Beyond Large Language Models: Knit Health Unveils Med-BEAM, a World Model for Healthcare, Backed by $35M from NEA
Med-BEAM predicts what happens next for patients and how different interventions could change their trajectory,
Press Release Disclaimer: This is a press release distributed through the XPR Media network. It has not been independently verified by our newsroom.
![]()
Knit Health, a healthcare AI company building a foundational model to predict and improve patient care, today announced a $35 million Series A led by New Enterprise Associates, Inc. (NEA), with participation from Town Hall Ventures, SignalFire, and existing investors. The financing will accelerate the commercial deployment of Med-BEAM, Knit’s world model for healthcare, across health systems and other healthcare organizations.
This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20261116994393/en/
The co-founders of Knit Health (from left to right): Jonas Knecht, Co-CTO; Jonathan Kolstad, CEO; Maya Petersen, Chief Scientist; Ted Robertson, COO.
Healthcare’s most important information is often not written down. It lives in the decisions clinicians make: the orders they place, the referrals they send, the diagnoses they reach, and what happens next. This makes it difficult for large language models to understand not just what has happened to a patient, but where that patient is headed.
Med-BEAM is designed to solve that problem. Trained on billions of real healthcare decisions and hundreds of millions of longitudinal patient records, the model learns from clinical experience at scale. It builds a living model of each patient, predicting the care they are likely to need and showing how different interventions could change their trajectory.
The result is a new infrastructure layer for healthcare: clinical reasoning that can power applications across hospitals and health systems, life sciences companies, health technology companies, frontier AI labs, and ultimately, consumers.
“Healthcare still operates too often on what amounts to chance: which doctor you see, which day you arrive, which hospital you enter,” said Jonathan Kolstad, co-founder and CEO of Knit Health. “The best clinical judgment already exists in medicine. We’re building the intelligence layer that makes that judgment available for every patient, everywhere. Med-BEAM can understand where a patient is headed, compare possible paths forward, and help identify which choices are more likely to lead to a better outcome.”
To demonstrate the power of its world model approach, Knit compared Med-BEAM with a suite of frontier lab LLMs to measure how accurately models could predict the clinical actions that would occur for hospitalized patients over a 24-hour period. No outcome was nominated in advance, and no model was told where to focus. Med-BEAM was up to 4x more accurate, 100x faster, and 250x less expensive than the frontier models tested. It also demonstrated superior calibration, meaning its confidence more closely matched actual outcomes.
“Med-BEAM represents a fundamentally new clinical intelligence infrastructure,” said Blake Wu, Partner at NEA. “One underlying model can power dozens of critical workflows from care management and patient navigation to clinical trial recruitment, specialist scheduling, hospital-at-home, and treatment-response prediction. That’s what makes Knit Health’s approach so powerful: the intelligence is foundational, while the applications are nearly limitless.”
Knit was built from the beginning for healthcare’s highest standards of privacy, security, and clinical rigor. The company trains exclusively on data for which it has clear, documented rights, with all data fully de-identified before it reaches Knit. Unlike general-purpose language models, Med-BEAM’s predictions are calibrated against real-world clinical outcomes, allowing the system to measure how reliable a prediction is and identify when there is insufficient evidence to support confidence.
Knit’s mission is to build the intelligence layer healthcare runs on: a foundational model that any user, human or AI, can turn to work through healthcare’s hardest questions. This funding marks the next step toward that vision, accelerating Med-BEAM’s deployment across healthcare workflows and use cases.
About Knit Health
Knit Health is a healthcare AI company building a foundational model to predict and improve patient care. Its world model, Med-BEAM, learns from real clinical experience to predict what is likely to happen next for a patient and how different interventions could change that path. Trained on billions of healthcare decisions across hundreds of millions of patient records, Med-BEAM creates a living model of where a patient is today and what care they are likely to need next. Purpose-built for healthcare, Med-BEAM was designed from day one around rigorous privacy and security standards. Founded in 2025 by a team of scientists from the University of California, Berkeley, Knit has raised $46.6 million to date, including a $35 million Series A led by NEA with participation from Town Hall Ventures and Signal Fire, alongside seed and pre-seed funding from Frist Cressey Ventures, Uncork Capital, Moxxie Ventures, Coalition Operators, and The Aligned Fund. For more information, visit knit.health.
View source version on businesswire.com: https://www.businesswire.com/news/home/20261116994393/en/
Media gallery


