Diagnostic validity and learning curve of non-NBI expert endoscopists in gastric intestinal metaplasia diagnosis.

Background: Endoscopists' experience influences narrow-band imaging (NBI)-guided gastric intestinal metaplasia (GIM) diagnostic performance. We aimed to evaluate the general gastroenterologists (GE) performance in NBI-guided GIM diagnosis compared to NBI experts (XP) and assess GEs' learning curve.

Methods: A cross-sectional study was conducted between 10/2019 and 2/2022. Histology-proven GIM who underwent esophagogastroduodenoscopy (EGD) were randomly assessed by 2XPs or 3GEs. Endoscopists' performance on NBI-guided diagnoses were compared to the pathological diagnosis (gold standard) in five areas of the stomach according to the Sydney protocol. The primary outcome were GIM diagnosis validity scores of GEs compared to XPs. The secondary outcome was the minimum number of lesions required for GEs to achieve an accuracy of GIM diagnosis ≥ 80%.

Results: One thousand one hundred and fifty-five lesions from 189 patients (51.3% male, mean age 66 ± 10 years) were examined. GEs performed EGD in 128 patients with 690 lesions. the GIM diagnosis sensitivity, specificity, positive predictive value, negative predictive value, and accuracy of GEs compared to the XPs, were 91% vs.93%, 73% vs.83%, 79% vs.83%, 89% vs.93%, and 83% vs.88%, respectively. GEs demonstrated lower specificity (mean difference - 9.4%; 95%CI - 16.3, 1.4; p = 0.008) and accuracy (mean difference - 5.1%; 95%CI - 3.3, 6.3; p = 0.006) compared to XPs. After 100 lesions (50% GIM), GEs achieved an accuracy of ≥ 80% and all diagnostic validity scores were comparable to the XPs (p < 0.05 all).

Conclusions: Compared to XPs, GEs had lower specificity and accuracy for GIM diagnosis. The learning curve for a GE to achieve comparable performance to XPs would necessitate at least 50 GIM lesions. Created with BioRender.com.