This diagnostic study assesses whether the incorporation of vascular severity, either via artificial intelligence or clinician assessment, is associated with improved short-term prediction of treatment-requiring retinopathy of prematurity and reduced examination burden.

This article discusses the increasing prevalence of individuals seeking mental health help from artificial intelligence (AI) and recommends strategies to help patients navigate AI use.

This US longitudinal cohort study assesses the association of artificial intelligence scribe adoption with changes in electronic health record time expenditure and visit volume and how associations vary by clinician characteristics.

This Viewpoint assesses the consequences of not striving for equipoise between electronic health record developers and third-party AI tools trying to compete with them.

This cross-sectional study evaluates whether large language model scoring of research domain criteria can be successfully applied to law enforcement and coroner or medical examiner death narratives in the US National Violent Death Reporting System.

JAMA+ AI Associate Editor Yulin Hswen, ScD, MPH, spoke with John Torous, MD, MBI, host of the JAMA Psychiatry Author Interviews podcast and director of digital psychiatry for the Department of Psychiatry at Beth Israel Deaconess Medical Center in Boston, Massachusetts, for JAMA+ AI Conversations.

This scoping review examines research on large language model use in pediatric clinical text analysis.

This cross-sectional study tests whether a large language model chatbot product can reliably generate appropriate responses to psychotic content.

The systematic review and meta-analysis evaluates the diagnostic performance of dermatologists with and without artificial intelligence support in studies of melanoma detection.

This cross-sectional study uses automated similarity metrics to examine how closely the responses of a large language model align with human therapist responses in motivational interviewing conversations.

This cross-sectional study investigates the proportion of artificial intelligence (AI)–enabled devices regulated by the US Food and Drug Administration (FDA) that had pediatric indications.

This individual participant data meta-analysis explores the association between a machine learning–based sleep electroencephalography (EEG) brain age index and dementia risk among community-dwelling adults from 5 longitudinal cohorts.

This Viewpoint discusses the evolving use of artificial intelligence (AI) by graduate medical education programs for initial review of medical residency applications; highlights some of the legal risks of such use; and suggests several voluntary AI standards to mitigate these risks.

Nature Machine Intelligence, Published online: 25 March 2026; doi:10.1038/s42256-026-01219-7

A few years ago, we introduced an article format called Reusability Reports to highlight good practices in code sharing and reporting. A renewed focus on reproducibility and transparency in code reporting seems warranted, as research output has accelerated with the widespread adoption of large language models.

Nature Machine Intelligence, Published online: 25 March 2026; doi:10.1038/s42256-026-01195-y

Frank et al. introduce Euclidean fast attention, a linear-scaling framework for 3D data. By leveraging Euclidean rotary encodings, the method overcomes the quadratic cost of standard attention to accurately capture long-range effects in physical systems.

Nature Machine Intelligence, Published online: 25 March 2026; doi:10.1038/s42256-026-01204-0

Muzellec and Kar use reverse predictivity to show that only a subset of artificial neural network (ANN) units align with primate brain responses. This reveals a substantial misalignment between ANNs and brains compared with the strong bidirectional alignment observed between two primate brains.

Nature Machine Intelligence, Published online: 23 March 2026; doi:10.1038/s42256-026-01177-0

We introduce a framework to analyse interpretability in deep learning, by drawing on a formal notion of model semantics from the philosophy of science. We argue that interpretability is only one aspect of a model’s semantics and illustrate our framework with examples from biomedicine.

Nature Machine Intelligence, Published online: 23 March 2026; doi:10.1038/s42256-026-01194-z

Madduri et al. introduce a computational framework grounded in control and game theory to model co-adaptation between users and decoders in neural interfaces. This framework enables a principled design of closed-loop systems that improve usability and personalization.

Nature Machine Intelligence, Published online: 17 March 2026; doi:10.1038/s42256-026-01208-w

Large language models (LLMs) include not only social stereotypes but also cognitive biases. As researchers work to identify, characterize and rectify these biases, we encourage the scientific community to recognize that, although often seen as errors, cognitive biases can also reflect functional, context-specific adaptations in reasoning.

Nature Machine Intelligence, Published online: 17 March 2026; doi:10.1038/s42256-026-01200-4

Guo et al. train a Mamba-based language model for molecule generation and find that data augmentation and experience replay can enable the efficient generation of property-optimized small molecules.

