New research on public attitudes toward AI indicates that most people are reluctant to let ChatGPT and other AI tools diagnose their health condition, but see promise in technologies that use AI to help diagnose cancer. These and other results of two nationally representative surveys will be presented at the annual meeting of the Society for Risk Analysis Dec. 7-10 in Washington, DC.

A new machine-learning method from CMU's He lab analyzes all major epileptic brain signals in one framework. The technique presents both a technical breakthrough and promising new direction for noninvasive presurgical planning.

On Saturday December 6, 2025 Alaska was rocked by a 7.0 magnitude quake. On average, about 55 earthquakes strike daily, according to the United States Geological Survey (USGS), totaling some 20,000 annually worldwide with 15 hitting within the magnitude 7.0 range and one reaching 8.0 or over. Earthquakes result in fatalities, damaged infrastructure, economic disruptions and can create lasting psychological trauma for individuals affected by them. They are also becoming more costly, in part because more people now live in the earthquake-prone areas, with damage reaching $14.7 billion per year in the US alone. There's no way to predict when earthquakes may hit yet, but a new paper may bring us a step closer to doing so. 

As nuclear medicine theranostics expands rapidly across clinical practice worldwide, a new supplement to the Journal of Nuclear Medicine Technology (JNMT) explores how nuclear medicine technologists are embracing their growing role within the field. Titled, Building the Future of Theranostics: Advancing Practice, Education, and Innovation Worldwide, the supplement brings together voices from across the globe, offering perspectives that span clinical lessons, educational frameworks, operational strategies, advocacy, equity, and biology.

 While targeted radiation can be an effective treatment for brain tumours, subsequent potential necrosis of the treated areas can be hard to distinguish from the tumours on a standard MRI. A new study led by a York University professor in the Lassonde School of Engineering found that a novel AI-based method is better able to distinguish between the two types of lesions on advanced MRI than the human eye alone, a discovery that could help clinicians more accurately identify and treat the issues.