This Viewpoint discusses new guidance on responsible use of artificial intelligence.

This cohort study validates the usefulness of a novel prediction model for cancer-associated likelihood in adult patients with dermatomyositis.

This prognostic study uses United Network for Organ Sharing data to develop, validate, and assess the clinical utility of an interpretable hybrid machine learning model to predict time to death or retransplant at 1, 5, and 10 years after a lung transplant.

This randomized clinical trial of men who have sex with men investigates whether a chatbot-delivered HIV self-testing service is similar to a self-testing service with online real-time support by human administrators in increasing self-testing uptake and counseling support.

This cross-sectional study examines artificial intelligence use in health care and other industries according to US firms participating in the 2023 to 2025 Business Trends and Outlook Survey.

This cross-sectional study examines internet searches and website traffic to identify recent trends in the use of artificial intelligence (AI) to aid in clinical decision-making and patient care.

This Viewpoint discusses the use of generative artificial intelligence to measure mental health.

This Viewpoint explores the application of a licensure paradigm to clinical artificial intelligence systems.

This cross-sectional study evaluates how current foundation models perform when presented with offline ophthalmology textual and multimodal questions compared with experienced and nonexperienced physicians and older large language models.

This nonrandomized clinical trial reports the development and evaluation of an artificial intelligence–augmented screening program designed to detect transthyretin cardiac amyloidosis.

This Viewpoint explores how generative artificial intelligence (AI) tools may affect adolescent health and well-being in the following domains: health information, cognition, critical thinking, mental health, body image, social connection, physical activity, and sleep.

This randomized clinical trial evaluates the effectiveness of an approach combining the Quick Dementia Rating System and Passive Digital Marker machine learning algorithm for the detection of Alzheimer disease and other related dementias in primary care.

This sytematic review examines US Food and Drug Administration (FDA) premarket clearances for artificial intelligence and machine learning devices in radiology with emphasis on testing.

This cross-sectional study surveyed US adolescents and young adults on their use of generative artificial intelligence (AI) for mental health advice, including frequency and perceived helpfulness.

This review examines the use of artificial intelligence in managing acute myeloid leukemia.

This cohort study investigates the association between older age of an unrelated donor and overall survival in patient receiving posttransplant cyclophosphamide vs conventional calcineurin inhibitor for graft-vs-host disease prophylaxis.

Nature Machine Intelligence, Published online: 28 November 2025; doi:10.1038/s42256-025-01146-z

Durstewitz et al. explore what artificial intelligence can learn from the brain’s ability to adjust quickly to changing environments. By linking neuroscience studies of flexible behaviour with advances in continual and in-context learning, this Perspective outlines ways to strengthen the exchange of ideas between the two fields and advance NeuroAI.

Nature Machine Intelligence, Published online: 19 November 2025; doi:10.1038/s42256-025-01122-7

Diffusion models are reframed by developing a generative blood cell classifier that performs reliably in low-data regimes, adapts to domain shifts, detects anomalies with robustness and provides uncertainty estimates that surpass clinical expert benchmarks.

Nature Machine Intelligence, Published online: 19 November 2025; doi:10.1038/s42256-025-01141-4

HypOp is a scalable method for solving complex combinatorial problems. This study reproduces its results, tests its robustness, extends it to new tasks and provides practical guidelines for broader scientific applications.

Nature Machine Intelligence, Published online: 14 November 2025; doi:10.1038/s42256-025-01140-5

Yu and colleagues present MSGo, an artificial intelligence exposomics tool trained on virtual mass spectra with masking that identifies pollutants by generating chemical structures that match measured spectral data.

Nature Machine Intelligence, Published online: 13 November 2025; doi:10.1038/s42256-025-01145-0

A new benchmark, KaBLE (knowledge and belief language evaluation), indicates that some large language models are unable to accurately distinguish belief from knowledge and fact, calling into question their use in real-word applications such as medicine and law.

Nature Machine Intelligence, Published online: 13 November 2025; doi:10.1038/s42256-025-01144-1

Biases in artificial intelligence models have been studied predominantly through Western lenses, overlooking South Asia’s unique contexts of caste, religion, colourism and representation. This Comment highlights region-specific biases in language and vision models and calls for fairness frameworks grounded in South Asian realities.

Nature Machine Intelligence, Published online: 13 November 2025; doi:10.1038/s42256-025-01142-3

Kazemian et al. report that untrained convolutional networks with wide layers predict primate visual cortex responses nearly as well as task-optimized networks, revealing how architectural constraints shape brain-like representations in deep networks.

