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.
In a recent interview, Gadi Lalazar, MD, discussed new research on natural language processing (NLP). The research shows NLP can improve recognition of incidental hepatic steatosis in ultrasound reports.
Read the original →A retrospective single-centre study found that echocardiography-based radiomics with machine learning achieved only moderate accuracy in distinguishing fetal ventricular disproportion.
Read the original →The FDA granted Breakthrough Device Designation to Primaa's Cleo Skin AI pathology tool. The tool now has both CE-IVDR and FDA status.
Read the original →A prospective diagnostic cohort study validated an AI-ECG algorithm as an adjunct to troponin tests for early heart attack diagnosis. The study took place in European emergency departments.
Read the original →A literature review finds that machine learning and bioinformatics have improved AML classification and risk stratification. Clinical implementation remains limited by retrospective designs.
Read the original →A random forest machine learning model achieved strong predictive performance for acute respiratory distress syndrome among critically ill patients with acute pancreatitis.
Read the original →An explainable XGBoost model using eight routine clinical parameters predicted sepsis-associated acute kidney injury in 3,437 children across five Chinese intensive care units. It outperformed pSOFA.
Read the original →Mumbai-based deep-tech company Dimension NXG (DNXG), the maker of AjnaLens, announced on November 7 the launch of OJAS Forward Deployed Engineering (FDE). The new division places engineering teams directly inside hospitals, health systems and government health programmes to take clinical AI from pilot to everyday use.
Read the original →Doximity (NYSE:DOCS) reported calendar Q3 2026 (fiscal Q2 2027) results that beat Wall Street's revenue expectations, with sales up 3.6% year on year to $174.5 million. The company expects next quarter's revenue to be around $195.5 million, close to analysts' estimates.
Read the original →NUHS, Singtel and Ericsson have launched a research centre. It will test AI, 5G-Advanced and 6G for home-based patient care and hospital robots.
Read the original →A systematic review of 57 studies finds that AI-enabled Pharma 4.0 tools after COVID-19 concentrated on early-stage drug discovery metrics. The review found limited evidence of clinical benefit.
Read the original →SK Biopharmaceuticals, a Korean firm focused on developing original prescription drugs, has built a massive artificial intelligence dataset.
Read the original →The FDA has issued a Request for Information (RFI) seeking input on AI in early-phase clinical trials. The RFI is consistent with recent FDA initiatives on leveraging AI technologies and improving early-phase clinical trial conduct.
Read the original →Roche Holding stock enters the weekend after an AI drug discovery tie-up and a new U.S. respiratory announcement.
Read the original →A Georgia Tech analysis published in Nature Health in September mapped 31 U.S. lawsuits involving AI tools in healthcare. Its authors concluded that accountability should extend well past the physician at the bedside. Courts have only begun to sort out who answers when an algorithm errs.
Read the original →Generative AI is transforming clinical decision support, but citations alone do not ensure transparency or accountability. The article explores evidence bias, commercial influence and clinical oversight. It highlights how UpToDate Expert AI combines AI capabilities with expert-reviewed clinical content.
Read the original →Experts in artificial intelligence, medicine, ethics, law and policy gathered at Carnegie Mellon University on Nov. 5. The occasion was the K&L Gates Initiative in Ethics and Computational Technologies conference on Artificial Intelligence in Medicine: Opportunities and Challenges.
Read the original →According to experts, 3D simulation technology and artificial intelligence open up many possibilities. They cannot, however, replace direct clinical training in medical education.
Read the original →Yakuodo, which operates more than 400 stores mainly in the Tohoku region, opened its Yakuodo Mobara Oshiba store in Mobara, Chiba Prefecture, on Nov. 6. The store is on the site of a food supermarket, Kasumi, that closed in 2024.
Read the original →