Abstract network of lines and dots, illustration
HealthJuly 15, 2020

Clinical NLP part 4: Taking predictive analytics strategies to the next level

Defined simply as the practice of data mining to identify specific patterns and predict future outcomes, predictive analytics holds great promise as a strategy for improving processes across a patient’s care plan and care transitions and even solving operational issues like operating room bottlenecks.

We hope you've enjoyed this blog series on clinical natural language processing (cNLP), and how it can impact many areas of healthcare including risk adjustment, quality measures, and medical necessity review.

How does data quality impact predictive analytics?

The data powering predictive analytics initiatives typically start in EHRs and rely on algorithms, surveillance solutions, and other applications to create insights that evolve to the level of data science.

Yet data itself presents its own unique set of challenges. Not only is it being collected in a variety of ways, but it comes in a variety of sources such as patient problem lists, laboratory results, medication lists, allergies, clinical notes and insurance related diagnosis and procedures. Some of these sources are structured and codified to a standard, many are not. Normalization of the data to an industry clinical standard is critical to complete accurate data aggregation. Without a method for extracting key data from free text documentation, healthcare organizations run the risk of incomplete information to support predictive analytics.

Real examples of predictive analytics in healthcare

The challenge of identifying sepsis offers a perfect example of how data can be used to improve health outcomes and even save lives. Sepsis is the body’s overwhelming and life-threatening response to infection that can lead to tissue damage, organ failure, and death.  In other words, it’s your body’s over-active and toxic response to an infection. Sepsis accounts for nearly 270,000 deaths each year in the U.S. and is the most expensive condition treated in U.S. hospitals. Early identification and treatment are the keys to reducing the high cost of sepsis care and improving patient outcomes. 

With accurate data and an advanced clinical NLP (cNLP) solution, this becomes manageable. There can be a lot of data points needed to monitor and project sepsis such as, demographics, vital signs, medications, lab values, and discrete documentation elements from nursing documentation, including medical problems, infectious diagnoses, as well as signs and symptoms of infection. These various data points come from a range from data elements – whether documented in the EHR or captured in free text fields by the nursing staff.

The coronavirus is exacting unprecedented demands on healthcare systems around the world that were already struggling to improve clinical outcomes and survive financially. Now these same systems are being stretched to the limit, scrambling for scarce resources and forcing providers, who are putting their lives on the line, to learn on the fly about how to detect and treat a once-in-a century threat, even as they continue to wrestle with established threats, like sepsis. In this context, a clinical NLP driven strategy (solution) can become a lifesaver. 

Today, the Health Language cNLP technology is empowering a clinical intelligence tools which trigger real time alerts to clinicians of patients who need emergency clinical attention due to deteriorating conditions such as, sepsis, COVID-19, and c. diff; however, these same surveillance, clinical intelligence principals can be used to detect a variety of other critical conditions such as over-sedation, sever pneumonia, and hemorrhage.

The Health Language cNLP solution

As we have referenced throughout this article series, the Health Language cNLP solution delivers the industry’s most comprehensive approach to identifying and using unstructured information and is easily integrated into health IT environments through application programming interfaces (APIs). Through functionality that enables extraction, conversion, and mapping of free text to industry standards, the application ensures interoperability and meaningful exchange of data assets that have the power to provide deeper analytics insights.

First and foremost, we hope you have enjoyed our four-part cNLP article series, but beyond that, hope that you have learned about new use cases where cNLP can deliver tremendous value. To learn more about the Health Language cNLP solution, contact us today to speak with one of our cNLP experts.

CPT® is a registered trademark of the American Medical Association (AMA).

Learn About Clinical NLP from Health Language


Celeste Adams, Pharm.D.
Senior Medical Informaticist of Health Language, Wolters Kluwer, Health

As Senior Medical Informaticist, Celeste supports the company’s Health Language solutions by focusing on providing harmonization and normalization services related to RxNorm, Medi-Span, and other terminologies.

Health Language Clinical Natural Language Processing
Automate the review of unstructured data, extract clinically relevant data, and codify extracted data to industry standards.
Back To Top