Objective To establish a diagnostic model for children with pneumonia of phlegm-heat syndrome based on decision tree and artificial neural network. Methods: Large-sample, multi-center children with pneumonia of phlegm-heat syndrome were used as data sources, using CRT, CHAID, QUEST, C5.0 decision tree and multi-layer perceptron (MLP), radial basis function (RBF) nerves. The network method was used to establish a diagnosis model of pediatric pneumonia of phlegm-heat syndrome and combined with the diagnostic rules of TCM theory analysis model. Results The precision of diagnostic models of pediatric pneumonia, phlegm-heat syndrome established by CRT, CHAID, QUEST and C5.0 algorithm decision trees were 83.1%, 91.0%, 89.5% and 93.2%. The decision tree model using C5.0 algorithm is better than the ago three. The neural network method of MLP and RBF algorithm was used to establish a diagnosis model of pediatric pneumonia, phlegm-heat syndrome. The accuracy rate was 92.1% and 90.8%. The neural network using MLP was better than the neural network using RBF algorithm. Conclusion Using the decision tree and neural network method, a diagnosis model of pediatric pneumonia, phlegm-heat syndrome can be established. Among them, sputum thick, sputum yellow, pulse slippery, cough, and fingerprint purple stagnation are the determining factors in diagnosis. ‘Phlegm’ and ‘Heat’ are the syndromes and pathogenesis of its phlegm-heat syndrome. This study provides an objective basis for clinical syndrome differentiation and treatment of pediatric pneumonia, and is beneficial to promote the standardization process of Chinese medicine.