Patient reported outcomes (PROs) include any report of the status of a patient's health condition that comes directly from the patient, without interpretation of the patient's response by a clinician or anyone else. PROs for functional status information describes the patient's physical and mental wellness at the whole-person level (as opposed to the cellular or organ level). Collecting and analyzing this information is critical to addressing the data needs in caring for aging global populations, and providing effective care for individuals with chronic conditions, multi-morbidity, and disability. However, functional status information has proven difficult to capture systematically within existing paradigms, leaving a space ripe for technological innovation.
To accelerate the use of functional status information in population health management and measurement, we developed and evaluated a natural language processing (NLP) pipeline for extracting these measures from free-text outpatient rheumatology notes within the American College of Rheumatology's Rheumatology Informatics System for Effectiveness registry, which integrates patient notes from over twenty different electronic medical records products and includes hundreds of rheumatology clinics across the U.S. We will discuss the motivation for using NLP to extract functional status and disease activity information from patient progress notes and the methods and results, as presented in Development of a Natural Language Processing System for Extracting Rheumatoid Arthritis Outcomes From Clinical Notes Using the National Rheumatology nformatics System for Effectiveness Registry.