Big Data Analysis Of Female Dysmenorrhea Based On Multiple Machine Learning Methods

Dysmenorrhea is one of the most common gynecological disorders, and when it is severe, it may have many adverse effects on the patient's life and work. In order to assist the treatment of dysmenorrhea and reduce the pain of patients as much as possible, this paper carries out a questionnaire survey on all the females in a university in Qingdao City. Based on the collected data, a variety of machine learning models including association rule, least absolute shrinkage and selection operator (LASSO), decision tree, and random forest are set up to find out the relevant factors affecting dysmenorrhea, and a dysmenorrhea prediction model is set up and optimized. The experimental results show that the various machine learning methods proposed in this paper have good effects on studying the causes of dysmenorrhea and predicting the occurrence of dysmenorrhea.