PDCA cycle-based standardized training and CXR image-quality performance of radiographers in multiethnic communities: a pre-post quality improvement study

High-quality chest X-Rays (CXRs) are critical for screening lung infectious diseases. However, CXR image-quality performance among radiographers in multiethnic primary care settings may be associated with language discordance, high clinical workloads, and limitations of apprenticeship-based training. This study evaluated the integration of a Plan-Do-Check-Act (PDCA) quality improvement (QI) framework as an instructional design model to enhance radiographer training and continuing medical education (CME), focusing on radiographic image-quality performance. A pre-post QI study was conducted among six junior radiographers (with ≤ 3 years of experience). Baseline CXR image-quality performance under the conventional apprenticeship model was assessed using 120 randomly sampled CXRs, which were independently evaluated by two blinded radiologists using a validated 12-point scoring tool. Inter-rater reliability was established using a two-way random-effects model ICC on a random subsample of 30 CXRs (ICC = 0.821). Following Ishikawa analysis, a “5-3-1” weighted scoring approach was used to prioritize factors, and the percentages of suboptimal cases attributed to each factor were calculated to identify educational barriers. A targeted one-month PDCA-based intervention was implemented. Post-intervention performance was evaluated using 150 CXRs. A linear mixed-effects model (LMM) was used as the primary analysis to account for clustering within radiographers. Each radiographer contributed 20 pre-intervention and 25 post-intervention CXRs. The baseline mean CXR score was 9.56 ± 1.11, with only 19.17% of CXRs achieving diagnostic excellence. Three main barriers compromised radiographers’ CXR image-quality performance: language discordance-related patient non-cooperation, high workload, and lack of standardized training. Following the PDCA intervention, the mean score improved to 11.03 ± 0.82, and the proportion of excellent CXRs increased to 80.67% ( P < 0.001). The LMM analysis demonstrated a statistically significant improvement, with post-intervention scores increasing by an estimated 1.395 points relative to baseline ( P < 0.01). Consistent improvements were observed across all individual radiographers and in six of the seven assessed image quality domains. For the regional CME program, 354 primary care radiographers were trained, and 349 passed the certification assessment (98.59%). Conventional apprenticeship-based training is insufficient for high-throughput, multiethnic screening environments. Integrating standardized instruction, peer review, bilingual protocols, and image-quality–focused credentialing within a PDCA framework is associated with observed short-term improvements in CXR image-quality performance.