Integrating Causal Machine Learning into Clinical Decision Support Systems: Insights from Literature and Practice

TL;DR

This paper explores how to design clinical decision support systems that incorporate causal machine learning to improve interpretability, usability, and trust in medical decision-making.

Contribution

It provides empirically grounded design requirements, principles, and features for integrating causal ML into CDSSs, addressing a gap in clinician-facing interface design.

Findings

Derived eight design requirements from literature and interviews.

Developed seven design principles for causal ML-based CDSSs.

Proposed nine practical design features to enhance clinical decision support.

Abstract

Current clinical decision support systems (CDSSs) typically base their predictions on correlation, not causation. In recent years, causal machine learning (ML) has emerged as a promising way to improve decision-making with CDSSs by offering interpretable, treatment-specific reasoning. However, existing research often emphasizes model development rather than designing clinician-facing interfaces. To address this gap, we investigated how CDSSs based on causal ML should be designed to effectively support collaborative clinical decision-making. Using a design science research methodology, we conducted a structured literature review and interviewed experienced physicians. From these, we derived eight empirically grounded design requirements, developed seven design principles, and proposed nine practical design features. Our results establish guidance for designing CDSSs that deliver causal insights, integrate seamlessly into clinical workflows, and support trust, usability, and human-AI collaboration. We also reveal tensions around automation, responsibility, and regulation, highlighting the need for an adaptive certification process for ML-based medical products.