Abstract 4140118: Identification of Obstructive and Non-Obstructive Hypertrophic Cardiomyopathy Patients Using Natural Language Processing in a Large Integrated Healthcare System

Abstract

Introduction: Accurately identifying and characterizing patients with hypertrophic cardiomyopathy (HCM) is critical for population management and care optimization. Research Question: To develop natural language processing (NLP) algorithms to identify and characterize obstructive (oHCM) and non-obstructive (nHCM) HCM patients directly from echocardiograms, and to compare with the presence or absence of HCM-related diagnosis codes. Methods: We developed and validated NLP algorithms to identify HCM from all adult (age≥18yrs) echocardiograms performed from 2010-2019 in Kaiser Permanente Northern CA (KPNC), capturing measures of any HCM, HCM subtype, hypertrophy subtype, septal and posterior LV wall thickness, resting and stress/Valsalva LVOT gradients, and systolic anterior motion. We developed a rules-based algorithm (following AHA/ACC criteria) to classify patients as having HCM, including oHCM or nHCM subtypes, and possible HCM (defined as wall thickness ≥2cm without other criteria meeting an HCM definition). We evaluated the presence of HCM-related ICD-9/10 diagnosis codes among patients classified as HCM/non-HCM from echocardiograms using NLP, and linked baseline demographics and clinical parameters from our integrated electronic medical record. Results: Among 472,405 adults with echocardiograms, we identified 2,892 patients with HCM based upon NLP-derived measures (all NLP measures achieved >95% positive predictive value and >95% negative predictive value), including 1,585 (55%) with oHCM, 1,145 (40%) with nHCM, and 162 (6%) which could not be classified (Figure). Among those 2,892 patients, 1,283 did not have any associated HCM ICD-9/10 diagnosis codes (Table). Among 469,513 patients with no identified HCM from NLP-based algorithms, HCM ICD-9/10 diagnosis codes existed in 1,567 patients (Table). We also identified 4,593 patients with possible HCM by NLP, only 4.5% of whom had an associated HCM code. Among confirmed HCM patients by NLP, oHCM patients were slightly older (66 vs 61 yrs), more likely female (53% vs 43%), had similar mean septal wall thickness (1.7cm vs 1.7cm), but were more likely to have a septal hypertrophy subtype (46% vs 28%) compared to nHCM patients. Conclusions: Echocardiogram-based NLP methods can improve the identification of and care for HCM patients. Many patients with possible HCM may be underdiagnosed, representing an opportunity for quality improvement.