Objective The aim of this study was to investigate the application of machine learning in the prediction of hemodynamic parameters in combined stenotic left coronary artery aneurysms. Methods This article first conducts parameterized modeling and simulation based on the geometric parameter range of combined stenosis left coronary artery aneurysm in clinical statistics. The obtained simulation data is used as the dataset, and two common machine learning models are constructed and trained for optimization to predict the two key hemodynamic parameters of wall shear stress and pressure. By comparing and analyzing the performance of these models on the training and testing sets, the accuracy of each model was evaluated, and the effectiveness of data-driven prediction of hemodynamic parameters for left coronary artery aneurysm with concomitant stenosis was verified. Results The effectiveness of machine learning methods in inverting hemodynamic parameters of aneurysms has been determined. In predicting wall shear stress, the trained deep learning model and random forest model achieved MSE、MAE and R2 of 0.0528, 0.0322, 0.9883, and 0.0782, 0.0463, and 0.9766, respectively. For pressure prediction, the accuracy of deep learning models and random forest models is comparable, with MSE、MAE and R2 of 4.67×10-6, 3×10-4, 0.9997, and 1.07×10-5, 5×10-4, and 0.9993, respectively. Conclusions Machine learning methods show high accuracy in predicting hemodynamic parameters in combined stenotic coronary artery aneurysm models, and the predictive accuracy of the model, computational efficiency, and the needs of the application scenarios need to be taken into account in machine learning prediction, so that the appropriate model can be selected according to the specific situation. This study has certain clinical significance, which helps doctors to more accurately evaluate the patient's condition and provides new ideas and methods for the diagnosis and treatment of cardiovascular diseases.