Consensus statement on the credibility assessment of ML predictors

TL;DR

This paper provides a consensus framework for assessing the credibility of machine learning predictors in biomedical applications, emphasizing causal understanding, error quantification, and bias robustness to ensure reliable healthcare decisions.

Contribution

It introduces twelve key statements for evaluating ML predictor credibility, addressing challenges like causal knowledge and bias, and offers guidelines for researchers, developers, and regulators.

Findings

12 key statements for credibility assessment

Comparison of ML predictors with biophysical models

Strategies for ensuring reliability and applicability

Abstract

The rapid integration of machine learning (ML) predictors into in silico medicine has revolutionized the estimation of quantities of interest (QIs) that are otherwise challenging to measure directly. However, the credibility of these predictors is critical, especially when they inform high-stakes healthcare decisions. This position paper presents a consensus statement developed by experts within the In Silico World Community of Practice. We outline twelve key statements forming the theoretical foundation for evaluating the credibility of ML predictors, emphasizing the necessity of causal knowledge, rigorous error quantification, and robustness to biases. By comparing ML predictors with biophysical models, we highlight unique challenges associated with implicit causal knowledge and propose strategies to ensure reliability and applicability. Our recommendations aim to guide researchers, developers, and regulators in the rigorous assessment and deployment of ML predictors in clinical and biomedical contexts.