Key REVEAL Characteristics
Due to very high Precision and Recall (the metrics by which the accuracy of NLP is measured), REVEAL has been successfully used in a broad range of applications.
Because REVEAL’s output is coded in a broad array of industry-standard terminologies, REVEAL is capable of handling a number of different domains and specialties.
NLP outputs rich content. However, the content may be difficult to retrieve and use due to non-standard representations. REVEAL’s revolutionary clinical model and concept representation simplify information retrieval and allow for rapid incorporation into existing workflows.
Robust healthcare NLP technology can power multiple applications, both at the point of care and at the back-end. Here we provide several examples of applications that can benefit from NLP.
Revenue Cycle Management (RCM) and Computer-Assisted Coding (CAC)
NLP can make the revenue cycle process and specifically the coding departments of healthcare organizations significantly more efficient. ICD-10 transition has made the use of NLP in CAC a certainty due to the 5x increase in codes.
Meaningful Use and Accountable Care
The American Recovery and Reinvestment Act of 2009 and Affordable Care Act of 2010 have necessitated Meaningful Use and Accountable Care related changes in healthcare applications such as electronic health/medical records (EHR/EMR), disease management and care coordination. These mandates will require correct identification of patient cohorts to be able to support reporting on required measures. NLP dramatically changes the ability to correctly identify the numerators and denominators for measure calculation.
With the inexorable move from pay-for-service to pay-for-performance, healthcare organizations are creating data infrastructure that gives them insight into their quality and efficiency. With retrospective and prospective analyses of data, healthcare organizations are attempting to improve quality and efficiency outcomes that make them more competitive. Currently, this data is limited to approximately the 20% discrete data available from EMR systems. With NLP, the remaining 80% unstructured data can be used in analytics, thus increasing the possibility of improving quality and efficiency outcomes.