Nature Machine Intelligence, Published online: 16 March 2026; doi:10.1038/s42256-026-01207-x

The case for stakeholder-driven AI auditing in automatic speech recognition

npj Digital Medicine, Published online: 03 April 2026; doi:10.1038/s41746-026-02579-5

An AI-based mental health guardrail and dataset for identifying psychiatric crises in text-based conversations

npj Digital Medicine, Published online: 03 April 2026; doi:10.1038/s41746-026-02512-w

Sensor-based digital health technologies to capture endpoints in recent clinical trials: a scoping review

npj Digital Medicine, Published online: 02 April 2026; doi:10.1038/s41746-026-02581-x

A robust vision language model for molecular status prediction and radiology report generation in adult-type diffuse gliomas

npj Digital Medicine, Published online: 02 April 2026; doi:10.1038/s41746-026-02572-y

Integrating large language models for enhanced predictive analytics in healthcare

npj Digital Medicine, Published online: 01 April 2026; doi:10.1038/s41746-026-02589-3

Multidimensional evaluation of large language models in radiology report readability

npj Digital Medicine, Published online: 01 April 2026; doi:10.1038/s41746-026-02591-9

Evaluating large language models for simplifying non-English medical consent with clinician involvement

npj Digital Medicine, Published online: 01 April 2026; doi:10.1038/s41746-026-02588-4

Comparative performance of LLMs and machine learning in predicting complications after percutaneous kyphoplasty for osteoporotic vertebral compression fractures

npj Digital Medicine, Published online: 01 April 2026; doi:10.1038/s41746-026-02576-8

Artificial intelligence assisted colorectal lesion detection in private practices a randomized controlled study

This prospective real-world quality improvement study evaluated an artificial intelligence–powered digital front door symptom assessment deployed within Portugal’s largest private health care network. The intervention was associated with reduced patient uncertainty, meaningful shifts in care-seeking behavior toward more appropriate care pathways, and a substantial improvement in the appropriateness of health care utilization.

Health systems govern AI by reviewing specific AI tools for defined use cases. But over two thirds of physicians use general-purpose AI daily in their practice, often through consumer platforms outside institutional oversight. Viewing these tools as risky because of the use of generative AI, health systems may disallow their use, paradoxically increasing the cybersecurity risk of patient data entering these platforms without agreed-upon institutional protections.

This Perspective examines the misalignment between health needs, health care resources, and artificial intelligence implementation capacity, demonstrating that Hart’s inverse care law persists in the AI era. Rural areas with the greatest health needs have the lowest AI capacity, risking amplification of existing disparities.

This Policy Corner proposes a structured human factors framework for artificial intelligence–enabled medical devices, distinguishing technical model performance from the safety and effectiveness of human interaction with AI outputs in real-world clinical workflows. It maps key AI-specific cognitive and system integration risks — such as automation bias, trust miscalibration, deskilling, and workflow disruption — to seven regulator-aligned design and evaluation recommendations spanning premarket usability engineering and postmarket monitoring.

CardioNets is a crossmodal deep learning framework that translates standard 12-lead electrocardiography signals into cardiac magnetic resonance–aligned functional parameters and synthetic CMR images, enabling scalable cardiac assessment without direct imaging. Across large, multicohort datasets, the model achieved superior performance to ECG-only baselines and diagnostic accuracy comparable to CMR-based models, supporting its potential to expand access to advanced cardiovascular assessment.

This article introduces MedVersa, a multimodal generalist foundation model trained on tens of millions of medical imaging instances that can accept heterogeneous inputs and generate diverse outputs across imaging workflows. The authors show that MedVersa matches or outperforms task-specific systems on multiple imaging tasks while producing clinically equivalent radiology reports and reducing reporting time and discrepancies in real-world evaluations.

A letter about “A Smartphone-Based Digital Ruler to Automatically Measure Strabismus in Ophthalmologist-Level: A Prospective, Multicenter Cohort Study.”

Author’s response to a letter, “Uncertainty-Aware Thresholding for Smartphone-Based Strabismus Measurement.”

