Funding & VC

Knit Health's $35 Million Series A Funds Med-BEAM Rollout

Knit Health raised $35 million in a Series A led by New Enterprise Associates. Its Med-BEAM model forecasts care paths and reported stronger clinical-action predictions.

By Daniel Okafor

3 min read

Knit Health Raises $35 Million Series A To Deploy Med-BEAM Healthcare Model
Knit Health Raises $35 Million Series A To Deploy Med-BEAM Healthcare ModelFree-Photos / pixabay

What's News

  • Knit Health raised $35 million in Series A funding, bringing total funding to $46.6 million.
  • New Enterprise Associates led the round; Town Hall Ventures and SignalFire participated.
  • Founded in 2025, Knit Health trained Med-BEAM on billions of decisions across hundreds of millions of patient records.
  • Knit Health reported up to four times greater accuracy, 100 times faster performance and 250 times lower cost than tested models.
  • Knit Health's 24-hour evaluation measured clinical-action prediction, not improved patient outcomes.

By Daniel Okafor

Knit Health has raised $35 million in a Series A round. The deal brings the company's total funding to $46.6 million.

New Enterprise Associates led the investment. Town Hall Ventures, SignalFire and existing investors also participated. Knit Health will use the proceeds to accelerate commercial deployment of Med-BEAM. The AI model predicts patients' care needs and evaluates how different interventions could affect their trajectories.

What does the $35 million fund?

Scientists from the University of California, Berkeley founded Knit Health in 2025. The company develops models that learn from clinical decisions and longitudinal patient records, which follow care over time.

Knit Health trained Med-BEAM on billions of healthcare decisions across hundreds of millions of patient records. According to the company, the model uses orders, referrals, diagnoses and subsequent events to estimate a patient's likely path.

In Knit Health's design, Med-BEAM does more than forecast the next event. Knit Health intends the model to assess likely care needs and compare possible interventions against a patient's trajectory. The company is positioning the technology as infrastructure across health systems, life sciences, health technology and other organizations.

Blake Wu, partner at NEA, said:

“Med-BEAM represents a fundamentally new clinical intelligence infrastructure. 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.”

What does the benchmark actually show?

In a company-reported comparison, Knit Health evaluated how accurately Med-BEAM and frontier language models predicted clinical actions for hospitalized patients over 24 hours. Knit Health said Med-BEAM outperformed the models tested on three measures:

  • Up to four times more accurate.
  • 100 times faster.
  • 250 times less expensive.

The findings support a narrower conclusion than proof of better care. Knit Health said the results concern prediction of clinical actions in the reported evaluation, rather than evidence of improved patient outcomes from deployment.

Knit Health also reported better calibration, meaning the model's confidence more closely reflected observed outcomes. That metric addresses forecast certainty separately from speed, cost and accuracy.

How does Knit Health handle patient data?

Knit Health says it trains only on data for which it has documented rights. The company also says it de-identifies information before it reaches its systems. Those controls address separate points in Knit Health's process: documented rights for training data and de-identification before model access.

Jonathan Kolstad, co-founder and CEO of Knit Health, said:

“Healthcare still operates too often on what amounts to chance: which doctor you see, which day you arrive, which hospital you enter.

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.”

Where will the funding take Med-BEAM?

The Series A will support deployment across the workflows that Knit Health and NEA identified:

  • Care management.
  • Patient navigation.
  • Clinical trial recruitment.
  • Specialist scheduling.
  • Hospital-at-home.
  • Treatment-response prediction.

Alongside that rollout, Knit Health will continue developing a model intended to help users assess likely care needs and compare possible interventions.

The next test for Knit Health is operational, not another model claim: whether Med-BEAM can move from the company's 24-hour benchmark into live workflows. The funding supports that rollout, but the reported results still establish prediction performance, not improved patient outcomes.

Source: pulse2.com

Share this article:

More from Daniel Okafor

Daniel Okafor

Show full bio

Correspondent covering money, funding and market shifts around entrepreneurship, startups and venture funding at Business Bearings.

2,186 articles

Related articles

« Previous articleNext article »