A prediction model and nomogram for technical difficulty of peroral endoscopic myotomy

Background and aims: Peroral endoscopic myotomy (POEM) is a promising endoscopic technique for achalasia. We aimed to establish a regression model and develop a simple nomogram to predict the technical difficulty of POEM in a single center with large volume cases. Methods: 3385 achalasia patients treated with POEM were included, and the technical difficulty was systemically evaluated. All of them were randomized into the training cohort (n= 1693) or internal validation cohort (n= 1692). Then, the prediction model and nomogram were proposed based on multivariate logistic regression analysis in the training cohort and assessed in the validation cohort. Results: Of 3385 patients, technical difficulty happened in 417 (12.32%) cases. In the training stage, six factors were weighted based on the βcoefficient from the regression model, including age, disease duration, sigmoid esophagus, mucosal edema, submucosal fibrosis, and tunnel length. The patients were categorized into low-risk (< 0.1), medium-risk (0.1–0.25), and high-risk (> = 0.25) groups. Our score model performed satisfying discrimination with the areas under the receiver-operating characteristic curve (AUC) of 0.743 (95% confidence interval (CI), 0.701–0.785) and calibration with goodness of fit in the Hosmer–Lemeshow test (P= 0.088) in internal validation. Conclusions: The prediction model and nomogram demonstrated good performance in predicting the technical difficulty of POEM.