Skip to main content

Health Plans and Payers: Top Five Natural Language Processing Applications

healthcare payers people meeting

The value of NLP for payers and health plans

Health plans and payers rely on medical record review for multiple different business-critical processes. Manual review of the vast amounts of unstructured medical data is very labor-intensive, requiring significant staff and time investment - with related high costs - and generally, slow headway. However, the vital member insights that can be gained from medical records and other unstructured healthcare data sources are too important to be ignored. To address this challenge, payers have increasingly been assessing technology options to streamline the process of identifying and extracting these insights in a more efficient, cost-effective manner.

Natural Language Processing (NLP) as an AI (Augmented Intelligence) technique has become increasingly popular with payers and health plans in recent years. By using NLP to analyze unstructured data like PDF medical records, call center transcripts, and Electronic Health Record (EHR) exports, companies are now able to streamline business processes where manual review is needed - extracting key healthcare insights from medical records in a fraction of the time, at a fraction of the cost.

Key NLP application areas for payers and health plans

Business-critical processes requiring medical record review include NCQA HEDIS™ quality measure reporting, clinical review/medical necessity and Medicare risk adjustment. The more established use of NLP in disease coding, and especially risk adjustment, has paved the way for NLP to also be applied in new areas to enhance predictive models, identify high risk members, reduce manual chart review and streamline business audit processes that require extensive medical record review.

The five most popular NLP application areas we see amongst payers and health plans today include:

  1. Member stratification: Social Determinants of Health (SDoH), disease severity and lifestyle choices are all valuable concepts to include into stratification and predictive outcome models. This information is generally not available in structured data fields in the medical record. NLP is used to extract these insights from medical notes and fill in these important missing pieces, to provide a complete picture of each member.
  2. HEDIS quality measures: Medical record review is required to identify supporting evidence for hybrid HEDIS measures such as colorectal cancer screening or comprehensive diabetes care. The manual processes to extract the facts trapped in unstructured text documents can involve reviewing numerous pages per member, and result in pdfs being reviewed multiple times for different reasons, with subsequent high costs and slow progress. As a result, without NLP, compliance is generally only assessed after the reporting year is finished and opportunities to close care gaps have been missed. By applying NLP processes through the reporting year care gaps can be identified and closed, therefore impacting numerator values. The business impact of reduced Centers for Medicare & Medicaid Services (CMS) star ratings on enrollment is substantial, potentially running into tens of millions of dollars.
  3. Voice of the customer information: Call center transcripts provide insights into member satisfaction. Lack of insight into social determinants of health (SDoH) such as ambulatory status, food insecurity and social isolation can have a major impact on the right decision for the member, and on their satisfaction with the health plan. Beyond basic sentiment analysis, a sophisticated NLP platform is needed to extract key concepts and relationships, for example to identify social isolation issues, transport problems and cultural factors, which can be used to improve understanding and customer satisfaction.
  4. Medical necessity and clinical review: NLP is now being used to streamline laborious medical record review with augmented intelligence processes that identify and validate the presence of supporting evidence in medical records for a particular treatment, device or procedure, based on policy requirement. Instead of requiring expert staff to manually read entire medical records, NLP can quickly scan the documents and extract the relevant criteria for skilled staff to more efficiently conduct their clinical review and assessment of the most effective treatment and support options.
  5. Medicare Advantage risk adjustment: This is one of the most common NLP applications—enabling additional revenue to be gained through identification of specific disease comorbidities in association with typical chronic diseases such as diabetes and heart failure. Review of clinical notes to identify diagnoses that are not captured in the discrete EHR fields is particularly important for long term conditions such as diabetes, chronic obstructive pulmonary disease (COPD), chronic heart failure (CHF), multiple sclerosis and chronic hepatitis, where you need to show the audit trail and evidence of face-to-face encounters and the date those occurred.

Enhancing healthcare efficiency with NLP

Leading health plans and payers are now using NLP to improve efficiency and outcomes in numerous business areas including care management, customer experience and HEDIS quality measures. Contact our expert healthcare team to learn more about how these organizations are using NLP today to extract critical insights from unstructured data - deepening and broadening their understanding of each member, to improve their care and experiences as a customer.

Access our webinar: "Top 5 key NLP application areas for Payers and Health Plans":


Ready to get started?

Request a Demo

Questions? Ask our experts