TheAmerican Cancer Society (ACS) and healthcare AI company Layer Health announced a multi-year collaboration aimed at using large language models (LLMs) to expedite cancer research.
ACS will use Layer Health’s LLM-powered data abstraction platform to pull clinical data from thousands of medical charts of patients enrolled in ACS research studies.
Those studies include the Cancer Prevention Study-3, a population study of 300,000 participants among whom several thousands have been diagnosed with cancer and provided their medical records.
According to the company, Layer Health's platform will provide data in less time with the aim of improving the efficiency of cancer research and allowing ACS to obtain deeper insights from medical records.
Layer Health’s AI platform is intended specifically for healthcare to examine a patients’ longitudinal medical record and answer complex clinical questions, using an evidence-based method aimed at justifying every answer with direct quotes from the chart.
This plan prioritizes transparency and explainability and removes the problem of “hallucination” that is periodically observed with other LLMs, the companies said.
"Abstracting high-quality real-world data from medical records has been one of the most significant bottlenecks in cancer research," David Sontag, CEO Layer Health, told MobiHealthNews.
"Traditional manual abstraction is slow, costly and highly variable, while past AI approaches struggled with scalability and accuracy. Our platform is designed to overcome these limitations by reasoning over entire patient histories and justifying every extraction with direct evidence from the record. By bringing this capability to ACS’s groundbreaking research, we’re not just improving efficiency, we’re enabling a new depth of discovery that simply wasn’t possible before."
THE LARGER TREND
Other companies in the medical records space includeDigitalOwl, a company that uses natural language processing to help analyze and summarize EHRs. The company collaborated in 2024 with ExamOne, a Quest Diagnostics company, to improve efficiency of record retrieval and analysis through DigitalOwl’s View product.
By using proprietary generative AI technology, DigitalOwl provides insurance and legal professionals with the ability to rapidly and accurately evaluate medical records, aiming to reduce the time spent on manual reviews.
Pocket Health is a platform that enables patients to access their medical imaging and other health records. In 2024, the company secured $33 million in an all-equity Series B funding round led by Round13 Capital. They used the new capital to expand its workforce and scale its offerings across the U.S. and Canada.