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.
Applied Radiology spoke with two leaders representing complementary perspectives on the current state of CT. The discussion covers the technologies shaping its future.
Read the original →Advances in artificial intelligence are opening up possibilities for how images are interpreted, reported, and acted upon.
Read the original →Emerging technologies in oncology care include specialized LLMs, AI-assisted CT scans for early detection, and foundational models that democratize pathology.
Read the original →A clinical study combined metabolomics, microbiome sequencing and machine learning. It identified molecular and microbial signatures that predict adverse reactions to Evodia rutaecarpa in patients.
Read the original →Healthcare organizations are spending millions adding AI point solutions onto outdated workflows. NextGen Healthcare's Gautam M. Shah explains why IT leaders should stop buying standalone tools and redesign the EHR into an active system of context. He says focusing on clinical capacity is the way to fix broken ambulatory care workflows.
Read the original →MEDITECH is partnering with Lifemed AI to deploy non-generative deep-learning neural networks. The tools automate pre-bill scrubbing and aim to eliminate hospital claim denials.
Read the original →Six AI scribe tools are compared for clinicians. They range from self-serve options such as Twofold and Freed to enterprise platforms such as Abridge, Dragon Copilot and Suki.
Read the original →Sunlight AI launched with $17.4M in seed funding. It offers an AI patient-to-payment operating layer intended to keep physicians independent.
Read the original →OpenAI says it is adding Orchestra's team and technology to work on Rosalind, its AI model for life sciences research. They will also join Rosalind Workbench, a related tool that aims to help researchers plan experiments and analyze results.
Read the original →Artificial intelligence is being applied across the full lifecycle of drug research and development. Stages named include target identification, virtual screening, lead compound optimization, clinical trial design optimization, patient enrollment stratification, real-world data analysis and post-marketing safety monitoring.
Read the original →Regulators from the US and UK discussed ongoing efforts to develop regulatory frameworks better suited to generative AI products. The discussion took place at The MedTech Conference in Boston on Tuesday.
Read the original →Rick Abramson, a radiologist by training and director of FDA's Digital Health Center of Excellence, spoke about how the agency views such devices. He said the idea emerged that these devices may be starting to behave more like a physician than like a heart valve or a defibrillator.
Read the original →A joint study by Ben-Gurion University of the Negev and Clalit Health Services found that leading large language models identify redundant medical interventions in the vast majority of cases. They stumbled mainly in gray areas where medical consensus itself is divided.
Read the original →Ten years ago, Dr. Tiffani Bright's work centered on clinical decision support, using rules written and checkable by humans. She said AI was not on her radar then because it was not yet in the clinic.
Read the original →AI is moving deeper into UAE healthcare, from detecting prostate cancer to predicting dementia. Hospitals now face the harder challenge of proving it can work reliably at scale.
Read the original →The Japan Automobile Manufacturers Association (JAMA) says frontier AI models have greatly increased hacking threats to vehicles. Honda's Mibe targets a viable automated driving business by around 2030. Quebec's CEST found that locked-down car software already limits independent repair.
Read the original →Researchers tasked an algorithm with predicting cancer patients' risk of dying. For some people, it was shockingly accurate.
Read the original →Hitachi announced on the 20th that it developed a physical AI solution for process manufacturing. It links predictive detection of equipment failure risk from data changes with equipment fault diagnosis using AI agents. The company says users can achieve advanced stable operation by reducing reliance on individual expertise, along with a drastic improvement in maintenance efficiency.
Read the original →Notta, a speech recognition service based in Chiyoda, Tokyo, announced on October 20 that Saiseikai Kawaguchi General Hospital in Kawaguchi, Saitama, has adopted its meeting recording and summarization service.
Read the original →The NEXT-Cue AI software incorporates analysis of brain MRI scans. It reportedly supports prognostic assessments of potential progression from mild cognitive impairment (MCI) to Alzheimer's disease within five years.
Read the original →Researchers at UT Southwestern Medical Center reported that AI-driven tools used in emergency triage may be susceptible to the same clinical stigmas associated with human assessments. The findings were published in npj Digital Medicine.
Read the original →Cedars-Sinai researchers explain how AI and consumer wearables could help predict sudden cardiac arrest years or hours before an event occurs.
Read the original →The article says AI risk prediction gives organizations time to act before a risk becomes a loss.
Read the original →Drawing on 25 years as a district nurse, Paulette Hamilton MP argues that AI must deliver real improvements for NHS patients and staff.
Read the original →Healthleap was founded in South Africa in 2022 by siblings Josiah Meyer and Jemima Meyer to address an operational vulnerability in inpatient clinical care. Jemima Meyer is a registered dietitian trained at the University of the Free State who completed her clinical service within the South African Military Health Service. The description says she experienced firsthand the friction of inpatient bedside screening in high-volume hospital environments.
Read the original →Specialty1 Partners is expanding its investment in artificial intelligence across its national specialty dental network. The investment targets clinical documentation, patient access, administrative automation, contract management and employee productivity.
Read the original →Hundreds of attempted uploads were stopped after the network installed endpoint controls. The controls are intended to keep patient records out of public AI tools.
Read the original →The SickKids AI program aims to deploy "responsible AI" across clinical care, research, education and operations.
Read the original →Nvidia plans to invest in four German startups, Agile Robots, Avelios Medical, Mirelo AI and Reflex Aerospace, as it expands AI investment in Europe, CNBC reported. The investment size was not disclosed. German Chancellor Friedrich Merz called on companies, including small and midsized firms, to open their data to AI, and CEO Jensen Huang said AI would strengthen Germany's industrial competitiveness.
Read the original →KT said on Tuesday it will work with medical AI specialist Acryl to help medical institutions use data and adopt AI services. The two companies signed a memorandum of understanding at Acryl's headquarters in Seoul. They plan to promote medical data standardisation, jointly identify and test medical AI technologies and services, and advance R&D and commercialisation.
Read the original →AI can generate 100x more drug candidates, but trials still need real patients. The article says the bottleneck has shifted and most sponsors have not noticed.
Read the original →Evogene Ltd. (NASDAQ: EVGN) (TASE: EVGN) is a computational chemistry company specializing in AI-driven generative design of small molecules. It will take part in the roadshow on the U.S. East Coast.
Read the original →The description covers the MHRA's plans for agile MedTech and AI regulation, the AI Airlock, and deeper collaboration with the FDA. It also points to expert insights on SelectScience.
Read the original →The MHRA is recruiting a Regional Deputy Director of US Partnerships. The role will liaise with the FDA.
Read the original →Karan Singhal, who leads health AI research at OpenAI, says the company's goal is to make "trustworthy, abundant, reliable health intelligence" free.
Read the original →The Lancet recently published an AI trial that called itself phase 1. The trial had no dose finding and was not a 3+3 or Simon two-stage design.
Read the original →Researchers at Mass General Brigham developed a new model that can estimate age and predict survival outcomes from just one photo.
Read the original →