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

Abstract

Obtaining continuously updated predictions is a major challenge for personalised medicine. Leveraging combinations of parametric regressions and machine learning approaches, the personalised online super learner (POSL) can achieve such dynamic and personalised predictions. We adapt POSL to predict a repeated continuous outcome dynamically and propose a new way to validate such personalised 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.

16 pages, 6 Figures, 2 Tables. Supplementary materials are available at https://arthurchatton.netlify.app/publication/ Accepted in Journal of the Royal Statistical Society, Series C

References in corpus (10)

• Smoothing parameter and model selection for general smooth models
• All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously
• Classifier Technology and the Illusion of Progress
• Least squares after model selection in high-dimensional sparse models
• Tunability: Importance of Hyperparameters of Machine Learning Algorithms
• Data science is science's second chance to get causal inference right: A classification of data science tasks
• A review of predictive uncertainty estimation with machine learning
• Practical considerations for specifying a super learner
• Individual dynamic prediction of clinical endpoint from large dimensional longitudinal biomarker history: a landmark approach
• A Personalized Predictive Model that Jointly Optimizes Discrimination and Calibration