This Medical News article discusses patient-facing artificial intelligence applications that are in various stages of development.

This Viewpoint discusses current regulatory frameworks governing the use of generative artificial intelligence (AI) in health care and proposes an alternative oversight system.

This cohort study examines whether dynamic, short-term prediction of preeclampsia in late gestation could be achieved using electronic health record–derived clinical and laboratory data across multiple health care settings.

This survey study examines the associations of patient trust in and choice of medical scenarios involving artificial intelligence with receiving information on governance mechanisms, clinician presence, performance, and data quality.

This Perspective discusses the changing role of the physician as the use of artificial intelligence in medicine increases.

JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, spoke with David Wu, MD, PhD, a resident physician in the Harvard Combined Dermatology Program at Mass General Brigham, and Adam Rodman, MD, MPH, director of AI programs at the Carl J. Shapiro Institute for Education and Research at Beth Israel Deaconess Medical Center, for JAMA+ AI Conversations.

This multicenter cohort study develops a vendor-agnostic artificial intelligence (AI) model for multidisease classification using 3-dimensional (3D) optical coherence tomography (OCT) scans from different vendors.

This Viewpoint discusses different ways to measure the return on investment on clinician-facing artificial intelligence tools as the technology advances.

This secondary analysis of a cluster trial uses school-level nested cross-validation to train and evaluate machine learning models for predicting individualized benefit from school-based mindfulness training.

JAMA+ AI Editor in Chief Roy Perlis, MD, MSc, spoke with JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, for JAMA+ AI Conversations.

This Viewpoint discusses the executive order signed by President Trump regarding a national policy framework for artificial intelligence (AI), including what it means for medical AI regulation, the legal questions it raises, and the merits of state-level experimentation in health care regulation.

This Narrative Review examines the evolving landscape of the application of large language models, highlighting innovations from other medical specialties, to provide otolaryngologists with the knowledge and direction needed to advance the field.

This cross-sectional study of US youths examines generative artificial intelligence usage by age category and time.

JAMA+ AI Editor in Chief Roy Perlis, MD, MSc, conducted an interview with ChatGPT about the history of chatbots and their clinical applications, for JAMA+ AI Conversations.

In this narrative medicine essay, a hematologist weighs the benefits and losses of surrendering the consult note to artificial intelligence.

This prognostic study investigates whether an automated deep-learning imaging-basedbiomarker using pretherapy and follow-up computed tomography (CT) scans can improve prediction of overall survival in advanced non-small cell lung cancer.

Nature Machine Intelligence, Published online: 27 February 2026; doi:10.1038/s42256-026-01196-x

Zhong et al. introduce Uni-HamGNN, a graph neural network model that predicts spin–orbit-coupled electronic structures quickly and accurately, enabling fast screening and the discovery of advanced quantum materials across the periodic table.

Nature Machine Intelligence, Published online: 27 February 2026; doi:10.1038/s42256-026-01199-8

Dhruv et al. introduce LLaMat, a family of LLMs for materials science, showing how specialized training enables smaller models to surpass larger general LLMs. The study reveals that extensively pretrained models like LLaMA-3 adapt less effectively than LLaMA-2 to new scientific domains.

Nature Machine Intelligence, Published online: 25 February 2026; doi:10.1038/s42256-026-01198-9

Wang et al. introduce Mac-Diff, a conditional diffusion model with locality-aware attention across modalities, to generate diverse conformational ensembles for unseen proteins, capturing both dynamic flexibility and structural heterogeneity.

Nature Machine Intelligence, Published online: 24 February 2026; doi:10.1038/s42256-026-01209-9

Author Correction: Mask-prior-guided denoising diffusion improves inverse protein folding

Nature Machine Intelligence, Published online: 24 February 2026; doi:10.1038/s42256-026-01203-1

Almost 10 years ago, AlphaGo defeated one of the world’s best professional players in the complex, ancient game of Go. It was a pivotal moment that spawned new research directions and marked the beginning of a busy decade in AI development.

Nature Machine Intelligence, Published online: 24 February 2026; doi:10.1038/s42256-026-01180-5

Gu et al. introduce a cardiac foundation model that learns from millions of heart signals and textual interpretations, enabling it to handle heart data collected either in hospitals or at home. It offers clear and reliable insights across different devices and settings.

Nature Machine Intelligence, Published online: 23 February 2026; doi:10.1038/s42256-026-01188-x

In a randomized controlled study at ICLR 2025, Thakkar et al. demonstrate that large language model-generated feedback can make reviews more informative while enhancing reviewer–author engagement.

Nature Machine Intelligence, Published online: 23 February 2026; doi:10.1038/s42256-026-01190-3

Wang et al. introduce MicroSyn-X, a synthetic X-ray data generation framework that overcomes data scarcity in miniature medical devices, enabling robust deep learning-based tracking and real-time robotic navigation in challenging surgical settings.

npj Digital Medicine, Published online: 09 March 2026; doi:10.1038/s41746-026-02482-z

Immersive competence as a source of bias in virtual reality clinical assessment

npj Digital Medicine, Published online: 08 March 2026; doi:10.1038/s41746-026-02507-7

Performance of breast cancer risk prediction algorithms across mammography systems in the UK screening programme

npj Digital Medicine, Published online: 07 March 2026; doi:10.1038/s41746-026-02475-y

Efficient cardiac MRI multi-structure segmentation for cardiovascular assessment with limited annotation by integrating data-level and network-level consistency

npj Digital Medicine, Published online: 07 March 2026; doi:10.1038/s41746-026-02457-0

Combining AI to reveal CCDC3-mediated pathways of colorectal cancer liver metastasis

npj Digital Medicine, Published online: 07 March 2026; doi:10.1038/s41746-026-02464-1

A novel digital twin strategy to examine the implications of randomized clinical trials for real-world populations

npj Digital Medicine, Published online: 07 March 2026; doi:10.1038/s41746-026-02519-3

AI-augmented communication improves HIV PrEP initiation and persistence in populations disproportionately impacted by HIV

npj Digital Medicine, Published online: 06 March 2026; doi:10.1038/s41746-026-02461-4

MS360°: a conceptual digital-first, data-driven hybrid care framework for personalised multiple sclerosis management

npj Digital Medicine, Published online: 06 March 2026; doi:10.1038/s41746-026-02501-z

Pricing models for diagnostic AI based on qualitative insights from healthcare decision makers

This study demonstrates that an end-to-end, multitask deep learning framework applied to overnight sleep electroencephalography can derive a latent representation of brain health distilled into a single, interpretable score. Across six large cohorts, the resulting brain health score outperformed demographic and conventional EEG metrics in predicting cognition, disease status, and mortality.

This Editorial examines why “human-in-the-loop” oversight in medical AI is not a single safeguard but a set of clinical, governance, and learning roles that must be deliberately designed. It argues that effective oversight must be adapted to local health systems, cultures, and values, rather than exported as a universal model.

This policy corner examines the European Health Data Space (EHDS), a new European Union regulation establishing a legal, technical, and ethical framework for cross-border access to and sharing of health data to accelerate artificial intelligence innovation in health care. It highlights the EHDS’s implications for non-EU stakeholders, particularly U.S.-based researchers and companies, emphasizing the opportunities for collaboration as well as the legal, procedural, and technical barriers that currently limit direct participation.

This Policy Corner examines the U.S. Food and Drug Administration’s new TEMPO (Technology-Enabled Meaningful Patient Outcomes) pilot, which introduces regulatory sandboxes to accelerate the use of health AI for chronic disease management while generating real-world evidence. It cautions that despite TEMPO’s focused design, unresolved questions about oversight, data quality, patient safety, and scalability must be addressed before broader adoption of sandboxes in U.S. health AI regulation.

This prospective, multicenter validation study assessed the real-world performance of a commercially available artificial intelligence tool for detecting nasogastric tube placement on chest radiographs. Although the system demonstrated high sensitivity and negative predictive value, its false-negative rate raised patient safety concerns, suggesting it is unsuitable as a primary decision-support tool for preventing NGT-related morbidity or mortality (i.e., “never events”).

A letter about “Evaluating Translational AI: A Two-Way Moving Target Problem.”

Author response to a letter about “Letter: Spillover Effects in Randomized Evaluations of Translational AI.”

