Comparative Outcomes of AI-Assisted Diagnosis vs. Traditional Diagnosis in Primary Care Settings

Background: To compare the outcomes of AI-assisted diagnosis with traditional diagnostic approaches in primary care settings, focusing on diagnostic accuracy, efficiency, cost, and patient satisfaction. Methods: A cross-sectional comparative study was conducted between January 2024 and January 2025 at Primary Care Setup in Lahore. A total of 72 patients were equally divided into two groups: AI-assisted diagnosis (n=36) and traditional physician diagnosis (n=36). Data on demographics, presenting complaints, diagnostic process measures, and patient outcomes were recorded. Statistical comparisons were made using independent t-tests and Chi-square tests, with p < 0.05 considered significant. Results: AI-assisted diagnosis demonstrated higher diagnostic accuracy (88.9% vs. 72.2%, p = 0.04), lower misdiagnosis rates, and greater patient satisfaction (83.3% vs. 61.1%, p = 0.03). Mean time to diagnosis (12.4 ± 3.5 vs. 21.7 ± 4.2 minutes, p < 0.001), number of tests ordered, and diagnostic costs were significantly lower in the AI group. Clinician confidence scores were also higher with AI support (p = 0.03). Conclusion: AI-assisted diagnostic systems significantly improved accuracy, efficiency, and patient satisfaction compared with traditional approaches. Integration of AI into primary care may enhance clinical decision-making and optimize resource utilization.