RS14 - Implementation of a Nurse-Navigator Run AAA Program Utilizing Natural Language Processing and the Electronic Medical Record Successfully Identifies AAA Patients Not Being Actively Followed

Objectives: Abdominal aortic aneurysms (AAA) are often identified incidentally on imaging studies. Patients and/or providers are frequently unaware of these AAA and the need for long-term follow-up. We sought to evaluate the outcome of a nurse-navigator run AAA program, which utilizes a natural language processing (NLP) algorithm applied to the electronic medical record (EMR), to identify patients with imaging report-identified AAA not being actively followed.

Methods: A commercially available AAA-specific NLP system (Illuminate, Overland Park, KS) was run on EMR data(Epic, Verona, WI) at a large, academic, tertiary hospital with an 11-year historical look back (1/1/2010-12/31/2020), to identify and characterize AAA. Beginning January 1, 2021, a direct link between the NLP system and the EMR enabled for real-time review of imaging reports for new AAA cases. A nurse-navigator(1.0 FTE) employed software filters to categorize AAA according to pre-defined metrics including repair status, and adherence to Society for Vascular Surgery imaging surveillance protocol. The nurse-navigator then interfaced with patients/providers to reestablish care for patients not being actively followed. The nurse-navigator characterized patients as case closed (eg: deceased, appropriate follow-up elsewhere, refuses follow-up, etc), cases awaiting review, and cases reviewed and placed in ongoing surveillance using AAA-specific software. The primary outcome measures were yield of surveillance imaging performed or scheduled, new clinic visits, and AAA surgery for patients not being actively followed. Contribution margin was estimated revenue minus the direct cost.

Results: During the prospective study period(1/1/2021-12/30/21), 6,340,505 imaging reports were processed by the NLP(fig1). After filtering for studies likely to include abdominal aorta, 243,889 imaging reports were evaluated resulting in the identification of 5,609 non-deceased patients with AAA. When stratified by maximum aortic diameter, 2,324 were 2.5-3.4cm, 478 were 3.5-3.9cm, 521 were 4-5cm, 271 were >5cm, 204 were saccular, 303 previously underwent open repair, 840 previously underwent endovascular repair and 688 were unknown. Of these, 1,621 cases were reviewed and closed, 1,393 were reviewed and placed in ongoing surveillance, and 2,595 are awaiting review. This yielded 40 finalized imaging studies, 29 scheduled imaging studies, 29 new patient clinic visits, and 4 AAA surgeries among patients not being actively followed. The program generated $60,032.24 in contribution margin.

Conclusions: Application of an AAA program leveraging NLP successfully identifies patients with AAA not receiving appropriate surveillance/counseling and repair. This program offers an opportunity to improve best practice-based care across a large health system.