Guilty! I text while I drive…eek! I know, I know, it is really bad and those anti-texting and driving commercials get me too. That is why I am making a concentrated effort to ease up this one vice (stop laughing those that know me!) of mine. Instead, I am beginning to use the voice text option and good ole Siri on my phone, which when I speak like a robot and articulate every word, does alright. But old habits die hard, which is why I understand and sympathize with physicians constantly having to change their behavior in light of all the regulatory demands in recent years.
One behavior that physicians are being asked to change is their practice patterns of dictating or handwriting clinical notes and discharge summaries. The change comes from the desire to move away from unstructured data to more structured data for consistent, easily minable and extractable information for more robust and quality reporting and analytics. 80% of clinical documentation that exists in healthcare today is unstructured and is buried in electronic medical records (EMR) and clinical notes1. Many healthcare providers are looking to natural language processing (NLP) technologies to assist in taking their valuable unstructured data, and turning it into meaningful and actionable structured data to improve patient care.
Natural Language Processing and Clinical Language Understanding
In its simplest definition, NLP is the interaction between artificial intelligence and linguistics. It encompasses anything a computer needs to understand typed or spoken language and also generate the language2. More specifically, NLP applied to the medical domain is called Clinical Language Understanding (CLU), with the main difference being that CLU works off of a complete, highly granular medical ontology, which has been tuned to relate and identify all kinds of medical facts so that the underlying NLP engine can “understand” what the caregiver is saying1. NLP has been around for years, but it wasn’t till recently that healthcare industry took notice of the value of this effectively powerful technology.
Benefits to Healthcare Industry
Clinical documentation has valuable information that can drive clinical decision making, impact patient care and reduce healthcare cost. However, often times the information within this important documentation is not leveraged due to the difficulties associated with manually sorting through volumes of text and extracting and analyzing the data.
The benefits to the healthcare industry are abundant with NLP. Joe Petro, Senior Vice President of Research and Development for Nuance Healthcare, does an excellent job describing just how NLP can positively impact healthcare. Below are his thoughts on the impact to Meaningful Use, Predictive Care and Effective Billing1:
Petro emphasizes that in order for physicians to qualify for government incentive payments associated with adopting and using EHRs they must capture specified facts, including things such as problem lists, allergies, smoking status and vital signs. These facts are oftentimes easy for a physician to capture through a narrative description (via voice), but can prove difficult and time consuming to capture via a structured EHR system template and more importantly pure structured representation of the patient story falls short of what a care team requires to deliver optimal care. Mr. Petro also points out that in 2009, 96 percent of 1,000 surveyed physicians said they were “concerned” about “losing the unique patient story with the transition to template-driven EMRs,” and 94 percent said that “including the physician narrative as part of patients’ medical records” is “important” or “very important” to realizing and measuring improved patient outcomes. Structured documentation, created via template, is easy to analyze and pull facts from, but has proven to be an unnatural means of documentation for physicians and does not capture the nuances of each unique patient story. Natural speech documentation capture combined with NLP delivers a means for physicians to tell a complete patient story with all its subtleties and makes available all of the clinical facts needed for the EMR to operate in an optimal way.
The application of NLP to healthcare can be done in a retrospective manner, (after the patient has left the hospital) or in a predictive manner (while the patient is still there). We all know that predictive care is more impactful to optimal, proactive patient care. With advancement that is taking place today, CLU solutions will move toward decision-support that will provide immediate feedback to physicians at the point-of-dictation, whether they are using a digital recorder, PDA, or mobile phone. For example, if a physician is documenting a prescription for a patient within the EMR and CLU technology is running in the background, the system might notify the physician that the patient could have an adverse reaction to that drug and would recommend an alternative.
When applied to billing, NLP can remove a lot of pain from the billing process, for both the physicians and the medical coders. Petro states that physicians, at times given their busy schedules, can be vague in their documentation which can negatively impact patient care, communication with other caregivers, and can complicate billing. Today, if a physician is vague with documentation they might get a phone call three weeks later from a medical coder who is trying to code their documentation for billing purposes. Chances are the physician won’t fully remember the extra detail that should have initially been captured and the exchange will be burdensome and ineffective. By applying NLP to the documentation process, CLU can scan and understand what the physician is saying and ask for added specificity or severity when necessary. Mr. Petro provides the example of if a physician says a patient had a “fracture of forearm,” did they mean lower forearm, right or left forearm, and what was the severity? By prompting the physician while the details are fresh in his/her mind, the end document will be more complete, which results in improved care, better cross-care communication, more accurate billing, and eliminates that phone call three weeks down the road. The benefits of NLP are also there for the medical coder. CLU can be used to scan and understand electronic medical records and help to auto-code information based on what is documented. For example, what was once dictated as “fracture of forearm,” was appropriately elaborated on to become “torus fracture of lower end of right radius,” and would be coded “S52.521” based on ICD standards, which will greatly increase the efficiency and effectiveness for the medical coders.
If NLP keeps up momentum, the days of manually sifting through countless patient charts to understand and extract vital patient information may be behind us. “By processing text directly with computer applications, an organization can leverage the wealth of available patient information in clinical documentation to improve communication between caregivers, reduce the cost of working with clinical documentation, and automate the coding and documentation improvement processes. Where other applications of technology often require caregivers to change their existing, proven processes to accommodate the technology, NLP allows applications to work with the most valuable form of clinical communication-the clinical narrative3.” NLP will bring the value of the “patient story” in a structured format…we will have the best of both worlds.
What are your thoughts? Do you think NLP has the potential to bring the best of both worlds together to improve patient care and reduce costs?
Resources for this blog post: