{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T17:07:16Z","timestamp":1787677636027,"version":"build-2784847793"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"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. Med."],"abstract":"<jats:sec><jats:title>Background<\/jats:title><jats:p>Extremely aggressive prostate cancer, including subtypes like small cell carcinoma and neuroendocrine carcinoma, is associated with poor prognosis and limited treatment options. This study sought to create a robust, interpretable machine learning-based model that predicts 1-, 3-, and 5-year survival in patients with extremely aggressive prostate cancer. Additionally, we sought to pinpoint key prognostic factors and their clinical implications through an innovative method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>This study retrospectively analyzed data from 1,620 patients with extremely aggressive prostate cancer in the SEER database (2000\u20132020). Feature selection was performed using the Boruta algorithm, and survival predictions were made using nine machine learning algorithms, including XGBoost, logistic regression (LR), support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), decision tree (DT), elastic network (Enet), multilayer perceptron (MLP) and lightGBM. Model performance was evaluated using metrics such as AUC, accuracy (F1 score), confusion matrix, and decision curve analysis. Additionally, Shapley Additive Explanations (SHAP) were applied to interpret feature importance within the model, revealing the clinical factors that influence survival predictions.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Among the nine models, the lightGBM model exhibited the best performance, with an AUC and F1 score of (0.8, 0.809) for 1-year survival prediction, (0.809, 0.751) for 3-year survival prediction, and (0.773, 0.611) for 5-year survival prediction. SHAP analysis revealed that M stage was the most important feature for predicting 1- and 3-year survival, while PSA level had the greatest impact on 5-year survival predictions. The model demonstrated good clinical utility and predictive accuracy through decision curve analysis and confusion matrix.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusion<\/jats:title><jats:p>The lightGBM model has good predictive power for survival in patients with extremely aggressive prostate cancer. By identifying key clinical factors and providing actionable predictions, the model has the potential to enhance prognostic accuracy and improve patient outcomes.<\/jats:p><\/jats:sec>","DOI":"10.3389\/fmed.2025.1512870","type":"journal-article","created":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T05:40:09Z","timestamp":1747028409000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["A prognostic model for highly aggressive prostate cancer using interpretable machine learning techniques"],"prefix":"10.3389","volume":"12","author":[{"given":"Cong","family":"Peng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoya","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Duxian","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"ref1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.3322\/caac.21820","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","year":"2024","journal-title":"CA Cancer J Clin"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1111\/j.1365-2559.2011.04039.x","article-title":"Histological variants of prostatic carcinoma and their significance","volume":"60","author":"Humphrey","year":"2012","journal-title":"Histopathology"},{"key":"ref3","doi-asserted-by":"publisher","first-page":"478","DOI":"10.1097\/MAJ.0b013e3181731e58","article-title":"Small cell (neuroendocrine) carcinoma of the prostate: etiology, diagnosis, prognosis, and therapeutic implications--a retrospective study of 30 patients from the rare cancer network","volume":"336","author":"Stein","year":"2008","journal-title":"Am J Med Sci"},{"key":"ref4","doi-asserted-by":"publisher","first-page":"756","DOI":"10.1097\/PAS.0000000000000208","article-title":"Proposed morphologic classification of prostate cancer with neuroendocrine differentiation","volume":"38","author":"Epstein","year":"2014","journal-title":"Am J Surg Pathol"},{"key":"ref5","first-page":"264","article-title":"Clinically rare subtypes of prostate cancer: Progress in research","volume":"29","author":"Sheng","year":"2023","journal-title":"Zhonghua Nan Ke Xue"},{"key":"ref6","doi-asserted-by":"publisher","first-page":"291","DOI":"10.1007\/s40487-023-00238-3","article-title":"Small-cell carcinoma of the prostate - challenges of diagnosis and treatment: a next of kin and physician perspective piece","volume":"11","author":"Abbott","year":"2023","journal-title":"Oncol Ther"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"5765","DOI":"10.3390\/cancers13225765","article-title":"Imaging of neuroendocrine prostatic carcinoma","volume":"13","author":"Taher","year":"2021","journal-title":"Cancers (Basel)"},{"key":"ref8","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1038\/s41585-021-00490-0","article-title":"Molecular events in neuroendocrine prostate cancer development","volume":"18","author":"Wang","year":"2021","journal-title":"Nat Rev Urol"},{"key":"ref9","doi-asserted-by":"publisher","first-page":"152","DOI":"10.1186\/s13073-021-00968-x","article-title":"Deep learning in cancer diagnosis, prognosis and treatment