Research

Paper

AI LLM March 25, 2026

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

Authors

Domenique Zipperling, Lukas Schmidt, Benedikt Hahn, Niklas Kühl, Steven Kimbrough

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.

Metadata

arXiv ID: 2603.24448
Provider: ARXIV
Primary Category: cs.HC
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24448v1</id>\n    <title>Integrating Causal Machine Learning into Clinical Decision Support Systems: Insights from Literature and Practice</title>\n    <updated>2026-03-25T16:00:06Z</updated>\n    <link href='https://arxiv.org/abs/2603.24448v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24448v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>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.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.HC'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-25T16:00:06Z</published>\n    <arxiv:primary_category term='cs.HC'/>\n    <author>\n      <name>Domenique Zipperling</name>\n    </author>\n    <author>\n      <name>Lukas Schmidt</name>\n    </author>\n    <author>\n      <name>Benedikt Hahn</name>\n    </author>\n    <author>\n      <name>Niklas Kühl</name>\n    </author>\n    <author>\n      <name>Steven Kimbrough</name>\n    </author>\n  </entry>"
}