{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T15:47:48Z","timestamp":1774453668915,"version":"3.50.1"},"reference-count":39,"publisher":"MDPI AG","issue":"19","license":[{"start":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T00:00:00Z","timestamp":1758844800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Murtha Cancer Center Program","award":["HU00012320028"],"award-info":[{"award-number":["HU00012320028"]}]},{"name":"MCCRP, Center for Prostate Disease Research","award":["HU00012520001"],"award-info":[{"award-number":["HU00012520001"]}]}],"content-domain":{"domain":["www.mdpi.com"],"crossmark-restriction":true},"short-container-title":["Diagnostics"],"abstract":"<jats:p>Background: Cancer staging, guided by anatomical and clinicopathologic factors, is essential for determining treatment strategies and patient prognosis. The current gold standard for prostate cancer is the American Joint Committee on Cancer (AJCC) Tumor, Lymph Node, and Metastasis (TNM) Staging System 9th Version (2024). This system incorporates five prognostic variables: tumor (T), spread to lymph nodes (N), metastasis (M), prostate-specific antigen (PSA) levels (P), and Grade Group\/Gleason score (G). While effective, further refinement of prognostic systems may improve prediction of patient outcomes and support more individualized treatment. Methods: We applied the Ensemble Algorithm for Clustering Cancer Data (EACCD), an unsupervised machine learning approach. EACCD involves three steps: calculating initial dissimilarities, performing ensemble learning, and conducting hierarchical clustering. We first developed an EACCD model using the five AJCC variables (T, N, M, P, G). The model was then expanded to include two additional factors, age (A) and race (R). Prostate cancer patient data were obtained from the Surveillance, Epidemiology, and End Results (SEER) program from the National Cancer Institute. Results: The EACCD algorithm effectively stratified patients into distinct prognostic groups, each with well-separated survival curves. The five-variable model achieved a concordance index (C-index) of 0.8293 (95% CI: 0.8245\u20130.8341), while the seven-variable model, including age and race, improved performance to 0.8504 (95% CI: 0.8461\u20130.8547). Both outperformed the AJCC TNM system, which had a C-index of 0.7676 (95% CI: 0.7622\u20130.7731). Conclusions: EACCD provides a refined prognostic framework for primary localized prostate cancer, demonstrating superior accuracy over the AJCC staging system. With further validation in independent cohorts, EACCD could enhance risk stratification and support precision oncology.<\/jats:p>","DOI":"10.3390\/diagnostics15192462","type":"journal-article","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T12:33:03Z","timestamp":1758889983000},"page":"2462","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Using Machine Learning to Create Prognostic Systems for Primary Prostate Cancer"],"prefix":"10.3390","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8733-2558","authenticated-orcid":false,"given":"Kevin","family":"Guan","sequence":"first","affiliation":[{"name":"F. Edward H\u00e9bert School of Medicine, Uniformed Services University of the Health Sciences (USUHS), Bethesda, MD 20814, USA"},{"name":"The Henry M. Jackson Foundation for the Advancement of Military Medicine Inc., Bethesda, MD 20817, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andy","family":"Guan","sequence":"additional","affiliation":[{"name":"F. Edward H\u00e9bert School of Medicine, Uniformed Services University of the Health Sciences (USUHS), Bethesda, MD 20814, USA"},{"name":"Commissioned Corps of the U.S. Public Health Service (USPHS), Rockville, MD 20852, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anwar E.","family":"Ahmed","sequence":"additional","affiliation":[{"name":"F. Edward H\u00e9bert School of Medicine, Uniformed Services University of the Health Sciences (USUHS), Bethesda, MD 20814, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew J.","family":"Waters","sequence":"additional","affiliation":[{"name":"F. Edward H\u00e9bert School of Medicine, Uniformed Services University of the Health Sciences (USUHS), Bethesda, MD 20814, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8250-7005","authenticated-orcid":false,"given":"Shyh-Han","family":"Tan","sequence":"additional","affiliation":[{"name":"F. Edward H\u00e9bert School of Medicine, Uniformed Services University of the Health Sciences (USUHS), Bethesda, MD 20814, USA"},{"name":"The Henry M. Jackson Foundation for the Advancement of Military Medicine Inc., Bethesda, MD 20817, USA"},{"name":"Center for Prostate Disease Research (CPDR), Murtha Cancer Center Research Program, Department of Surgery, Uniformed Services University of the Health Sciences, Bethesda, MD 20817, USA"},{"name":"Genitourinary Malignancies Branch, Center for Cancer Research, National Cancer Institute, Bethesda, MD 20814, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5787-3441","authenticated-orcid":false,"given":"Dechang","family":"Chen","sequence":"additional","affiliation":[{"name":"F. Edward H\u00e9bert School of Medicine, Uniformed Services University of the Health Sciences (USUHS), Bethesda, MD 20814, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,9,26]]},"reference":[{"key":"ref_1","first-page":"12","article-title":"Cancer statistics, 2024","volume":"74","author":"Siegel","year":"2024","journal-title":"CA Cancer J. Clin."},{"key":"ref_2","first-page":"175","article-title":"Quantifying the role of PSA screening in the US prostate cancer mortality decline","volume":"19","author":"Etzioni","year":"2008","journal-title":"Cancer Causes Control"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"608","DOI":"10.7326\/L17-0738","article-title":"Reconciling the Effects of Screening on Prostate Cancer Mortality in the ERSPC and PLCO Trials","volume":"168","author":"Tsodikov","year":"2018","journal-title":"Ann. Intern. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"697","DOI":"10.1016\/j.euo.2023.12.005","article-title":"Comparing the Performance of Digital Rectal Examination and Prostate-specific Antigen as a Screening Test for Prostate Cancer: A Systematic Review and Meta-analysis","volume":"7","author":"Matsukawa","year":"2024","journal-title":"Eur. Urol. Oncol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1093\/jnci\/djac066","article-title":"Grade Migration of Prostate Cancer in the United States During the Last Decade","volume":"114","author":"Borregales","year":"2022","journal-title":"J. Natl. Cancer Inst."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"2054","DOI":"10.1001\/jama.2015.14905","article-title":"Prostate Cancer Incidence and PSA Testing Patterns in Relation to USPSTF Screening Recommendations","volume":"314","author":"Jemal","year":"2015","journal-title":"JAMA"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"120","DOI":"10.7326\/0003-4819-157-2-201207170-00459","article-title":"Screening for prostate cancer: U.S. Preventive Services Task Force recommendation statement","volume":"157","author":"Moyer","year":"2012","journal-title":"Ann. Intern. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1473","DOI":"10.15585\/mmwr.mm6941a1","article-title":"Prostate Cancer Incidence and Survival, by Stage and Race\/Ethnicity\u2014United States, 2001\u20132017","volume":"69","author":"Siegel","year":"2020","journal-title":"MMWR Morb. Mortal. Wkly. Rep."},{"key":"ref_9","first-page":"93","article-title":"The Eighth Edition AJCC Cancer Staging Manual: Continuing to build a bridge from a population-based to a more \u201cpersonalized\u201d approach to cancer staging","volume":"67","author":"Amin","year":"2017","journal-title":"CA Cancer J. Clin."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1471","DOI":"10.1245\/s10434-010-0985-4","article-title":"The American Joint Committee on Cancer: The 7th Edition of the AJCC Cancer Staging Manual and the Future of TNM","volume":"17","author":"Edge","year":"2010","journal-title":"Ann. Surg. Oncol."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"428","DOI":"10.1016\/j.eururo.2015.06.046","article-title":"A Contemporary Prostate Cancer Grading System: A Validated Alternative to the Gleason Score","volume":"69","author":"Epstein","year":"2016","journal-title":"Eur. Urol."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Sun, C., Yang, D., Zhu, J., Zhou, Y., Xiang, C., and Wu, S. (2022). Modified the 8th AJCC staging system for patients with advanced prostate cancer: A study based on SEER database. BMC Urol., 22.","DOI":"10.1186\/s12894-022-01135-z"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Chen, D., Xing, K., Henson, D., Sheng, L., Schwartz, A.M., and Cheng, X. (2009). Developing prognostic systems of cancer patients by ensemble clustering. J. Biomed. Biotechnol., 2009.","DOI":"10.1155\/2009\/632786"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"12","DOI":"10.1007\/s42519-021-00234-8","article-title":"Using Weighted Differences in Hazards as Effect Sizes for Survival Data","volume":"16","author":"Wang","year":"2022","journal-title":"J. Stat. Theory Pract."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"3611","DOI":"10.1002\/cam4.1629","article-title":"Creating prognostic systems for cancer patients: A demonstration using breast cancer","volume":"7","author":"Hueman","year":"2018","journal-title":"Cancer Med."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Qi, R., Wu, D., Sheng, L., Henson, D., Schwartz, A., Xu, E., Xing, K., and Chen, D. (2013). On an ensemble algorithm for clustering cancer patient data. BMC Syst. Biol., 7.","DOI":"10.1186\/1752-0509-7-S4-S9"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"12","DOI":"10.21037\/jgo.2016.11.10","article-title":"The anatomy of the TNM for colon cancer","volume":"8","author":"Henson","year":"2017","journal-title":"J. Gastrointest. Oncol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1423","DOI":"10.1111\/1759-7714.13926","article-title":"Expanding TNM for lung cancer through machine learning","volume":"12","author":"Hueman","year":"2021","journal-title":"Thorac. Cancer"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1511","DOI":"10.1111\/aogs.14137","article-title":"A prognostic system for epithelial ovarian carcinomas using machine learning","volume":"100","author":"Grimley","year":"2021","journal-title":"Acta Obstet. Gynecol. Scand."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"744","DOI":"10.1016\/j.ygyno.2020.09.047","article-title":"Using machine learning to create prognostic systems for endometrial cancer","volume":"159","author":"Praiss","year":"2020","journal-title":"Gynecol. Oncol."},{"key":"ref_21","first-page":"514","article-title":"Using Machine Learning to Expand the Ann Arbor Staging System for Hodgkin and Non-Hodgkin Lymphoma","volume":"3","author":"Wang","year":"2023","journal-title":"Bio. Med. Informatics"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Yang, C.Q., Wang, H., Liu, Z., Hueman, M.T., Bhaskaran, A., Henson, D.E., Sheng, L., and Chen, D. (2021). Integrating additional factors into the TNM staging for cutaneous melanoma by machine learning. