Key result
Minority patients in Virginia face an ~18% CVD readmission rate, driven largely by Black patients.
Observational (n=201,419)
Yes
Answers are grounded in this paper and cite their sources.
AI-driven predictive models applied to a large state database highlight significant disparities and varying rates of CVD readmissions among racial and ethnic minorities.
Background: Cardiovascular disease (CVD) disproportionately affects racial and ethnic minorities, with higher readmission rates contributing to health disparities. This study aims to leverage artificial intelligence (AI) to identify predictors of CVD readmissions among racial and ethnic minorities in Virginia (REMiV). Methods: We analyzed 201,419 discharge records from the Virginia Health Information database, focusing on balck and hispanic patients with Diseases&Disorders of the Circulatory System,aged 18-85 who were readmitted through emergency or urgent departments with CVD between 2010 and 2020. Ongoing detailed analyses using SAS and R are being conducted to identify potential predictors of CVD readmissions. Machine learning techniques are being applied to develop predictive models. Results: Preliminary findings from 36,598 (18.17%) readmissions include: 1. Even split between female (50.06%) and male (49.94%) readmissions. 2. Majority of readmitted patients were Black (97.53%), with 2.35% Hispanic. 3. Medicare coverage for 63.81% of readmitted patients. 4. Varying readmission rates: Heart Failure and Shock (23.23%), Chest Pain (11.70%). 5. Average age of readmitted patients: 61.30 years (SD 14.17). Ongoing Analysis: 1. Developing AI-driven predictive models to enhance readmission risk assessment. 2. Exploring interactions between demographic, clinical, and hospital characteristics. 3. Investigating socioeconomic factors and their impact on readmission rates. 4. Analyzing geographical patterns of readmissions across Virginia. 5. Evaluating the effectiveness of different treatments and procedures on readmission rates. Conclusions: Initial results highlight significant disparities in CVD readmissions among REMiV. Ongoing development of AI-driven predictive models and in-depth analysis of multiple factors will provide a comprehensive understanding of readmission risks. This work-in-progress aims to inform targeted interventions, reduce health disparities, and improve cardiovascular outcomes in minority populations.
No takes yet. Share an insight, caveat, or question.
Moudden et al. (2025) conducted an observational in Cardiovascular disease readmissions (n=201,419). Risk factors for CVD readmission was evaluated on CVD readmissions.
Synapse has enriched 10 related papers. Consider them for comparative context: