Layer Health is a healthcare AI company that spun out of MIT, and it is backed by $4 million in funding from GV (Google Ventures), General Catalyst, and Inception Health. The company’s goal is to solve the information problem in healthcare.
This information problem begins the moment a patient visits a health institution. And every interaction generates a trail of breadcrumbs, including clinical notes, lab results, and patient messages. After being combined, these breadcrumbs tell a rich story of a patient’s health journey and clinical care.
But the most nuanced and valuable data is unstructured, hard to understand, and often inaccessible without a team of nurses and data scientists. This issue consumes significant resources across the healthcare ecosystem and makes it harder to scale new businesses and health innovations.
Layer Health’s first product, Distill, handles the information problem using AI to quickly perform any clinical, administrative, or research task requiring unstructured data chart review. And this includes registry submissions, quality measurement, curation of real-world evidence, clinical document improvement, and revenue cycle management.
Distill integrates into existing products and workflows, ingesting clinical notes and analyzing them at scale. Behind the scenes, Layer Health’s machine learning (ML) algorithms utilize the power of large language models (LLMs) to deliver accurate results without the need for labeled data, reducing development time from months to as little as a day. And Distill also learns and adapts from customer interactions, creating highly efficient customer-specific models fine-tuned for specific use cases.
A number of beta customers are using Distill, and the company is excited to onboard more soon.
1.) xCures – a health technology company with a rich clinical data repository – uses Distill to organize and structure health data for more precise cancer treatment recommendations and efficient clinical trial matching. And using the company’s language models trained and validated on xCures’ unique data, the company can more accurately extract intricate and nuanced details from patient medical records. Distill stands to expedite xCures significantly’ and their customers’ workflows in curating real-world evidence, ultimately enhancing patient care.
2.) The Froedtert & the Medical College of Wisconsin health network utilizes Distill to support quality improvement efforts. And the company’s AI platform will supercharge the organization’s nurse abstraction team during chart review, enabling them to quickly and effectively find and submit data to clinical registries. Clinical registries are essential for benchmarking across clinical specialties and identifying areas for improving the quality of care.
Safely deploying AI in healthcare is of the utmost importance – going well beyond security and privacy. The company’s previous work has given the company both deep expertise and humility. We believe that LLMs, although incredibly powerful, are not a panacea for healthcare and that AI will make mistakes. This is why they are building transparency into Distill from the start.
For example, the platform enables customers to understand the evidence for every prediction and they have a clinical team dedicated to validating our models across diverse datasets and clinical use cases. And the company’s research team – at the forefront of advancing AI in healthcare – is also developing the methods necessary to ensure AI safety.
The members of the Layer Health team have worked together for nearly a decade, earning recognition as leaders in AI and ML. With ties to MIT and Harvard, the team has been at the forefront of using LLMs to solve the information problem for healthcare systems, providers, payers, and researchers. The founding team includes:
– David Sontag is a CEO, a leader in AI for healthcare, and an MIT professor with over 100 published papers in AI and ML.
– Divya Gopinath, an ML engineer and architect focused on trustworthy AI, was previously a founding engineer at TruEra and a researcher at MIT.
– Luke Murray is an expert in human-computer interaction who previously built MedKnowts while a researcher at MIT and Know Your Data at Google.
– Monica Agrawal is a pioneer in LLMs and recently received a PhD from MIT, who previously built some of the first ML models for Flatiron Health.
– Steven Horng is an emergency physician and clinical informatician at Harvard Medical School who has been deploying ML in live clinical settings for over 15 years.
