Diagnostics

Virtual reality isn’t quite there yet as a go-to screening tool for cognitive decline, but it can augment conventional methods. And senior citizens are open to its use for that purpose when it’s administered by their primary care doctor.

If geriatricians and primary care doctors could know which of their aging patients are at risk for Alzheimer’s disease, they could help these patients and their families prepare for what’s to come.

Allowing natural language processing to pore over disparate data stored in electronic health records, researchers in Canada have shown the AI-based technology can reveal real-world experiences and outcomes of patients with stage III breast cancer.

A Harvard-affiliated academic data science center is partnering with a major manufacturer of portable ultrasound systems to boost the diagnostic powers of point-of-care ultrasound, aka “POCUS,” using AI.

The venture arm of 32-hospital UnityPoint Health is partnering with VIDA Diagnostics, investing $1 million to fine-tune and broaden the use of VIDA’s AI software for flagging signs of trouble in lung images.

The power of AI in medicine has come to light in Alabama, where an 11-year-old in medical peril had the good fortune to have a dad who’s an AI-specialized computer programmer working in healthcare.

Medical-device giant Medtronic is partnering with Viz.ai to offer stroke centers capabilities for automatically flagging large vessel occlusions while the patient is still on the bed of a CT scanner.

A convolutional neural network (CNN) has beaten a team of 11 pathologists at diagnosing melanoma.

Machine learning can tease out which location-specific—or “area-level”—social determinants of health warrant close monitoring in people who have diabetes and are at risk of losing control over it.  

It’s not unusual for hospitalized patients to take a sudden turn for the worse. A continuous inspection of electronic medical records by machine-learning algorithms can warn of impending trouble in real time, giving physicians a chance to proactively intervene.

Using a dataset of records from nearly 3 million pediatric patients, South Korean researchers have developed and validated a deep-learning algorithm that can tell emergency doctors which children will need to be admitted to critical-care units.

Hospital inpatients who are likely to turn violent can be identified by algorithmic analysis of routine clinical notes stored in electronic health records, according to a study published in JAMA Network Open July 3.