Atomic Fact-Checking Increases Clinician Trust in Large Language Model Recommendations for Oncology Decision Support: A Randomized Controlled Trial
Organizations: Department of Diagnostic and Interventional Radiology, TUM University Hospital Rechts der Isar, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany · Department of Radiation Oncology, TUM University Hospital Rechts der Isar, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany · Department of Internal Medicine III: Hematology and Clinical Oncology, University Hospital Regensburg, University of Regensburg, Regensburg, Germany · Bavarian Cancer Research Center (BZKF), Regensburg, Germany · Institute for Cardiovascular Radiology and Nuclear Medicine, TUM University Hospital, German Heart Center Munich, TUM School of Medicine and Health, Technical University of Munich, Munich, Germany · Department of Computer Science; TUM School of Computation Information and Technology; Technical University of Munich, Garching, Germany · German Consortium for Translational Cancer Research (DKTK), Partner Site Munich, Munich, Germany
Abstract
Question: Does atomic fact-checking, which decomposes AI treatment recommendations into individually verifiable claims linked to source guideline documents, increase clinician trust compared to traditional explainability approaches? Findings: In this randomized trial of 356 clinicians generating 7,476 trust ratings, atomic fact-checking produced a large effect on trust (Cohen's d = 0.94), increasing the proportion of clinicians expressing trust from 26.9% to 66.5%. Traditional transparency mechanisms showed a dose-response gradient of improvement over baseline (d = 0.25 to 0.50). Meaning: Decomposing AI recommendations into individually verifiable claims linked to source guidelines produces substantially higher clinician trust than traditional explainability approaches in high-stakes clinical decisions.