AI-Assisted Medical Records Management and EHR Workflow Optimization for Community Health Centres Serving Immigrant Populations

Abstract

This study investigates the persistent problem of documentation burden, incomplete patient records, multilingual communication challenges, and workflow inefficiencies in community health centres serving immigrant populations, where conventional EHR systems often struggle to capture and manage complex patient information effectively. The purpose of the research was to examine whether AI-assisted medical records management improves EHR workflow optimization, record completeness, multilingual documentation performance, service delivery quality, and overall operational effectiveness in these settings. The study adopted a quantitative, cross-sectional, case-based design and collected data from 200 respondents drawn from selected cloud-enabled and enterprise-style EHR case contexts within community health centres, including physicians, nurses, medical records officers, administrative staff, and IT/EHR support personnel. The key variables included AI-assisted medical records management, automated documentation support, intelligent record retrieval, error detection and validation, multilingual documentation support, EHR workflow optimization, record accuracy and completeness, service delivery quality, and operational effectiveness. Data were analyzed using descriptive statistics, Cronbach’s alpha reliability testing, correlation analysis, and multiple regression modeling. The findings showed strong positive perceptions of AI-supported records management, with mean scores of 3.98 for AI-assisted medical records management, 4.07 for EHR workflow optimization, 4.12 for record accuracy and completeness, 4.15 for multilingual documentation support, and 4.18 for service delivery quality. Reliability values were high, with Cronbach’s alpha ranging from 0.821 to 0.914. Correlation analysis revealed significant positive relationships between AI-assisted medical records management and EHR workflow optimization (r = 0.71, p < .001), record accuracy and completeness (r = 0.69, p < .001), and service delivery quality (r = 0.71, p < .001). Regression results further confirmed that AI-assisted medical records management significantly predicted EHR workflow optimization (β = 0.59, p < .001), while the overall model explained 46.2% of workflow variance (R² = 0.462, F(4,195) = 41.82, p < .001). The study implies that AI-enabled documentation systems can strengthen workflow efficiency, multilingual recordkeeping, and equitable service delivery in immigrant-focused community healthcare settings.