Radiologist Interaction with Artificial Intelligence-Generated Preliminary Reports: A Longitudinal Multi-Reader Study

Synopsis

Multi-case, multi-reader longitudinal study with five radiologists interpreting 756 chest radiographs over seven sequential batches; reading times fell from 25.8s to 19.3s and acceptability rose from 54.6% to 60.2% as readers adapted.

Keywords

·radiology ·AI report generation ·longitudinal reader study ·chest radiograph ·acceptability

Related entries

• AI Assistance Reduces Persistence and Hurts Independent Performance
  April 6, 2026 · arXiv
• How AI Impacts Skill Formation
  January 28, 2026 · arXiv
• Sometimes right, sometimes wrong: Drivers' responses to inconsistently accurate automated vehicle system confidence information
  January 20, 2026 · Accident Analysis & Prevention 2026
• Evolving with AI: A Longitudinal Analysis of Developer Logs
  January 15, 2026 · arXiv
• Personalization capabilities of current technology chatbots in a learning environment: An analysis of student-tutor bot interactions
  2025 · Education and Information Technologies 2025
• Generative AI for Analysts
  December 12, 2025 · arXiv