Causal machine learning for predicting treatment outcomes

TL;DR

This paper discusses how causal machine learning can improve personalized treatment outcome predictions by estimating individual effects, integrating diverse data sources, and guiding clinical decisions with caution to avoid bias.

Contribution

It provides a comprehensive overview of causal ML methods for treatment outcome prediction, highlighting benefits, key components, and guidelines for clinical application.

Findings

Causal ML enables personalized treatment effect estimation.

Integration of clinical and real-world data enhances predictions.

Recommendations improve reliability and clinical translation.

Abstract

Causal machine learning (ML) offers flexible, data-driven methods for predicting treatment outcomes including efficacy and toxicity, thereby supporting the assessment and safety of drugs. A key benefit of causal ML is that it allows for estimating individualized treatment effects, so that clinical decision-making can be personalized to individual patient profiles. Causal ML can be used in combination with both clinical trial data and real-world data, such as clinical registries and electronic health records, but caution is needed to avoid biased or incorrect predictions. In this Perspective, we discuss the benefits of causal ML (relative to traditional statistical or ML approaches) and outline the key components and steps. Finally, we provide recommendations for the reliable use of causal ML and effective translation into the clinic.