Researchers across the pond have developed and externally validated an AI model that can predict flareups of ulcerative colitis. 

The tool’s sensitivity was recorded as 99.1% for abnormal radiographs and 99.8% for critical radiographs—better than two board-certified radiologists who also interpreted the exams. 

“This study suggests that deep learning algorithms can be useful in improving the detection of fractures," experts wrote Monday in Pediatric Radiology. 

By now it’s a difficult-to-dispute likelihood: AI won’t replace doctors making diagnoses, but doctors who use AI will displace doctors who don’t use AI. The hypothesis gets a fresh airing out from the vantage point of the general public. 

When put to the test, the new model was able to predict Alzheimer’s risk with 90.2% accuracy.

Many patients who would clearly benefit by lowered LDL cholesterol levels are choosing to forgo first-time recommendations for statin regimens, according to a population-level study. 

Does the future of digital healthcare lie with biocomputers powered by engineered cultures derived from human brain cells? If so, it’s already underway in Baltimore.

ChatGPT and similar technologies coming down the medical pike have far to go before they’re reliable sources of accurate and appropriate health information. That doesn’t mean they’re non-factors now.