{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,2]],"date-time":"2026-10-02T23:50:53Z","timestamp":1790985053503,"version":"4.1.0"},"reference-count":33,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:00:00Z","timestamp":1771459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T00:00:00Z","timestamp":1771459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/100008363","name":"Kr\u00e6ftens Bek\u00e6mpelse","doi-asserted-by":"publisher","award":["R204\u2010A12597"],"award-info":[{"award-number":["R204\u2010A12597"]}],"id":[{"id":"10.13039\/100008363","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005940","name":"Dansk Kr\u00e6ftforsknings Fond","doi-asserted-by":"publisher","award":["270"],"award-info":[{"award-number":["270"]}],"id":[{"id":"10.13039\/501100005940","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001732","name":"Danmarks Grundforskningsfond","doi-asserted-by":"publisher","award":["DNRF126"],"award-info":[{"award-number":["DNRF126"]}],"id":[{"id":"10.13039\/501100001732","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Andrology"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Approximately one\u2010fourth of patients with clinical stage I testicular cancer relapse. For decades, risk stratification has been based on different tumor characteristics for seminomas and non\u2010seminomas. Previous studies primarily used Cox proportional\u2010hazards models and included only a limited number of variables. Machine learning techniques can integrate large datasets and may uncover novel combinations of risk factors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Objectives<\/jats:title>\n                    <jats:p>To develop and validate a unified machine learning\u2010based relapse prediction model for clinical stage I testicular cancer, regardless of histologic subtype, using nationwide histopathological and clinical data.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Materials and Methods<\/jats:title>\n                    <jats:p>A population\u2010based cohort study of 1377 patients diagnosed with clinical stage I testicular cancer in Denmark from 2013 to 2018. Histopathological and clinical data were obtained through centralized pathology assessment and systematic medical record review. Two tree\u2010based binary classifiers (CatBoost and LightGBM) were trained to predict relapse, and a random survival forest model was used to estimate time\u2010to\u2010relapse. Data were split into training (80%, 5\u2010fold cross\u2010validation) and a test set (20%), balanced by seminoma\/non\u2010seminoma subtypes and outcome. Subgroup analyses were performed for seminoma and non\u2010seminoma. Binary models were evaluated using receiver operating characteristic area under the curve, precision\u2010recall area under the curve, and Matthew's correlation coefficient; random survival forest performance was assessed using concordance index and Integrated Brier Score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>CatBoost outperformed LightGBM (receiver operating characteristic area under the curve = 0.74) and demonstrated a high negative predictive value (0.86). The random survival forest achieved a concordance index of 0.71. Predictive performance was stronger in the non\u2010seminoma than in the seminoma subgroups. Top\u2010ranked predictive features included lymphovascular invasion, embryonal carcinoma, tumor necrosis, rete testis invasion, tumor size, and elevated lactate dehydrogenase and \u03b2\u2010human chorionic gonadotropin. Tumor necrosis and the anatomical location of lymphovascular invasion emerged as novel predictors.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion and Conclusion<\/jats:title>\n                    <jats:p>A unified machine learning\u2010based model for relapse prediction in clinical stage I testicular cancer is feasible and demonstrates moderate predictive accuracy. It is particularly useful for ruling out relapse and shows greater robustness in non\u2010seminoma. These findings provide a framework for validation in independent cohorts and highlight key predictive features for future research.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/andr.70195","type":"journal-article","created":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T10:52:51Z","timestamp":1771498371000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["A Unified Machine Learning Model for Relapse Prediction in Clinical Stage I Testicular Cancer"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0256-0074","authenticated-orcid":false,"given":"Thomas","family":"Wagner","sequence":"first","affiliation":[{"name":"Department of Pathology Copenhagen University Hospital Herlev and Gentofte Hospital  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ramtin Zargari","family":"Marandi","sequence":"additional","affiliation":[{"name":"Centre of Excellence for Health, Immunity and Infections (CHIP), Copenhagen University Hospital Rigshospitalet  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9985-174X","authenticated-orcid":false,"given":"Jakob","family":"Lauritsen","sequence":"additional","affiliation":[{"name":"Department of Oncology Copenhagen University Hospital Rigshospitalet  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel