Physicians from a variety of specialties show a strong preference for structured radiology reports that are enhanced with embedded images, according to a study presented at the SCAR meeting. The results, while not entirely surprising, highlight an
Physicians from a variety of specialties show a strong preference for structured radiology reports that are enhanced with embedded images, according to a study presented at the SCAR meeting.
The results, while not entirely surprising, highlight an important area where radiologists can avoid marginalization by providing added value to their reports, said Dr. Bruce Reiner, director of radiology research at the VA Maryland Health Care System.
With the goal of persuading his facility's CIO to invest in a structured reporting system, Reiner developed a study to quantify the added value of structured reports with embedded images.
Reiner and colleagues gathered seven chest/abdomen CT exams and provided different reports for the exams. The content of the reports remained constant, but the reports offered four presentation styles:
? Prose without images
? Structured report without images
? Prose with embedded images
? Structured report with embedded images
The researchers presented the reports to six surgeons, seven primary care physicians, and four physicians from varying subspecialties. They asked the clinicians to rate each report based on content, clarity, completeness, consistency, and confidence.
The clinicians showed a significant preference for structured text reports. They also showed an increased preference for both prose and structured text reports with embedded images. This preference was consistent across all the physician specialties, Reiner said.
In terms of overall report value, the clinicians gave the highest ratings to structured text reports with embedded images.
The sample size was small, and there was an inherent bias in the sample because all the clinicians had previously dealt only with text-only reports, Reiner said. Still, the positive results for structured, multimedia reports provides an opportunity for radiologists to become technology experts in the organization and distribution of imaging data sets.
The next step is to study whether perceived value on the part of the clinicians will translate into an actual increase in referrals, he said.
MRI-Based AI Radiomics Model Offers 'Robust' Prediction of Perineural Invasion in Prostate Cancer
July 26th 2024A model that combines MRI-based deep learning radiomics and clinical factors demonstrated an 84.8 percent ROC AUC and a 92.6 percent precision-recall AUC for predicting perineural invasion in prostate cancer cases.
Breast MRI Study Examines Common Factors with False Negatives and False Positives
July 24th 2024The absence of ipsilateral breast hypervascularity is three times more likely to be associated with false-negative findings on breast MRI and non-mass enhancement lesions have a 4.5-fold likelihood of being linked to false-positive results, according to new research.
Can Polyenergetic Reconstruction Help Resolve Streak Artifacts in Photon Counting CT?
July 22nd 2024New research looking at photon-counting computed tomography (PCCT) demonstrated significantly reduced variation and tracheal air density attenuation with polyenergetic reconstruction in contrast to monoenergetic reconstruction on chest CT.