Natural Language Processing

The Health Navigator Natural Language Processing (NLP) engine is a unique technology designed to function and act much like a physician or nurse would when listening to a patient.

This technology takes the words people use to describe their symptoms and converts them into meaningful medical information that can be utilized by digital health applications and medical providers.


How it works…


People describe health concerns and symptoms using many different words and phrases. It can be something brief like “headache”. Or, it can be something longer like “I have bad diarrhea and tummy pain.” A person may even use common slang terms such as puking, throwing up, or barfing to describe a symptom like vomiting.

  • The Health Navigator NLP engine recognizes sentences, phrases, slang, and even common misspellings that patients use to describe their medical complaints and problems. Further, it also recognizes the medical terms that doctors and nurses use to document symptoms, diseases, and conditions.
  • The NLP engine translates narrative free-text into a usable and intelligent medical terminology: Health Navigator’s proprietary Coded Chief Complaints vocabulary. The Coded Chief Complaints clinical vocabulary covers over 99% of reasons for patient visits.
  • The NLP engine can translate common self-diagnosis language that a patient may enter such as “bladder infection”. See our Clinical Documentation Support solution for how this CarePath works.
  • The NLP engine has an overall accuracy of 95-99% in correctly identifying the reason for visit.

The Health Navigator NLP engine works with both US and UK English free-text.


How it improves care . . .


Eliciting the patient’s chief complaint is one of the first tasks of health personnel in any patient encounter. A chief complaint, reason for encounter, reason for visit (RFV), or reason for call (RFC) should be recorded for each medical encounter. Identifying the chief complaint is also the first step in every digital health encounter.

Doing this well is important for patient safety and quality care.

Here are two examples of how natural language processing can improve patient care:

  • Answering Services and Medical Call Centers: The Health Navigator NLP engine has been shown to help non-clinical answering service personnel to understand “what callers tell them, prioritize symptoms, and direct callers to nurses in an efficient manner.” Medical call center leaders have reported that the Health Navigator NLP engine and resultant improvements in workflow resulted in “immediate staff delight…, patients experiencing less waiting time for nurses, more consistency identification of true crises, and reduced patient safety issues related to missed symptoms”.
  • Artificial Intelligence, Digital Health Assistants, and Health Bots: Natural Language Processing of a consumers’ description of their symptoms and problems is an essential first step in a digital health encounter. Partners like Microsoft have integrated the Health Navigator NLP engine to help healthcare organizations “empower their customers with self-service access to health information, with the goal of improving outcomes and reducing costs”.

Natural Language Processing of the Reason for Visit - Demo Application

Here is a sample user interface of a patient entering a self-diagnosis in the NLP.