"Bias in AI in Epic Electronic Medical Records and Its Impact on Executive Communication: Conceptual Analysis" links #AIBias, transparent communication and trust. It proposes ECATF for equitable #HealthAI governance. doi.org/10.2196/85584

"Upskilling in Healthy Longevity Medicine and Its Association With Physicians’ Implementation Intent and Self-Reported Clinical Confidence" reports higher physician confidence and HLM integration after training. #Longevity #HLM #MedicalEducation mededu.jmir.org/2026/1/e83779/

"4. Interdisciplinary Digital Health Summit" brings together around 100 medical societies to advance digital medicine, covering #AI, #Telemedicine, #Wearables, #DigitalHealth and #HealthData.

Willkommen - Digital Health Summit

Sehr geehrte Kolleginnen und Kollegen, sehr geehrte Expertinnen und Experten der digitalen Gesundheit, herzlich laden wir Sie ein, den 4. Interdisziplinären Digital Health Summit am 21. und 22.…

digital-health-summit.com

"Unsafe by design? The launch of the Lancet Series on the digital determinants of health" examines digital environments as public health determinants and calls for safety by design, stronger governance and prevention. #DigitalHealth #PublicHealth

Unsafe by design?

Co-hosted by The Lancet and DTH-Lab, this webinar will launch a new three-paper Lancet Series on the digital determinants of health. Bringing together Series authors, young people, public health…

dthlab.org

"Less can be better: decomposing clinical data modalities in large language model-based healthcare applications" finds task-specific value of multimodal AI: #EHR data excels for risk prediction, while multimodality improves #ClinicalDecisionSupport. academic.oup.com/jamia/advanc...

"Can Intelligent Monitoring Help Older Adults Live Safely at Home Longer?" AI monitoring may support aging in place through early detection of falls and infections, combined with human care. #AI #Aging #RemoteMonitoring www.jmir.org/2026/1/e109278

"Transformation Before Innovation: Getting the Foundations Right" shows why #DigitalTransformation needs #Leadership, #Governance, training and resilient infrastructure before #AI deployment. www.youtube.com/watch?v=hD89...

Strategic Transformation: The Prerequisite for Successful Healthcare AI

In this video, JMIR Correspondent Boon-How Chew breaks down why digital health and AI implementations consistently fail due to organizational—not technological—fundamentals. Dr. Chew discusses why…

youtube.com

"OncoRAG: graph-based retrieval enabling clinical phenotyping from oncology notes using local mid-size language models" achieves 0.80–0.84 F1 with local 14B LLMs. #Oncology #RAG #LLM #ClinicalAI

"Automating infection indicator extraction in home healthcare through instruction-tuned large language models" reports 0.879 partial micro-F1 with Gemma-12B. #LLM #HealthcareAI #InfectionSurveillance doi.org/10.1093/jami...

Automating infection indicator extraction in home healthcare through instruction-tuned large language models

AbstractObjective. Home healthcare (HHC) clinical notes contain critical infection indicators that clinicians need in structured “indicator + context” pair

doi.org

"Mobile Apps for Heart Rate Variability: App Store Search and Content Analysis" reviewed 206 HRV apps. Only 93 allowed full analysis; proprietary feedback algorithms were often insufficiently transparent. #HRV #mHealth #DigitalHealth cardio.jmir.org/2026/1/e84764/

"Tokenising the patient journey: from records to representations" presents temporal AI models that turn fragmented health records into reusable representations of longitudinal patient journeys. #AI #HealthData #EHR #DigitalHealth

"A scoping review on the mental health harms of LLM-based chatbots" reviews 119 studies and identifies risks including cognitive overreliance, AI dependence, unsafe responses and AI psychosis. #LLM #AI #MentalHealth

A scoping review on the mental health harms of LLM-based chatbots

Chatbots based on large language models (LLMs) are increasingly used in everyday life. Although concerns about negative impacts on mental health are raised, a synthesis of the research and themes of the...

doi.org

"Social Media Discussions of Anti-Diabetic Drugs and the Popularity of GLP-1 Therapies: Content Analysis" finds diabetes discourse dominated by weight-loss therapies, especially GLP-1 drugs, with access, shortages and insurance key concerns. #Diabetes #GLP1 #Ozempic

JMIR Publications@jmirpub.bsky.social · 4d ago

Everyone has an opinion about GLP-1s. But what does the internet actually say when you look at 23,580 posts? The answer goes beyond Ozempic and weight loss. Check out the full article: https://diabetes.jmir.org/2026/1/e87590/ #GLP1 #Ozempic #Diabetes #DigitalHealth #HealthResearch #JMIR

"Introducing AI-Powered Nonprofits" shows how nonprofits use #AI to scale impact in #Health, #Education and #Climate, while emphasizing human-centered and inclusive technology. ssir.org/introducing-...

Introducing AI-Powered Nonprofits (SSIR)

AI-powered nonprofits (APNs) are deploying artificial intelligence in creative, powerful, and rapidly changing ways. Despite operating in disparate issue areas, APNs around the world are following…

ssir.org

"RheumBench: A Specialist-Validated Rubric-Based Benchmark for Evaluating Large Language Models in Rheumatology" finds major performance gaps, severe errors and overconfidence across 10 LLM systems. #LLM #Rheumatology #AI #PatientSafety

RheumBench: A Specialist-Validated Rubric-Based Benchmark for Evaluating Large Language Models in Rheumatology

Large language models (LLMs) are increasingly used for clinical decision support, yet scalable and specialty-specific methods for evaluating their performance and safety remain limited. We developed…

researchsquare.com

"Anreize zur Steuerung von Versorgungspfaden in der ambulanten Versorgung" examines OECD evidence on gatekeeping and cost-sharing. Effects depend on primary-care capacity, provider incentives and whether pathways can be bypassed. #Gatekeeping #PrimaryCare

"Primary Care Coordination: International Insights and Policy Options for Germany" compares primary care systems in 9 European countries and Israel, deriving lessons for Germany’s planned primary care model. #PrimaryCare #HealthPolicy

"The Architect of Trust: Dr Tom Ferguson’s Legacy" restores the history of the e-patient and highlights patient empowerment, participatory medicine, trust and access to health knowledge. #ePatients #PatientEmpowerment #ParticipatoryMedicine

"Reinventing Clinical Guidelines in the AI Era" examines how generative AI may reshape clinical guidelines while preserving clinician autonomy, reducing bias, and keeping evidence central to care. #AI #ClinicalAI #Guidelines events.nejm.org/events/819

NEJM Group Live-Streamed Health Care Events

Advancing medical knowledge from research to practice

events.nejm.org

"Mixed Methods Studies Examining the Physical Activity Practices Among African American and Black Women: Protocol for a Methodological Scoping Review" maps mixed-methods research on #PhysicalActivity, #BlackWomen & #HealthEquity. www.youtube.com/watch?v=9JR9...

Mapping Mixed Methods Physical Activity Research Among African American & Black Women

In this video, Annette Moore Hubbell from Illinois State University presents a protocol for a methodological scoping review examining mixed methods studies on physical activity practices among…

youtube.com

"AI-assisted rheumatology triage changes with referral framing" shows that wording can distort LLM triage: anxious framing increased psychological attribution nearly 3-fold, while demographics had no detectable effect. #AI #LLM #Rheumatology #Triage doi.org/10.1093/rheu...

AI-assisted rheumatology triage changes with referral framing

AbstractObjectives. Two in three US physicians now use healthcare AI, and large language models (LLMs) are entering the triage workflows that determine whi

doi.org

"The Multicriteria Decision Analysis for Extended Reality (MCDA-XR) Governance Framework for Health Care Adoption" proposes 10 criteria for XR governance; safety/comfort ranked highest (4.61/5). #XR #DigitalHealth #Healthcare www.youtube.com/watch?v=OMxb...

Beyond the Pilot: A Governance Framework for Extended Reality in Healthcare

José Ferrer Costa from Universitat Oberta de Catalunya discusses research introducing MCDA-XR, a strategic decision-support framework designed to help healthcare organizations evaluate, prioritize,…

youtube.com

"The Influence of Robot Facial Expression and Inclusion Behavior on Rapport and Trust in Older Adults: Mixed-Factorial Experimental Study" finds positive robot expressions boost rapport/trust, especially with exclusion. #Robotics #HRI #HealthyAging www.youtube.com/watch?v=ZGV8...

How Robot Expressions and Social Behavior Build Trust with Older Adults

Hsiu-Ping Yueh from National Taiwan University discusses research evaluating how a social robot's facial expressions and interaction styles influence rapport, acceptance, and trust among…

youtube.com

“‘It helps me stay on track’: patient experiences using a mobile app for self-management of systemic sclerosis with a focus on fatigue in women” RENEW was user-friendly and supported fatigue self-management; accessibility and personalization remain priorities. #SSc #mHealth doi.org/10.1093/rap/...

‘It helps me stay on track’: patient experiences using a mobile app for self-management of systemic sclerosis with a focus on fatigue in women

AbstractObjectives. Fatigue is common and burdensome in people with systemic sclerosis (SSc), significantly impacting daily functioning and quality of life

doi.org

"Perceptions, knowledge and adoption of artificial intelligence in rheumatology: results from a British Society for Rheumatology survey" finds frequent AI use but low AI knowledge and concerns over privacy, liability and explainability. #AI #Rheumatology doi.org/10.1093/rheu...

Perceptions, knowledge and adoption of artificial intelligence in rheumatology: results from a British Society for Rheumatology survey

AbstractObjectives. Artificial intelligence (AI) and machine learning applications are rapidly expanding across healthcare. Successful implementation of AI

doi.org

"When the Chatbot Leaks: Securing Patient-Facing Medical AI in the Age of Dual-Use Large Language Models" shows that RAG is no security boundary: a patient-facing chatbot exposed its prompt, configuration, knowledge base and 1,000 patient conversations. #MedicalAI #RAG doi.org/10.1056/AIp2...

When the Chatbot Leaks: Securing Patient-Facing Medical AI in the Age of Dual-Use Large Language Models

Patient-facing chatbots based on retrieval-augmented generation (RAG) are increasingly promoted to deliver curated, evidence-based health information. However, RAG is not a security boundary; a cha...

doi.org

"Humanoid Colleagues and the Rheumatology Workforce: Preparing for a New Era" proposes supervised, four-stage humanoid training in rheumatology, with no independent practice and physician control. #Rheumatology #AI #Robotics www.ovid.com/10.1002/acr2...

Humanoid Colleagues and the Rheumatology... : ACR Open Rheumatology

Rheumatology faces sustained workforce strain, widening access gaps, and escalating administrative burden. Fellowship expansion and integration of...

ovid.com

"Digital rheumatology—Structured prompting as reusable clinical tools" proposes 5 levels of clinical AI use, culminating in reusable, auditable reasoning skills. The proof of concept remains unvalidated. #AI #Rheumatology #LLM www.sciencedirect.com/science/arti...

"Robust Assessment of Free-Living Physical Behaviors and Activity Intensity Using Dual-Wearable Multitask Learning" shows dual-sensor wearables improve free-living activity classification. #Wearables #AI doi.org/10.2196/94302

"Evaluating the First CE-Marked LLM-Based Chatbot for Evidence-Based Neurology" found 76.2% correct answers for Prof. Valmed. CE marking ensured regulatory conformity, not superior performance. #LLM #Neurology #MedicalAI #CE doi.org/10.1111/ene....

Evaluating the First <fc>CE</fc>‐Marked <fc>LLM</fc>‐Based Chatbot for Evidence‐Based Neurology

Prof. Valmed, the first CE-marked LLM-based medical retrieval tool in Europe, was tested and compared using an established neurology benchmark. Its performance was comparable to most other evaluated…

doi.org