Every story in this issue with a short summary, so you can decide what to read before leaving the site. Summaries are written by AI (Claude) only from each publisher's own description and checked by Jev for anything not in that description. They are not full translations. Follow "Read the original" for the full story.
An artificial intelligence (AI) model analyzed ECG recordings from two different brands of smartwatches for more than 2,200 adults in South Korea. The study found that the AI model was able to identify people with and without reduced heart pumping function.
Read the original →The article explains how radiology artificial intelligence functions under FDA regulations, GMLP principles, clinical workflows, and multisociety governance frameworks.
Read the original →Researchers in Uganda have developed a multitask multimodal artificial intelligence model. It improves tuberculosis diagnosis, lesion detection, and report generation from chest radiographs.
Read the original →AI assistance significantly improved physicians’ accuracy in diagnosing middle ear diseases from endoscopic images, according to a study at Asan Medical Center (AMC). Junior trainee doctors showed the largest gain, at 32.2 percentage points.
Read the original →A peer-reviewed study evaluated the suite on 258,373 X-rays at 100 centers in 26 countries. Marketplace will route AI results into OnePacs.
Read the original →Google.org is awarding Clalit $2 million to build a multilingual AI system. The system is meant to help patients book care, complete intake, and access healthcare more easily.
Read the original →Ambient AI is becoming commonplace, but it might have more flaws than most doctors realize. Jay Anders explains why.
Read the original →Cancer survivor Karen Booth is among the first patients to experience new AI technology that is improving patient care.
Read the original →Chief Healthcare Executive interviewed leaders from Providence, Northwell, Intermountain Health, Kaiser Permanente, Mayo Clinic and more. The interviews cover the pressing issues facing their systems and health care as a whole.
Read the original →A pediatric emergency specialist at Samsung Medical Center says fears of staffing shortages drove her to develop an AI agent. The agent gathers information from parents before they meet medical staff.
Read the original →Medipal, an AI company specializing in hospital operations automation, operated an exhibition booth at ASLS KOREA 2026.
Read the original →AstraZeneca and Barts Health NHS Trust have launched an 18-month collaborative working project using Deontics’ Cancer Pathways IQ technology. It supports the modernisation of multidisciplinary team (MDT) working within the breast cancer pathway. This is the first live deployment of the technology within an operational breast cancer MDT.
Read the original →Quanome will exchange newly issued shares for a 5% stake in QAI Labs. QAI Labs' NOVA-3 platform combines AI, quantum algorithms and laboratory research.
Read the original →Laboratoires Pierre Fabre and XtalPi have entered into a drug discovery collaboration. It aims to develop novel clinical candidates across multiple research programs in oncology.
Read the original →AI is moving from experimentation into regulated environments. Pharmaceutical manufacturers must rethink how they demonstrate software reliability, manage risk and maintain a validated state.
Read the original →Geoffrey Hinton told the Guardian in an interview published Nov. 3 that "either later this year or next year we'll see Chornobyl" from AI. He cited an AI-enabled attack on power generation as one example.
Read the original →Wyoming residents search about artificial intelligence more often than people in any other US state when adjusted for population. The state recorded 4,681 annual AI-related searches per...
Read the original →Proposals for monitoring medical AI could make failures easier to trace. They could also leave patients and clinicians uncertain about who is responsible.
Read the original →Google has released an AI course for healthcare professionals. It has four courses totaling about five hours and is open to physical, occupational and speech therapists. It covers safe use of AI in non-clinical tasks such as patient explanations and administrative work.
Read the original →Niigata University of Health and Welfare announced findings from a validation using breast cancer MRI images. The results show the importance of separating patient data used to build a model from data used to evaluate it when assessing medical AI performance.
Read the original →