Application of Artificial Intelligence for Preoperative Diagnostic and Prognostic Prediction in Epithelial Ovarian Cancer Based on Blood Biomarkers

TLDR

Unsupervised clustering of early‑stage epithelial ovarian cancer patients revealed subgroups with markedly worse survival, underscoring the need for pre‑operative prognostic tools. The study aimed to build an ovarian‑cancer‑specific predictive framework for clinical stage, histotype, residual tumor burden, and prognosis using machine‑learning models trained on routine blood biomarkers. Seven supervised classifiers—including GBM, SVM, RF, CRF, Naïve Bayes, NN, and Elastic Net—were trained on 32 peripheral‑blood parameters and age, outperforming conventional regression in predicting multiple EOC clinical variables. Ensemble tree‑based methods, particularly RF, achieved the highest performance, with 92.4 % accuracy and 0.968 AUC for distinguishing EOC from benign tumors, 69 % accuracy and 0.760 AUC for stage prediction, and successful pre‑operative prediction of high‑grade serous and mucinous histotypes and resection completeness; unsupervised clustering also identified high‑risk subgroups.

Abstract

We aimed to develop an ovarian cancer-specific predictive framework for clinical stage, histotype, residual tumor burden, and prognosis using machine learning methods based on multiple biomarkers.Overall, 334 patients with epithelial ovarian cancer (EOC) and 101 patients with benign ovarian tumors were randomly assigned to "training" and "test" cohorts. Seven supervised machine learning classifiers, including Gradient Boosting Machine (GBM), Support Vector Machine, Random Forest (RF), Conditional RF (CRF), Naïve Bayes, Neural Network, and Elastic Net, were used to derive diagnostic and prognostic information from 32 parameters commonly available from pretreatment peripheral blood tests and age.Machine learning techniques were superior to conventional regression-based analyses in predicting multiple clinical parameters pertaining to EOC. Ensemble methods combining weak decision trees, such as GBM, RF, and CRF, showed the best performance in EOC prediction. The values for the highest accuracy and area under the ROC curve (AUC) for segregating EOC from benign ovarian tumors with RF were 92.4% and 0.968, respectively. The highest accuracy and AUC for predicting clinical stages with RF were 69.0% and 0.760, respectively. High-grade serous and mucinous histotypes of EOC could be preoperatively predicted with RF. An ordinal RF classifier could distinguish complete resection from others. Unsupervised clustering analysis identified subgroups among early-stage EOC patients with significantly worse survival.Machine learning systems can provide critical diagnostic and prognostic prediction for patients with EOC before initial intervention, and the use of predictive algorithms may facilitate personalized treatment options through pretreatment stratification of patients.