Novel workflow automatically integrates AI results into structured radiology reports
A novel reporting workflow can automatically integrate artificial intelligence results into structured radiology reports, also saving physicians’ precious minutes during their day, according to new research.
German experts detailed their experience with the “AI to SR pipeline” in an analysis published Tuesday in Insights into Imaging [1]. University Medical Center Mainz in 2016 started using the commercially available AI tool, which automatically detects and localizes pathologies on chest X-rays.
Two expert radiologists evaluated 60 examinations to see whether the results were correctly and completely transferred to the structured template. In a second test, three residents also created reports from the 60 examinations, including 20 free text versions, 20 conventionally structured and 20 using the pipeline.
“We found that reports can be generated faster using the AI to SR pipeline compared with free-text reporting and conventional SR,” Tobias Jorg, MD, with the institution’s Department of Diagnostic and Interventional Radiology, and colleagues wrote March 19. “In addition, subjective quality assessment revealed higher ratings for reports created with the pipeline compared to free-text reporting.”
In clinical routine at the hospital, X-ray images are sent to the picture archiving and communication system after their acquisition. From there, they are then automatically forwarded to the AI tool for further analysis, and then with each analyzed chest X-ray, the results are output in a DICOM, structured reporting format. This typically takes about five minutes from the time the exam is executed to the final step.
Radiologists created chest X-ray reports with the pipeline much faster (about 66.8 seconds) when compared to free-text reports (85.6 seconds) and conventional SR (85.8). Rads also rated the AI reports significantly higher on a five-point scale compared to the alternatives, Jorg et al. reported.
“With the AI-to-structured reporting pipeline, chest X-ray reports can be created in a standardized, time-efficient, and high-quality manner,” the authors advised. “The pipeline has the potential to improve AI integration into daily clinical routine, which may facilitate utilization of the benefits of AI to the fullest.”
Read more at the link below.
Marty Stempniak has covered healthcare since 2012, with his byline appearing in the American Hospital Association's member magazine, Modern Healthcare and McKnight's. Prior to that, he wrote about village government and local business for his hometown newspaper in Oak Park, Illinois. He won a Peter Lisagor and Gold EXCEL awards in 2017 for his coverage of the opioid epidemic.