
Smartphones and LLMs Detect Huntington’s Disease
By feeding raw smartphone eye-tracking data into off-the-shelf language models, researchers bypassed the need for custom medical AI to spot Huntington’s disease.
Discover the newest research about AI innovations in Research.

By feeding raw smartphone eye-tracking data into off-the-shelf language models, researchers bypassed the need for custom medical AI to spot Huntington’s disease.

Regulators are clearing the path for AI that writes its own clinical notes, shifting the technology from a simple second pair of eyes to an active administrative partner.

Medical AI models are passing clinical tests by reading machine settings instead of actual patient disease.

High-tech cancer diagnostics are currently a luxury of the wealthiest health systems, but a shift in how we analyze basic tissue slides could soon level the playing field.

A new language model attempts to solve a major diagnostic bias by separating normal hormonal transitions from actual viral damage in women.

A new wave of AI models is finding invisible patterns in routine heart tests to predict sudden cardiac arrest before it strikes.

A new machine learning model proves that tracking silent organ damage is far more predictive of survival than standard blood pressure readings.

A life-sciences giant just bought its way from the laboratory bench directly to the hospital bedside.

A new algorithm can spot hyperacute stroke tissue changes on cheap, standard CT scans, but it struggles to map the exact boundaries of smaller lesions.

A new partnership between a smart ring maker and a pharmaceutical giant reveals how drugmakers are using consumer hardware to keep patients compliant.