Nature Machine Intelligence, Published online: 13 November 2025; doi:10.1038/s42256-025-01143-2

Theilman and Aimone introduce a natively spiking algorithm for solving partial differential equations on large-scale neuromorphic computers and demonstrate the algorithm on Intel’s Loihi 2 neuromorphic research chip.

npj Digital Medicine, Published online: 09 December 2025; doi:10.1038/s41746-025-02179-9

Multi-dimensional omics integrated machine learning framework identifies macrophage-fibroblast-tumor co-infiltration patterns to predict prognosis in gastric cancer

npj Digital Medicine, Published online: 08 December 2025; doi:10.1038/s41746-025-02220-x

Harnessing machine learning for the development, validation, and prognostic evaluation of MASHRisk score: insights from a multicohort study

npj Digital Medicine, Published online: 08 December 2025; doi:10.1038/s41746-025-02197-7

Comparing content within a culturally-adapted digital treatment for Hispanic patients with alcohol use disorder

npj Digital Medicine, Published online: 08 December 2025; doi:10.1038/s41746-025-02188-8

Anatomically-guided Masked Autoencoder with Domain-Adaptive Prompting (AMAP) for multimodal cerebral aneurysm detection and segmentation

npj Digital Medicine, Published online: 08 December 2025; doi:10.1038/s41746-025-02181-1

STD-Net: a spatio-temporal decoupling network for multiphasic liver lesion segmentation and characterization

npj Digital Medicine, Published online: 08 December 2025; doi:10.1038/s41746-025-02217-6

An interpretable deep learning model for first-trimester fetal cardiac screening

npj Digital Medicine, Published online: 08 December 2025; doi:10.1038/s41746-025-02196-8

Self-supervised stain normalization empowers privacy-preserving and model generalization in digital pathology

npj Digital Medicine, Published online: 08 December 2025; doi:10.1038/s41746-025-02161-5

Deep learning-based brain age predicts stroke recurrence in acute ischemic cerebrovascular disease

This study investigates the real-world impact of a generative artificial intelligence scribe on health care practitioners’ well-being and documentation workload in ambulatory care. Using a 24-week, stepped-wedge, randomized trial, the authors demonstrate that ambient AI can meaningfully reduce burnout and time spent on notes without compromising documentation quality or billing accuracy.

In two landmark randomized controlled trials, Afshar et al. and Lukac et al. collectively evaluate three artificial intelligence scribing products in clinical practice, finding modest time savings for clinicians and reductions in clinician burnout. With their current functionality, AI scribes show early promise for improved productivity, and we lay out the conditions under which these tools may substantially improve productivity in the future.

This issue of NEJM AI

This randomized, pragmatic trial evaluated the performance of two large language model-powered ambient AI scribes (Microsoft DAX Copilot and Nabla) on a sample of 238 outpatient physicians across 14 specialties, measuring documentation time, physician burnout, cognitive task load, and work exhaustion. Nabla modestly reduced the time spent writing notes, while both tools showed potential to improve burnout and task load, with usability and accuracy deemed acceptable, highlighting AI scribes’ promise for enhancing physician workflow and well-being in real-world settings.

This study introduces a self-supervised electrocardiogram transformer foundation model that achieves high diagnostic accuracy across multiple cardiac prediction tasks. By enabling robust performance with limited labeled data, the approach expands AI’s potential in complex diagnostic areas such as myocardial ischemia and coronary microvascular and vasomotor dysfunction.

This article presents the development and silent prospective validation of Smart Match, a machine-learning system designed to predict patient-specific perioperative blood transfusion needs. It describes how data-driven modeling can replace traditional procedure-based blood ordering schedules, enabling more personalized and efficient approaches to perioperative blood management.

This review examines how artificial intelligence and machine learning could transform neurocritical care by enabling real-time detection of secondary brain injury. Drawing on three illustrative cases, it demonstrates how AI-assisted monitoring might enhance decision-making for delayed cerebral ischemia, seizure detection, and physiologic trend analysis while outlining the challenges of safely integrating these tools into clinical practice.

This perspective seeks to indicate how the lack of security in AI platforms may increase risk in clinical settings, particularly when these tools are used for translation or when patients share sensitive information about immigration status, employment, or housing.

This article summarizes key themes from the U.S. Food and Drug Administration’s 2024 public workshop on Artificial Intelligence in Drug and Biological Product Development, held in collaboration with the Clinical Trial Transformation Initiative. It outlines emerging challenges and policy priorities — spanning data access, model transparency, regulatory clarity, and cross-sector collaboration — central to establishing a risk-based, trustworthy framework for AI use in drug development.

