{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T18:15:36Z","timestamp":1785521736629,"version":"3.56.0"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T00:00:00Z","timestamp":1779235200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T00:00:00Z","timestamp":1785196800000},"content-version":"vor","delay-in-days":69,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China Project","doi-asserted-by":"crossref","award":["82360359"],"award-info":[{"award-number":["82360359"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science and Technology Innovation 2030- Major Project of \"New Generation Artificial Intelligence\" -Robust, Fair, and Trustworthy Comprehensive Evaluation System for Models","award":["2022ZD0160705"],"award-info":[{"award-number":["2022ZD0160705"]}]},{"name":"National Science and Technology Innovation 2030- Major Project of \"New Generation Artificial Intelligence\"","award":["2022ZD0160700"],"award-info":[{"award-number":["2022ZD0160700"]}]},{"name":"Xinjiang Key Laboratory of Artificial intelligence Assisted lmaging Diagnosis Fund","award":["XJRGZN2024011"],"award-info":[{"award-number":["XJRGZN2024011"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Discov Onc"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>We developed interpretable machine learning(ML) models to predict overall survival in bladder cancer patients. This approach aims to improve the interpretability and transparency of our modeling results.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We collected clinical and pathological information on bladder cancer patients from the SEER database, allocating it to training and validation sets in a 7:3 ratio. At the same time, we obtained an external validation cohort from Kashgar First People\u2019s Hospital in Xinjiang, China. We performed LASSO regression and Cox regression analyses to identify relevant risk factors and then combined these to develop CoxPH and six ML models: Random Survival Forest(RSF), Gradient Boosting with Component Linear(GLMboost), decision tree(dt), boosted tree(bt), DeepSurv, and neural multi-task logistic regression(NMTLR). We evaluated the predictive performance of these ML models using the consistency index (C-index), the area under the cumulative\/dynamic curve (AUC) and the integrated Brier score and Kolmogorov-Smirnov(KS). For interpretability assessment, we employed three complementary methods: (1)time-dependent variable importance to quantify feature contribution across follow-up periods; (2)partial correlation survival plots to visualize individual variable effects; and (3)aggregated survival SHapley additive interpretation(SurvSHAP) plots with mean absolute deviation metrics to validate feature impact stability at both individual and population levels.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The final ML model consists of 14 factors: the patient\u2019s age, AJCCStage, chemotherapy, Mstage, marital, Tstage, bone metastasis(BoneMets), stage, radiation, histology, liverMets, Nstage, sex. Our predictive models demonstrates significant discriminative ability, with the boosting tree model performing the best. The AUC for 1-year, 3-year, and 5-year overall survival (OS) was above 0.770 for the training set, validation set, and external validation set, respectively, with the overall Brier score consistently below 0.180. The interpretability analysis of the boosting trees model further indicated that AJCCStage, age, chemotherapy, stage, Mstage, marital were the most influential predictors via quantifiable SurvSHAP values and time-dependent importance weights, with their effects visually validated through partial correlation survival curves.