Breast cancer prediction models based on family history are more effective than those that do not focus on that information, according to a new study published in The Lancet Oncology.

Researchers have created a machine learning model that identified 98 percent of malignant atypical ductal hyperplasia (ADH) lesions prior to surgery, according to a single-center study published in JCO Clinical Cancer Informatics. The approach saved 16 percent of women from unnecessary surgery.

Though the use of AI is still in early stages, its wide-reaching potential is expected to be felt by all industries in the near future. The technology is expected to contribute up to $15.7 trillion to the global economy by 2030, according to a PwC global AI study.

When diagnosing acute venous thromboembolism (VTE)—a disease that includes deep-vein thrombosis of the leg or pelvis and its complication, pulmonary embolism—PET/CT imaging with a 18F-GP1 radiotracer performed with a higher detection rate than conventional imaging, according to research published in The Journal of Nuclear Medicine.  

Several healthcare companies have made it onto the Ethisphere Institute’s World’s Most Ethical Companies list for 2019.

Women see worse outcomes than men after thoracic aortic surgery requiring hypothermic circulatory arrest (HCA), researchers reported in the Feb. 26 edition of Circulation.

The Department of Justice has asked a judge to approve the $69 billion merger between CVS Health and Aetna, which was closed by the two companies at the end of 2018, Reuters reported. The deal has been hung up on court approval, though it has been approved by all other regulators and the DOJ.

More than half of radiologists who experience burnout cope with those feelings through exercise, according to a new report from Medscape. Radiologists also handle such feelings by speaking with friends and family, sleeping, playing/listening to music and isolating themselves from others.

When endovascular thrombectomy procedures for acute ischemic stroke take more than an hour or require more than three attempts to remove the clot, outcomes significantly worsen, according to a study published Feb. 25 in the Journal of the American College of Cardiology.

Researchers at the University of Alberta have developed a new AI-based software––Ensemble Algorithm with Multiple Parcellations for Schizophrenia Prediction, or EMPaSchiz––that will allow physicians to identify schizophrenia in fMRI scans with 87 percent accuracy. Their research was published in NJP Schizophrenia.