Answers are grounded in this paper and cite their sources.
Objectives: Fear of cancer recurrence (FCR) is a common psychological issue among breast cancer patients, yet predictive methods are lacking. This study aimed to construct and compare three models for predicting FCR among recovering breast cancer patients. Methods: A total of 490 breast cancer patients in rehabilitation were recruited from a university hospital in Harbin, China. Factors affecting FCR were collected using specific questionnaires. Multivariate analysis identified effective influencing factors, which were used as independent variables in a logistic regression model, an artificial neural network (ANN) model, and a random forest model. The dependent variable was high-level FCR. Models were validated using 10 × 10 cross-validation, and their performance was compared using AUC values, sensitivity, specificity, accuracy, positive predictive value, and negative predictive value. Results: Six factors influenced FCR: age, occupational status, chemotherapy, self-image, cancer-caused fatigue, and disease perception. The logistic regression model showed an accuracy of 83.7%, sensitivity of 79.3%, specificity of 86.9%, positive predictive value of 85.1%, negative predictive value of 81.7%, and an AUC value of 0.746. The ANN model had an accuracy of 78.2%, sensitivity of 80.0%, specificity of 75.8%, positive predictive value of 81.9%, negative predictive value of 73.4%, and an AUC value of 0.746. The random forest model demonstrated an accuracy of 84.4%, sensitivity of 89.4%, specificity of 77.4%, positive predictive value of 84.4%, negative predictive value of 84.2%, and an AUC value of 0.892. Conclusion: The random forest model outperformed the ANN and logistic regression models in predicting FCR in recovering breast cancer patients, making it a valuable tool for screening high-risk FCR groups during rehabilitation.
No takes yet. Share an insight, caveat, or question.
Yang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: