Search

Background: Self-reported racial classification is often used as a proxy for phenotypic differences among clinical populations. We demonstrate an approach to identify differences between Black and White individuals using clinical notes among patients hospitalized with heart failure (HF). Methods: We identified HF hospitalizations for patients at Yale and developed a word frequency embedding (TF-IDF)-based natural language processing (NLP) model on clinical notes to classify “tokens” or words from notes of Black and White individuals based on their frequency. We manually classified these tokens into clinical and non-clinical entities. We evaluated the frequency of clinical tokens successfully identified in ICD diagnosis codes and qualitatively assessed non-clinical tokens for stigmatizing language across Black and White patients. Results: There were 8798 patients (mean age 81±13y, 50% female) with a total of 14,655 unique patient encounters. Of these, 4293 were for Black patients. The NLP-based model determined Black vs White race of patients based only on notes with an AUROC of 0.92 after removing all explicit mentions of race. Of the top 80 tokens that identified Black vs White patients from notes, 53 (66%) were identified as clinical entities. The clinical tokens were underrepresented in structured ICD diagnosis for both Black and White, with a median 88% (IQR=27%, Q1=66%, Q3=94%) of Black-identifying tokens defining clinical conditions and 72% (IQR=45%, Q1=43%, Q3=89%) for White-identifying tokens. Among non-clinical tokens, there was a greater occurrence of stigmatizing words in the notes of Black patients (40% vs 32% in White). Conclusion: We demonstrate that an NLP-based approach can better define clinical differences between Black and White patients, and can be used to screen for stigmatizing language against Black and other minority groups.

Introduction: There is limited literature on the cardiovascular manifestations of post-acute sequelae of SARS-CoV-2 infection (PASC). Methods: All consecutive adult patients presenting to the cardiology clinic at Yale-New Haven Hospital since July 2020, with positive COVID-19 serologic testing, were included. Results: Of 71 patients, average age was 46 years (range 19-74 years), 44 (62%) were female. 51 (72%) were White. 19 (27%) patients were hospitalized for COVID-19 ( Table ). Comorbidities included Hypertension (27%), hyperlipidemia (25%), diabetes (24%), and obesity (30%). On average, patients presented four months after COVID-19 diagnosis. The most common symptoms at presentation were dyspnea (45%, almost all exertional), palpitations (49%), and chest pain/pressure (49%). Patients also had memory impairment (20%), fatigue (39%), and headache (14%). There was no significant difference in cardiopulmonary symptoms (dyspnea, palpitations, and chest pain/pressure) by hospitalization status (p=0.70). TTE was abnormal in 13 of 62 patients and cardiac MRI was abnormal in 10 of 17 patients. Women experienced more cardiopulmonary symptoms (p=0.02) than men. Hospitalized patients were more likely to have ventricular dysfunction than non-hospitalized patients, although there were no significant differences in abnormal MRI findings (p=0.38). Diagnostic yield included: nonischemic cardiomyopathy (6%); new ischemia (3%); coronary vasospasm (1%); new atrial fibrillation (1%); possible myocarditis based on symptoms, MRI LGE (8%) or inflammation (3%). Two people met POTS criteria; majority of patients had evidence of sinus tachycardia and exertional fatigue consistent with orthostatic intolerance and deconditioning. Conclusions: In this cohort of patients referred to a cardiology clinic for PASC, cardiopulmonary symptoms did not differ by hospitalization status, however women were more likely to experience these symptoms than men.