Research expected to help cull outcomes in claims and EHR data

By | December 15, 2018

The National Science Foundation has awarded a $ 224,793 grant to Vanguard Medical Technologies, an incubation firm, to find outcomes data for researchers.

The firm is charged with developing technology that will enable clinical trials to use artificial intelligence to dive into an electronic health records system and cull out useful data.

As regulatory bodies look to real-word evidence to improve the quality of care, pharmaceutical companies are exploring how to run studies to understand real-world impacts on clinical outcomes, according to the foundation. Too often, these companies find that outcomes are unavailable or inaccurate in claims and structured data within electronic health record systems.

“This award reflects advanced science in an area of critical need,” says Dan Riskin, MD, principal investigator on the project. “The ability to use real world outcomes in pragmatic clinical trials will lead to safer and better targeted care.”

Also See: AHRQ issues app challenge for patient-reported outcomes data

The overall goal of the project is to enable accurate EHR-based studies to support precision medicine, according to documents from the foundation.

National Science Foundation

National Science Foundation

“EHR-based subgroup analytics and comparative effectiveness studies will increasingly be used to augment regulatory and reimbursement approval,” the foundation contends. “These efforts require accurately recognizing clinical outcomes in real world scenarios. Studies attempting to identify real world outcomes, such as pain and disease-free survival, have shown low accuracy rates in claims and EHR discrete data. This proposal aims to accurately detect challenging outcomes from EHR data using advanced semantic technologies to achieve safer and more effective use of real world evidence in clinical practice.”

The project’s first phase will create an application to extract clinical outcomes from EHR data, using national language processing technology to dive into the record for exposure, intervention and outcome data, then validate the developed outcome detection engine using de-identified outcome clinical data to assess accuracy of featured data extraction and inferred outcomes.

After completing the program, Vanguard Medical Technologies will spin off the new technology to Verantos, a contract research company, to run clinical trials.

More information on the National Science Foundation’s small business grant programs is available here.

Joseph Goedert

Joseph Goedert

Goedert is senior editor of Health Data Management, a SourceMedia publication.

More from this Author

Health Data Management: Feed