Submitted by sjc313 on Fri, 06/06/2025 - 08:41
Stephen Morris, Efthalia Massou and Kevin Herbert, Primary Care Unit, Department of Public Health and Primary Care
Stephen Morris, Efthalia Massou and Kevin Herbert have co-authored a recent article published in eClinicalMedicine titled "Artificial intelligence for diagnostics in radiology practice: a rapid systematic scoping review."
The study evaluated current evidence on the use of artificial intelligence (AI) to support diagnostic processes in radiology. The team conducted a review of literature published between January 2020 and January 2025, screening over 8,000 articles and including 140 studies. These studies explored AI implementation, perceptions, effectiveness, cost implications, and real-world experiences.
The review found that AI shows promise in improving diagnostic accuracy and reducing interpretation time. However, challenges such as limited guidance, lack of transparency, high technical demands, and insufficient training persist. Evidence was mixed on user experiences, cost-effectiveness, and workflow impacts, with concerns about increased false positives and integration into routine practice.
The authors emphasize that AI should be viewed as a complementary tool rather than a standalone solution and highlight key evidence gaps needing further research. The project was funded by the National Institute for Health and Care Research (NIHR) Health and Social Care Delivery Research programme and involved stakeholder workshops with radiology staff and public representatives.
Read the full article here.