Objective To explore the risk factors that affect the prognosis of children with acute myeloid leukemia (cAML), to construct a prognostic nomogram model and further to verify the predictive value of this model. Methods The data of 1 068 children with cAML were downloaded from TARGET database, and 839 cases with complete data were included after screening. The clinicopathological features of the children were collected, including age, sex, race, survival status, white blood cell count, central nervous system leukemia, whether there were extramedullary invasion diseases such as green tumor (chloroma), the number of peripheral blood mother cells, remission status, whether there were fusion genes, the number of abnormal chromosomes and structural changes. Univariate Cox regression analysis was used to screen the factors related to prognosis, and multivariate Cox regression analysis was used to further screen independent prognostic factors. A nomogram model was established to predict the overall survival (OS) of 3, 5 and 7 years. The prediction accuracy and discriminant ability of the nomogram model were determined by the concordance index (C index), the calibration curve, and the area under the ROC curve (AUC). The stability of the nomogram model was verified by internal verification. Results Multivariate Cox regression analysis showed that the independent influencing factors of OS were white blood cell count at diagnosis, monosomy-7, t (6; 11) (q27; q23), t (10; 11) (p11. 2; q23), t (8; 21), inv (16), and NPM mutation, and the nomogram model was successfully constructed based on the above predictors. The C index of the nomogram model constructed by the training set was 0. 704 (95% CI was 0. 677-0. 731), and the AUC values for predicting 3-, 5- and 7-year survival rates were 0. 701, 0. 709 and 0. 708, respectively. The C index of the nomogram model constructed by the internal verification set was 0. 702 (95% CI was 0. 689-0. 715), and the AUC values for predicting 3-, 5- and 7-year survival rates were 0. 700, 0. 713 and 0. 713, respectively. The calibration curves of the training set and the verification set showed that the predicted risk was consistent with the actual disease risk. The risk score was calculated based on the regression coefficient of multivariate Cox regression analysis. The children in training set and internal verification set were divided into the high risk score group and low risk score group. The results of Kaplan-Meier survival analysis showed that the OS of the high risk score group was significantly lower than that of low risk score group. Conclusion The influencing factors for the prognosis of children with cAML are white blood cell count at diagnosis, monosomy-7, (t 6; 11) (q27; q23), (t 10; 11) (p11. 2; q23), (t 8; 21), inv (16), and NPM mutation; the prognostic nomogram model successfully constructed based on the above predictive factors can objectively and accurately predict the prognosis of children with cAML. [ABSTRACT FROM AUTHOR]