A letter to the editor about “Faulty Artificial Intelligence, or the Sleep of Reason.”

Author response to a letter about “Faulty Artificial Intelligence, or the Sleep of Reason.”

When an airport’s IT system fails, passengers are stranded and flights are grounded. When a bank experiences an outage, customers may temporarily lose access to their accounts. But when these same failures occur in hospitals, the consequences are far more serious. Delayed treatments, disrupted diagnostics, and in the worst cases, lives put at risk.  Modern ...;

AI Is Moving From Curiosity to Clinical Context Artificial intelligence is rapidly shifting from novelty to necessity in everyday life. As mainstream AI tools introduce health-related features, more people are turning to algorithms for guidance when symptoms appear. This reflects growing expectations for immediate access to information. People want answers when a concern arises, not ...;

Healthcare leaders are under growing pressure to become more efficient, less administrative, and better patient outcomes without risking their operations. Generative AI has become a promising application, and its implementation needs to be carefully considered. It is not the only step of understanding the practical functioning of generative AI in healthcare . The key difficulty ...;

Healthcare AI is moving from “interesting prototype” to “operational system.” That shift changes the standard of proof. In a demo, it is enough to show a great AUC, a clean confusion matrix, and a few impressive examples. In production, the first hard question is different: Can you explain what happened when something goes wrong? The second question ...;

The front desk is essential to healthcare and dental practices, yet it often encounters bottlenecks, errors, and administrative overload. Increasing patient expectations and staffing shortages make it difficult for traditional reception models to keep pace. Healthcare virtual receptionists use a hybrid approach that blends AI automation with human support. This model streamlines scheduling, patient intake, ...;

Healthcare systems require predictive analytics as their fundamental operational capability. Data-driven forecasting enables hospitals and healthcare networks to decrease readmissions while they prepare for patient influx and detect clinical hazards at earlier stages. The increasing healthcare data volumes require predictive models to convert unprocessed data into usable information. Creating these systems needs more than expertise ...;

GPCRs: An Uncharted Frontier  Some scientific challenges are so complex that they shape entire fields, and G-protein coupled receptors (GPCRs) are one of them. These membrane-bound receptors influence everything from immune function to neurological health, yet astonishingly, more than half have never advanced into clinical development[1]. If drug discovery has its own form of “dark matter,” ...;

With OpenAI and Anthropic both unveiling dedicated AI tools for medical professionals and patients, 2026 is already proving to be a pivotal year for AI in healthcare.   These and other similar tools are designed to support doctors, improve access to information, streamline administrative tasks, and offer a guide for navigating healthcare interactions. It’s a meaningful step towards bringing critical clinical information closer to patients’ fingertips.  But when it comes to the patient experience, these AI tools may still be wanting.  ...;

Every major advance in medicine—from penicillin to gene sequencing—has forced society to reconsider how we define safety, trust, and responsibility. Artificial intelligence in healthcare is no different. But unlike previous breakthroughs, AI learns from the most intimate resource humans possess: our health data. And the systems that handle that data are nowhere near ready for the responsibilities we ...;

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.

To prepare for advanced automation, revenue cycle executives are stripping away complex EHR customizations and rethinking long-term vendor contracts.

Lina Scroggins is tasked by Mercy with making technology work for the patients. It?s a unique role that few healthcare...

A recent survey of CIOs and other IT leaders finds that application rationalization is a high priority for them, but...

Bradley Olson, Vice President of Managed Care for Mercyhealth, explains why revenue cycle leaders high claim denial rates to persist....

During a HealthLeaders panel on AI and patient engagement, executives focused on using the technology to create what patients really...

A panel of healthcare executives at this week?s HealthLeaders virtual summit identifies key opportunities and challenges to deploying agentic AI

View the full video of the latest webinar presented in HealthLeaders' The Winning Edge series.

Regulating AI by health insurers is becoming a politically divisive topic, and it's scrambling traditional partisan lines.

Fisher-Titus Medical Center sits in a rural section of northwest Ohio, yet it?s less than two hours from four major...

The latest webinar as part of HealthLeaders' The Winning Edge program focused on ways to boost physician well-being.

Remote patient monitoring is a standard of care in the health system's newest hospital.