{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T23:54:06Z","timestamp":1790985246444,"version":"4.1.0"},"reference-count":35,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T00:00:00Z","timestamp":1764720000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Immunol."],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Malignant 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).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We retrospectively analyzed 87 patients with FIGO III\/IV HGSOC with treatment-na\u00efve ascites treated at Peking University Third Hospital (May 2019\u2013Mar 2024; median follow-up, 33 months). Ascites (&amp;gt;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\u2013Hochberg 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\u2013area under the curve (ROC-AUC) for P-DCR]. Model interpretability used Shapley Additive Explanations (SHAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Across 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\n                      <jats:italic>k<\/jats:italic>\n                      (\u22485\u20137). Kaplan\u2013Meier 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\n                      <jats:sup>+<\/jats:sup>\n                      CD57\n                      <jats:sup>+<\/jats:sup>\n                      CD4\n                      <jats:sup>+<\/jats:sup>\n                      and CCR7\n                      <jats:sup>-<\/jats:sup>\n                      CD45RA\n                      <jats:sup>+<\/jats:sup>\n                      CD4\n                      <jats:sup>+<\/jats:sup>\n                      populations, were repeatedly associated with higher risk; age contributed strongly to PFI.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Integrating 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.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fimmu.2025.1698793","type":"journal-article","created":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T05:20:44Z","timestamp":1764739244000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Decoding ascitic immunological niches with multi-modal machine learning reveals prognostic and chemoresistant determinants in ovarian cancer"],"prefix":"10.3389","volume":"16","author":[{"given":"Lin","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhui","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaolan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lin","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qinkun","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuelin","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yufei","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinran","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunliang","family":"Shang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyan","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,12,3]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"216057","DOI":"10.1016\/j.canlet.2023.216057","article-title":"Molecular characteristics and clinical behaviour of epithelial ovarian cancers","volume":"555","author":"Hollis","year":"2023","journal-title":"Cancer Lett"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(18)32552-2","article-title":"Epithelial ovarian cancer","volume":"393","author":"Lheureux","year":"2019","journal-title":"Lancet"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.tjog.2023.09.017","article-title":"Front-line chemo-immunotherapy for treating epithelial ovarian cancer: Part I CA125 and anti-CA125","volume":"62","author":"Yang","year":"2023","journal-title":"Taiwanese J Obstetrics Gynecology"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.tjog.2023.11.005","article-title":"Front-line chemoimmunotherapy for treating epithelial ovarian cancer: Part II promising results of phase 2 study of paclitaxel-carboplatin-oregovomab regimen","volume":"63","author":"Yang","year":"2024","journal-title":"Taiwanese J Obstetrics Gynecology"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(21)00342-9","article-title":"Chemotherapy with or without avelumab followed by avelumab maintenance versus chemotherapy alone in patients with previously untreated epithelial ovarian cancer (JAVELIN Ovarian 100): an open-label, randomised, phase 3 trial","volume":"22","author":"Monk","year":"2021","journal-title":"Lancet Oncol"},{"key":"B6","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1038\/s41416-020-0875-x","article-title":"The untapped potential of ascites in ovarian cancer research and treatment","volume":"123","author":"Ford","year":"2020","journal-title":"Br