JMIR Publications

ABSTRACT

Background:

Management of abdominal aortic aneurysm (AAA) requires serial imaging surveillance to evaluate aneurysm dimension. Natural language processing (NLP) has been previously developed to retrospectively identify patients with AAA from electronic health records (EHR). However, there are no reported studies which use NLP to identify AAA patients in near real-time from radiology reports.

Objective:

To develop and validate a rule-based natural language processing (NLP) algorithm for near real-time automatic extraction of AAA diagnosis from radiology reports for case identification.

Methods:

The AAA-NLP algorithm was developed and deployed to an EHR big data infrastructure for near real-time processing of radiology reports from 5/1/2019 to 9/30/2020. NLP extracted named entities for AAA case identification and classified subjects as cases and controls. The reference standard to assess algorithm performance was manual review of processed radiology reports by trained physicians following standardized criteria. Reviewers were blinded to diagnosis of each subject. The AAA-NLP algorithm was refined in three successive iterations. For each iteration the AAA-NLP algorithm was modified based on performance compared to the reference standard.

Results:

120 radiology reports were randomly selected for each iteration; a total of 360 reports were reviewed. At each iteration, the AAA-NLP algorithm performance improved. The algorithm identified AAA cases in near real-time with high positive predictive value (98%), sensitivity (95%), specificity (98%), F1 score (97%), and accuracy (97%).

Conclusions:

Implementation of NLP for accurate identification of AAA cases from radiology reports with high performance in near real-time is feasible. This NLP technique will support automated input for patient care and clinical decision support tools for the management of AAA patients.