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The boosting trees model prognostic model has the best performance and can be used to predict OS in bladder cancer patients, helping physicians to accurately assess patients\u2019 overall survival rates, and providing valuable and important references for patient diagnosis, treatment, and prognosis evaluation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s12672-026-05099-6","type":"journal-article","created":{"date-parts":[[2026,5,20]],"date-time":"2026-05-20T05:45:39Z","timestamp":1779255939000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable machine learning models for bladder cancer overall survival prediction development and external validation via SEER database and Chinese cohort analysis"],"prefix":"10.1007","volume":"17","author":[{"given":"Saimaitikari","family":"Abudoubari","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abudouresuli","family":"Tuersun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sailidan","family":"Mutailipu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenbin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiange","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mayidili","family":"Nijiati","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoguang","family":"Zou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,5,20]]},"reference":[{"issue":"8","key":"5099_CR1","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1007\/s00345-019-02984-4","volume":"38","author":"A Richters","year":"2020","unstructured":"Richters A, Aben KKH, Kiemeney LALM. The global burden of urinary bladder cancer: an update. World J Urol. 2020;38(8):1895\u2013904.","journal-title":"World J Urol"},{"issue":"9","key":"5099_CR2","doi-asserted-by":"publisher","first-page":"2060","DOI":"10.1002\/ijc.29670","volume":"137","author":"F Bray","year":"2015","unstructured":"Bray F, Ferlay J, Laversanne M, et al. Cancer Incidence in Five Continents: Inclusion criteria, highlights from X and the global status of cancer registration. Int J Cancer. 2015;137(9):2060\u201371.","journal-title":"Int J Cancer"},{"issue":"1","key":"5099_CR3","doi-asserted-by":"publisher","first-page":"5","DOI":"10.21037\/tau.2018.09.11","volume":"8","author":"MGK Cumberbatch","year":"2019","unstructured":"Cumberbatch MGK, Noon AP. Epidemiology, aetiology and screening of bladder cancer. Transl Androl Urol. 2019;8(1):5\u201311.","journal-title":"Transl Androl Urol"},{"issue":"12","key":"5099_CR4","doi-asserted-by":"publisher","first-page":"2356","DOI":"10.1002\/cam4.4625","volume":"11","author":"W Shangguan","year":"2022","unstructured":"Shangguan W, Hu J, Xie Y, et al. Conditional survival of trimodal therapy for nonmetastatic muscle-invasive bladder cancer: A SEER database analysis. Cancer Med. 2022;11(12):2356\u201365.","journal-title":"Cancer Med"},{"issue":"1","key":"5099_CR5","doi-asserted-by":"publisher","first-page":"17","DOI":"10.3322\/caac.21763","volume":"73","author":"RL Siegel","year":"2023","unstructured":"Siegel RL, Miller KD, Wagle NS, et al. Cancer statistics, 2023[J]. CA Cancer J Clin. 2023;73(1):17\u201348. https:\/\/doi.org\/10.3322\/caac.21763.","journal-title":"CA Cancer J Clin"},{"issue":"2","key":"5099_CR6","doi-asserted-by":"publisher","first-page":"726","DOI":"10.3390\/jcm12020726","volume":"12","author":"S Yang","year":"2023","unstructured":"Yang S, Zhou H, Feng C, et al. Web-Based Nomograms for Overall Survival and Cancer-Specific Survival of Bladder Cancer Patients with Bone Metastasis: A Retrospective Cohort Study from SEER Database. J Clin Med. 2023;12(2):726.","journal-title":"J Clin Med"},{"key":"5099_CR7","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1016\/j.csbj.2024.06.035","volume":"23","author":"H Liu","year":"2024","unstructured":"Liu H, Zhang W, Zhang Y, et al. Mime: A flexible machine-learning framework to construct and visualize models for clinical characteristics prediction and feature selection. Comput Struct Biotechnol J. 2024;23:2798\u2013810.","journal-title":"Comput Struct Biotechnol J"},{"issue":"1","key":"5099_CR8","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1186\/s13054-024-05138-0","volume":"28","author":"C Guan","year":"2024","unstructured":"Guan C, Gong A, Zhao Y, et al. Interpretable machine learning model for new-onset atrial fibrillation prediction in critically ill patients: a multi-center study. Crit Care. 2024;28(1):349.","journal-title":"Crit Care"},{"issue":"5","key":"5099_CR9","doi-asserted-by":"publisher","first-page":"2135","DOI":"10.1002\/alz.12948","volume":"19","author":"SA Martin","year":"2023","unstructured":"Martin SA, Townend FJ, Barkhof F, et al. Interpretable machine learning for dementia: A systematic review. Alzheimers Dement. 