Deep learning has bested experienced neurosurgeons at predicting poor outcomes, including mortality, among patients admitted comatose with severe traumatic brain injuries.

Randall Thompson, MD, immediate past president of the American Society of Nuclear Cardiology (ASNC), explains the current ASNC lobbying efforts.

Most radiological hardware and software systems now offer gender options beyond female/male classification, a recent analysis shows. 

A model that can achieve accuracy in line with that of radiologists when labeling open-access datasets could be a key factor to overcoming limitations of artificial intelligence implementation, researchers explained in Nature Communications.

Researchers revealed that less than 1% of more than 46,000 patients took advantage of online self-scheduling tools.

Homogenous datasets can create unintended research bias that hinders the clinical efficacy of AI applications, experts recently explained in PLOS Digital Health.

A Chinese study of 2.8 million participants found that 94% of users flagged for AFib indeed have the heart rhythm disorder.

Such diagnoses were higher among community practices compared to academic institutions, with lack of subspecialty training a likely underlying factor, experts wrote in JACR.