Sentence-level provenance improves usability of AI medical record summaries

In a formative usability study of 46 clinicians, a sentence-level 'click to inspect' interface for AI-generated medical record summaries achieved a mean System Usability Scale score of 86.25 (95% CI 83.96–88.54) and a net promoter score of 35. Rapid access to supporting evidence…

• The interface enabled verification of individual summary statements with minimal friction, reducing reliance on manual searching through long notes.
• Participants included residents and attendings from multiple specialties, including radiology and interventional radiology.

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.