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0257949"},{"key":"ref_23","unstructured":"Surveillance, Epidemiology, and End Results (SEER) Program (2025, February 06). SEER*Stat Database: Incidence\u2014SEER Research Data, 17 Registries, November 2023 Submission (2000\u20132021), Available online: https:\/\/seer.cancer.gov\/data-software\/documentation\/seerstat\/nov2023\/."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"975","DOI":"10.1001\/jamaoncol.2019.0826","article-title":"Association of Black Race with Prostate Cancer-Specific and Other-Cause Mortality","volume":"5","author":"Dess","year":"2019","journal-title":"JAMA Oncol."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1208","DOI":"10.1158\/1055-9965.EPI-08-0502","article-title":"Race and time from diagnosis to radical prostatectomy: Does equal access mean equal timely access to the operating room?\u2014Results from the SEARCH database","volume":"18","author":"Banez","year":"2009","journal-title":"Cancer Epidemiol. Biomark. Prev."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"369.e9","DOI":"10.1016\/j.urolonc.2020.11.031","article-title":"The effect of race\/ethnicity on histological subtype distribution, stage at presentation and cancer specific survival in urethral cancer","volume":"39","author":"Wenzel","year":"2021","journal-title":"Urol. Oncol."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/j.prnil.2023.09.004","article-title":"Prognosis after radical prostatectomy in men older than 75 years: Long-term results from a single tertiary center","volume":"12","author":"Lee","year":"2024","journal-title":"Prostate Int."},{"key":"ref_28","unstructured":"Kumar, B.S. (2023). Perspective Chapter: Using Effect Sizes to Study the Survival Difference between Two Groups. Recent Advances in Biostatistics, IntechOpen."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1198\/jasa.2011.tm10183","article-title":"Hierarchical Clustering with Prototypes via Minimax Linkage","volume":"106","author":"Bien","year":"2011","journal-title":"J. Am. Stat. Assoc."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"361","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4","article-title":"Multivariable prognostic models: Issues in developing models, evaluating assumptions and adequacy, and measuring and reducing errors","volume":"15","author":"Harrell","year":"1996","journal-title":"Stat. Med."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"298","DOI":"10.1002\/pros.24272","article-title":"Incorporating artificial intelligence in urology: Supervised machine learning algorithms demonstrate comparative advantage over nomograms in predicting biochemical recurrence after prostatectomy","volume":"82","author":"Tan","year":"2022","journal-title":"Prostate"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"913","DOI":"10.1002\/pros.24188","article-title":"Machine learning algorithms can more efficiently predict biochemical recurrence after robot-assisted radical prostatectomy","volume":"81","author":"Evren","year":"2021","journal-title":"Prostate"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1002\/pros.24793","article-title":"Machine learning and explainable artificial intelligence to predict pathologic stage in men with localized prostate cancer","volume":"85","author":"Semwal","year":"2025","journal-title":"Prostate"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"842","DOI":"10.1002\/pros.24703","article-title":"Development and validation of an imageless machine-learning algorithm for the initial screening of prostate cancer","volume":"84","author":"Martelin","year":"2024","journal-title":"Prostate"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1355","DOI":"10.1002\/pros.24233","article-title":"Predicting survival after radical prostatectomy: Variation of machine learning performance by race","volume":"81","author":"Nayan","year":"2021","journal-title":"Prostate"},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"1828","DOI":"10.1038\/s41467-024-45475-w","article-title":"Prediction of plasma ctDNA fraction and prognostic implications of liquid biopsy in advanced prostate cancer","volume":"15","author":"Fonseca","year":"2024","journal-title":"Nat. Commun."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"21276","DOI":"10.1073\/pnas.1117029108","article-title":"Molecular classification of prostate cancer using curated expression signatures","volume":"108","author":"Markert","year":"2011","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"101679","DOI":"10.1016\/j.xcrm.2024.101679","article-title":"Proteomic landscape profiling of primary prostate cancer reveals a 16-protein panel for prognosis prediction","volume":"5","author":"Sun","year":"2024","journal-title":"Cell Rep. Med."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1186\/s12935-025-03677-2","article-title":"An online clustering algorithm predicting model for prostate cancer based on PHI-related variables and PI-RADS in different PSA populations","volume":"25","author":"Hu","year":"2025","journal-title":"Cancer Cell Int."}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/19\/2462\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T12:39:59Z","timestamp":1758890399000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/15\/19\/2462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,26]]},"references-count":39,"journal-issue":{"issue":"19","published-online":{"date-parts":[[2025,10]]}},"alternative-id":["diagnostics15192462"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics15192462","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,26]]}}}