Abstract
Abstract 10374: Ankle and Toe-Brachial Index for Peripheral Artery Disease Identification: Unlocking Clinical Data Through Novel Methods
Circulation (New York, N.Y.), Vol.144(Suppl_1), p.A10374
11/16/2021
DOI: 10.1161/circ.144.suppl_1.10374
Abstract
Objectives:
Develop a natural language processing (NLP) system for identification of patients with peripheral artery disease (PAD).
Background:
Despite its high prevalence and clinical impact, research on PAD remains limited due to poor accuracy of billing codes. Ankle and toe-brachial index (ABI, TBI) can be used to identify PAD patients with high accuracy using electronic health record (EHR) data.
Methods:
A random sample of 800 ABI test reports from 94 Veterans Affairs (VA) facilities during 2015-2017 were selected and annotated by clinical experts. We trained the NLP system using random forest models and optimized it through sequential iterations of 10-fold cross validation and error-analysis on 600 test reports and evaluated its final performance on a separate set of 200 reports. We also assessed the accuracy of NLP-extracted ABI and TBI values for identifying patients with PAD in a separate cohort undergoing ABI testing.
Results:
The NLP system had an overall precision (positive predictive value) of 0.85, recall (sensitivity) of 0.93 and F1-measure (overall accuracy) of 0.89 to correctly identify ABI/TBI values and laterality. Among 261 patients with ABI testing (49% PAD), the NLP system achieved a positive predictive value of 92.3%, sensitivity of 83.1% and specificity of 93.1% to identify PAD when compared to a structured chart review (Table). The above findings were consistent in a range of sensitivity analysis (Table).
Conclusion:
We successfully developed and validated an NLP system for identifying patients with PAD within the VA’s EHR. Our findings have broad implications for PAD research and quality improvement efforts.
Details
- Title: Subtitle
- Abstract 10374: Ankle and Toe-Brachial Index for Peripheral Artery Disease Identification: Unlocking Clinical Data Through Novel Methods
- Creators
- Julia Friberg - Iowa City VA Medical CenterAbdul H Qazi - Massachusetts General Hosp, Boston, MABRENDEN Boyle - MNCarrie Franciscus - Iowa City VA Medical CenterMary Vaughan-Sarrazin - University of IowaDax Westerman - Vanderbilt UniversityOlga V Patterson - University of UtahSharidan K Parr - Vanderbilt UniversityMichael E Matheny - Vanderbilt UniversityShipra Arya - Stanford UniversityKim G Smolderen - University of New HavenBRIAN Lund - Coralville, IAGlenn T Gobbel - Vanderbilt UniversitySaket Girotra - University of Iowa
- Resource Type
- Abstract
- Publication Details
- Circulation (New York, N.Y.), Vol.144(Suppl_1), p.A10374
- DOI
- 10.1161/circ.144.suppl_1.10374
- ISSN
- 0009-7322
- eISSN
- 1524-4539
- Language
- English
- Date published
- 11/16/2021
- Academic Unit
- Epidemiology; Cardiovascular Medicine; General Internal Medicine; Internal Medicine; Health Management and Policy
- Record Identifier
- 9984363552202771
Metrics
5 Record Views