Integrative art therapy has achieved great results in improving neurosis, palliative care, mental development of special children, and mental health education of adolescents. Integrative art therapy is an applied technique that integrates artistic creation and psychotherapy. This topic studies the influence of integrated art therapy on adolescent mental health based on big data analysis, and establishes a big data analysis model of adolescent mental health. Through DM(data mining), the most valuable information is extracted, expressed in an easy-to-understand way, and analyzed and evaluated accordingly. In this process, the information should be filtered, hoping to get the information that meets the purpose of mining. Descriptive mining is used to describe the general properties of the mined data. If we want to make predictions by inferring the current data, we should use predictive mining. The results show that the scores of each item factor of SCL-90 self-rating scale in the experimental group have been improved obviously. It is mainly manifested in: somatization, obsessive-compulsive symptoms, interpersonal sensitivity, depression, hostility, terror and paranoia. The scores of these seven items have all dropped below 1.5. The median probability of using C4.5 model to predict the mental state as “abnormal” is 0.8135, and the lowest probability of using BPNN (BP neural network) model to predict the mental state as “abnormal” is 0.6082. This provides an idea for designing a psychological crisis prevention system based on the comprehensive C4.5 and BPNN technologies.