By clicking “Accept All Cookies”, you agree to the storing of cookies on your device to enhance site navigation, analyze site usage, and assist in our marketing efforts. View our Privacy Policy for more information.
AI and ML
Extract Insights from EHRs
NLP

Machine Learning (ML) and Natural Language Processing (NLP) to Extract Actionable Insights from Provider Notes in EHR

Learn more about how Clinovera worked with the Division of Endocrinology, Diabetes and Hypertension at a leading academic medical center to develop and validate new NLP technology to extract valid medical information from EHRs.
Natural Language Processing in Healthcare
Published on
September 27, 2023

Learn more about how Clinovera worked with the Division of Endocrinology, Diabetes and Hypertension at a leading academic medical center to develop and validate new NLP technology to extract valid medical information from EHRs.

About the Client

  • Leading Academic Medical Center
  • Business: Division of Endocrinology, Diabetes and Hypertension
  • Summary: Creating a solution using NLP to successfully analyze narrative EHR data in the care process 
  • Services: Artificial Intelligence and Machine Learning, Natural Language Processing, Extract Insights from EHRs

Description

EHR data plays an ever more critical role in monitoring and improving the quality of care, conducting longitudinal studies, and designing clinical trials. One of the main challenges for healthcare organizations is that a significant amount of valuable data is found in narrative documents, such as provider notes or radiology reports.

Clinovera understands that natural language processing can illustrate complex concepts that represent the critical next frontier in the analysis of EHR data. Several important examples of complex concepts where NLP technologies could be beneficial include the decline of treatment by patients, discussion of bariatric surgery between patients with obesity and their clinicians, and documentation of smoking status. 

As an additional step, our client intends to overlay insights extracted from unstructured narratives with structured information in the patient record. For example, the NLP and ML algorithms may identify that a provider has recommended a specific procedure – such as bariatric surgery. The patient record structured content may help determine if the patient followed up on the provider’s recommendations.

Results

The Clinovera approach harnesses the power of natural language processing (NLP) to successfully analyze the client’s narrative EHR data, enabling the improvement of identification of diagnoses, medications, and other concepts. Our solution establishes connections between these elements in the patient record – to improve overall care.

Weekly newsletter
No spam. Just the latest releases and tips, interesting articles, and exclusive interviews in your inbox every week.
Read about our privacy policy.
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.