Columbia-led team develops open-source framework to accelerate health AI research
NEW YORK, NY -- A research team led by Columbia University has developed an open-source framework designed to streamline and accelerate artificial intelligence research using health data, addressing longstanding challenges in data standardization, reproducibility, and collaboration across institutions.
The framework, called MEDS, introduces both a standardized data format and a growing ecosystem of interoperable tools intended to support the development and evaluation of machine learning models using clinical data.
A study describing the framework was published in NEJM AI.
The researchers say the framework could help reduce technical barriers that currently slow health AI research and make it difficult for scientists to reproduce findings or compare models across studies and institutions.
“MEDS is a simple way to make all different sources of electronic health record (EHR) data look the same to your code, regardless of what hospital or clinic or EHR software system the data came from,” says Matthew McDermott, PhD, assistant professor of biomedical informatics at Columbia University and study leader. “MEDS lets us share code that we can use to train models on many different sites of care without needing to share sensitive patient data — and often without needing to even do the more challenging step of fully ‘harmonizing’ the data into a consistent clinical vocabulary. This infrastructure will allow researchers to spend less time rebuilding pipelines and more time answering clinically meaningful questions.”
Standardizing health data for clinical AI research
Electronic health record data are often stored in institution-specific formats that require extensive preprocessing before they can be used for AI development. According to the study authors, these inconsistencies can create significant duplication of effort, limit collaboration, and hinder reproducibility.
MEDS addresses these issues by providing a lightweight, extensible standard for representing longitudinal clinical data in machine learning workflows. The framework also includes open-source tooling that supports data transformation, preprocessing, benchmarking, and model development.
The authors emphasize that MEDS was designed specifically for AI and machine learning applications, complementing rather than replacing existing clinical data standards.
The framework is intended to support a broad range of use cases in biomedical AI research, including predictive modeling, representation learning, multimodal modeling, and large-scale benchmarking studies. Because the ecosystem is open source, researchers across academia, healthcare, and industry can contribute tools and extensions.
“The big successes in AI have always been driven by the community coming together and being able to collaborate, often in a decentralized, open-source manner, on tools, model parts, and ultimately ecosystems that let us build larger models that scale to massive datasets,” McDermott said. “These impressive results in MEDS are just reflecting the benefits you get when the community can share tools or abstract common parts of their pipelines out into a shared library and use them across everyone's data.”
The study also highlights the importance of reproducibility and transparency in health AI development as machine learning models increasingly move toward clinical deployment.
The researchers say they hope MEDS will foster broader collaboration across institutions and accelerate innovation in clinical AI while promoting more transparent and reproducible science. Already, MEDS has been adopted across 21 institutions spanning 12 countries.
###
Columbia University Irving Medical Center (CUIMC) is a clinical, research, and educational campus located in New York City. Founded in 1928, CUIMC was one of the first academic medical centers established in the United States of America. CUIMC is home to four professional colleges and schools that provide global leadership in scientific research, health and medical education, and patient care including the Vagelos College of Physicians and Surgeons, the Mailman School of Public Health, the College of Dental Medicine, the School of Nursing. For more information, please visit cuimc.columbia.edu.
Journal
NEJM AI
Method of Research
Computational simulation/modeling
Article Title
MEDS — An Emerging Data Standard and Ecosystem for Health AI Research
Article Publication Date
28-May-2026
Insilico Medicine to showcase AI-driven innovation at BIO 2026 International Convention
Company to deliver three presentations spanning AI drug discovery, quantum computing, and next-generation pipeline strategy
image:
BIO 2026
view moreCredit: BIO 2026
Cambridge, MA, May 29, 2025 — Insilico Medicine ( “Insilico”, HKEX:3696 ), a clinical-stage, generative AI–driven drug discovery company, today announced the company will showcase its latest advances in AI-driven drug discovery, quantum-enabled research, and clinical development through three featured speaking sessions at the BIO 2026 International Convention on June 22-25 at the San Diego Convention Center.
Led by Alex Zhavoronkov, Ph.D, founder , co-CEO and CBO of Insilico Medicine, the Insilico team will be meeting with biopharma partners, investors, and researchers to explore collaboration opportunities at Booth # 4021. At the event, Insilico will showcase the capabilities of its end-to-end Pharma.AI platform and latest pipeline.
As a recognized leader in generative AI–driven drug discovery, Insilico Medicine will present the following featured BIO 2026 speaking sessions:
ADCs, GLP-1s, and Beyond: How China is Impacting the 2026 BD Landscape Jun 22 3:00 PM - 4:00PM at 32AB
Quantum Computing in Drug Discovery June 22 4:15PM - 5:15PM at 28ABCDE
Strategic Innovation: Building Smarter Pipelines for Challenging Targets June 25 9:00 AM - 10:00 AM at 29AB
The synergy among AI-driven drug design (AIDD), quantum algorithms, and automation labs are becoming the next-gen engine redefining target identification and compound optimization. At the same time, de-risking early science and investments hinges on meticulous program design, early validation strategies, and milestone-driven execution. As a pioneer deeply embedding AI into drug discovery, Insilico Medicine will share unique insights from the intersection of cutting-edge tech and clinical translation.
“BIO 2026 International Convention is a premier event for fostering the collaborations that drive biotech innovation” said Alex Zhavoronkov, PhD, Founder, co-CEO and CBO of Insilico Medicine. “We look forward to engaging with industry leaders and demonstrating how our Pharma.AI platform, LifeStar 2 laboratory and MMAI Gym for Science are accelerating the discovery of novel therapeutics. Our goal is to forge partnerships that will help enable longer, healthier lives for people around the world.”
