FDA Sentinel Initiative engages Cerner Enviza and John Snow Labs to advance the use of natural language processing in pharmacoepidemiology studies
Cerner Enviza, an Oracle company, in association with John Snow Labs has been chosen by the FDA Sentinel Innovation Center to develop machine learning and natural language processing tools to improve the FDA’s understanding of the impact of medications in large, real-world populations using electronic health record (EHR) data.
On April 10, 2023, Oracle issued a press release announcing that its company Cerner Enviza, along with John Snow Labs, has been chosen by the United States Food and Drug Administration (FDA) to innovate artificial intelligence (AI) tools for the FDA drug safety Sentinel Initiative. The collaborators will progress machine learning (ML) and natural language processing (NLP) technologies to extract real-world data (RWD) from clinical notes within EHRs to demonstrate the validity of structured, semi-structured, and unstructured EHR RWD and improve the identification of study outcomes and covariates for use in pharmacoepidemiologic studies.
The 2-year use case study, called the Multi-source Observational Safety Study for Advanced Information Classification Using NLP (MOSAIC-NLP) project, will evaluate the association between the asthma drug, montelukast, and adverse events related to mental health in patients with asthma. MOSAIC-NLP will be led by Cerner Enviza and will also be supported by the clinical expertise of the Children’s Hospital of Orange County, National Jewish Health, and Kaiser Permanente Washington Health Research Institute.
The Sentinel System is the FDA’s national electronic system that, by harnessing RWD sources, has transformed the way researchers monitor the safety of FDA-regulated medical products since its launch in 2008. Mass General Brigham and Harvard Pilgrim Health Care Institute head the Sentinel Innovation Center, a testbed for exploring innovative study methods.
“Development and evaluation of tools that can enhance our ability to utilize unstructured EHR data is a key strategic priority for the Sentinel Innovation Center,” asserted Rishi Desai, Mass General Brigham executive leadership team member, Sentinel Innovation Center. “We look forward to this new relationship and exciting initiative led by Cerner Enviza.”
Cerner Enviza brings to the collaboration one of the largest and most comprehensive EHR databases in the US, and decades of life science expertise. John Snow Labs is renowned for its healthcare AI and NLP prowess. Together, in the MOSAIC-NLP project, they will develop a new methodology to demonstrate how the use of ML and NLP technologies within deidentified linked EHR and claims data may help fill gaps in knowledge and help the FDA carry out pharmacoepidemiology studies to better understand the effects of medicines in large populations.
Global Head of Cerner Enviza, Mike Kelly, commented: “This is an incredible opportunity to work with these exceptional leaders to use Oracle’s de-identified EHR data to help transform unstructured clinical notes into validated and useable data for physicians and researchers. Connected technologies and unified data can accelerate innovation and, in turn, help providers realize better recommendations and outcomes for their patients.”
John Snow Labs CTO David Talby said: “We are thrilled to team with Cerner Enviza to apply NLP in such an important real-world evidence project”. John continued: “We’re honored by the Sentinel Innovation Center’s vote of confidence in our joint ability to help investigate this use case. Together, Cerner Enviza and John Snow Labs have all the right expertise, data, and technology to make it happen.”
