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 new narrative review finds AI tools improving diagnostic sensitivity and workflow efficiency in radiology. It also warns of demographic bias, limited interpretability, and uneven external validation.
Read the original →Charlottesville, Virginia-based medical technology company RIVANNA announced FDA 510(k) clearance for BoneEnhance. BoneEnhance is a machine learning module for its imaging products.
Read the original →A deep learning model trained on ultrasound images from six healthy horses could recognize most standardized FLASH examination windows. Performance varied widely, and the tool remains a proof of concept.
Read the original →Early wins with ambient AI scribes, shared control over clinical decision support tools and incremental pilots can build the trust needed for a decades-long transformation.
Read the original →A new Perspective in Globalization and Health proposes a five-layer AI framework and an IGAD-anchored roadmap for climate-health early warning across the Horn of Africa. It also catalogs data and other challenges.
Read the original →A new British Society of Echocardiography position statement maps where artificial intelligence is ready for clinical use across the echocardiography workflow. It also identifies where significant governance questions remain.
Read the original →A mapping review of 218 studies finds generative AI tools in cancer care are expanding rapidly. They are validated mostly on accuracy rather than clinical outcomes.
Read the original →At the AI in Hospitals Conference in Toronto in the last week of September, speakers presented advances in AI in healthcare and management advice for handling its growing presence. A lively discussion was set off when one of the speakers noted Canada's expertise in AI.
Read the original →Abridge is an AI platform for clinical documentation, developed by the clinician-led company Abridge, founded in 2018. It turns patient-clinician conversations into structured draft notes for clinicians to review within electronic health record workflows.
Read the original →AI Energy Group said it played a role in supporting the arrival of the Chinese People's Liberation Army Navy hospital ship Auspicious Ark (Hull 868) at the Port of Tema, Ghana.
Read the original →Officials are moving behind the scenes to head off a conflict brewing between states and the federal government over regulating AI.
Read the original →All 53 WHO European Region Member States adopted a new AI in healthcare roadmap. It prioritises patient safety, governance and digital transformation.
Read the original →India must adopt a robust legal framework to ensure the safe, ethical and accountable use of artificial intelligence in healthcare, clinical research and medical education. Errors in these areas can have serious consequences for patients and medical professionals.
Read the original →Artificial intelligence holds great potential to transform health care, but its clinical adoption in Korea remains slow. The description attributes the slow adoption to inadequate re...
Read the original →Microsoft beat physicians at diagnosis. The same team published a framework for what medical superintelligence would actually take.
Read the original →OpenEvidence is partnering with ASAM to integrate evidence-based addiction treatment guidelines and clinical resources into its AI medical research platform.
Read the original →The piece examines how generative AI amplifies the hybrid-threat mix of propaganda, drones, blockade and political manipulation in Mali.
Read the original →The ministry's office for public records management and information disclosure introduced AI-OCR to convert paper applications to text, and RAG-based generative AI that searches past cases and related documents to generate answers. The aim is to reduce the burden of processing disclosure and review requests. System builder System Exe announced it on October 29, 2026.
Read the original →SPAIA Keiba is publicly releasing three horses in tomorrow's races that its Diamond Course-exclusive training diagnosis AI rated AA or higher.
Read the original →