The American Cancer Society (ACS) and Layer Health have announced a multi-year collaboration that will leverage artificial intelligence to enhance broad cancer research efforts, building upon the foundation of a successful breast cancer pilot program that has already demonstrated promising results.
The partnership will utilize Layer Health’s AI-powered data abstraction platform to extract clinical information from thousands of medical charts of patients enrolled in ACS research studies, including the Cancer Prevention Study-3, which involves 300,000 participants.
Before expanding to other cancer types, the collaboration was initially tested in a breast cancer patient pilot program. According to the press release, Layer Health’s platform demonstrated exceptional performance, “pulling complex concepts from patient charts with an accuracy of 95-100% on all pilot variables, beating human performance.”
This high level of accuracy suggests significant potential for accelerating breast cancer research specifically, which remains one of the most common cancer types affecting women globally.
“We are excited to work with Layer Health to streamline and scale our data abstraction process,” said Dr. Alpa Patel, Senior Vice President of Population Science, American Cancer Society. “This collaboration will help us accelerate our research and generate more meaningful insights that can drive progress in the fight against cancer.”
The collaboration aims to overcome significant challenges in cancer research. Traditionally, gathering information from patient medical records has been labor-intensive and time-consuming, relying heavily on manual effort. Previous machine learning approaches struggled with scalability and couldn’t effectively generalize across records from different hospital systems.
Layer Health’s platform uses large language models (LLMs) specifically designed for healthcare to analyze patients’ longitudinal medical records and answer complex clinical questions. The system provides evidence-based answers with direct quotes from patient charts, prioritizing transparency and avoiding the “hallucination” problem sometimes seen with other LLMs.
“This collaboration with the American Cancer Society marks a significant milestone in how technology can support the fight against cancer,” said Dr. David Sontag, CEO, Layer Health. “We are proud to provide a solution that not only streamlines the research process but also empowers organizations like the ACS to scale their insights and accelerate their groundbreaking work.”