selection","volume":"13","author":"Tran","year":"2021","journal-title":"Genome Med"},{"key":"ref10","doi-asserted-by":"publisher","first-page":"e42895","DOI":"10.2196\/42895","article-title":"Multidimensional machine learning for assessing parameters associated with COVID-19 in Vietnam: validation study","volume":"7","author":"Nguyen","year":"2023","journal-title":"JMIR Form Res"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1146\/annurev.bioeng.8.061505.095802","article-title":"Machine learning for detection and diagnosis of disease","volume":"8","author":"Sajda","year":"2006","journal-title":"Annu Rev Biomed Eng"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"E184","DOI":"10.1093\/neuros\/nyz403","article-title":"An online calculator for the prediction of survival in glioblastoma patients using classical statistics and machine learning","volume":"86","author":"Senders","year":"2020","journal-title":"Neurosurgery"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"202","DOI":"10.4111\/icu.20230435","article-title":"Applications of artificial intelligence in urologic oncology","volume":"65","author":"Pak","year":"2024","journal-title":"Investig Clin Urol"},{"key":"ref14","doi-asserted-by":"publisher","first-page":"1779","DOI":"10.2147\/JMDH.S410301","article-title":"Machine learning and AI in Cancer prognosis, prediction, and treatment selection: a critical approach","volume":"16","author":"Zhang","year":"2023","journal-title":"J Multidiscip Healthc"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"20410","DOI":"10.1038\/s41598-020-77220-w","article-title":"A comparison of machine learning methods for survival analysis of high -dimensional clinical data for dementia prediction","volume":"10","author":"Spooner","year":"2020","journal-title":"Sci Rep"},{"key":"ref16","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.3390\/math9111244","article-title":"Deep learning-based survival analysis for high-dimensional survival data","volume":"9","author":"Hao","year":"2021","journal-title":"Mathematics"},{"key":"ref17","doi-asserted-by":"publisher","first-page":"1347","DOI":"10.1056\/NEJMra1814259","article-title":"Machine learning in medicine","volume":"380","author":"Rajkomar","year":"2019","journal-title":"N Engl J Med"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1016\/j.eururo.2013.09.025","article-title":"Predicting survival of patients with node-positive prostate Cancer following multimodal treatment","volume":"65","author":"Abdollah","year":"2014","journal-title":"Eur Urol"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1093\/bioinformatics\/btr597","article-title":"MissForest--non-parametric missing value imputation for mixed-type data","volume":"28","author":"Stekhoven","year":"2012","journal-title":"Bioinformatics"},{"key":"ref20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v036.i11","article-title":"Feature selection with the Boruta package","volume":"36","author":"Kursa","year":"2010","journal-title":"J Stat Softw"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"215","DOI":"10.1186\/s12967-022-03364-0","article-title":"Machine learning for the prediction of acute kidney injury in patients with sepsis","volume":"20","author":"Yue","year":"2022","journal-title":"J Transl Med"},{"key":"ref22","doi-asserted-by":"crossref","first-page":"233","DOI":"10.1145\/1143844.1143874","article-title":"The relationship between precision-recall and ROC curves","volume-title":"Proceedings of the 23rd international conference on machine learning","author":"Davis","year":"2006"},{"key":"ref23","doi-asserted-by":"publisher","first-page":"108255","DOI":"10.1016\/j.pharmthera.2022.108255","article-title":"Current and emerging therapies for neuroendocrine prostate cancer","volume":"238","author":"Alabi","year":"2022","journal-title":"Pharmacol Ther"},{"key":"ref24","doi-asserted-by":"publisher","first-page":"3792","DOI":"10.3390\/cancers12123792","article-title":"Neuroendocrine and aggressive-variant prostate cancer","volume":"12","author":"Spetsieris","year":"2020","journal-title":"Cancers"},{"key":"ref25","doi-asserted-by":"publisher","first-page":"20","DOI":"10.1016\/j.ctrv.2019.03.001","article-title":"Aggressive variants of prostate cancer - are we ready to apply specific treatment right now?","volume":"75","author":"Tsaur","year":"2019","journal-title":"Cancer Treat Rev"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1007\/s00134-003-1761-8","article-title":"A readers' guide to the interpretation of diagnostic test properties: clinical example of sepsis","volume":"29","author":"Fischer","year":"2003","journal-title":"Intensive Care Med"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"391","DOI":"10.1038\/s41585-019-0193-3","article-title":"A new era: artificial intelligence and machine learning in prostate cancer","volume":"16","author":"Goldenberg","year":"2019","journal-title":"Nat Rev Urol"},{"key":"ref28","doi-asserted-by":"publisher","first-page":"354","DOI":"10.3390\/diagnostics11020354","article-title":"Artificial intelligence and machine learning in prostate cancer patient management-current trends and future perspectives","volume":"11","author":"T\u0103taru","year":"2021","journal-title":"Diagnostics"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"101506","DOI":"10.1016\/j.xcrm.2024.101506","article-title":"Harnessing artificial intelligence for prostate cancer management","volume":"5","author":"Zhu","year":"2024","journal-title":"Cell