Performance of Predictive Models in Cervical Cancer Recurrence: A Systematic Review and Meta-Analysis of Biomarkers and Prognosis

Abstract

This study investigates the use of Predictive Analytics Frameworks (PAF) for identifying biomarkers of recurrent cervical cancer and predicting prognosis. It addresses the limited comprehensive evaluations of the effectiveness of predictive models in this area, despite the growing application of machine learning in healthcare. The purpose of this systematic review and meta-analysis is to assess the performance of predictive analytics models in terms of sensitivity, accuracy, specificity, and the area under the curve (AUC-ROC) for identifying cervical cancer biomarkers and predicting prognosis. To address this research problem, a systematic review and meta-analysis was conducted, covering studies published between 2014 and 2024. A total of 1,515 studies were initially identified from the PubMed and Scopus databases, with 50 research studies meeting the inclusion criteria. Repeated measures ANOVA and meta-analysis were applied using data collected over an 8-year period to evaluate recurrence trends and the predictive power of various models. The findings suggest that predictive analytics models show significant potential for improving diagnostic accuracy in identifying cervical cancer biomarkers. However, the review also highlights several limitations, including the small number of included studies, heterogeneity across studies, and potential bias in retrospective analyses. In conclusion, while predictive analytics frameworks demonstrate promise in improving cervical cancer prognosis and biomarker identification, further research is required to validate these findings and assess their broader clinical utility. The study underscores the importance of continued exploration of predictive models to enhance decision-making in oncology.