91社区

Arthur Chatton, PhD

IVADO postdoctoral fellow |
Facult茅 de Pharmacie, Universit茅 de Montr茅al

WHEN: Monday, January 22, 2024, from 4 to 5 p.m.

WHERE: Hybrid| 2001 91社区 College, Rm 1140 |

NOTE: Arthur Chatton will be presenting in-person

Abstract

Obtaining continuously updated predictions is a major challenge for personalized medicine. In end-stage kidney diseases, a major cause of morbidity and mortality worldwide, dialysis is the standard therapy. However, achieving high blood-filtered volumes time after time and across patient populations requires clinical skills and readily accessible information and data. Nephrologists and nurses must continually re-assess multiple parameters refreshed with each HDF session and consider time-varying clinical status changes, which is daunting in busy dialysis centres.

Dynamic prediction models provide predicted outcome values that can be updated over time for an individual as new measurements become available. Previous approaches to prediction were mainly based on parametric models, but there is a current trend towards using more flexible machine learning approaches. Ensemble methods leverage combinations of parametric regressions and machine learning approaches into one final prediction.

We extend an ensemble method called super learner for (i) dynamically predicting a repeated continuous outcome and (ii) optimizing the prediction for the patients the clinician faces up by combining approaches trained on the personal history of the patient or on an external (i.e., "historical") cohort. We also propose a new way to validate such personalized prediction models. We illustrate its performance by predicting the convection volume of patients undergoing hemodiafiltration, a specific dialysis technique, in Montr茅al, Canada.

The personalized dynamic super learner 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 its use and implementation.

Learning Objectives

By the end of this session, attendees will:

• Have a better understanding of the super learning framework;
• Become acquainted with dynamic prediction;
• Understand the challenges of validating personalized prediction models.

Speaker Bio

Arthur Chatton is a French biostatistician working on the crossroads of causal inference and prediction. His current interests focus mainly on using machine learning approaches for causal inference, either for estimation purposes or identifiability checking. His work is supported by an IVADO postdoctoral fellowship. He has an MSc and a PhD in Biostatistics from the Universit茅 de Nantes, France.