Personalized dynamic super learning: an application in predicting hemodiafiltration convection volumes

扫码查看

原文链接

NETL
NSTL
Oxford Univ Press

外文摘要：Obtaining continuously updated predictions is a major challenge for personalized medicine. Leveraging combinations of parametric regressions and machine learning algorithms, the personalized online super learner (POSL) can achieve such dynamic and personalized predictions. We adapt POSL to predict a repeated continuous outcome dynamically and propose a new way to validate such personalized or dynamic prediction models. We illustrate its performance by predicting the convection volume of patients undergoing hemodiafiltration. POSL outperformed its candidate learners with respect to median absolute error, calibration-in-the-large, discrimination, and net benefit. We finally discuss the choices and challenges underlying the use of POSL.

外文关键词：

cross-validationdynamic predictionmachine learningpanel datapersonalized medicinestacking

作者：

Arthur Chatton、Michele Bally、Renee Levesque、Ivana Malenica、Robert W. Platt、Mireille E. Schnitzer

展开 >

作者单位：

Faculte de Pharmacie, Universite de Montreal, Montreal, QC, Canada

Faculte de Pharmacie, Universite de Montreal, Montreal, QC, Canada##Departement de Pharmacie et Centre de Recherche, Centre Hospitalier de I'Universite de Montreal, Montreal, QC, Canada

Service de Nephrologie, Departement de Medecine, Universite de Montreal, Montreal, QC, Canada

Department of Statistics, Harvard University, Cambridge, MA, USA

Departments of Pediatrics and Epidemiology, Biostatistics and Occupational Health, McGill University, Montreal, QC, Canada##Centerfor Clinical Epidemiology, Lady Davis Institute, Jewish General Hospital, Montreal, QC, Canada

Department of Epidemiology, Biostatistics, Occupational Health, McGill University, Montreal, QC, Canada##Faculte de Pharamacie and Departement de Medecine Sociale et Preventive, Ecole de Sante Publique, Universite de Montreal, Montreal, QC, Canada

展开 >

出版年：

2025

DOI：

10.1093/jrsssc/qlae070

Journal of the royal statistical society, Series C. Applied statistics

ISSN：0035-9254

年,卷(期)：2025.74(Pt.3)

参考文献量85