
A multi-hospital initiative sparked by the COVID-19 crisis has shown that, by working together, institutions in any industry can develop predictive AI models that set a new standard for both accuracy and generalizability.
Published today in Nature Medicine, a leading peer-reviewed healthcare journal, the collaboration demonstrates how privacy-preserving federated learning techniques can enable the creation of robust AI models that work well across organizations, even in industries constrained by confidential or sparse data.
Usually in AI development, when you create an algorithm on one hospital's data, it doesn't work well at any other hospital, said Dr. Ittai Dayan, first author on the study, who led AI development at Mass General Brigham and this year founded healthcare startup Rhino Health.
But by developing our model using federated learning and objective, multimodal data from different continents, we were able to build a generalizable model that can help frontline physicians worldwide, he said.
Other large-scale federated learning projects are already underway in the healthcare industry, including a five-member study for mammogram assessment and pharmaceutical giant Bayer's work training an AI model for spleen segmentation.
Beyond healthcare, federated learning can help energy companies analyze seismic and wellbore data, financial firms improve fraud detection models, and autonomous vehicle researchers develop AI that generalizes to different countries' driving behaviors.
Federated Learning: AI Takes a Village Companies and research institutions developing AI models are typically limited by the data available to them. This can mean that smaller organizations or niche research areas lack enough data to train an accurate predictive model. Even large datasets can be biased by an organization's patient or customer demographics, specific data-recording methods or even the brand of scientific equipment used.
To gather enough training data for a robust, generalizable model, most organizations would need to pool data with their peers. But in many cases, data privacy regulations limit the ability to directly share data - like patient medical records or proprietary datasets - on a common supercomputer or cloud server.
That's where federated learning comes in.
Dubbed EXAM (for EMR CXR AI Model), the new study in Nature Medicine - led by Mass General Brigham and NVIDIA - brought 20 hospitals across five continents together to train a neural network that predicts the level of supplemental oxygen a patient with COVID-19 symptoms may need 24 and 72 hours after arriving to point-of-care settings like the emergency department. It's among the largest, most diverse clinical federated learning studies to date.
Many Hands Make AI Work Federated learning enabled the EXAM collaborators to create an AI model that learned from every participating hospital's chest X-ray images, patient vitals, demographic data and lab values - without ever seeing the private data housed in each location's private server.
Every hospital trained a copy of the same neural network on local NVIDIA GPUs. During training, each hospital periodically sent only updated model weights to a centralized server, where a global version of the neural network aggregated them to form a new global model.
It's like sharing the answer key to an exam without revealing any of the study material used to come up with the answers.
The results of the EXAM initiative show it's possible to train high performing and generalizable AI models in healthcare without private identifiable data exchanging hands, thus upholding data privacy, said Dr. Brad Wood, coauthor and director of the NIH Center for Interventional Oncology and Chief of Interventional Radiology at the NIH Clinical Center.
The findings are impactful well beyond this cross-hospital model for COVID-19 predictions, and showcase federated learning as a promising solution for the field in general, he continued. This provides the framework toward more effective and compliant big data sharing, which may be required to realize the potential of AI deep learning in medicine.
The global EXAM model, shared with all participating sites, resulted in a 16 percent improvement of the AI model's average performance. Researchers saw an average increase of 38 percent in generalizability when compared to models trained at any single site.
Each participating hospital saw improved performance with the global federated learning model (green), compared to the model trained only on local data (blue). Figure originally published in Nature Medicine. The performance boost was especially dramatic for hospitals with smaller datasets, visible in the chart above.
Federated learning allows researchers all over the world to collaborate on a common objective: to develop a model that learns from and generalizes to everyone's data, said Sira Sriswasdi, co-director of the Center for AI in Medicine at Chulalongkorn University and King Chulalongkorn Memorial Hospital in Thailand, one of the 20 hospitals that collaborated on EXAM. With NVIDIA GPUs and the NVIDIA Clara software, participating in the study was an easy process that yielded impactful results.
Hospitals, Startups Pursue Further EXAMination Bringing together collaborators across North and South America, Europe and Asia, the original EXAM study took just two weeks of training to achieve high-quality prediction of patient oxygen needs, an insight that can help physicians determine the level of care a patient requires.
Since then, its collaborators validated that the AI model may generalize and perform well in settings independent from sites that helped build and train the model. Three additional hospitals in Massachusetts - Cooley Dickinson Hospital, Martha's Vineyard Hospital and Nantucket
Most recent headlines
05/01/2027
Worlds first 802.15.4ab-UWB chip verified by Calterah and Rohde & Schwarz to be ...
04/08/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
04/07/2026
April 7 2026, 19:00 (PDT) Detective Conan: Fallen Angel of the Highway Opens in...
01/06/2026
January 6 2026, 05:30 (PST) Dolby Sets the New Standard for Premium Entertainment at CES 2026
Throughout the week, Dolby brings to life the latest innovatio...
02/05/2026
Dalet, a leading technology and service provider for media-rich organizations, t...
01/05/2026
January 5 2026, 18:30 (PST) NBCUniversal's Peacock to Be First Streamer to ...
15/04/2026
Open Broadcast Systems has announced that BBC World Service has selected its IP ...
15/04/2026
LiveU has announced an expansion of its collaboration with Sony Corporation, add...
15/04/2026
Ateme has announced a collaboration with NVIDIA to support live Apple Immersive ...
15/04/2026
The Professional Fighters League (PFL) has announced a multi-year partnership renewal with DAZN DACH, covering Germany, Switzerland, Austria, Liechtenstein, and...
15/04/2026
Canon U.S.A. (NAB Booth C3825) today took the lid off of the CINE-SERVO 40-1200m...
15/04/2026
Panasonic Video and Audio Systems North America and NEP Group will demonstrate a...
15/04/2026
For the fourth year running, independent analysts found businesses across all industries and verticals pay roughly the same amount in fees as they spend on stor...
15/04/2026
The Soccer Tournament (TST) has announced a media rights deal with NBC Sports to...
15/04/2026
JB&A will host the Pre-NAB 2026 Technology Event on April 17-18 at Flamingo Las Vegas, ahead of NAB Show. The event features hands-on demonstrations and technic...
15/04/2026
The Sennheiser Group will exhibit at NAB Show 2026 (Booth 4931, Central Hall), with demonstrations from Sennheiser, Neumann, and Merging across three areas: Rel...
15/04/2026
NAB Show 2026 will take place April 18-22 at the Las Vegas Convention Center, wi...
15/04/2026
AI-Media has announced the LEXI Text Encoder and LEXI Voice Encoder at NAB Show 2026, the company's first new encoder hardware release in more than a decade...
15/04/2026
Italian camera support manufacturer Cartoni will introduce several new products at NAB Show 2026 (Booth C6540, Central Hall), including the Master 30 OB fluid h...
15/04/2026
Lawo and swXtch.io have announced a memorandum of understanding at NAB Show 2026, under which Lawo will explore incorporating swXtch.io's groundSwXtch softw...
15/04/2026
CacheFly will exhibit at NAB Show 2026 (Booth W3129, April 19-22, Las Vegas Convention Center), showcasing three new additions to its content delivery platform:...
15/04/2026
Synamedia has announced GO Shorts, a new module within its Synamedia Go OTT platform that uses AI to convert an operator's existing content library into a s...
15/04/2026
The NAB Show kicks off on Saturday, and the SVG and SVG Europe editorial teams a...
15/04/2026
AJA Video Systems has announced an agreement to acquire Comprimato, a live video encoding and processing software company. The deal will unite the two companies...
15/04/2026
Prime Video Sports' NBA Playoffs coverage, which includes the entire SoFi NB...
15/04/2026
Just announced, the SDE standard provides a unified method and file format to ensure consistent and reliably comparable noise predictions
Sports and entertainm...
15/04/2026
From immersive storytelling to laugh-out-loud comedies, podcasts are booming in ...
15/04/2026
Books have always moved with us, whether tucked in our bags or humming in our he...
15/04/2026
For many artists, independent venues are where music careers begin and fan communities take shape. Independent venue operators work hard every day to keep local...
15/04/2026
From gripping thrillers to poignant memoirs, the 21st century has had no shortage of unforgettable books. To celebrate the standout storytelling of our modern e...
15/04/2026
Vintage broadcast experts release second plug-in
Telsie T is the second plug-in to be released by SonicWorld, a German audio company who specialise in servi...
15/04/2026
Includes eight free UAD plug-ins
Universal Audio's latest bundle brings together a selection of their renowned plug-ins and virtual instruments, and is ...
15/04/2026
Maximum uptime for broadcasters: Rohde & Schwarz launches R&S BroadcastShield at...
15/04/2026
Image courtesy of MD Helicopters...
15/04/2026
Virginia Gov. Abigail Spanberger, L3Harris VP Mark Farley, and state and local l...
15/04/2026
U.S. Space Forces Ground-Based Optical Sensor System upgrade at the Maui Space S...
15/04/2026
NBCU-Versant notches 13.1% of TV viewing in February, its best since August 2024...
15/04/2026
New data reveals older Kiwis are financially resilient, loyal to local products,...
15/04/2026
aconnic AG (ISIN: DE000A0LBKW6), Munich, announces the market launch of the ACCE...
15/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/04/2026
Evergent introduces its Agentic Revenue Orchestration Platform, transforming how subscription businesses across direct-to-consumer streaming, pay-TV, telecommun...
15/04/2026
Harmonic's XOS Media Processor Delivers Exceptional Video Quality to More than Half of U.S. Public Media Viewership
Harmonic (NASDAQ: HLIT) today announce...
15/04/2026
LONGMONT, COLORADO, APRIL 15, 2026 DPA Microphones N Series Digital Wireless System users in North America can now take full advantage of the system's exc...
15/04/2026
Cobalt Iron, a leading provider of SaaS-based enterprise data protection, today announced the launch of Compass Tape Gateway (CTG), a transformative enhancemen...
15/04/2026
Disguise to Showcase Cutting-Edge Experience Tech for Sports, Broadcast and More...
15/04/2026
Arooj Aftab Makes the Music She Wants to Hear The singular artist explores the juxtaposition of grief and joy, dark and light, in her distinctive sound.
Apri...
15/04/2026
Share
Copy link
Facebook
X
Linkedin
Bluesky
Email...
15/04/2026
Interra Systems, a provider of end-to-end quality assurance solutions for the digital media industry, is proud to announce its central role in the digital trans...