A random forest-neural network coupled model for predicting the recurrence location of uterine cancer

Abstract

With increasing developments and progress, the status and influence of women in society have significantly improved, with more attention paid to women’s health. According to relevant statistics, uterine cancer is a highly-incident malignant tumor in females and urges more research to improve the survival rate of uterine cancer patients. In this study, we established a prediction model to determine the location of uterine cancer recurrence by combining random forest and neural network algorithms. Data of uterine cancer patients were collected from major hospitals, and professional doctors evaluated and graded the patients’ physical fitness indicators based on their experience, which were then used to construct the model and obtain the prediction results. Compared to traditional method, the proposed method of this paper showed that the model was more effective and accurate in predicting the location of uterine cancer recurrence, with a prediction accuracy rate of up to 88.63%.