Modeling and analytics of multi-factor disease evolutionary process by fusing petri nets and machine learning methods

Recent years, informatization methods have been gradually applied to medical treatment, in which machine learning and evolutionary computation play an important role. However, the effective methods for the study of multi-factor disease evolutionary process are still largely open. There are some issues in the field of disease analysis, such as the lack of visual multi-factor disease evolution model and effective analysis methods. For a universal method of data analysis and medical diagnosis, the machine learning algorithms should be combined with the formal modeling methods to fully realize the complementary advantages, make model has the advantages of visualization and efficient data analysis. This work proposes a novel research idea for the modeling analysis of current multi-factor diseases and reveal its feasibility, so as to explore potential pharmaceutical targets and enable doctors and patients to better understand the evolution process of multi-factor diseases. It is worth mentioning that, in order to verify the feasibility of the proposed idea, we applied it to the analysis of the role of monoamine hormones in depression. The model incorporates the machine learning algorithms, and it finally outputs the pathogenic probability under different hormone levels, reflecting the importance of different factors on depression. The application case proved that we provide a clear process model and a novel research method for multi-factor disease evolutionary process analysis.