Mercy project heart failure device patients

Mercy wins Gateway to Innovation Award using Linguamatics NLP on EHR Notes in Heart Failure Patients

July 11 2018

Linguamatics is pleased to congratulate US healthcare system Mercy on their recent award win at the 12th Gateway to Innovation conference. Mercy won the Innovative IT Project of the Year Award for using Linguamatics I2E Natural Language Processing (NLP) solution to extract clinical analytics insights from their Electronic Health Records (EHR) notes for cardiac patients.

Mercy Technical Services provides contract research services for medical device and pharmaceutical clients to support use of real world evidence (RWE) in Food and Drug Administration submissions. This award recognizes a project that demonstrates value or impact to the organization by solving a business problem or by addressing a specific strategic objective for the company.

NLP used to Extract Real World Evidence from EHRs

As a large health system with a mature and consolidated Epic EHR system, Mercy has a significant data set of patient treatments and outcomes. There is a multitude of information documented in the EHR, such as lists of specific symptoms, diagnoses derived from echocardiogram reports, and certain benchmarking classifications. Since typically 80% of this information is unstructured text, many valuable clinical insights are unavailable in discrete fields, and therefore vital patient information can be trapped when making clinical decisions.

NLP text mining platforms like Linguamatics I2E extract information from unstructured text-based EHRs and transform it into actionable insights that can be placed into a dataset and analyzed.

As part of a collaboration agreement with Medtronic, Mercy needed to mine EHR data to evaluate heart failure device performance – letting the manufacturer know how to improve its implantable products and helping Mercy's own clinicians make better data-driven decisions on treatment.

Mercy has been using Linguamatics I2E NLP technology to extract this previously inaccessible data from seven years’ of almost 34 million [2] clinician notes from both inpatient and outpatient encounters for its cardiac patients. They have extracted key cardiology measures - ejection fraction measurement; symptoms such as shortness of breath, fatigue and palpitations; New York Heart Association classifications – that they can now analyze as discrete data sets. 

EHR Data Mining Saved Significant Time in Major Mercy Real World Data Project

"Perhaps 60 percent of the data you would really like is available to you as discrete data in the EHR. The remaining 40 percent is contained in text and clinical notes, and in order to get the meaningful data out, you have to [use] something like NLP to capture it… the results we have gotten have been tremendous… it’s restored my faith in NLP’s ability to get us out of this data capturing conundrum," said Joseph Drozda, M.D., cardiologist, director of outcomes research at Mercy. [1]

Having gained big insights into how Cardiac Resynchronization Therapy (CRT) devices can help its cardiac patients from this project, Mercy hopes to put the Linguamatics I2E NLP software to work on an array of other projects to help optimize its workflows and improve quality and outcomes.

"One of the biggest benefits for us was availability of Linguamatics medical ontology libraries. Instead of us having to sit here and try to come up with every single way a doctor could have said 'shortness of breath' in a note, they have these libraries: We can start our queries with the libraries, do some validation and maybe alter the query a bit so it's more tailored to the Mercy system. It's been a real time-saver." said Kerry Bommarito, Manager of Data Science at Mercy. 

"We're able to see how patients progress over time, we can see if certain treatments affect the result," said Bommarito. "If their results decline, we can see: What kind of medication are they on? Are we putting a cardiac device in them to improve their results? We're able to get at that progression of disease in the patient population and see if there are factors that affect it or could improve it." [3]

Mercy Plans to Expand Use of NLP to Ease Physician Fatigue and Documentation

The Medtronic cardiac study is still ongoing, but Mercy is already planning to expand its use of NLP. "Internally, some of the things we want to do with this are focused on physician fatigue and documentation – using NLP to help ease that," said Bommarito. They have also teamed up with Johnson & Johnson to access real-world data on medical devices. J&J will use the data mined by Mercy using Linguamatics I2E to assess the health outcomes achieved by medical devices and to inform its regulatory decision-making. 

"This cardiac project has "really opened our eyes to many possibilities as to what we can find in the note and how can it supplement what's documented there discretely," said Mark Dunham, Director of Data Engineering and Analytics at Mercy.

"Are there opportunities to find things that could have been documented discretely and were not? And could we push them back and color in around the edges where we could get better-quality data? We're just scratching the surface of what we can do with this." [3]

Want to learn more about the capabilities of NLP text mining software Linguamatics I2E? Get in touch with the team to find out more or read more about how NLP improves population health management and provides risk stratification insights.

References:
[1] https://www.healthdatamanagement.com/news/nlp-to-help-mercy-health-bette...
[2] https://www.healthcare-informatics.com/article/ehr/its-mission-capture-u...
[3] https://www.healthcareitnews.com/news/how-mercy-using-nlp-its-epic-ehr-i...