The American healthcare system has long struggled with one of its most persistent inefficiencies: getting the right medical equipment to the right patient at the right time. For decades, the durable medical equipment (DME) sector operated on paper-heavy workflows, fragmented billing systems, and supplier networks that left patients navigating a labyrinth of prior authorizations, insurance ...;

Introduction to LatentHQ and Its Expertise in Healthtech Software Development LatentHQ is a leading software development company specializing in the healthcare industry. With years of experience and expertise, we have successfully delivered top-notch solutions to various healthcare providers, from small clinics to large hospitals. Our team of professionals has an in-depth understanding of the unique ...;

Kiran Veernapu has spent well over two decades building systems that extract millions in savings from healthcare operations. His track record spans aviation supply chains, enterprise software, and multi-hospital data platforms, which is work that produced roughly $17 million in documented cost reductions and a 30% drop in surgical billing errors. He’s also reviewed over ...;

Healthcare administration has never been simple, and that is part of what makes the work meaningful. Each day involves balancing priorities that do not always slow down or align neatly. Electronic health records, revenue cycle operations, compliance requirements, patient access, and vendor coordination all move at the same time. Most decisions are interconnected, and most ...;

Drug safety challenges don’t stop once a therapy completes clinical trials and reaches the market. Surprises in emerging safety profiles can derail promising programs even after a drug is approved. Today, artificial intelligence (AI)-powered models are helping pharmacovigilance (PV) teams detect these risks faster through the streamlining of post-approval safety data management.   Much of the early adoption of AI in PV has focused on using large language models (LLMs), hybrid data extraction pipelines, and human-in-the-loop oversight in ...;

For today’s seniors, aging in place is no longer just a preference — it has become a defining goal. Remaining at home supports dignity, emotional stability, comfort, and quality of life. However, maintaining independence safely requires one critical factor: mobility. The ability to move confidently, prevent falls, and navigate daily routines often determines whether seniors ...;

Thermobalancing therapy, patented in the US and invented by Dr. Simon Allen and Ariane Adjani of Oxford, alleviates the terrible symptoms of kidney stones from the first days of use and throughout the stone dissolution process. And what can you see on the internet where artificial intelligence is used to search for information about the ...;

In conversations about hospitality, AI is everywhere. From automation and robotics to hyper-personalisation, the industry is repeatedly told that the next competitive edge will come from adopting advanced technology and doing so quickly.  Step back, however, and a more grounded picture emerges. Most operators are not chasing AI for its own sake and rightly so. Research we conducted1 shows ...;

Artificial intelligence (AI) tools are everywhere now, including mental healthcare. Patients are turning to them to ask questions about their diagnoses, symptoms, medications and treatment recommendations. In many cases, this looks no different from when patients used Google or WebMD. The notable evolution is in the consolidation and seeming personalization of information generated through an AI-driven search.   For some patients, this ...;

The winners of the MedGemma Impact Challenge demonstrated the potential of Google’s open medical models for solving diverse healthcare challenges.

Google and DocMorris have announced a partnership to create a more intuitive and supportive digital health experience.

<p data-block-key="1tp3e">At Google’s annual health event, The Check Up, we shared how our products, research and partnerships are making the most of AI to help everyone live healthier lives.</p>

At The Check Up, Google announced a $10M investment in clinician AI training and how AI is upgrading Search and Fitbit for better health data.

An overview of how Google Earth AI is supporting the global health community’s work to predict outbreaks and deliver proactive care.

A new Google AI initiative aims to improve heart health outcomes for people living in remote Australian communities.

New research shows how Google AI helps radiologists detect breast cancer earlier and more accurately, while giving radiologists more time for patient care.

Working with Google, Taiwan uses 20 years of health data and Gemini to bring predictive diabetes care to millions in its population-wide health system.

To achieve meaningful ROI, health systems must layer AI on top of standardized digital workflows rather than using it to...

The clash between payers and providers over AI-driven coding is intensifying, with insurers arguing that documentation tools are inflating reimbursement...

What health system executives are actually doing to make AI work inside their organizations.

Recent survey data reveals that while AI adoption is growing, revenue cycle leaders must prioritize collaborative governance and front-end accuracy...

For CNOs who are struggling to address nursing workforce gaps, this CNO recommends finding encouragement at the bedside, where success...

CommonSpirit's $1.9B move to end a major revenue cycle outsourcing deal signals a strategic shift as health systems reconsider control...

Health system executives at HIMSS discussed how they're embedding the technology into workflows while maintaining clinician trust.

AMA data showing 81% physician AI adoption signals a turning point for health systems as leaders confront new governance, workflow,...

UCSF Health implemented an AI tool at the request of the bedside nurses who felt that their assignments were unbalanced,...

AI adoption in healthcare revenue cycle is accelerating, but a widening trust gap is preventing organizations from moving beyond pilots.

As technology moves into real-world use, healthcare leaders are balancing efficiency gains with oversight and trust.