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.
A study of 39 million physician AI queries found doctors consult AI more on treatment decisions than on diagnosis. The findings raise questions about expertise, judgment and when to consult specialists.
Read the original →Artificial intelligence in cardiovascular medicine advances diagnostics, risk prediction and clinical decision support.
Read the original →A retrospective Chinese study used blood-based inflammatory–nutritional indices taken at admission, together with machine learning, to predict new diabetic foot ulcers during hospitalization. The description reports that it achieved high d
Read the original →Sagility has acquired Chirok Health. The deal adds specialized clinical documentation improvement (CDI), medical coding quality assurance and revenue integrity to its global AI-led operations platform.
Read the original →Bengaluru-based Surgy Health launched SurgyOne on October 23 for mid-market hospital groups in India and the Gulf Cooperation Council countries. It is a hospital information system and electronic health record built around an AI agent that can find information, draft routine work and carry it out once a staff member approves. It is available now for demonstrations and pilots.
Read the original →Galeon is an electronic health record platform for hospitals, developed by the French company Galeon, which was founded in Annecy in 2016. It is delivered as subscription software and brings patient information into a shared interface for authorised healthcare professionals.
Read the original →A feasibility study of a large language model decision aid for juvenile idiopathic arthritis found high ratings for safety and preference acknowledgment. Agreement on treatment was below 30 percent.
Read the original →Masimo, described as a Danaher subsidiary, received FDA clearance for AI-enabled atrial fibrillation detection in its Radius VSM wearable monitor. The system uses artificial intelligence to identify potential AFib episodes in patients using Masimo's hospital-grade wireless device. The feature is intended for acute care settings.
Read the original →The FDA is weighing evidence standards for AI medical devices such as prescription bots. The AMA opposes upfront uncertainty, while ATA Action supports post-market monitoring. UpDoc, the AMA and others back risk-based regulation.
Read the original →The healthcare technology sector has moved from speculative expansion to a phase of capital discipline and operational accountability. Between 2020 and 2023, growth was marked by aggressive hiring, low-cost capital, fragmented point-solution experimentation and unvalidated clinical software pilots. Macroeconomic shifts and balance-sheet pressures among institutional buyers have changed the commercial environment approaching 2027.
Read the original →Lahrmann and colleagues developed an artificial intelligence system that uses dual stain triage for HPV-based cervical cancer screening. The work was described as a retrospective analysis.
Read the original →Trials of therapeutic chatbots are producing encouraging signals. They also show evidence of important limitations.
Read the original →Microsoft announced on October 22 (US time) that research on its medical diagnostic AI MAI-DxO was published in the journal Science. The system works by having multiple virtual doctors discuss a case. In an evaluation of a configuration using GPT-5, it was assessed on complex cases.
Read the original →Microsoft showed a tool that diagnoses disease through debate and verification among multiple AIs. It recorded higher accuracy than doctors in a difficult clinical case evaluation. Microsoft has also started research to check whether it can be used in actual patient care.
Read the original →