Ultrasonography and a novel combined prediction model for anticipating hypoxemia during painless gastroscopy

Over the years, the application of ultrasound as a non-invasive diagnostic tool has become increasingly widespread in clinical practice. Additionally, the incidence of hypoxemia is relatively high among patients undergoing painless gastroscopy. The primary objective of the present study was to predict the occurrence of hypoxemia in painless gastroscopy by measuring the anatomical parameters of the upper respiratory tract using ultrasound. The present single-center, prospective, observational study included 218 patients. Before anesthesia, basic information (age, sex, BMI) was collected. Preanesthetic ultrasound examined upper airway parameters, including distance from the skin to the hyoid bone (DSH), distance from the skin to the epiglottis (DSE), distance from the skin to the anterior commissure of the vocal cords (DSAC), tongue thickness (TT), hyoid-mental distance (HMD) and anterior condylar translation (ACT). Binary logistic regression was applied to identify independent predictors, and the predictive performance of each variable and a combined model was evaluated using the area under the receiver operating characteristic curve (AUC), calibration analysis and decision curve analysis (DCA). A total of 218 patients were analyzed in the present study. A binary logistic regression model identified BMI, DSH, DSE, DSAC, TT and ACT as the independent indicators associated with hypoxemia in painless gastroscopy. A novel combined predictive model equation was derived: logit(P)=1.053 x BMI + 1.363 x DSH + 1.658 x DSE + 1.839 x DSAC + 1.075 x TT-0.894 x ACT. The model demonstrated excellent discrimination with an AUC of 0.989, 95% CI: 0.979-0.999, significantly outperforming individual predictors (AUC range: 0.775-0.879). Calibration curves confirmed good agreement between predicted and observed risk, and DCA indicated clinical utility of the model. In conclusion, BMI, DSH, DSE, DSAC, TT, ACT and the novel combined predictive model incorporating aforementioned parameters are potentially valuable predictors fort the occurrence of hypoxemia in painless gastroscopy. This study was registered at the Chinese Clinical Trial Registry (trial registration no. ChiCTR2500109627; registered on 23 September 2025).