Dawson","family":"Murray","sequence":"additional","affiliation":[{"name":"Centre of Excellence for Health, Immunity and Infections (CHIP), Copenhagen University Hospital Rigshospitalet  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mikkel","family":"Bandak","sequence":"additional","affiliation":[{"name":"Department of Oncology Copenhagen University Hospital Rigshospitalet  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Birgitte","family":"Gr\u00f8nk\u00e6r Toft","sequence":"additional","affiliation":[{"name":"Department of Pathology Copenhagen University Hospital Rigshospitalet  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5474-8696","authenticated-orcid":false,"given":"Dan","family":"Berney","sequence":"additional","affiliation":[{"name":"Centre of Cancer Biomarkers and Biotherapeutics, Barts Cancer Institute Barts Cancer Institute Charterhouse Square, Queen Mary University of London  London UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gedske","family":"Daugaard","sequence":"additional","affiliation":[{"name":"Department of Oncology Copenhagen University Hospital Rigshospitalet  Copenhagen Denmark"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,2,19]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1002\/ijc.33999"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"e_1_2_11_4_1","unstructured":"Danish Testicular Cancer Group (DaTeCa).\u00c5rsrapport 2023\u20132024. Sundhed.dk website (2025). Accessed September 28 2025 https:\/\/sundk.dk\/media\/443jw34l\/dateca\u2010aarsrapport_2023\u20102024_offentliggjort_version_20250616.pdf."},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2014.07.001"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2013.53.5831"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2017.12.030"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.euf.2024.06.001"},{"key":"e_1_2_11_9_1","unstructured":"M. P.Laguna P.Albers F.Algaba et\u00a0al. EAU Guidelines on Testicular Cancer EAU Guidelines 2022. Accessed December 15 2025 https:\/\/uroweb.org\/guideline\/testicular\u2010cancer."},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.annonc.2022.01.002"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eururo.2017.09.025"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1111\/bju.14967"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.23.00959"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejca.2024.114025"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.1200\/CCI.20.00072"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.2147\/CLEP.S401737"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.2340\/1651\u2010226X.2025.42281"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1136\/bmjopen\u20102019\u2010033713"},{"key":"e_1_2_11_19_1","article-title":"Medical Artificial Intelligence Toolbox (MAIT): An Explainable Machine Learning Framework for Binary Classification, Survival Modelling, and Regression Analyses","author":"Zargari Marandi R.","year":"2025","journal-title":"arXiv:"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.11363"},{"key":"e_1_2_11_21_1","first-page":"3146","volume-title":"Advances in Neural Information Processing Systems 30","author":"Ke G.","year":"2017"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2501.14094"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1186\/s13040\u2010023\u201000322\u20104"},{"key":"e_1_2_11_24_1","article-title":"A Unified Approach to Interpreting Model Predictions","volume":"30","author":"Lundberg S. M.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pntd.0010758"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOAS169"},{"key":"e_1_2_11_27_1","first-page":"1","article-title":"scikit\u2010survival: A Library for Time\u2010to\u2010Event Analysis Built on Top of scikit\u2010learn","volume":"21","author":"P\u00f6lsterl S.","year":"2020","journal-title":"J"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.110234"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.5858\/arpa.2016\u20100226\u2010OA"},{"key":"e_1_2_11_30_1","doi-asserted-by":"publisher","DOI":"10.1097\/PAS.0000000000000917"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1002\/cncr.11234"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.humpath.2010.04.018"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12885\u2010020\u201007097\u20105"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijin.2022.05.002"}],"container-title":["Andrology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/andr.70195","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/andr.70195","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/andr.70195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T18:20:06Z","timestamp":1772994006000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/andr.70195"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,19]]},"references-count":33,"alternative-id":["10.1111\/andr.70195"],"URL":"https:\/\/doi.org\/10.1111\/andr.70195","archive":["Portico"],"relation":{},"ISSN":["2047-2919","2047-2927"],"issn-type":[{"value":"2047-2919","type":"print"},{"value":"2047-2927","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,19]]},"assertion":[{"value":"2025-09-30","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70195"}}