Cerner Enviza, an Oracle company, now works with John Snow Labs to support the US Food and Drug Administration’s drug safety Sentinel initiative. By developing artificial intelligence (AI) tools aimed at extracting critical information from clinical notes in electronic health records (EHR), Oracle and John Snow will help the FDA better understand the impact of drugs on large populations. Looking at the asthma drug montelukast and its potential mental health side effects, this two-year project will show how the use of machine learning and natural language processing (NLP) technologies with unstructured data can help fill knowledge gaps.
Cerner Enviza leverages decades of life sciences experience spanning commercial, real-world, clinical, and regulatory research. This includes working with a broad range of Oracle vendor networks to accelerate the discovery, development, and delivery of healthcare discoveries and therapies. Known for its AI and NLP in healthcare, John Snow Labs is the developer of the Spark NLP library. Together, Cerner Enviza and John Snow Labs will develop a new methodology to improve computerized interrogation or phenotyping of digital patient data and clinical notes to support pharmacoepidemiology.
Cerner Enviza, who will lead the team, was selected by the Sentinel Innovation Center, which is led by Mass General Brigham and the Harvard Pilgrim Health Care Institute.
“Developing and evaluating tools that can enhance our ability to leverage unstructured EHR data is a key strategic priority for the Sentinel Innovation Center. We look forward to this new relationship and exciting initiative led by Cerner Enviza,” said Rishi Desai, Ph.D., member of the leadership team at Mass General Brigham, Sentinel Innovation Center.
Traditional manual methods of analyzing clinical notes can often be a bottleneck to fully understand the symptoms and outcomes patients are experiencing at a population level. However, advances in AI offer scalable and transportable NLP processes.
“This is an incredible opportunity to work with these extraordinary leaders to leverage Oracle’s de-identified EHR data to transform unstructured clinical notes into validated and actionable data for physicians and researchers,” said Mike Kelly, Global Head, Cerner Enviza. “Connected technologies and unified data can accelerate innovation and, in turn, help providers deliver better recommendations and outcomes for their patients.”
“We are thrilled to be working with Cerner Enviza to apply NLP to such an important real-world evidence project,” said David Talby, CTO, John Snow Labs. “We are honored by the Sentinel Innovation Center’s vote of confidence in our collective ability to explore this use case. Together, Cerner Enviza and John Snow Labs have the right expertise, data and technology to make this happen.”
The project, known as the Multi-Source Observational Safety Study for Advanced Information Classification Using NLP (MOSAIC-NLP), is also supported by the participation of the Children’s Hospital of Orange County, National Jewish Health and the Kaiser Permanente Washington Health Research Institute, the clinical results will provide expertise and advice.
