AUTHOR=Yang Lin , He Tianhui , Wang Jing , Zhang Xiaolan , Zeng Lin , Sun Qinkun , Song Yuelin , Nie Yufei , Gao Xinran , Shang Chunliang , Guo Hongyan 

TITLE=Decoding ascitic immunological niches with multi-modal machine learning reveals prognostic and chemoresistant determinants in ovarian cancer

JOURNAL=Frontiers in Immunology

VOLUME=Volume 16 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/immunology/articles/10.3389/fimmu.2025.1698793

DOI=10.3389/fimmu.2025.1698793

ISSN=1664-3224

ABSTRACT=BackgroundMalignant ascites in high-grade serous ovarian cancer (HGSOC) represent a fluid extension of the tumor microenvironment, embedding immune programs that may inform prognosis and treatment response. We investigated whether ascitic T-cell phenotypes, integrated with clinical variables, improve prediction of overall survival (OS), progression-free survival (PFS), progression-free interval (PFI), and platinum-based drug chemotherapy resistance (P-DCR).MethodsWe retrospectively analyzed 87 patients with FIGO III/IV HGSOC with treatment-naïve ascites treated at Peking University Third Hospital (May 2019–Mar 2024; median follow-up, 33 months). Ascites (>1,000 mL) underwent standardized processing and multiparametric flow cytometry to quantify T-cell subsets. To prevent information leakage, we used repeated nested cross-validation with event-stratified folds: inner folds performed endpoint-specific screening with Benjamini–Hochberg FDR control, redundancy reduction, and multicollinearity checks; clinical covariates were added by incremental contribution testing. Cox proportional hazards, Random Survival Forests (RSFs), and DeepSurv modeled survival endpoints; a random-forest classifier modeled P-DCR. Performance was summarized on outer folds [C-index for survival; receiver operating characteristic–area under the curve (ROC-AUC) for P-DCR]. Model interpretability used Shapley Additive Explanations (SHAP).ResultsAcross endpoints, combined clinical + ascites features outperformed single-source features, with RSF consistently best. Outer-fold testing C-indices for RSF with combined features were 0.72 (OS), 0.70 (PFS), and 0.74 (PFI). The P-DCR classifier achieved a mean AUC of 0.69 with combined features (accuracy, 0.66; sensitivity, 0.70; specificity, 0.62). Feature-count sensitivity analyses showed performance gains plateauing at modest k (≈5–7). Kaplan–Meier curves derived from combined-feature risk scores demonstrated clear stratification. SHAP analyses indicated protective effects of poly(ADP-ribose) polymerase (PARP) inhibitor maintenance across endpoints, while ascitic T-cell subsets, including PD-1+CD57+CD4+ and CCR7-CD45RA+CD4+ populations, were repeatedly associated with higher risk; age contributed strongly to PFI.ConclusionsIntegrating ascitic immunophenotyping with clinical factors improves risk prediction in HGSOC, with RSF offering robust performance under rigorous, leakage-safe validation. Ascites-resident T-cell states provide complementary, reproducible prognostic signals for survival and platinum response, supporting their potential utility for patient stratification and hypothesis generation for immunomodulatory strategies.