EVALUATING THE ROLE OF ARTIFICIAL INTELLIGENCE IN ENHANCING DIAGNOSTIC ACCURACY AND WORKFLOW EFFICIENCY AMONG RESOURCE-CONSTRAINED ENVIRONMENTS

Abstract

Radiology departments in rural healthcare settings, such as the District Headquarters (DHQ) Hospital Bagh, often encounter substantial operational challenges, including high patient volumes, limited technological and human resources, and radiologist fatigue. In response to these constraints, artificial intelligence (AI) has emerged as a promising adjunct to enhance diagnostic efficiency and accuracy.This study aimed to assess the impact of an AI-based decision-support system on diagnostic accuracy, interpretation time, and radiologists’ confidence levels when interpreting chest X-rays in a district hospital environment. A prospective within-subjects study was conducted over 10 weeks, involving 12 radiologists. Each participant interpreted two equivalent sets of 120 chest X-rays first without AI assistance (Phase 1) and subsequently with AI support (Phase 2). The primary outcome measures included diagnostic accuracy, mean interpretation time, and self-reported confidence scores.Implementation of AI assistance resulted in statistically significant improvements across all metrics. Diagnostic accuracy increased from 78% to 89% (p < 0.001), interpretation time was reduced by 26.8% (from 142 to 104 seconds per image), and mean confidence levels rose from 6.8 to 8.4 on a 10-point scale. Notably, early-career radiologists exhibited the most pronounced gain in diagnostic accuracy (15%), whereas senior radiologists achieved the greatest time reduction (approximately 45 seconds per case). Overall, the integration of an AI-based decision-support tool substantially enhanced radiological performance in this resource-limited setting. These findings underscore the potential of AI technologies to strengthen diagnostic quality, optimize workflow efficiency, and alleviate workload pressures within district-level hospitals.