Objective To analyze the risk factors for unfavorable outcomes following vital pulp therapy （VPT） in carious first permanent molars in children and to develop a nomogram-based predictive model. Methods Clinical data from 862 pediatric patients （862 teeth） who underwent VPT for caries-induced pulp exposure in first permanent molars at Suzhou Stomatological Hospital between January 2020 and December 2024 were retrospectively analyzed. Patients were randomly divided into a training set （n = 603） and a validation set （n = 259） in a 7∶3 ratio. The least absolute shrinkage and selection operator （LASSO） regression was applied to identify optimal predictive variables， which were subsequently incorporated into a multivariable logistic regression analysis to construct a nomogram-based prediction model. Model discrimination， calibration， and clinical utility were evaluated using receiver operating characteristic （ROC） curves， calibration curves， and decision curve analysis （DCA）， respectively. Results The incidence of unfavorable outcomes was 12.60% （76/603） in the training set and 12.36% （32/259） in the validation set. LASSO regression identified eight variables with non-zero coefficients： root development， history of spontaneous pain， pulp vitality status， pulp-capping material， cavity classification， timing of restoration， irreversible pulpitis， and hemostasis time > 5 minutes. Multivariable logistic regression analysis revealed that root development （OR = 6.077）， history of spontaneous pain （OR = 5.331）， pulp vitality status （OR = 4.926）， cavity classification （OR = 4.579）， timing of restoration （OR = 3.013）， hemostasis time > 5 minutes （OR = 2.431）， and irreversible pulpitis （OR = 2.392） were independent risk factors for unfavorable outcomes following VPT in carious first permanent molars. Conversely， the use of iRoot BP Plus as a pulp-capping material （OR = 0.440） was identified as a protective factor. ROC curve analysis demonstrated an area under the curve （AUC） of 0.899 （95% CI： 0.872 - 0.926， P < 0.001） in the training set and 0.936 （95% CI： 0.903 - 0.963， P < 0.001） in the validation set. Internal validation using the bootstrap method with 1 000 resampling iterations showed excellent agreement between predicted and observed probabilities on the calibration curves， and DCA confirmed the favorable clinical utility of the model. Conclusion Root development， history of spontaneous pain， pulp vitality status， cavity classification， timing of restoration， prolonged hemostasis time （> 5 minutes）， irreversible pulpitis， and the choice of pulp-capping material are strong predictors of unfavorable outcomes following VPT in carious first permanent molars in children. The developed nomogram provides a valuable tool for the early identification of high-risk patients and guiding clinical decision-making.