{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,29]],"date-time":"2026-09-29T13:36:50Z","timestamp":1790689010431,"version":"4.1.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T00:00:00Z","timestamp":1632960000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/publicdomain\/zero\/1.0\/"}],"funder":[{"name":"John P. Murtha Cancer Center Research Program","award":["(64349-MCC Comprehensive Research)"],"award-info":[{"award-number":["(64349-MCC Comprehensive Research)"]}]},{"DOI":"10.13039\/100008321","name":"Pennsylvania State University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100008321","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n<jats:title>Background<\/jats:title>\n<jats:p>Integrating additional factors into the TNM staging system is needed for more accurate risk classification and survival prediction for patients with cutaneous melanoma. In the present study, we introduce machine learning as a novel tool that incorporates additional prognostic factors to improve the current TNM staging system.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec002\">\n<jats:title>Methods and findings<\/jats:title>\n<jats:p>Cancer-specific survival data for cutaneous melanoma with at least a 5 years follow-up were extracted from the Surveillance, Epidemiology, and End Results Program of the National Cancer Institute and split into the training set (40,781 cases) and validation set (5,390 cases). Five factors were studied: the primary tumor (T), regional lymph nodes (N), distant metastasis (M), age (A), and sex (S). The Ensemble Algorithm for Clustering Cancer Data (EACCD) was applied to the training set to generate prognostic groups. Utilizing only T, N, and M, a basic prognostic system was built where patients were stratified into 10 prognostic groups with well-separated survival curves, similar to 10 AJCC stages. These 10 groups had a significantly higher accuracy in survival prediction than 10 stages (C-index = 0.7682 vs 0.7643; increase in C-index = 0.0039, 95% CI = (0.0032, 0.0047); p-value = 7.2\u00d710<jats:sup>\u221223<\/jats:sup>). Nevertheless, a positive association remained between the EACCD grouping and the AJCC staging (Spearman\u2019s rank correlation coefficient = 0.8316; p-value = 4.5\u00d710<jats:sup>\u221213<\/jats:sup>). With additional information from A and S, a more advanced prognostic system was established using the training data that stratified patients into 10 groups and further improved the prediction accuracy (C-index = 0.7865 vs 0.7643; increase in C-index = 0.0222, 95% CI = (0.0191, 0.0254); p-value = 8.8\u00d710<jats:sup>\u221243<\/jats:sup>). Both internal validation using the training set and temporal validation using the validation set showed good stratification and a high predictive accuracy of the prognostic systems.<\/jats:p>\n<\/jats:sec>\n<jats:sec id=\"sec003\">\n<jats:title>Conclusions<\/jats:title>\n<jats:p>The EACCD allows additional factors to be integrated into the TNM to create a prognostic system that improves patient stratification and survival prediction for cutaneous melanoma. This integration separates favorable from unfavorable clinical outcomes for patients and improves both cohort selection for clinical trials and treatment management.<\/jats:p>\n<\/jats:sec>","DOI":"10.1371\/journal.pone.0257949","type":"journal-article","created":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T18:20:35Z","timestamp":1633026035000},"page":"e0257949","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":13,"title":["Integrating additional factors into the TNM staging for cutaneous melanoma by machine learning"],"prefix":"10.1371","volume":"16","author":[{"given":"Charles Q.","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenqiu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew T.","family":"Hueman","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aadya","family":"Bhaskaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Donald E.","family":"Henson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li","family":"Sheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5787-3441","authenticated-orcid":true,"given":"Dechang","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"issue":"1","key":"pone.0257949.ref001","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3322\/caac.21551","article-title":"Cancer statistics, 2019","volume":"69","author":"RL Siegel","year":"2019","journal-title":"CA Cancer J Clin."