged top-5 clinical-code accuracy over autoregressive and history-independent flow-matching baselines. Finally, in a controlled counterfactual simulation, conditional guidance approximates the known effect of an antihypertensive intervention without training a task-specific outcome model.
الكلمات المفتاحية
الموضوع
بيانات النشر
- المجلة
- غير متاح
- وصول مفتوح
- وصول مفتوح أخضر
اقتبس هذه المقالة
APA 7
Estévez, S. R., Liu, K., Chiu, C., Owusu, B. A., Kadam, U., Altman, R. B., & Schaar, M. V. D. (2026). Learning Continuous Patient Trajectories from Electronic Health Records. https://omanscience.com/ar/articles/learning-continuous-patient-trajectories-from-electronic-health-records
MLA 9
Estévez, Silas Ruhrberg, et al. "Learning Continuous Patient Trajectories from Electronic Health Records." https://omanscience.com/ar/articles/learning-continuous-patient-trajectories-from-electronic-health-records.
شيكاغو (المؤلف–التاريخ)
Estévez, Silas Ruhrberg, Kara Liu, Christopher Chiu, Benjamin Atta Owusu, Umesh Kadam, Russ B. Altman, and Mihaela van der Schaar. 2026. "Learning Continuous Patient Trajectories from Electronic Health Records." https://omanscience.com/ar/articles/learning-continuous-patient-trajectories-from-electronic-health-records.
هارفارد
Estévez, S. R., Liu, K., Chiu, C., Owusu, B. A., Kadam, U., Altman, R. B. and Schaar, M. V. D. (2026) 'Learning Continuous Patient Trajectories from Electronic Health Records', Available at: https://omanscience.com/ar/articles/learning-continuous-patient-trajectories-from-electronic-health-records.
فانكوفر
Estévez SR, Liu K, Chiu C, Owusu BA, Kadam U, Altman RB, et al. Learning Continuous Patient Trajectories from Electronic Health Records. https://omanscience.com/ar/articles/learning-continuous-patient-trajectories-from-electronic-health-records
IEEE
S. R. Estévez, K. Liu, C. Chiu, B. A. Owusu, U. Kadam, R. B. Altman, and M. V. D. Schaar, "Learning Continuous Patient Trajectories from Electronic Health Records," https://omanscience.com/ar/articles/learning-continuous-patient-trajectories-from-electronic-health-records.