Rep Med"},{"key":"ref30","doi-asserted-by":"publisher","first-page":"2802","DOI":"10.3390\/cancers12102802","article-title":"Comparison of the tree-based machine learning algorithms to cox regression in predicting the survival of Oral and pharyngeal cancers: analyses based on SEER database","volume":"12","author":"Du","year":"2020","journal-title":"Cancers"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"18424","DOI":"10.1038\/s41598-023-45804-x","article-title":"Development of machine learning prognostic models for overall survival of prostate cancer patients with lymph node-positive","volume":"13","author":"Peng","year":"2023","journal-title":"Sci Rep"},{"key":"ref32","doi-asserted-by":"publisher","first-page":"17821","DOI":"10.1038\/s41598-022-22118-y","article-title":"Survival analysis of localized prostate cancer with deep learning","volume":"12","author":"Dai","year":"2022","journal-title":"Sci Rep"},{"key":"ref33","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.artmed.2017.02.005","article-title":"A novel hierarchical selective ensemble classifier with bioinformatics application","volume":"83","author":"Wei","year":"2017","journal-title":"Artif Intell Med"},{"key":"ref34","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1186\/s12859-023-05300-5","article-title":"A diabetes prediction model based on Boruta feature selection and ensemble learning","volume":"24","author":"Zhou","year":"2023","journal-title":"BMC Bioinformatics"},{"key":"ref35","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1016\/j.ejca.2019.08.011","article-title":"Clinical features of neuroendocrine prostate cancer","volume":"121","author":"Conteduca","year":"2019","journal-title":"Eur J Cancer"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"2220","DOI":"10.1056\/NEJMoa1809064","article-title":"First-line Atezolizumab plus chemotherapy in extensive-stage small-cell lung cancer","volume":"379","author":"Horn","year":"2018","journal-title":"N Engl J Med"},{"key":"ref37","doi-asserted-by":"publisher","first-page":"883","DOI":"10.1016\/S1470-2045(16)30098-5","article-title":"Nivolumab alone and nivolumab plus ipilimumab in recurrent small-cell lung cancer (CheckMate 032): a multicentre, open-label, phase 1\/2 trial","volume":"17","author":"Antonia","year":"2016","journal-title":"Lancet Oncol"},{"key":"ref38","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1148\/rg.2018170108","article-title":"Prostate-specific membrane antigen PET: clinical utility in prostate cancer, normal patterns, pearls, and pitfalls","volume":"38","author":"Hofman","year":"2018","journal-title":"Radiographics"},{"key":"ref39","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1111\/bju.13540","article-title":"Prospective evaluation of 68Gallium-prostate-specific membrane antigen positron emission tomography\/computed tomography for preoperative lymph node staging in prostate cancer","volume":"119","author":"van Leeuwen","year":"2017","journal-title":"BJU Int"},{"key":"ref40","doi-asserted-by":"publisher","first-page":"143","DOI":"10.1016\/j.juro.2010.03.039","article-title":"Predicting biochemical recurrence-free survival for patients with positive pelvic lymph nodes at radical prostatectomy","volume":"184","author":"von Bodman","year":"2010","journal-title":"J Urol"},{"key":"ref41","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1373\/clinchem.2012.198739","article-title":"The long and winding road to FDA approval of a novel prostate cancer test: our story","volume":"59","author":"Rittenhouse","year":"2013","journal-title":"Clin Chem"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.bbcan.2014.04.001","article-title":"Prostate-specific antigen and other serum and urine markers in prostate cancer","volume":"1846","author":"Stephan","year":"2014","journal-title":"Biochim Biophys Acta"},{"key":"ref43","doi-asserted-by":"publisher","first-page":"74","DOI":"10.3389\/fsurg.2018.00074","article-title":"Current imaging techniques for lymph node staging in prostate cancer: a review","volume":"5","author":"Muteganya","year":"2018","journal-title":"Front Surg"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1111\/iju.13734","article-title":"Urinary biomarkers of prostate cancer","volume":"25","author":"Fujita","year":"2018","journal-title":"Int J Urol"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"11906","DOI":"10.1038\/ncomms11906","article-title":"Targeted proteomics identifies liquid-biopsy signatures for extracapsular prostate cancer","volume":"7","author":"Kim","year":"2016","journal-title":"Nat Commun"},{"key":"ref46","doi-asserted-by":"publisher","first-page":"14837","DOI":"10.1038\/s41598-022-19134-3","article-title":"Urinary marker panels for aggressive prostate cancer detection","volume":"12","author":"Lih","year":"2022","journal-title":"Sci Rep"}],"container-title":["Frontiers in Medicine"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1512870\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T05:40:12Z","timestamp":1747028412000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fmed.2025.1512870\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,12]]},"references-count":46,"alternative-id":["10.3389\/fmed.2025.1512870"],"URL":"https:\/\/doi.org\/10.3389\/fmed.2025.1512870","relation":{},"ISSN":["2296-858X"],"issn-type":[{"value":"2296-858X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,12]]},"article-number":"1512870"}}