Bayesian data assimilation to support informed decision-making in individualised chemotherapy

TL;DR

This paper demonstrates how Bayesian data assimilation improves decision-making in personalized chemotherapy by providing comprehensive uncertainty quantification over traditional MAP-based methods, especially with frequent data collection.

Contribution

It introduces Bayesian data assimilation methods for chemotherapy monitoring, showing their advantages over MAP-based approaches in uncertainty quantification and decision support.

Findings

Sequential Bayesian DA is computationally efficient.

DA methods better quantify risks of treatment failure or toxicity.

Frequent data collection enhances patient care decisions.

Abstract

An essential component of therapeutic drug/biomarker monitoring (TDM) is to combine patient data with prior knowledge for model-based predictions of therapy outcomes. Current Bayesian forecasting tools typically rely only on the most probable model parameters (maximum a-posteriori (MAP) estimate). This MAP-based approach, however, does neither necessarily predict the most probable outcome nor does it quantify the risks of treatment inefficacy or toxicity. Bayesian data assimilation (DA) methods overcome these limitations by providing a comprehensive uncertainty quantification. We compare DA methods with MAP-based approaches and show how probabilistic statements about key markers related to chemotherapy-induced neutropenia can be leveraged for more informative decision support in individualised chemotherapy. Sequential Bayesian DA proved to be most computational efficient for handling interoccasion variability and integrating TDM data. For new digital monitoring devices enabling more frequent data collection, these features will be of critical importance to improve patient care decisions in various therapeutic areas.