Survival Period Prediction in Cervical Cancer Patients Using the Selective Stacking Technique

다국어 초록 (Multilingual Abstract)

Objectives: This study aims to increase the effectiveness of cervical cancer treatment by developing a survival predictionmodel using an innovative ensemble machine learning approach, namely the selective stacking technique. Methods: Patientdata obtained from the Faculty of Medicine, Chiang Mai University, Thailand, were utilized to validate the real-world applicabilityof the proposed approach. The selective stacking model employed a two-stage machine learning framework in whichoutputs from base machine learning models were systematically combined through meta-level learning. Importantly, theperformance of the proposed model was compared with that reported in previous studies that relied on individual machinelearning algorithms as baselines. To provide deeper insight into the predictive mechanisms of the model, local interpretablemodel-agnostic explanations were applied to assess feature importance and identify the most influential factors contributingto model predictions. Results: The classification model developed using the selective stacking technique demonstrateda marked improvement in prediction accuracy, achieving an accuracy of 91.41%. The regression model also showed robustperformance, with a root mean square error of 18.92 and an r value of 0.669. Feature importance analysis indicated that sideeffect status involving surrounding organs emerged as the most influential factor in survival prediction. Conclusions: Theselective stacking model exhibited superior predictive performance compared with the base models, suggesting that this approachoffers a promising strategy for cervical cancer survival prediction and may support the development of more personalizedtreatment planning.