Imaging orders sent via electronic health records (EHRs) have less complete—and consequently less reliable—patient information than those found in physician notes on the same patient in the same EHR, according to research published online Dec. 5 in the Journal of the American Medical Informatics Association.

Massachusetts General Hospital (MGH) in Boston is diving straight into the hype of blockchain by collaborating with Korean blockchain startup MediBloc to improve the health system’s patient data sharing and storage capabilities, according to a report published Dec. 5 by CoinDesk.

Radiology has the highest use of telemedicine for patient interactions than any other medical specialty, according to results from a nationally representative survey published in the December issue of Health Affairs by the American Medical Association (AMA).

By using radiomics, Chinese researchers found that the diagnostic performance of mammography could improve and offer complementary information to radiologists regarding benign and malignant breast tumors, as reported in the Journal of the American College of Radiology on Dec. 5.

Artificial intelligence (AI) and big data can help radiologists provide better care while reducing costs, but a majority of institutions lack the infrastructure to optimally consume and utilize these technologies, said Paul Chang, MD, of the University of Chicago, during RSNA's 2018 Annual Meeting.

Tech company Amazon has launched a new medical language processing service that, by using artificial intelligence (AI), can extract data from patient records and reports to help healthcare professionals make better treatment decisions, address data privacy and decrease overall costs, according to a report published Nov. 28 by TechCrunch.

Ambra Health, makers of the leading cloud-based, medical image management suite, today announced a new collaboration with Google Cloud to advance healthcare research with anonymized medical imaging data.

Researchers from Stanford University have determined that convolutional neural networks (CNNs) trained with just 20,000 labeled images can accurately classify chest x-rays as either normal or abnormal, according to a new study published Nov. 13 in Radiology.