Skip to main content

Comparing "Pineapples to Apples": Utilizing NLP for HEDIS Metrics so your Healthcare Plan Measures up

NLP and HEDIS- comparing pineapples to apples

How do you ensure your healthcare company outshines the competition with so many choices out there? There’s an app for that! Well no - not yet, at least there wasn’t at the time I wrote this blog- I double checked. There is however, the National Committee for Quality Assurance (although no app, they do have a very informative Twitter account.)

The committee’s mission is to help continually ensure quality in health from all parties involved. For insurance companies, they use the Healthcare Effectiveness Data and Information Set (HEDIS) as it is “one of the most widely used sets of health care performance measures in the United States.”[1]. So rather than trying to compare two things that may sound like they are certainly similar, such as ‘pineapples to apples’, people now have a true method of payer comparison.

To learn more about big data analytics for population health, download our case study.

Download the case study

HEDIS consists of a set of measures around patient care and service. Measures vary from simple documentation of an adult Body mass index (BMI), a calculation involving only height and weight; to the more complicated documentation of comprehensive diabetes care.

How does HEDIS help healthcare and patients?

HEDIS helps healthcare assess the results of a value based care model rather than fee for service, which awards more money for each service that is given. This is how everyone can see how each healthcare provider compares, apples to apples.

Why should patients care about HEDIS? As a patient, I want to know if my provider is good at delivering care for my specific condition(s), and that they are being paid for my continued wellness.

Fee for service isn’t a good model for healthcare. In fact it’s the opposite - it practically promotes more appointments, tests and yes, even procedures (for the sake of greater compensation, not for better health) - widely opening up a door for negligence and fraud. According to the Department of Justice nearly $100 Billion yearly has it’s claim toward health care fraud.[2] - clear proof we need another way - which is where value based care comes in.

So how can natural language processing (NLP) prove its value in this space?

As an insurance provider we’ve worked with recently told us, proving value is no easy task. For many in the healthcare industry, manually abstracting HEDIS metrics from a Cloudera lake with terabytes of information feels more like a drowning hazard than accessing a clear pool of information. It’s difficult enough for a company to stay afloat with just one of the HEDIS metrics, such as comprehensive diabetes care, let alone many. This manual process is time consuming and has real potential to make one of our newest epidemics even worse - Computer Vision Syndrome (aka. Digital Eye Strain)[3].

So let’s use math to put this to the test. As of this blog there are 289 HEDIS Review Nurse jobs on indeed.com being advertised with salaries ranging from $45-85K annually.[4] We can add our nurse above with an average salary of $65K to show some hidden costs. Now imagine the cost and time required for repeating the same measure, not to mention the cost of additional measures! We know that some companies are paying at least $2M a year to manage this process.

Linguamatics Health NLP platform I2E helps automate much of the work... looking for the same clinical criteria over, and over again - so we don’t waste good clinical minds and money. It’s better to build a query on a criteria, make sure it works, then move on to query number two. NLP minimizes the manual effort needed, (perhaps a few hours for manually sampling and additional curation), and ensures that no data is missed. Don’t get me wrong - I would never say that the human element can be taken away from any clinical analysis - but it can be cut down significantly.

Just rinse and repeat on the next set of criteria...utilizing NLP-driven automation saves time and money long-term. It allows us to continue comparing the apples to applesand leaving the pineapples for better uses...like piña coladas!

1. What is HEDIS [Internet]. [cited 17 Apr 2017]. Available: http://www.ncqa.org/hedis-quality-measurement/what-is-hedis

2. Health Care Fraud Unit | CRIMINAL-FRAUD | Department of Justice [Internet]. [cited 24 Apr 2017]. Available: https://www.justice.gov/criminal-fraud/health-care-fraud-unit

3. Computer Vision Syndrome [Internet]. [cited 23 May 2017]. Available: https://www.aoa.org/patients-and-public/caring-for-your-vision/protecting-your-vision/computer-vision-syndrome?sso=y

4. Hedis Review Nurse Jobs, Employment | Indeed.com [Internet]. [cited 24 Apr 2017]. Available: https://www.indeed.com/q-Hedis-Review-Nurse-jobs.html

Learn more about big data solutions for the healthcare industry.

Ready to get started?

Request a Demo

Questions? Ask our experts