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 study examines author self-reported disclosures of use of artificial intelligence (AI) in the preparation of manuscripts submitted to JAMA Network journals since implementation of a requirement of disclosure in 2023.

This study examines self-disclosed use of artificial intelligence (AI) in research manuscripts submitted to BMJ Group journals, including the types of tools used and frequency of use.

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.

This cohort study introduces a deep-learning method for assessing myopia and high myopia risk in schoolchildren in China using fundus images and baseline refraction data.

This diagnostic study investigates if an artificial intelligence algorithm can diagnose bronchopulmonary dysplasia or pulmonary hypertension in the retinal images of preterm infants obtained during retinopathy of prematurity screening examinations.

This cohort study using a matched case-control design characterizes differences in documentation and treatment of psychiatric symptoms in primary care outpatient notes generated using ambient scribes compared with human or no scribes.

This survey study examines the associations of generative artificial intelligence (AI) use with negative affective symptoms in a large nationally representative sample of US adults.

This Viewpoint discusses speed and safety in pediatric artificial intelligence.

This quality improvement study assesses the vulnerability of leading commercial large language models to invisible text injection manipulation in simulated medical peer review.

JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, spoke with Cecilia Lee, MD, MS, a professor of ophthalmology at Washington University in St Louis, for JAMA+ AI Conversations.

This quality improvement study assesses the association of a natural language processing tool classifying patient portal messages as high acuity with clinician time to first read in a large, integrated health care system.

This Special Communication explores the use of artificial intelligence in mental health care delivery, outlining the potential benefits and negative consequences, and suggests strategies that may help mitigate the risks.

This cohort study evaluates use of a machine learning algorithm with molecular imaging to analyze imaging data during lung cancer surgery to determine the malignant potential of nodules.

This Medical News article discusses the growing use of generative artificial intelligence chatbots as sources of mental health support.

Nature Machine Intelligence, Published online: 30 January 2026; doi:10.1038/s42256-026-01178-z

On the troubling rise of generative AI suspicion in academic publishing

Nature Machine Intelligence, Published online: 28 January 2026; doi:10.1038/s42256-026-01181-4

Mixtures are ubiquitous in industrial formulations. A framework unifying predictive and generative machine learning now offers a blueprint for data-driven design of multi-component battery electrolytes.

Nature Machine Intelligence, Published online: 28 January 2026; doi:10.1038/s42256-025-01173-w

Yang et al. introduce a unified framework for liquid electrolyte design, integrating a forward predictive model with an inverse generative approach, where three generated high-conductivity candidates were identified and experimentally validated.

Nature Machine Intelligence, Published online: 27 January 2026; doi:10.1038/s42256-025-01174-9

Addendum: Resolving data bias improves generalization in binding affinity prediction

Nature Machine Intelligence, Published online: 27 January 2026; doi:10.1038/s42256-026-01183-2

Agentic artificial intelligence (AI) frameworks are in vogue. However, implementing such systems in scientific research workflows requires clear motivations and explanations, given the risk of wasting computational as well as human resources.

Nature Machine Intelligence, Published online: 26 January 2026; doi:10.1038/s42256-025-01164-x

TongGeometry both solves and proposes olympiad-level geometry problems. It uses guided tree search to find hard but concise problems, making advanced mathematical reasoning more accessible.

Nature Machine Intelligence, Published online: 26 January 2026; doi:10.1038/s42256-025-01165-w

A dual-branch framework that disentangles cell states from drug-induced regulatory shifts to predict transcriptional responses is presented. It captures nonlinear dose–time dynamics and excels in generalizing to unseen cellular contexts.

