npj Digital Medicine, Published online: 20 October 2025; doi:10.1038/s41746-025-01992-6

Unlocking the potential: multimodal AI in biotechnology and digital medicine—economic impact and ethical challenges

npj Digital Medicine, Published online: 20 October 2025; doi:10.1038/s41746-025-01988-2

A deep learning based automatic report generator for retinal optical coherence tomography images

npj Digital Medicine, Published online: 17 October 2025; doi:10.1038/s41746-025-02008-z

When helpfulness backfires: LLMs and the risk of false medical information due to sycophantic behavior

npj Digital Medicine, Published online: 17 October 2025; doi:10.1038/s41746-025-01989-1

Semi-automated surveillance of surgical site infections using machine learning and rule-based classification models

npj Digital Medicine, Published online: 17 October 2025; doi:10.1038/s41746-025-01987-3

Navigating the tradeoff between personal privacy and data utility in speech anonymization for clinical research

npj Digital Medicine, Published online: 16 October 2025; doi:10.1038/s41746-025-01985-5

Evaluating the performance of general purpose large language models in identifying human facial emotions

npj Digital Medicine, Published online: 16 October 2025; doi:10.1038/s41746-025-01994-4

Generalized multi task learning framework for glucose forecasting and hypoglycemia detection using simulation to reality

npj Digital Medicine, Published online: 16 October 2025; doi:10.1038/s41746-025-02007-0

Automated real-time assessment of intracranial hemorrhage detection AI using an ensembled monitoring model (EMM)

Nature Machine Intelligence, Published online: 21 October 2025; doi:10.1038/s42256-025-01139-y

Questions over whether neural networks learn universal or model-specific representations framed a community event at the Cognitive Computational Neuroscience conference in August 2025, highlighting future directions on a fundamental topic in NeuroAI.

Nature Machine Intelligence, Published online: 21 October 2025; doi:10.1038/s42256-025-01119-2

Powerful generative AI models for designing biological macromolecules are being developed, with applications in medicine, biotechnology and materials science, but these models are expensive to train and modify. Leyva et al. introduce the Key-Cutting Machine, an optimization-based platform for proteins and peptides that iteratively leverages structure prediction to match desired backbone geometries.

Nature Machine Intelligence, Published online: 21 October 2025; doi:10.1038/s42256-025-01124-5

Graber et al. characterize biases and data leakage in protein–ligand datasets and show that a cleanly filtered training–test split leads to improved generalization in binding affinity prediction tasks.

Nature Machine Intelligence, Published online: 21 October 2025; doi:10.1038/s42256-025-01111-w

Choi et al. introduce a machine learning model that integrates diverse multi-view data to predict disease phenotypes. The model includes an interpretable explainer that identifies interacting biological features, such as synergistic genes in astrocytes and microglia associated with Alzheimer’s disease.

Nature Machine Intelligence, Published online: 21 October 2025; doi:10.1038/s42256-025-01116-5

Multimodal AI combines different types of data to improve decision-making in fields such as healthcare and engineering, but work so far has focused on vision and language models. To make these systems more usable in the real world, Liu et al. discuss the need to develop approaches with deployment in mind from the start, working closely with experts across relevant disciplines.

Nature Machine Intelligence, Published online: 20 October 2025; doi:10.1038/s42256-025-01121-8

Irie and Lake present a metalearning framework that enables artificial neural networks to address classic challenges by providing both incentives to improve specific capabilities and opportunities to practice them.

Nature Machine Intelligence, Published online: 20 October 2025; doi:10.1038/s42256-025-01127-2

Recurrent neural networks are widely used to model brain dynamics. Tolmachev and Engel show that single-unit activation functions influence task solutions that emerge in trained networks, raising the question of which design choices best align with biology.

Nature Machine Intelligence, Published online: 16 October 2025; doi:10.1038/s42256-025-01133-4

Although it is possible to use deep learning models to predict static protein conformations from sequencing data, proteins are not static biochemical artefacts. ItsFlexible is a graph-based deep learning tool that is trained on a new dataset of experimentally captured protein motif conformations to classify the dynamic characteristics of proteins.

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.

Googler Thomas Wagner shares how he used Gemini to learn more about his son’s rare disease, and jumpstart research.

<p data-block-key="0svxl">At The Check Up 2025, we shared more about the potential of AI in health and our latest health AI research, partnership and product updates.</p>

At The Check Up 2025, we shared more about our latest health AI research, partnership and product updates.

Ubie, a health tech startup in Japan, is using Google AI to change patient — and healthcare worker — experiences for the better.

Learn how AI is making accurate health information more accessible and personalized and how AI can accelerate scientific discoveries with AI co-scientist.

Here are Google’s latest AI updates from February 2025

Google and the Institute of Women's Cancers are embarking on a journey together to revolutionize the fight against women’s cancers.

Recap some of Google’s biggest AI news from 2024, including moments from Gemini, NotebookLM, Search and more.

Open Health Stack, a set of open-source tools from Google, allows developers to create digital health solutions for low-resource settings around the world.

When I first began working in health insurance, I noticed a striking contradiction. The United States spends nearly 18.3 percent of GDP on healthcare, yet life expectancy and other population health outcomes lag behind comparable nations. Americans live over four years fewer on average than people in similar economies, while preventable illnesses still drive significant ...;

A paradox at the heart of AI adoption  In 2025, one of the most striking lessons about artificial intelligence isn’t coming from Silicon Valley boardrooms, it’s coming from hospital hallways.  Doctors, among the most data-driven professionals in the world, are embracing generative AI tools faster than anyone expected. Yet at the same time, they’re clear-eyed about their own readiness: they know ...;

With the UK Government recently inking deals with tech giants Open AI, Anthropic and Google to ‘enhance public services’, and the publication of ‘Fit for the Future’, a 10-year plan to improve the health system, it’s clear that the UK Government is pinning its hopes on AI’s potential to transform the nation’s health, productivity and prosperity.   Harnessing AI to ...;

In today’s fast-paced world, managing mental health has become a daily challenge for millions. But what if the very data you produce each day, your sleep patterns, screen time, or even your heart rate, could help you understand and improve your wellbeing? That’s where data analytics and AI therapy come together. By pairing self-tracking tools ...;

Alongside a redesign of care models to make full use of the amazing power of AI, healthcare providers must also address their ability to handle the data involved. Healthcare stands to benefit hugely from AI but those highly-sought gains in efficiency and patient outcomes will be harder to achieve if organisations persist with bolting on ...;

For years and years, healthcare has provided convenience, reminders, and easier accessibility to patient care, while sometimes it feels like it’s mechanical. Imagine a patient is managing diabetes; every morning, their app sends some message like “take your pills.” Looks very impressive, but has no context or no personalization at all. This results in a ...;

In healthcare, front desk staff serve as the heart of a practice’s daily operations. They greet patients, manage appointments, handle billing inquiries, and ensure a smooth flow of communication between staff and patients. But as patient volumes grow and administrative demands rise, it’s easy for front desk teams to feel overwhelmed. That’s where automated patient ...;

The shift from smart widgets to agentic workflows  Most organizations meet AI through a feature: a transcript button here, a summarizer there. Useful? Sure. Transformational? Not really. The bigger unlock is agentic AI—systems that don’t just predict or label, but that capture signals, decide with context, and then act inside your operations with auditable guardrails. ...;

Zingage has raised a $12.5 million seed round to build and AI platform for home healthcare. Bessemer Venture Partners led the round, with participation from TQ Ventures, South Park Commons, WndrCo, and executives from Ramp. The New York startup also officially launched Zingage Operator, an AI platform that manages the minute-to-minute work of delivering care ...;