Home » Readers Write » Currently Reading:

Readers Write: Natural Language Processing: Putting Big Data to Work to Drive Efficiencies and Improve Patient Outcomes

August 26, 2013 Readers Write 1 Comment

Natural Language Processing: Putting Big Data to Work to Drive Efficiencies and Improve Patient Outcomes
By Dan Riskin, MD

8-26-2013 6-26-06 PM

Natural language processing (NLP) is increasingly discussed in healthcare, but often in reference to different technologies such as speech recognition, computer-assisted coding (CAC), and analytics. NLP is an enabling technology that allows computers to derive meaning from human, or natural language input.

For example, a physician’s note may state that a patient “has poorly controlled diabetes complicated by peripheral neuropathy.” When notes are analyzed through an NLP system, coded features are returned that can:

  • Suggest codes such as ICD-9 or ICD-10 that may feed a CAC billing application;
  • Classify a patient according to applicable quality measures such as poorly controlled diabetes mellitus, to support a reporting tool;
  • Populate a data warehouse;
  • Feed analytics applications to support descriptive or predictive modeling, such as the likelihood of a patient being readmitted to a hospital within 30 days of discharge.

Healthcare is data intensive from both clinical and business perspectives. While the industry’s transition to electronic data collection and storage in recent years has increased significantly, this has not actually forced physicians to code the majority of meaningful content. Eighty percent of meaningful clinical data remains within the unstructured text, as it does in most industries. This means that it remains in a format that cannot be easily searched or accessed electronically.

NLP can be leveraged to drive improvements in financial, clinical, and operational aspects of healthcare workflow:

For financial processes, automating data extraction for claims, financial auditing, and revenue cycle analytics can impact the top line. NLP can automatically extract underlying data, making claims more efficient and offering the potential for revenue analytics.

For clinical processes, automatically extracting key quality measures can support downstream systems for reporting and analytics. NLP can infer whether a patient meets a quality measure rather than requiring individuals to manually document each measure for each patient.

For operational processes, descriptive and predictive modeling can support more effective and efficient operations. NLP can extract hundreds of data elements per patient rather than the 2-4 codes listed in claims, producing better models and supporting business insight and diversion of resources to high risk patients.

So, NLP is a powerful enabling technology, but it is not an end user application. It is not speech recognition or revenue cycle management or analytics. It can, however, enable all of these.

There is a battle underway that is increasingly recognized in the healthcare space. Individual hospital divisions seek turnkey solutions and frequently purchase NLP-enabled products. But at a broader level, health systems as a whole do not want to pay repeatedly for similar technology. They seek best-of-breed infrastructure, wanting a combination of electronic health records, data warehouses, NLP, and analytics.

This battle will increasingly highlight best-of-breed data warehouses, data integration vendors, and natural language processing technologies as health systems search for a scalable, affordable, and flexible healthcare infrastructure to feed a suite of clinical, operational, and financial applications.

Dan Riskin, MD is CEO of Health Fidelity of Palo Alto, CA.

View/Print Text Only View/Print Text Only

HIStalk Featured Sponsors


Currently there is "1 comment" on this Article:

  1. As Dr. Riskin points out, physician’s notes contain a wealth of information, and NLP, which is one facet of Big Data, is the key to accessing and mining the value of unstructured text. Big Data has three main features differentiating it from normal data: Volume, Velocity, and Variety. Unstructured text is in the Variety category, and NLP lets analysts apply structure to and extract actionable information from unstructured text.

    For example, consider a patient’s smoking status. An EHR may have a checkbox to indicate smoking status, but can it tell you whether the patient wants to quit, how many times they’ve tried to quit, and what cessation methods they’ve used? When did the patient begin smoking? Do they smoke, or are they using chewable tobacco? Or perhaps your patient is to young to smoke, but tobacco use is still a factor, as with premature babies admitted to the NICU with underdeveloped lungs. When they go home, are they entering a smoking household? If so, that is a major factor, and not one that an EHR is likely to capture. That kind of second order effect is impossible to capture and analyze in a traditional EHR without the use of NLP.

    Much of what we read about Big Data in industry publications and blogs is vendor-driven and filled with hype, but the hype is fading, and what remains are useful applications of the technology. NLP is already powering healthcare analytics, such as Population Health Management, enabling better outcomes at the individual and population level.

    Thomas C. Mueller, MBA, CDMP, CHPA
    Forward Health Group

Subscribe to Updates



Text Ads

Report News and Rumors

No title

Anonymous online form
Rumor line: 801.HIT.NEWS



Founding Sponsors


Platinum Sponsors



























































Gold Sponsors
















Reader Comments

  • Vaporware?: Secretary Shulkin: "the American healthcare system hasn’t yet figured out interoperability, but the VA can lead the wa...
  • Justa CIO: The reported go live date for McLaren Oakland is wrong. There are no dates set for activations for any locations. Post...
  • Brian Too: I admit I am partial to the quoted ICD-10-CM of "S07.9XXA Crushing injury of head, part unspecified, initial encounter....
  • Cosmos: As others in the comments section have pointed out before, GE's EMR for athletes is ironically a health record for the h...
  • HIT MD: I appreciate the thoughtful postings on this topic, particularly those by Ross Martin and LMNOP. I've never participate...
  • My Two Cents: Re: I wish we could all just get along and put the patient at the center of what we do. Yep, I get more and more disc...
  • bbc: Did you take the Hippocratic Oath in Med school? does the slightest thought of helping your patients concern you at all...
  • My Two Cents: I have a few concerns about the article Mr. Crane wrote on Drug Pricing Transparency and respectfully disagree and quest...
  • Brian Too: Aha! That makes more sense now. Thank you for clarifying....
  • So.....: Why not embed this functionality in to the patient portal and let the patient take on the leg work and the extra clicks?...

Sponsor Quick Links