This perspective examines the unique challenges of drug development for rare, ultrarare, and hyper-rare diseases, including small and geographically dispersed patient populations, limited natural history data, and clinical heterogeneity. It highlights strategies to address these obstacles with the advent of artificial intelligence, such as advanced analytical methods, use of individual-level and synthetic data, and the creation of centralized databases through public–private partnerships to expand available evidence.

This perspective highlights the urgent need for consistent oversight of predictive artificial intelligence models in health care. It proposes short-term randomized deployment as a practical standard to ensure institutional accountability, safety, and equity in AI implementation.

This article analyzes how current reimbursement mechanisms hinder the adoption of clinically effective and regulated artificial intelligence tools in health care, despite rapid technological progress. It examines current payment barriers, proposes policy reforms to align economic incentives with innovation, and outlines emerging challenges and opportunities in the regulation of generative AI.

A letter to the editor about “AI Agents, Automaticity, and Value Alignment in Health Care.”

Author’s response to a letter to the editor about “AI Agents, Automaticity, and Value Alignment in Health Care.”

Why people are asking chatbots about their feelings  When it’s 2 a.m. and your thoughts won’t turn off, a general AI chatbot is always awake. People use it to name a feeling, make sense of a conflict, or ask what to do about worry, sleep, or sadness. The appeal is obvious: instant answers, no appointment, ...;

AI search is rapidly transforming the way businesses and consumers across industries approach digital discovery and engagement. In this article, I explore emerging AI search trends and their impact on the modern business world, with a particular focus on the healthcare and life sciences sectors. By comparing general AI search advancements to the unique demands ...;

 Istanbul’s leading clinic now uses artificial intelligence to deliver more natural and fully personalized hair transplant results in Turkey. ISTANBUL – 2025 marks a breakthrough in hair restoration technology. Hair Center of Turkey, one of the most trusted hair transplant clinics in Turkey, has become the first in the country to introduce AI-powered hair transplant ...;

AI-powered systems are changing the way people work out from home. These smart tools act like personal trainers, showing you how to do exercises correctly and safely. They can guide you step by step, watch your movements, and even remind you when it’s time to work out. You don’t need to go to a gym ...;

Australia’s mental health sector is at an inflection point. As appointment demand far outpaces workforce supply, particularly in rural and NDIS-heavy regions, clinics are turning to AI not as a gimmick, but as critical infrastructure to survive. What was once seen as a novelty layer on top of traditional service delivery is rapidly becoming the ...;

Dentists have long been overlooked by tech providers who have focused on the larger healthtech market. The result is offices forced to use 20-40 year old software that consistently breaks and requires physical servers in the closet.  To solve this, Archy today raised $20 million in Series B funding led by TCV, with participation from ...;

Clinicians today spend more time on screens than they do with patients. Studies show that for every hour of direct care, physicians devote nearly two to documentation, billing, and compliance tasks. What was once considered the necessary paperwork of medicine has grown into a cycle of administrative burden that drains time, energy, and focus from ...;

We hear about needing eight hours of sleep a night, but almost no one talks about the energy waves that punctuate our day. Our bodies function not in a single on/off mode, but through repeated cycles called ultradian rhythms —lasting, roughly 90–120 minutes. During such cycles, your brain shifts between peak focus and natural lulls ...;

Global healthcare systems are facing several difficulties, from ineffective patient care to high physician turnover. These issues have the potential to seriously impair the standard of care given as the demand for medical services rises. The application of artificial intelligence (AI) in healthcare environments is one viable remedy. The data processing, pattern recognition, and decision ...;

We’re launching a new 27 billion parameter foundation model for single-cell analysis built on the Gemma family of open models.

Google announces its first cohort of 25 startups using AI to improve public services.

Learn more about Google’s partnership with NBA player Stephen Curry.

Doctors, developers and researchers gathered in Paris to prototype new medical solutions using Google’s AI models.

This field guide and investment support AI’s potential in evidence-based mental health interventions and research.

Here are Google’s latest AI updates from June 2025

Google Health and Google Cloud are collaborating with Taiwan’s National Health Insurance Administration.

Read Ruth Porat's remarks on AI and cancer research at the American Society of Clinical Oncology.

Learn how the 2025 Growth Academy: AI for Health cohort is building the next generation of healthcare solutions.

As AI moves from hype to reality in the revenue cycle, an upcoming HealthLeaders webinar will provide practical strategies for...

The new tool is designed to comb through individual patient data in the EHR, finding clinical care connections that doctors...

This week?s The Winning Edge webinar, sponsored by FinThrive, offered a blueprint for using AI in revenue cycle management, ranging...

A new survey reveals that leaders are accelerating AI and digital transformation investments to drive innovation and workforce development for...

Revenue Cycle Managers are deploying AI across their departments, using the technology to improve efficiency and reduce the data-crunching burden...