},{"issue":"4","key":"pone.0257949.ref002","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1177\/107327480501200403","article-title":"Cutaneous melanoma: prognostic factors","volume":"12","author":"J Homsi","year":"2005","journal-title":"Cancer Control"},{"key":"pone.0257949.ref003","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-40618-3","volume-title":"AJCC Cancer Staging Manual","author":"MB Amin","year":"2017","edition":"8"},{"key":"pone.0257949.ref004","volume-title":"Manual for staging of cancer","author":"O Beahrs","year":"1977"},{"issue":"3","key":"pone.0257949.ref005","doi-asserted-by":"crossref","first-page":"976","DOI":"10.1200\/JCO.1999.17.3.976","article-title":"Multi-institutional melanoma lymphatic mapping experience: the prognostic value of sentinel lymph node status in 612 stage I or II melanoma patients","volume":"17","author":"JE Gershenwald","year":"1999","journal-title":"J Clin Oncol."},{"key":"pone.0257949.ref006","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1007\/978-3-030-41008-7_3","article-title":"Immunotherapy for Melanoma","volume":"1244","author":"AA Albittar","year":"2020","journal-title":"Adv Exp Med Biol"},{"issue":"23","key":"pone.0257949.ref007","doi-asserted-by":"crossref","first-page":"2479","DOI":"10.1200\/JCO.2013.54.2340","article-title":"Prediction of survival in patients with thin melanoma: results from a multi-institution study","volume":"32","author":"A Maurichi","year":"2014","journal-title":"J Clin Oncol"},{"issue":"10","key":"pone.0257949.ref008","doi-asserted-by":"crossref","first-page":"2484","DOI":"10.1002\/1097-0142(19950515)75:10<2484::AID-CNCR2820751014>3.0.CO;2-U","article-title":"Primary cutaneous melanoma. Identification of prognostic groups and estimation of individual prognosis for 5093 patients","volume":"75","author":"C Garbe","year":"1995","journal-title":"Cancer"},{"issue":"4","key":"pone.0257949.ref009","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1067\/msy.2002.127546","article-title":"A long-term analysis of 1018 patients with melanoma by classic Cox regression and tree-structured survival analysis at a major referral center: implications on the future of cancer staging","volume":"132","author":"BJ Averbook","year":"2002","journal-title":"Surgery"},{"issue":"18","key":"pone.0257949.ref010","doi-asserted-by":"crossref","first-page":"7577","DOI":"10.1002\/cam4.2644","article-title":"Predictive value of a nomogram for melanomas with brain metastases at initial diagnosis","volume":"8","author":"H Liu","year":"2019","journal-title":"Cancer Med"},{"issue":"2","key":"pone.0257949.ref011","first-page":"85","article-title":"A selective review on random survival forests for high dimensional data","volume":"36","author":"H Wang","year":"2017","journal-title":"Quant Biosci"},{"key":"pone.0257949.ref012","article-title":"Developing prognostic systems of cancer patients by ensemble clustering","author":"D Chen","year":"2009","journal-title":"Biomed Res Int"},{"issue":"4","key":"pone.0257949.ref013","doi-asserted-by":"crossref","first-page":"S9","DOI":"10.1186\/1752-0509-7-S4-S9","article-title":"On an ensemble algorithm for clustering cancer patient data","volume":"7","author":"R Qi","year":"2013","journal-title":"BMC Syst Biol"},{"issue":"8","key":"pone.0257949.ref014","doi-asserted-by":"crossref","first-page":"1015","DOI":"10.2217\/fon.16.5","article-title":"An algorithm for expanding the TNM staging system","volume":"12","author":"D Chen","year":"2016","journal-title":"Future Oncol."