Personalized Screening Intervals for Biomarkers using Joint Models for Longitudinal and Survival Data

TL;DR

This paper develops a method to personalize screening intervals for biomarkers by selecting appropriate models and optimal future measurement times based on information theory, improving early disease detection.

Contribution

It introduces a novel approach to optimize and personalize biomarker screening schedules using joint models and information theory measures.

Findings

Effective model selection at time t for individual patients.

Method to determine optimal future measurement time u.

Enhanced prediction accuracy for clinical endpoints.

Abstract

Screening and surveillance are routinely used in medicine for early detection of disease and close monitoring of progression. Biomarkers are one of the primarily tools used for these tasks, but their successful translation to clinical practice is closely linked to their ability to accurately predict clinical endpoints during follow-up. Motivated by a study of patients who received a human tissue valve in the aortic position, in this work we are interested in optimizing and personalizing screening intervals for longitudinal biomarker measurements. Our aim in this paper is twofold: First, to appropriately select the model to use at time t, the time point the patient was still event-free, and second, based on this model to select the optimal time point u > t to plan the next measurement. To achieve these two goals we develop measures based on information theory quantities that assess the information we gain for the conditional survival process given the history of the subject that includes both baseline information and his/her accumulated longitudinal measurements.