Enhancing Quality-of-Care Initiatives with NLP

December 2 2015

CMIOs-Importance-of-Clinical-NLP

 

The transition to new value-based payment models is spurring provider demand for technologies that enhance patient care and minimize safety risks, and in turn reduce costs. Of particular interest are tools to help providers predict the likelihood of potentially avoidable outcomes, such as a hospital readmission, pulmonary nodules turning cancerous or the contraction of sepsis.

According to a recent Linguamatics survey, most hospital CMIOs support the use of predictive models to improve the quality of care. In addition, CMIOs believe that these models can be enhanced with the use of Natural Language Processing (NLP) to access insightful data from unstructured chart notes.

Consider, for example, a health system that wants to improve predictions for 30-day hospital readmissions. More accurate predictions help providers identify their highest risk patients so that appropriate proactive measures can be taken to minimize readmission risks. Predictions may consider certain risk factors, such as a patient’s likelihood of medication non-adherence, their ambulatory status, or their post-discharge living arrangements. Often highly relevant information, such as “the patient is going home with husband” or “the patient lives alone” is only captured in free-text form. NLP unlocks critical insights from unstructured text and thus facilitates better patient care.  

The surveyed CMIOs suggested several other potential applications that would leverage the power of NLP to enhance quality of care and patient safety initiatives. One specific recommendation was to use NLP to improve clinical documentation and decision support rules so that women who had had bilateral mastectomies would no longer receive mammogram-scheduling reminders. Another suggested scenario was to leverage NLP to extract ejection-fraction data to improve the classification of heart failure patients. Additional applications included using NLP to rapidly review pathology reports and test results to quickly detect serious health issues, and to analyze chart notes in order to develop more robust clinical decision support (CDS) capabilities at the point of care.

Providers will continue to demand more insights from patient data, thanks to new outcomes-based payment models, Accountable Care, the Triple Aim, and Meaningful Use. As organizations seek to improve the delivery of care, NLP will become essential for managing the ever-expanding volumes of unstructured data and for transforming that data into actionable insights.