a b s t r a c t
Ovarian cancer is the second leading cause of deaths among gynecologic cancers in the world. Approximately 90% of women with ovarian cancer reported having symptoms long before a diagnosis was
made. Literature shows that recurrence should be predicted with regard to their personal risk factors and
the clinical symptoms of this devastating cancer. In this study, ensemble learning and five data mining
approaches, including support vector machine (SVM), C5.0, extreme learning machine (ELM), multivariate adaptive regression splines (MARS), and random forest (RF), were integrated to rank the importance
of risk factors and diagnose the recurrence of ovarian cancer. The medical records and pathologic status
were extracted from the Chung Shan Medical University Hospital Tumor Registry. Experimental results
illustrated that the integrated C5.0 model is a superior approach in predicting the recurrence of ovarian
cancer. Moreover, the classification accuracies of C5.0, ELM, MARS, RF, and SVM indeed increased after
using the selected important risk factors as predictors. Our findings suggest that The International Federation of Gynecology and Obstetrics (FIGO), Pathologic M, Age, and Pathologic T were the four most critical
risk factors for ovarian cancer recurrence. In summary, the above information can support the important
influence of personality and clinical symptom representations on all phases of guide interventions, with
the complexities of multiple symptoms associated with ovarian cancer in all phases of the recurrent
trajectory.