Nature Machine Intelligence, Published online: 21 January 2026; doi:10.1038/s42256-025-01172-x

Capturing the complexity of cardiovascular dynamics demands multiple monitoring modalities, each with inherent trade-offs. Diffusion-based modeling offers a promising route for synthesizing and generating cross-modal data.

npj Digital Medicine, Published online: 06 February 2026; doi:10.1038/s41746-026-02367-1

xGNN4MI: explainability of graph neural networks in 12-lead electrocardiography for cardiovascular disease classification

npj Digital Medicine, Published online: 06 February 2026; doi:10.1038/s41746-025-02318-2

Development of deep learning model to screen for primary open-angle glaucoma in African ancestry individuals

npj Digital Medicine, Published online: 06 February 2026; doi:10.1038/s41746-026-02342-w

Wearable EEG devices in the detection of mild cognitive impairment: a systematic review

npj Digital Medicine, Published online: 06 February 2026; doi:10.1038/s41746-026-02406-x

A weakly supervised transformer for rare disease diagnosis and subphenotyping from EHRs with pulmonary case studies

npj Digital Medicine, Published online: 06 February 2026; doi:10.1038/s41746-026-02413-y

Multidisciplinary prediction of running-related injuries using machine learning

npj Digital Medicine, Published online: 06 February 2026; doi:10.1038/s41746-026-02404-z

Physics constrained graph neural network for real time prediction of intracranial aneurysm hemodynamics

npj Digital Medicine, Published online: 06 February 2026; doi:10.1038/s41746-026-02409-8

Independent and collaborative performance of large language models and healthcare professionals in diagnosis and triage

npj Digital Medicine, Published online: 05 February 2026; doi:10.1038/s41746-026-02379-x

Neck-to-knee dixon MRI thigh volume as a superior mass biomarker for Sarcopenia: evidence from the UK biobank

This study introduces TARGET-AI, a multimodal framework that integrates longitudinal electronic health record embeddings with contrastively pretrained electrocardiogram (ECG) image representations to estimate pretest disease probability and guide targeted AI-ECG screening for structural heart disease. By evaluating a sequential, resource-aware deployment strategy across temporally and geographically distinct cohorts, the work positions AI-ECG as a context-sensitive screening tool that improves precision and reduces false positives in low-prevalence disease settings.

We introduce health artificial intelligence target product profiles as a method to define the performance thresholds that AI models must meet to deliver clinical benefit within specific health care environments. Using hypertrophic cardiomyopathy detection as a use case, we demonstrate how this framework enables health systems to guide model development or selection based on clinical context, resource constraints, and predicted value.

Reflections on the alignment (or lack thereof) of artificial intelligence models to clinical, human values in health care; proposal to piggyback on emerging newer attributes for AI model cards to encourage documentation of clinical values and alignment procedures.

Delayed cerebral ischemia is a common, severe complication following subarachnoid hemorrhage, significantly affecting patient outcomes. This study demonstrates the successful integration of a real-time DCI prediction algorithm into a live intensive care unit environment using a silent validation methodology.

This case study evaluated seven publicly available chatbots, both general–purpose and behavioral health–focused, for their ability to provide support for alcohol misuse through simulated 7-day interactions. Clinician raters found that, although the chatbots consistently demonstrated empathy, the quality and accuracy of the information varied widely, with all tools showing notable limitations in providing reliable behavioral health guidance.

A letter about “Machine Learning–Based Patient Preference Prediction: A Proof of Concept.”

A letter about Starke et al.’s “Machine Learning–Based Patient Preference Prediction: A Proof of Concept.”

Author’s response to a letter about “Machine Learning–Based Patient Preference Prediction: A Proof of Concept.”

This perspective article explores what constitutes a high-value application in medical artificial intelligence.

This study evaluated the ability of generative pretrained transformer 4o to grade short-answer responses from first-year medical students compared with human graders. Using iterative, pedagogy-guided prompt refinement, GPT-4o achieved moderate agreement with human scores, suggesting that artificial intelligence–assisted grading could help reduce the burden of assessing open-ended questions in medical education.

This editorial explores the utility of multiple-choice questions and short-answer questions for assessment in medical education. It also addresses the extent to which the study by Kuling et al. demonstrates whether a large language model can adequately grade short-answer questions.

