Causal machine learning for predicting treatment outcomes

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.

Accepted version; not Version of Record

References in corpus (15)

• Recursive Partitioning for Heterogeneous Causal Effects
• Meta-learners for Estimating Heterogeneous Treatment Effects using Machine Learning
• Nonparametric methods for doubly robust estimation of continuous treatment effects
• Prediction meets causal inference: the role of treatment in clinical prediction models
• Causal Machine Learning: A Survey and Open Problems
• Learning Counterfactual Representations for Estimating Individual Dose-Response Curves
• Sharp Sensitivity Analysis for Inverse Propensity Weighting via Quantile Balancing
• Machine Learning Estimation of Heterogeneous Treatment Effects with Instruments
• DoWhy: Addressing Challenges in Expressing and Validating Causal Assumptions
• A Causal Roadmap for Generating High-Quality Real-World Evidence
• Estimating and evaluating counterfactual prediction models
• G-Net: A Deep Learning Approach to G-computation for Counterfactual Outcome Prediction Under Dynamic Treatment Regimes
• Combining Observational and Randomized Data for Estimating Heterogeneous Treatment Effects
• On Weighted Orthogonal Learners for Heterogeneous Treatment Effects
• B-Learner: Quasi-Oracle Bounds on Heterogeneous Causal Effects Under Hidden Confounding

Cited by in corpus (3)

• What if? Causal Machine Learning in Supply Chain Risk Management
• Impact of Near-Positivity Violations on IPTW-Estimated Marginal Structural Survival Models With Time-Dependent Confounding
• Individualized prescriptive inference in ischaemic stroke