Oracle Health this week announced that its Cerner Enviza life sciences division will work with John Snow Labs to develop a new artificial intelligence methodology to enhance computerized queries, or phenotyping, of digital patient data and clinical notes to support the U.S. Food and Drug Administration's Sentinel Initiative drug studies.

WHY IT MATTERS

The Sentinel Innovation Center, spearheaded by Mass General Brigham and Harvard Pilgrim Health Care Institute, selected Cerner Enviza to lead the team on the FDA's Multi-source Observational Safety Study for Advanced Information Classification Using NLP project, according to the announcement.

Sentinel's Active Risk Identification and Analysis system leverages EHR data aggregators, warehouses and networks to assess the safety of FDA-approved drugs under real-world conditions.

Manual analyses of clinical notes can be a barrier to understanding patient experiences at the population level, but NLP offers the opportunity to scale clinical data, the companies say.

The two-year MOSAIC-NLP project leverages the partners' expertise and experience with augmented intelligence to improve how the agency gleans pertinent medical product safety information from EHR data.

Cerner Enviza and John Snow intend to use AI to extract information from clinical notes to study the possible mental health side effects of the asthma drug montelukast as a use case. 

They'll also work with Oracle provider networks to demonstrate how machine learning can help accelerate the discovery and deployment of health insights and therapies.

"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," said Mike Kelly, global head of Cerner Enviza, in the statement.

"Connected technologies and unified data can accelerate innovation and, in turn, help providers realize better recommendations and outcomes for their patients," he added.

Children’s Hospital of Orange County, National Jewish Health and Kaiser Permanente Washington Health Research Institute are also supporting MOSAIC-NLP.

THE LARGER TREND

EHR is a rich data source that researchers have been using to analyze everything from diagnosing hypertension and personalizing Type 2 diabetes care to the time clinicians spend on documentation.

By automating certain processes, AI can help reduce clinician burnout. But machine learning and predictive analytics also hold promise in uncovering drivers of population health. 

In a discussion last year at HIMSS22 about workable automation strategies, digital transformation specialists focused on data governance in AI-enabled analytics and developing use cases. 

Jason Joseph, chief digital and information officer at Michigan-based BHSH System, stressed that it's important to use the right data in order to get the right insights.

"As we get more advanced with our clean, cleanliness of data, we start capturing more data, we start to get more and more precise to the point where it could become fully automated," he said.

With EHR data, manually gathering data for clinical decisions can be tedious and doctors may not always be able to find all the information they need. 

"Medical school is all about gathering information, learning about anatomy, physiology, disease states, and then applying that to humankind in order to get them to their goals and keep them well," said Dr. Nick Patel, chief digital officer at Prisma Health in South Carolina. 

"But when you throw a layer of EHR in there, you lose a lot of that because you're having to snip into how do you get all this information so you can make a good clinical decision?"

ON THE RECORD

"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," Dr. Rishi Desai, Mass General Brigham executive leadership team member for the Sentinel Innovation Center, said in the announcement.

Andrea Fox is senior editor of Healthcare IT News.
Email: afox@himss.org
Healthcare IT News is a HIMSS Media publication.

Tina Manoharan will offer more detail in the HIMSS23 session "AI and Data Interoperability: A Symbiotic Relationship for Healthcare." It is scheduled for Tuesday, April 18 at 4:15 p.m. - 5:15 p.m. CT at South Building, Level 4, room S401.