2023;19(5):2135\u201349.","journal-title":"Alzheimers Dement"},{"issue":"11","key":"5099_CR10","doi-asserted-by":"publisher","first-page":"e70056","DOI":"10.1111\/cts.70056","volume":"17","author":"AV Ponce-Bobadilla","year":"2024","unstructured":"Ponce-Bobadilla AV, Schmitt V, Maier CS, et al. Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development. Clin Transl Sci. 2024;17(11):e70056.","journal-title":"Clin Transl Sci"},{"issue":"24","key":"5099_CR11","doi-asserted-by":"publisher","first-page":"11080","DOI":"10.7150\/thno.49864","volume":"10","author":"R Cao","year":"2020","unstructured":"Cao R, Yang F, Ma SC, et al. Development and interpretation of a pathomics-based model for the prediction of microsatellite instability in Colorectal Cancer. Theranostics. 2020;10(24):11080\u201391.","journal-title":"Theranostics"},{"issue":"1","key":"5099_CR12","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1186\/s13062-025-00650-x","volume":"20","author":"H Dai","year":"2025","unstructured":"Dai H, Yu Z, Zhao Y, et al. Integrating machine learning models with multi-omics analysis to decipher the prognostic significance of mitotic catastrophe heterogeneity in bladder cancer. Biol Direct. 2025;20(1):56.","journal-title":"Biol Direct"},{"issue":"5","key":"5099_CR13","first-page":"511","volume":"12","author":"J Wang","year":"2025","unstructured":"Wang J, Kang Q, Tian S, et al. Development, Validation, and Deployment of a Time-Dependent Machine Learning Model for Predicting One-Year Mortality Risk in Critically Ill Patients with Heart Failure. Bioeng (Basel). 2025;12(5):511.","journal-title":"Bioeng (Basel)"},{"issue":"10","key":"5099_CR14","doi-asserted-by":"publisher","first-page":"950","DOI":"10.1002\/bco2.425","volume":"5","author":"K Sato","year":"2024","unstructured":"Sato K, Sazuka T, Arai T, et al. Machine learning analysis for detecting late recurrence and loss to follow-up after renal cell carcinoma surgery. BJUI Compass. 2024;5(10):950\u20136.","journal-title":"BJUI Compass"},{"issue":"38","key":"5099_CR15","doi-asserted-by":"publisher","first-page":"e22191","DOI":"10.1097\/MD.0000000000022191","volume":"99","author":"Z Wang","year":"2020","unstructured":"Wang Z, Zhou Y, Guan C, et al. The impact of previous cancer on overall survival of bladder cancer patients and the establishment of nomogram for overall survival prediction. Med (Baltim). 2020;99(38):e22191.","journal-title":"Med (Baltim)"},{"issue":"44","key":"5099_CR16","doi-asserted-by":"publisher","first-page":"e17725","DOI":"10.1097\/MD.0000000000017725","volume":"98","author":"Y Zhang","year":"2019","unstructured":"Zhang Y, Hong YK, Zhuang DW, et al. Bladder cancer survival nomogram: Development and validation of a prediction tool, using the SEER and TCGA databases. Med (Baltim). 2019;98(44):e17725.","journal-title":"Med (Baltim)"},{"key":"5099_CR17","doi-asserted-by":"publisher","first-page":"1164401","DOI":"10.3389\/fonc.2023.1164401","volume":"13","author":"Y Li","year":"2023","unstructured":"Li Y, Chen T, Fu B, et al. Survival nomogram for high-grade bladder cancer patients after surgery based on the SEER database and external validation cohort. Front Oncol. 2023;13:1164401.","journal-title":"Front Oncol"},{"issue":"23","key":"5099_CR18","doi-asserted-by":"publisher","first-page":"3495","DOI":"10.3390\/diagnostics13233495","volume":"13","author":"FH Yagin","year":"2023","unstructured":"Yagin FH, Alkhateeb A, Raza A, et al. An Explainable Artificial Intelligence Model Proposed for the Prediction of Myalgic Encephalomyelitis\/Chronic Fatigue Syndrome and the Identification of Distinctive Metabolites. Diagnostics (Basel). 2023;13(23):3495.","journal-title":"Diagnostics (Basel)"},{"key":"5099_CR19","doi-asserted-by":"publisher","first-page":"1420328","DOI":"10.3389\/fonc.2024.1420328","volume":"14","author":"Z Javanmard","year":"2025","unstructured":"Javanmard Z, Zarean Shahraki S, Safari K, et al. Artificial intelligence in breast cancer survival prediction: a comprehensive systematic review and meta-analysis. Front Oncol. 