VIDEO: Mark Flyer, MD, CIIP, of Maimonides Medical Center, shares the experiences and lessons learned when his facility implemented a critical test results management system.
The timely and reliable delivery of critical test results has become a major priority for radiologists. Without effective systems in place, delayed communication could threaten patient safety and physician efficiency.
Recognizing this, Maimonides Medical Center implemented a critical test result management (CTRM) system four years ago. The system, a Nuance product, has dramatically improved the radiology department’s workflow, said Mark Flyer, MD, CIIP.
“The concern was… getting these results to the right person and making sure patients don’t fall through the cracks,” Flyer said in an interview at this year’s SIIM conference where he presented about their use of this system. “We saw an opportunity to improve on patient care and communication, making sure that critical results are communicated efficiently, quickly and to the right person.”
The facility learned quite a few lessons along the way - one major one being that physicians across the board preferred physician-to-physician communication of results. In a survey conducted by the hospital, physicians noted their concern with the automated system was that lack of direct interaction.
“We in radiology have tried to back track a little and always put out the call first to the doctor,” Flyer said.
But when that direct contact isn’t possible, this system allowed them to effectively relay that information, he noted. The system has improved productivity by making it easier to convey the results. Hospital officials also made tweaks to the system to make it more flexible and tailored to specific physicians’ schedules and preferred contact methods.
Above all, the system has brought physicians a heightened understanding of the need for communication, Flyer said.
“Our job is not done once we issue a report and make a finding,” he said. “Our job is half done. The other half entails making sure that information gets into the hands of the person that has to act on it, so the patient will be the ultimate beneficiary of this.”
Deep Learning Detection of Mammography Abnormalities: What a New Study Reveals
June 19th 2023In multiple mammography datasets with the original radiologist-detected abnormality removed, deep learning detection of breast cancer had an average area under the curve (AUC) of 87 percent and an accuracy rate of 83 percent, according to research presented at the recent Society for Imaging Informatics in Medicine (SIIM) conference.
Detecting Intracranial Hemorrhages: Can an Emerging AI Advance Have an Impact?
June 9th 2022A 3D whole brain convolutional neural network could provide enhanced sensitivity and specificity for diagnosing intracranial hemorrhages on computed tomography, according to new research presented at the Society for Imaging Informatics in Medicine (SIIM) conference in Kissimmee, Fla.