Radiologist availability of clinical records and turnaround time, from SIIM 2016.
Having instant access to clinical notes and data may increase turn around time for radiologists, according to a study presented at the annual meeting of the Society for Imaging Informatics in Medicine in Portland, OR.
Researchers from Johns Hopkins School of Medicine in Baltimore, MD, sought to determine if ensuring that radiologists had instant access to patient information related to the ordered radiology examinations would have an impact on turn-around time (TAT). Access to the information was provided by RAD Assistant, a Java-based application that links to the facility’s electronic health records. The TAT was defined as the period of time between when the study was available for reading to the finalization of the report.
The study compared the TAT during a 96-hour period when the RAD Assistant server was unavailable to a similar period when the server was available the week before. The researchers pointed out that there were many variables that could affect TAT, aside from the availability of the server, such as the number of available radiologists, the number of studies to be read, computer problems, and other issues.
The findings showed that the average TAT for the 9,282 studies that took place for 96 hours when the RAD Assistant was available was 18.3% faster than for the 8,681 studies that took place during the equivalent length down time. When the researchers evaluated TAT for attendings who did not have have preliminary reports from residents or fellows, TAT with the RAD assistant was still quicker, with a 21.1% faster turnaround.
A survey sent out to the radiologists also showed that 90% of the users believed that the system allowed for faster TAT, with 96% saying that they were frustrated when the system was down.
The researchers suggested that further study be done from a larger dataset to confirm their findings.
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.