2025;14:1420328.","journal-title":"Front Oncol"},{"key":"5099_CR20","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.puhe.2024.07.027","volume":"236","author":"LY Zhang","year":"2024","unstructured":"Zhang LY, Wang P, Wang YB, et al. Global, regional, and national burden of bladder cancer, 1990\u20132019: an age-period-cohort analysis based on the Global Burden of Disease 2019 study. Public Health. 2024;236:193\u2013203.","journal-title":"Public Health"},{"issue":"7","key":"5099_CR21","doi-asserted-by":"publisher","first-page":"3084","DOI":"10.1007\/s00261-024-04786-8","volume":"50","author":"MR Nouh","year":"2025","unstructured":"Nouh MR, Ezz Eldin O. Precise vesical wall staging of bladder cancer in the era of precision medicine: has it been fulfilled? Abdom Radiol (NY). 2025;50(7):3084\u201391.","journal-title":"Abdom Radiol (NY)"},{"issue":"1","key":"5099_CR22","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.eururo.2020.03.055","volume":"79","author":"JA Witjes","year":"2021","unstructured":"Witjes JA, Bruins HM, Cathomas R, et al. European Association of Urology Guidelines on Muscle-invasive and Metastatic Bladder Cancer: Summary of the 2020 Guidelines. Eur Urol. 2021;79(1):82\u2013104.","journal-title":"Eur Urol"},{"issue":"2","key":"5099_CR23","doi-asserted-by":"publisher","first-page":"1685","DOI":"10.1002\/cam4.5003","volume":"12","author":"K Krajc","year":"2023","unstructured":"Krajc K, Miro\u0161evi\u010d \u0160, Sajovic J, et al. Marital status and survival in cancer patients: A systematic review and meta-analysis. Cancer Med. 2023;12(2):1685\u2013708.","journal-title":"Cancer Med"}],"container-title":["Discover Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12672-026-05099-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12672-026-05099-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12672-026-05099-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T17:05:09Z","timestamp":1785517509000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12672-026-05099-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,20]]},"references-count":23,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["5099"],"URL":"https:\/\/doi.org\/10.1007\/s12672-026-05099-6","relation":{},"ISSN":["2730-6011"],"issn-type":[{"value":"2730-6011","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,20]]},"assertion":[{"value":"13 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 May 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The study using data from the Surveillance, Epidemiology, and End Results (SEER) database was exempt from ethical review and informed consent requirements due to the public and de-identified nature of the dataset, and the research was conducted in accordance with the Declaration of Helsinki. The external validation cohort data were obtained from the First People\u2019s Hospital of Kashi Prefecture, Xinjiang, China, and this study was formally approved by the Ethics Committee of the First People\u2019s Hospital of Kashi Prefecture. All research procedures involving the external validation cohort were performed in compliance with the Declaration of Helsinki and relevant national and institutional ethical guidelines. This is a retrospective observational study. The SEER database data are publicly available with all patient information anonymized, thus the requirement for informed consent to participate was waived for this part of the study. For the external validation cohort from the First People\u2019s Hospital of Kashi Prefecture, the Ethics Committee of the hospital also waived the requirement for individual informed consent to participate due to the retrospective design, fully anonymized clinical records, and no additional interventions applied to the patients.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All data used in this study are fully anonymized. No identifiable personal information (including names, contact details, medical record numbers, and unique biometric identifiers) or identifiable clinical images of patients are included in the manuscript. Therefore, the requirement for individual patient consent to publish is not applicable, and this study complies with relevant ethical guidelines and journal requirements for publication consent.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"1091"}}