por John R. Fischer
, Senior Reporter | November 21, 2023
Google Ventures, General Catalyst, and Inception Health have poured $4 million into Layer Health, a new startup developing AI solutions for deciphering and leveraging unstructured data to improve patient care and healthcare practice operations.
A spinoff of the Massachusetts Institute of Technology, Layer Health has already developed its first product, Distill, which integrates with hospital systems and workflows and uses AI to analyze clinical notes, lab results, and other medical documentation to extract value from their unstructured data. It then applies these insights to perform clinical, administrative, and research tasks, including registry submissions, quality measurement, the curation of real-world evidence, clinical document improvement, and revenue cycle management.
"The most nuanced and valuable data is unstructured and hard to understand, often inaccessible without a team of nurses and data scientists. This issue consumes significant resources across the healthcare ecosystem and makes it difficult to scale new businesses and health innovations," said Layer Health in a statement.
Here is a breakdown of Distill's capabilities:
Eliminates the need for labeling – Using large language models, Layer Health can produce accurate results from raw unstructured data, reducing extraction and value establishment processes from months-long efforts to tasks that can be completed in a day.
Adapts based on customer interactions – Creates customer-specific models fine-tuned for specific use cases.
Provides transparency – To reduce mistakes made by AI, Layer Health provides customers with evidence for every prediction it makes to verify the accuracy of its results. It has a clinical team that tests its models’ effectiveness using different data sets and clinical use cases, and its research team is currently developing methods to ensure it is safe to use.
The solution is undergoing beta testing, with customers using it for various purposes, including xCures, for creating more precise cancer treatment recommendations and efficient clinical trial matching; and the Froedtert & the Medical College of Wisconsin health network, to identify specialties and areas that require improvements.
Leading Layer Health will be David Sontag as CEO. Sontag is an expert on AI for healthcare and an MIT professor with over 100 published papers on AI and machine learning.
Other founders include Divya Gopinath, an ML engineer and architect specializing in trustworthy AI, and MIT researcher; Luke Murray, an expert in human-computer interaction who built MedKnowts while a researcher at MIT and Know Your Data at Google; Monica Agrawal, a Ph.D. graduate from MIT specializing in large language models; and Steven Horng, an emergency physician and clinical informatician at Harvard Medical School. Back to HCB News