Preserving the patient narrative with NLP

Clinical NLP Important Applications

The advent of accountable care, meaningful use, and the triple aim is creating an unprecedented demand for insightful patient data. Though structured data reveals valuable information, some 80% of EHR data resides in an unstructured narrative format. Furthermore, of the 1.2 billion clinical documents produced in the US each year, 60% of the valuable information exists in unstructured narrative documents that are largely inaccessible for data mining and quality measurement.

To gain better insight into patient data, providers might be inclined to expand their use of templates to capture discrete observations. Unfortunately, when purely coded templates take the place of free-text narratives, the resulting documentation often fails to capture subtle circumstances of a patient’s story. Frequently the patient narrative is the most effective means of communicating detailed information between healthcare professions.

What alternatives do providers have for preserving the patient narrative, while at the same time gain additional insights from a patient’s complete medical record? One option is to tap into the power of Natural Language Processing (NLP) technology.

NLP technology allows users to extract information from unstructured text in order to analyze populations and uncover key insights for a wide variety of analytical reporting. For example, NLP can help organizations improve readmission predictions by mining discharge data for relevant socioeconomic factors, or facilitate care coordination by mining pathology reports to detect critical findings.

In a recent study involving 12 CMIOs from leading US-based health systems, 91% of the participants expressed strong interest in NLP tools to manage large volumes of unstructured data. In fact, most of the CMIOs believed their organizations would need to adopt NLP technology in order to gain the level of insights required to support accountable care across their Medicare, Medicaid, and commercial risk patient populations.

The CMIOs acknowledged that structured data, such as disease codes, were valuable for analytical reporting, but also recognized that the information was, at times, too limiting. Most viewed NLP as a tool that would provide the additional specificity needed to differentiate patient groups, which they considered a requirement in today’s evolving risk-based payment environment.

As payment models and reporting requirements continue to evolve, the demand for better access to actionable patient data will continue to grow. NLP will thus become an essential tool for organizations as they work to meet new reporting objectives, improve the efficiency of care delivery, and, advance the health objectives of their patient population.