Since pioneering next-generation AI in drug discovery, Insilico Medicine has built an extensive therapeutic portfolio across a variety of therapeutic areas, rapidly advancing its internal R&D pipeline and setting a new standard for efficiency. While traditional early-stage drug discovery can take 2.5 to 4 years, Insilico has nominated 30 preclinical candidates at an average pace of just 12 to 18 months per program, synthesizing and testing only 60 to 200 molecules each—highlighting the exceptional capabilities of its AI-driven platform.
Among the company's clinical-stage programs, Rentosertib, the world's first AI-discovered novel-mechanism anti-fibrotic candidate, has completed Phase 2a proof-of-concept clinical trial, demonstrating promising efficacy trends and a favorable safety profile. ISM5411, the PHD1/2 inhibitor with best-in-class potential for treating inflammatory bowel disease (IBD) has completed 2 Phase 1 trials, showing good safety and gut-restrictedPK profile. Additionally, three of Insilico's anti-tumor programs have now reached the first-in-patient dosing stage, and interim results are expected to be shared in the near future.
Since founding in 2014, Insilico has published over 200 peer-reviewed papers. Leveraging sustained scientific breakthroughs at the intersection of biotechnology, artificial intelligence, and automation, Insilico ranked Top 100 global corporate institutions in Nature Index's "2025 Research Leaders: global corporate institutions for biological sciences and natural sciences publications".
About Insilico Medicine
Insilico Medicine is a pioneering global biotechnology company dedicated to integrating artificial intelligence and automation technologies to accelerate drug discovery, drive innovation in the life sciences, and extend healthy longevity to people on the planet. The company was listed on the Main Board of the Hong Kong Stock Exchange on December 30, 2025, under the stock code 03696.HK.
By integrating AI and automation technologies and deep in-house drug discovery capabilities, Insilico is delivering innovative drug solutions for unmet needs including fibrosis, oncology, immunology, pain, and obesity and metabolic disorders. Additionally, Insilico extends the reach of Pharma.AI across diverse industries, such as advanced materials, agriculture, nutritional products and veterinary medicine. For more information, please visit www.insilico.com
Frontiers wins two awards at the 2026 EPIC Awards for pioneering work on AI in publishing and research integrity
Frontiers wins a gold award and a silver award at the 2026 EPIC Awards of the Society for Scholarly Publishing – for a landmark whitepaper on AI in research and publishing, and a digital campaign making research integrity visible.
Frontiers
Frontiers has won a gold award and a silver award across two categories at the 2026 Excellence in Publishing, Information Technology & Communications (EPIC) Awards, presented by the Society for Scholarly Publishing (SSP) during its 48th Annual Meeting in Chula Vista, California, US, on 28 May 2026.
A roadmap for responsible AI use in research and publishing
Frontiers’ whitepaper Unlocking AI’s untapped potential: responsible innovation in research and publishing received the gold award in the Reports category. Published in December 2025, it is the first large-scale study to examine AI adoption, trust, training, and governance across authoring, reviewing, and editorial workflows.
Drawing on a global survey of 1,645 active researchers, the whitepaper found that 53% of peer reviewers already use AI tools. AI adoption is rising rapidly across the wider research community, reaching 87% among early-career researchers. Frontiers translates these findings into evidence-based policy recommendations for publishers, institutions, funders, and tool developers – a practical roadmap to align publishing policy with how researchers are already using AI, and to unlock AI’s full potential to strengthen scientific rigor, reproducibility, and trust.
Elena Vicario, Director of Research Integrity at Frontiers, said:
“The whitepaper shows that AI use in research is already happening, at scale, across every region and career stage. The question is whether our policies are keeping pace, and how we translate this momentum into stronger, more transparent, and more equitable research practices. Winning the gold award signals that the industry is ready to address that question now, and Frontiers is proud to be leading that conversation.”
Guardians of Science: making research integrity visible
AI-generated content, misinformation, and papermills are reshaping trust in science. Frontiers’ digital campaign, Guardians of Science: unveiling the human force behind research integrity, answers the question: who protects the scientific record, and how?
Led by Frontiers Brand team, the campaign received the silver award in the Narrative / Multidisciplinary Digital Projects category. Through an integrated multimedia experience combining video, editorial storytelling, and social-first distribution, the campaign spotlights our Research Integrity team and the advanced technology they use. Their expertise, judgment, and ethical oversight guide every review. A first-of-its-kind podcast-style interview with Frontiers AI Review Assistant, AIRA, makes complex detection technology accessible, human, and engaging. The “Day in the life” interview series brings our Research Integrity and Auditing teams into focus, affirming transparent, expert-led, and responsibly AI-enabled quality control as the bedrock of trust and credibility.
Gilbert De Gregorio, Director of Communications at Frontiers, said:
“The Guardians of Science campaign transformed the abstract concept of research integrity into compelling, human-centered stories. Winning the silver award demonstrates that trust has to be earned in plain sight. Giving a voice to our Research Integrity team – and even to our AI Review Assistant, AIRA – helped reframe conversations about research integrity, quality assurance, and the role of AI in publishing.”
Now in its second year, the EPIC Awards celebrate outstanding achievements in scholarly publishing and have drawn more than 98 entries in 2026. Frontiers' two awards recognize our work on two fronts: setting a roadmap for responsible AI use in research and publishing, and upholding research integrity. Together, they reinforce our commitment to making science open and trusted.
No comments:
Post a Comment