New technologies have greatly changed the healthcare industry.  Modern healthcare made diagnosis, treatment, and patient care faster, more accurate, and easier to access. AI in diagnostics, telehealth services, and advanced surgical tools are all examples of how technology is changing healthcare.  In this blog, we explore the key ways in which modern healthcare is evolving through technology, its impact on patient ...;

The potential of AI for healthcare is undeniable, with the technology fuelling a resurgence of venture capital flowing into medical software and healthcare technology. While initial AI implementations often focused on novel, standalone applications like ambient AI scribes, a quiet but significant shift is now underway.   The real revolution is happening in the back office. AI tools ...;

The Global Healthcare system is at a crossroads as AI and technological advancements are making it more flexible, reliable, and stronger. The older populations living with multiple chronic illnesses, growing workforce shortages, widening care inequities, and spiralling healthcare costs. They are putting pressure on hospitals that are operating well beyond their traditional capabilities. After the outrage of ...;

Healthcare is changing fast. What used to be talk about digital intelligence is now just part of daily life in clinics across the country. Dentists and other professionals are using machine learning to speed up admin work and, more importantly, to sharpen the precision of life-saving treatments. If you care about top-notch local care, finding ...;

Artificial intelligence is shaking up the world of medical diagnostics and patient care faster than anyone expected. It’s not just the big hospitals cashing in on high-tech tools—local clinics are getting in on the action too, even the ones offering urgent dental care. Picture this: the next time you land in the chair of an ...;

Tech is shaking up medicine. It’s not just about fancy machines in research labs anymore—AI is right there in the dentist’s office, smoothing out the whole process. Maybe you’ve noticed it yourself: booking a Mississauga dentist appointment online, getting instant confirmations and reminders, and never waiting as long in the lobby. These smart systems don’t ...;

AI-enhanced edge databases transform patient care by handling real-time data from wearables and remote monitoring directly at the edge, guaranteeing access in any environment, connected or not. This innovation fuels the virtual healthcare surge, offering instant scalability and offline synchronization for uninterrupted outcomes that modern providers demand. Edge Computing Advantages Edge computing pushes processing to ...;

Why First Impressions Matter More in Healthcare Than Anywhere Else When patients search for medical care online, they are often stressed, uncertain, or in pain. Their expectations are simple. They want clear answers, fast loading pages, and an easy way to take the next step. Page speed and user experience play a much bigger role ...;

When it comes to disposable vapes, the Lost Mary MT15000 stands out as a premium choice for both seasoned vapers and those just starting their journey. With an extended puff count, sleek design, and a variety of tantalizing flavors, it’s no wonder that the MT15000 has become a favorite among vape enthusiasts. If you’re considering ...;

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.

During this installment of HealthLeaders' The Winning Edge series, revenue cycle leaders from Mercyhealth and Wellstar Health System share how...

Healthcare organizations are embracing AI as a transformative tool in clinical care, but they?ve seen few successes so far. How...

SpotitEarly, which is already testing whether the company's beagles can detect breast cancer, forges partnership with Fox Chase Cancer Center.

As payers deploy AI to automate claim reviews, revenue cycle leaders share the strategies they are adopting to fight back....

More than 40% of healthcare execs and clinicians surveyed say they know of a colleague who has used unapproved AI....

As payers deploy advanced tech to scrutinize claims, health systems like Mercyhealth and WellStar are fighting back with stricter contracts...

Ambient AI scribes are being hailed by physicians as a game changer that helps free them to focus on their...

Dangerous AI bots and 'digital darkness' events top the annual list of healthcare technology gone wrong.

A new report finds funding hit its highest level since 2022, driven by bigger bets on AI and a small...

Research shows that adoption of AI tools in pediatric critical care is in its infancy.

To maintain peak efficiency, health systems and hospitals need to clear out underperforming, duplicate and legacy apps and platforms. That's...