Knit Health, a startup building an artificial intelligence model that predicts what care patients will need next, has raised a $35 million Series A led by NEA. Town Hall Ventures, SignalFire and existing investors also joined the round, the company said in a statement Monday.

Chief executive Jonathan Kolstad first disclosed the funding to Will Maddox at Axios Pro. The money will go toward rolling out Med-BEAM across health systems and other healthcare groups. Knit calls the model a “world model for healthcare.”

Scientists from the University of California, Berkeley founded Knit in 2025. The company has raised $46.6 million so far. Earlier seed and pre-seed backers include Frist Cressey Ventures, Uncork Capital, Moxxie Ventures, Coalition Operators and The Aligned Fund.

Learning from clinical decisions, not just notes

According to Knit, much of healthcare’s key information never makes it into clinical notes. It sits in the orders, referrals and diagnoses that clinicians make, and in what happens next. That makes it hard for large language models to tell where a patient is heading, the company said.

What does Med-BEAM predict?

Med-BEAM learns from billions of real healthcare decisions and hundreds of millions of patient records that follow people over time. It predicts the care a patient is likely to need and shows how different treatments could change their course.

Knit said it trains only on data it has clear, documented rights to use, and that all of that data is fully de-identified before it reaches the company. The model checks its predictions against real clinical outcomes, which lets it flag when there is too little evidence to be confident.

“Healthcare still operates too often on what amounts to chance: which doctor you see, which day you arrive, which hospital you enter,” Kolstad said in the statement.

How Med-BEAM compares with frontier models

How did Med-BEAM perform against other AI models?

Knit tested Med-BEAM against a group of models from frontier AI labs. Each had to predict the clinical actions for hospitalized patients over the next 24 hours. Knit said it did not pick the outcome in advance.

Med-BEAM was up to four times more accurate, 100 times faster and 250 times cheaper than the models tested, the company said. Knit added that the model’s confidence matched real outcomes more closely.

Blake Wu, a partner at NEA, said one model could power “dozens of critical workflows.” He listed care management, patient navigation, clinical trial recruitment, specialist scheduling, hospital-at-home care and treatment-response prediction.

Este artículo fue escrito con la asistencia de IA.
News Factory APP - noticias agénticas para impulsar tu SEO y AEO.