AI Insight
This randomized mixed-methods study with 34 oncologists evaluated four AI systems for generating literature reviews across clinical vignettes. Despite containing similar references, an evidence-graded report format was rated significantly lower in utility than a standard format, revealing that presentation style substantially affects perceived usefulness beyond accuracy alone. Through quantitative ratings and qualitative interviews, researchers identified that oncologists prefer concise, scannable reports with clear citations, bolded guidelines, quantitative data, and explicit statements of uncertainty, while trust erodes with citation mismatches and overconfident recommendations.
Why it matters
As AI tools become more prevalent in clinical decision-making, this research demonstrates that accuracy alone is insufficient for effective AI medical assistants. The findings provide concrete design requirements for developers creating AI tools for healthcare professionals, potentially improving clinical workflow integration and physician trust in AI-generated medical information.
Understand the Science
⚠️ Preprint – Noch nicht peer-reviewed
Dieser Artikel wurde noch nicht von unabhängigen Experten begutachtet. Die Ergebnisse sind vorläufig und sollten mit Vorsicht interpretiert werden.
Doctors increasingly rely on AI in the clinic, yet which report features make AI-generated responses useful and trustworthy remains unclear. In this randomized mixed-methods study, 34 oncology physicians provided 294 ratings of four blinded AI systems across five vignettes, alongside 20 semi-structured interviews analyzed with a prespecified LLM-assisted qualitative pipeline. Despite similar references, an evidence-graded report adapted from OpenEvidence was rated significantly lower in overall utility than standard OpenEvidence (mean difference, -0.96; 95% CI, -1.26 to -0.66; P<.001). Qualitative analysis identified six themes and seven design requirements. Oncologists valued rapid orientation, evidence retrieval, and verification, preferring concise, scannable reports with quantitative outcomes, recognizable bolded guidelines, explicit uncertainty, and verifiable citations. Trust deteriorated with citation mismatch, buried provenance, evidence misclassification, overconfident recommendations, and poor organization. Evidence presented differently can alter perceptions of clinical utility and trust; accuracy alone is insufficient, and report design must also be empirically evaluated.