Objective To explore the value of lung high-frequency ultrasound score combined with oxygenation index in predicting weaning outcomes in mechanically ventilated children. Methods The clinical data of 116 mechanically ventilated children were retrospectively analyzed, and they were divided into the success group (n=106) or the failure group (n=10) according to the weaning outcomes. The lung high-frequency ultrasound score and oxygenation index within 2 hours before weaning were compared between the two groups. A multivariate logistic regression model was used to analyze the impacts of the above two indicators on weaning outcomes in mechanically ventilated children. Receiver operating characteristic (ROC) curves were plotted to evaluate the value of lung high-frequency ultrasound score combined with oxygenation index in predicting weaning outcomes in mechanically ventilated children. Results The lung high-frequency ultrasound score in the success group was lower than that in the failure group, while the oxygenation index was higher than that in the failure group (all P<0.05). Results of multivariate logistic regression analysis showed that lung high-frequency ultrasound score (OR=1.650, 95%CI: 1.188-2.293) and oxygenation index (OR=0.976, 95%CI: 0.956-0.997) were independent influencing factors for weaning outcomes in mechanically ventilated children (all P<0.05), based on which a prediction model formula was constructed: Logit(P)=-4.557 + 0.501 × lung high-frequency ultrasound score - 0.024 × oxygenation index. Results of ROC curve analysis showed that the area under the ROC curve of the prediction model of lung high-frequency ultrasound score combined with oxygenation index was 0.825 (95%CI: 0.697-0.954), with a sensitivity of 0.600, a specificity of 0.925, and a Youden index of 0.525. Conclusion Both lung high-frequency ultrasound score and oxygenation index are independent influencing factors for weaning outcomes in mechanically ventilated children. The combined prediction model based on these two indicators has good predictive value for weaning outcomes.