Medical AI is already in hospitals, but most of the devices haven't been properly tested
Of 1,357 AI devices the FDA has cleared for use in patient care, three were tested on whether patients lived longer or better.
Read the original →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.
Of 1,357 AI devices the FDA has cleared for use in patient care, three were tested on whether patients lived longer or better.
Read the original →The opinion piece says physician verification ensures prescription accuracy and protects patient safety.
Read the original →Researchers in China have developed an exploratory AI framework that combines DWI lesion features, SWI-derived deep medullary vein markers, and clinical metadata. It is used to predict ninety-day functional outcomes.
Read the original →A new study based on a very large real-world dataset suggests an AI model can predict next-day migraine risk using a person's headache severity and patterns over the previous 30 days. The model reached 91.2% precision.
Read the original →Grapevines are among the most economically and culturally significant crops on Earth. They remain under constant threat from fungal, bacterial and viral pathogens that attack their leaves.
Read the original →The piece references Fei-Fei Li's warning about the collapse of the middle. It uses a surgeon, a product manager, and a laid-off analyst to show what comes next.
Read the original →Building advanced models matters less than putting them to productive use.
Read the original →Artificial intelligence is entering a new phase in India's healthcare sector. Hospitals are increasingly looking beyond experimental pilots.
Read the original →A Tameside NHS project that uses AI to support patients at risk of emergency department (A&E) attendance has received a prestigious national award.
Read the original →Bengaluru-based Prodoc AI has raised an undisclosed seed round led by the Dr A. Velumani Family Office. It plans to build an Agentic AI layer for hospital workflows.
Read the original →One of the most stubborn obstacles in computational drug discovery is the cold-start problem. It concerns predicting whether a new drug will interact with a protein target when the model has never seen it.
Read the original →Artificial intelligence could help discover new drugs and solve complex engineering problems. But as systems become more capable of acting independently, questions arise about safety and human control.
Read the original →Peptide hormones are short chains of amino acids that act as powerful chemical messengers. They regulate metabolism, growth, development, and homeostasis.
Read the original →Deep Health AI India Ltd submitted a revised audit report for FY26 to include entity names in the consolidated financial statements, confirming no change in financial results. The auditor flagged key matters regarding an exceptional loss on a proposed acquisition and the deviation in utilization of Rights Issue proceeds.
Read the original →Okayama University Hospital in Kita Ward, Okayama, has installed multilingual, AI-based interactive digital signage inside the hospital. The signage automatically guides visitors to consultation and examination locations.
Read the original →Dr.Love Inc. announced on October 2 that its best-friend AI service Dr.Love launched officially on October 1. The service is offered as a place to talk about small everyday worries and feelings that are hard to put into words. It includes a "Chiguhagu diagnosis" feature.
Read the original →The partnership aims to advance "paylightX", a platform for dental clinics, through joint development.
Read the original →