The purpose of this paper is to explore the use of eye movement and physiological indicators to evaluate the usability design of the radiotherapy software user interface.First, five important radiotherapy software interface design elements were selected through the expert consultation method, and two different styles of design levels were designed for five design elements by using expert consultation. Secondly, eight radiotherapy software interface prototypes were designed through orthogonal experimental design methods by using the SPSS statistical analysis software for experimental testing. Subsequently, specific experimental test tasks were formulated, and 8 eye movement indicators and 4 physiological indicators were included as the evaluation indicators for the usability of the radiotherapy software interface. At the same time, 20 radiotherapy technicians were recruited to participate in this radiotherapy software usability test, and data of eye movement indicators and physiological indicators were collected for usability evaluation of radiotherapy software.The results of the study show that the electrodermal activity showed significant statistical differences in 8 different pages, which can be used to evaluate and model the usability of radiotherapy software. Then, the partial least squares regression method was used to establish the usability predictive model for interface design elements and electrodermal activity, and the validity of the model was verified.This model can be effectively used to evaluate and predict the usability of the radiotherapy software interface and optimize the usability design of the radiotherapy software interface.