The Pennsylvania-based health system plans to expand the use of AI tools in digital diagnostics and adopt AI tools in...

Ben Eubanks of Lighthouse Research & Advisory explains how leaders can embrace technology without losing the workforce connection that defines...

In this week's The Winning Edge webinar, sponsored by FinThrive, panelists discussed how revenue cycle teams are using Ai across...

Discover how healthcare CFOs can control labor-related costs through smarter workforce investment, technology and vendor optimization, and cross?functional collaboration, without...

OSF HealthCare is conducting continuous virtual monitoring of moms and fetuses from the beginning of labor through delivery.

Seattle Children's Hospital CIO Zafar Chaudry says an enterprise-wide deployment of a new tool will save millions in recruitment and...

A new article published in the Journal of Medical Internet Research challenges the foundational research model that has shaped the digital health industry for decades. The article, "From Efficacy to Scale: Addressing Digital ...

As voice artificial intelligence (AI) speeds toward use in clinical settings, a researcher from Simon Fraser University is highlighting the urgent need for ethical, legal, and social oversight—especially in therapeutic ...

Researchers from Johns Hopkins Medicine and the Johns Hopkins Bloomberg School of Public Health report that an AI-powered lifestyle intervention app for prediabetes reduced the risk of diabetes similarly to traditional, human-led ...

Researchers at the University of California San Diego have created a model driven by generative AI that will help prevent injuries in athletes and also aid in rehabilitation after an injury. The model could also help athletes ...

A multinational collaboration at Eitri medical innovation center in Bergen, Norway, has used machine learning models to identify patient groups at risk of being mistreated.

The neurons in our brain that underlie thought connect to each other using tiny branch-like structures on their surfaces known as dendritic spines. Now scientists at Columbia's Zuckerman Institute and their colleagues have ...

Artificial intelligence (AI) might be able to help doctors make glaucoma screening widely available, a new study says.

Randomized, controlled clinical trials are crucial for telling whether a new treatment is safe and effective. But often scientists don't fully report the details of their trials in a way that allows other researchers to gauge ...

For many people, the rise of artificial intelligence–generated images has sparked anxiety—about misinformation, deepfakes and the blurring line between what's real and what's not. But in the world of medical imaging, ...

New research from the University of South Australia shows that the way we count our population could distort how health services are planned and funded—with some regions potentially over- or under-invested by more than ...

Scientists at ARUP Laboratories have developed an artificial intelligence (AI) tool that detects intestinal parasites in stool samples more quickly and accurately than traditional methods, potentially transforming how labs ...

JMIR Publications today announced the publication of a timely recap and interview with the co-chair of the Division of Clinical Informatics (DCI) Network's conference on ethical, effective implementation of artificial intelligence ...

Every day, millions of people are discharged after extended hospital stays, but matching these patients with appropriate care facilities can be arduous, often reliant on months-old, inaccurate data.

One huge reason why the world of medicine hasn't yet found "the cure" for hard-to-treat malignancies like acute myeloid leukemia (AML) and many other forms of cancer is that the world of science is still striving to fully ...

Researchers have identified factors associated with survival for patients initially diagnosed with metastatic breast cancer who were seen at UT Southwestern Medical Center and its affiliated sites. Their findings, published ...

A new peer-reviewed study in the journal Marketing Science finds that direct-to-consumer (DTC) advertising for prescription smoking-cessation drugs meaningfully reduces cigarette use. At the same time, the research found ...

A study published in the British Journal of Health Psychology reveals the negative behavioral and psychological consequences of commercial fitness apps reported by users on social media. These impacts may undermine the potential ...

As more people turn to ChatGPT and other large language models (LLMs) for mental health advice, a new study details how these chatbots—even when prompted to use evidence-based psychotherapy techniques—systematically violate ...

A new development in affordable, open-source mobile networks that enables near-real-time control of robotic arms could help doctors work on patients in remote locations in the years to come.

Inspired by tensions between health and financial well-being during the COVID-19 pandemic, a new model could significantly improve predictions of how disease will spread by acknowledging the trade-offs in a health crisis ...

Brain connectivity patterns and environmental factors can predict which older adults will successfully increase physical activity after receiving a cardiovascular diagnosis. Nagashree Thovinakere and colleagues studied 295 ...

Grid cells are a class of specialized neurons in a brain region called the entorhinal cortex, which is known to support spatial navigation and some memory processes. Past neuroscience studies have found that as humans and ...

Scientists at University of California San Diego have developed a new approach to destroying cancer stem cells—hard-to-find cells that help cancers spread, come back after treatment and resist therapy. The new approach, ...