Road traffic congestion has become a normal state and caused many problems in large cities of China, and lane-changing model has attracted increased attention in recent years. This study is aimed to explore the changing trend and quantify the logical relationship between driver's heart rate and lane-changing behavior under urban traffic congestion. First, the testing scheme of driver's heart rate and lane-changing has been designed. Tested drivers and testing paths are chosen strictly to achieve the experiments as well. Then, with the drivers' behavior-related data, the backpropagation neural network theory is introduced to build the driver's ''pressure-state-response'' model under urban traffic congestion, which takes driver's pressure and state as input variables, and driver's response is selected as output variables. As the result of pressure-state-response model, it is significant that effect of urban traffic congestion on driver's heart rate and lanechanging proportion. The validation results indicate that the pressure-state-response model works well to predict the proportion of risky lane-changing, and the pressure-state-response model can be used for warning the risky lanechanging directly under urban traffic congestion.