The authors of the survey report note that AI tools mentioned by respondents run the gamut from automated appointment reminders to dynamic “care gap” messaging. 

Providers are up to three times more likely to trust the opinion of humans over AI, even when the algorithm is proven to detect more cancerous lesions than radiologists. 

Some AI decision-support models have a proclivity for recommending aggressive care pathways. And doing so on the basis of patient demographics, not medical necessity.

As applications of AI spread rapidly across healthcare, ambient scribes are poised to become one of the fastest technology adoptions in the history of the sector. 

Even with thorough treatment and surgery, women with a personal history of breast cancer are at increased risk of developing second cancers in the future. 

The tool extracts brain region and white matter lesion volumes from any MRI of the brain, even less specialized sequences not traditionally used in the diagnosis or management of MS. 

Researchers have taken inspiration from starfish to design an AI-powered wearable device that delivers accurate real-time heart monitoring.

Is trial and error any way for a sprawling health system to roll out AI? Duke Health’s chief medical information officer believes so.