J Cancer"},{"key":"B7","doi-asserted-by":"publisher","first-page":"5226","DOI":"10.3390\/jcm10225226","article-title":"Management of ascites in patients with cirrhosis: An update","volume":"10","author":"Zaccherini","year":"2021","journal-title":"J Clin Med"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1158\/0008-5472.CAN-22-2273","article-title":"Long-chain acylcarnitines induce senescence of invariant natural killer T cells in hepatocellular carcinoma","volume":"83","author":"Cheng","year":"2023","journal-title":"Cancer Res"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202206768","article-title":"ERK inhibition promotes engraftment of allografts by reprogramming T-cell metabolism","volume":"10","author":"Tan","year":"2023","journal-title":"Adv Sci (Weinh)"},{"key":"B10","doi-asserted-by":"publisher","first-page":"4534","DOI":"10.1038\/s41467-025-58841-z","article-title":"Targeting Setdb1 in T cells induces transplant tolerance without compromising antitumor immunity","volume":"16","author":"Tan","year":"2025","journal-title":"Nat Commun"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1989.10478874","article-title":"The robust inference for the Cox proportional hazards model","volume":"84","author":"Lin","year":"1989","journal-title":"J Am Stat Assoc"},{"key":"B12","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1186\/s12911-024-02525-z","article-title":"Improved nonparametric survival prediction using CoxPH, Random Survival Forest & DeepHit Neural Network","volume":"24","author":"Asghar","year":"2024","journal-title":"BMC Med Inf Decision Making"},{"key":"B13","doi-asserted-by":"publisher","first-page":"105607","DOI":"10.1016\/j.ijmedinf.2024.105607","article-title":"Survival analysis for lung cancer patients: A comparison of Cox regression and machine learning models","volume":"191","author":"Germer","year":"2024","journal-title":"Int J Med Inf"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxac039","article-title":"An online framework for survival analysis: reframing Cox proportional hazards model for large data sets and neural networks","volume":"25","author":"Tarkhan","year":"2024","journal-title":"Biostatistics"},{"key":"B15","doi-asserted-by":"publisher","first-page":"496","DOI":"10.1016\/j.csbj.2022.01.004","article-title":"Violations of proportional hazard assumption in Cox regression model of transcriptomic data in TCGA pan-cancer cohorts","volume":"20","author":"Zeng","year":"2022","journal-title":"Comput Struct Biotechnol J"},{"key":"B16","doi-asserted-by":"publisher","first-page":"110234","DOI":"10.1016\/j.knosys.2022.110234","article-title":"SurvSHAP (t): time-dependent explanations of machine learning survival models","volume":"262","author":"Krzyzi\u0144ski","year":"2023","journal-title":"Knowledge-Based Syst"},{"key":"B17","doi-asserted-by":"publisher","first-page":"4270","DOI":"10.1038\/s41598-024-54943-8","article-title":"Exploring the impact of stage and tumor site on colorectal cancer survival: Bayesian survival modeling","volume":"14","author":"Alinia","year":"2024","journal-title":"Sci Rep"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.7326\/M22-0844","article-title":"Assessing performance and clinical usefulness in prediction models with survival outcomes: practical guidance for Cox proportional hazards models","volume":"176","author":"McLernon","year":"2023","journal-title":"Ann Internal Med"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMra2302038","article-title":"Artificial intelligence and machine learning in clinical medicine, 2023","volume":"388","author":"Haug","year":"2023","journal-title":"New Engl J Med"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.1109\/MMUL.2023.3272513","article-title":"Interpretability of machine learning: Recent advances and future prospects","volume":"30","author":"Gao","year":"2023","journal-title":"IEEE MultiMedia"},{"key":"B21","doi-asserted-by":"publisher","first-page":"105132","DOI":"10.1088\/1402-4896\/ad7a2b","article-title":"Quantifying noncovariance of quantum channels with respect to groups","volume":"99","author":"Lundberg","year":"2024","journal-title":"Physica Scripta"},{"key":"B22","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1186\/s40537-024-00905-w","article-title":"Feature selection strategies: a comparative analysis of SHAP-value and importance-based methods","volume":"11","author":"Wang","year":"2024","journal-title":"J Big Data"},{"key":"B23","doi-asserted-by":"publisher","first-page":"16865","DOI":"10.1038\/s41598-023-44155-x","article-title":"The