There is an "immaturity" between machines and humans, said Paul J. Chang, MD, of the University of Chicago. Unless radiology departments augment their current IT infrastructure, AI could become another technological-driver of burnout.

Electronic medical records (EMRs) contain mounds of valuable, but unformatted information making it difficult to use as a source for research, wrote first author, Changhwan Lee, with Hanyang University in Seoul, Korea, and colleagues.  AI may be able to solve that problem.

“Integration of a scoring system into structured prostate MRI reports could be of great value to clinical research as well as routine clinical care...," wrote authors of a new study published in the American Journal of Roentgenology, which examined how background signal-intensity changes affect prostate cancer detection.

The Protecting Access to Medicare Act (PAMA) mandating the use of a clinical decision support (CDS) system when ordering advanced imaging tests could affect up to six million emergency department visits annually, according to estimates published in a Jan. 29 Radiology study. The law is set to go into effect in January 2020.

Although online portals allow some patients to easily access their radiology reports, new research published Jan. 8 in the American Journal of Roentgenology found that lumbar spine MRI reports in particular are written at a reading level too advanced for the average patient to comprehend.

After implementing a structured reporting template for brain tumor imaging, radiologists became more confident in their reports and felt they better facilitated decision-making, according to a single-center study published in Academic Radiology. Patients were also more satisfied with their reports.

DICOM metadata offers more accurate study information, according to a Jan. 8 study published in the Journal of Digital Imaging. This may ultimately help increase the efficiency of MRI exams while reducing their associated costs.

Long wait times can negatively impact patient satisfaction, which then harms the patient-centered, value-based care imaging departments seek to provide. But collecting the necessary data for improvements can be difficult, according to the authors of a case study published in the Journal of Digital Imaging.

Follow-up recommendations in radiology reports commonly contain little standardization. Machine learning and deep learning methods are each effective for deciphering reports and may provide the foundation for real-time recommendation extraction, according to a recent study in the Journal of the American College of Radiology.

Using data from the Human Connectome Project, researchers were able to reassess inconsistent findings from neuroimaging studies of Alzheimer’s patients, according to a study published online Dec. 14 in the journal BRAIN.

Radiology has continuously been on the forefront of adopting new technologies. But at one institution, it took a bit of training and exposure to existing interactive multimedia reporting features before radiologists were willing to adopt it into clinical practice.

A deep learning algorithm developed by researchers at the Mayo Clinic in Rochester, Minnesota, segmented abdominal CT images to determine body composition similarly to, and at times, better than trained radiologists.