importance of interpreting machine learning models for blood glucose prediction in diabetes: an analysis using SHAP","volume":"13","author":"Prendin","year":"2023","journal-title":"Sci Rep"},{"key":"B24","doi-asserted-by":"publisher","first-page":"10732748231209892","DOI":"10.1177\/10732748231209892","article-title":"RoBERTa-assisted outcome prediction in ovarian cancer cytoreductive surgery using operative notes","volume":"30","author":"Laios","year":"2023","journal-title":"Cancer Control"},{"key":"B25","doi-asserted-by":"publisher","first-page":"632.e1","DOI":"10.1016\/j.ajog.2024.06.047","article-title":"Prediction of nonresectability using the updated Predictive Index value model assessed by imaging and surgery in tubo-ovarian cancer: a prospective multicenter ISAAC study","volume":"231","author":"Moro","year":"2024","journal-title":"Am J Obstetrics Gynecology"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0279590","article-title":"The role of immune cell subsets in ascitic fluid and their relationship with prognosis in high-grade serous ovarian cancer","volume":"215","author":"Yoshida-Court","year":"2023","journal-title":"J Immunol"},{"key":"B27","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-012-2446-8","article-title":"Impact of residual lesion size on postoperative recurrence and overall survival: A multicenter retrospective analysis","volume":"42","author":"Chang","year":"2024","journal-title":"J Clin Oncol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-012-2446-8","article-title":"Correlation between postoperative residual tumor diameter and survival outcomes in solid tumor patients","volume":"30","author":"Chang","year":"2023","journal-title":"Ann Surg Oncol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"73","DOI":"10.21147\/j.issn.1000-9604.2025.01.06","article-title":"Composite score of PD-1+CD8+ tumor-infiltrating lymphocytes and CD57+CD8+ tumor ascites lymphocytes is associated with prognosis and tumor immune microenvironment of patients with advanced high-grade serous ovarian cancer","volume":"37","author":"He","year":"2025","journal-title":"Chin J Cancer Res"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1038\/s43018-023-00599-8","article-title":"Single-cell analyses implicate ascites in remodeling the ecosystems of primary and metastatic tumors in ovarian cancer","volume":"4","author":"Zheng","year":"2023","journal-title":"Nat Cancer"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1473","DOI":"10.1038\/s41467-017-01728-5","article-title":"Unique phenotypes and clonal expansions of human CD4 effector memory T cells re-expressing CD45RA","volume":"8","author":"Tian","year":"2017","journal-title":"Nat Commun"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1038\/nm1093","article-title":"Specific recruitment of regulatory T cells in ovarian carcinoma fosters immune privilege and predicts reduced survival","volume":"10","author":"Curiel","year":"2004","journal-title":"Nat Med"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.3389\/fimmu.2024.1448041","article-title":"Increased peritoneal TGF-\u03b21 is associated with ascites-induced NK-cell dysfunction and reduced survival in high-grade epithelial ovarian cancer","volume":"15","author":"Maas","year":"2024","journal-title":"Front Immunol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1016\/S0140-6736(10)61268-8","article-title":"MRC OV05; EORTC 55955 investigators. Early versus delayed treatment of relapsed ovarian cancer (MRC OV05\/EORTC 55955): a randomised trial","volume":"376","author":"Rustin","year":"2010","journal-title":"Lancet"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.24149","article-title":"Role of surgical outcome as prognostic factor in advanced epithelial ovarian cancer: a combined exploratory analysis of 3 prospectively randomized phase 3 multicenter trials: by the AGO-OVAR and GINECO groups","volume":"115","author":"Du Bois","year":"2009","journal-title":"Cancer"}],"container-title":["Frontiers in Immunology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2025.1698793\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T05:20:44Z","timestamp":1764739244000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fimmu.2025.1698793\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,3]]},"references-count":35,"alternative-id":["10.3389\/fimmu.2025.1698793"],"URL":"https:\/\/doi.org\/10.3389\/fimmu.2025.1698793","relation":{},"ISSN":["1664-3224"],"issn-type":[{"value":"1664-3224","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,3]]},"article-number":"1698793"}}