},{"key":"pone.0257949.ref015","first-page":"58","article-title":"Clustering big cancer data by effect sizes","author":"H Wang","year":"2017","journal-title":"In 2017 IEEE\/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)"},{"issue":"8","key":"pone.0257949.ref016","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":"MT Hueman","year":"2018","journal-title":"Cancer Med"},{"key":"pone.0257949.ref017","first-page":"33","article-title":"Creating Prognostic Systems by the Mann-Whitney Parameter.","author":"H Wang","year":"2018","journal-title":"In 2018 IEEE\/ACM International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)"},{"key":"pone.0257949.ref018","doi-asserted-by":"crossref","first-page":"288","DOI":"10.3389\/fendo.2019.00288","article-title":"Creating prognostic systems for well differentiated thyroid cancer using machine learning","volume":"10","author":"C Yang","year":"2019","journal-title":"Front Endocrinol"},{"issue":"3","key":"pone.0257949.ref019","doi-asserted-by":"crossref","first-page":"e000518","DOI":"10.1136\/esmoopen-2019-000518","article-title":"Expanding the TNM for cancers of the colon and rectum using machine learning: a demonstration","volume":"4","author":"M Hueman","year":"2019","journal-title":"ESMO Open"},{"key":"pone.0257949.ref020","article-title":"Development of Prognostic Systems for Cancer Patients","author":"H Wang","year":"2020","journal-title":"The George Washington University"},{"key":"pone.0257949.ref021","article-title":"A prognostic system for epithelial ovarian carcinomas using machine learning","author":"PM Grimley","year":"2021","journal-title":"Acta Obstet Gynecol Scand"},{"issue":"9","key":"pone.0257949.ref022","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":"M Hueman","year":"2021","journal-title":"Thoracic cancer"},{"key":"pone.0257949.ref023","unstructured":"Surveillance, Epidemiology, and End Results (SEER) Program (www.seer.cancer.gov) Research Data (2000\u20132018), National Cancer Institute, DCCPS, Surveillance Research Program, released April 2021, based on the November 2020 submission. Available from: https:\/\/seer.cancer.gov\/ (cited 20 June 2021)."},{"key":"pone.0257949.ref024","unstructured":"SEER Cause-specific Death Classification. Available from URL: https:\/\/seer.cancer.gov\/causespecific\/ (accessed 20 June 2021)."},{"key":"pone.0257949.ref025","unstructured":"CS Lymph Nodes Eval. Available from URL: https:\/\/staging.seer.cancer.gov\/cs\/input\/02.05.50\/melanoma_skin\/nodes_eval\/?breadcrumbs=(~schema_list~),(~view_schema~,~melanoma_skin~) (accessed 20 June 2021)."},{"issue":"4","key":"pone.0257949.ref026","doi-asserted-by":"crossref","first-page":"1075","DOI":"10.1245\/s10434-013-3464-x","article-title":"Age as a predictor of sentinel node metastasis among patients with localized melanoma: an inverse correlation of melanoma mortality and incidence of sentinel node metastasis among young and old patients","volume":"21","author":"CM Balch","year":"2014","journal-title":"Ann Surg Oncol"},{"issue":"1","key":"pone.0257949.ref027","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/ckj\/sfaa188","article-title":"External validation of prognostic models: what, why, how, when and where?","volume":"14","author":"CL Ramspek","year":"2021","journal-title":"Clinical Kidney Journal"},{"key":"pone.0257949.ref028","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding groups in data: an introduction to cluster analysis","author":"L Kaufman","year":"1990"},{"issue":"495","key":"pone.0257949.ref029","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":"J Bien","year":"2011","journal-title":"J Am Stat Assoc"},{"key":"pone.0257949.ref030","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1214\/aoms\/1177730491","article-title":"On a test of whether one of two random variables is stochastically larger than the other","volume":"18","author":"HB Mann","year":"1947","journal-title":"Ann Math Stat."},{"key":"pone.0257949.ref031","first-page":"666","volume-title":"Fifth Berkeley Symposium on Mathematical Statistics and Probability, Statistical Laboratory of the University of California, Berkeley, June 21\u201318 July 1965 and 27 December 1965\u20137 January 1966","author":"B Efron","year":"1967"},{"issue":"8","key":"pone.0257949.ref032","doi-asserted-by":"crossref","first-page":"2359","DOI":"10.1177\/0962280216680245","article-title":"Use of the concordance index for predictors of censored survival data","volume":"27","author":"AR Brentnall","year":"2018","journal-title":"Stat Methods Med Res"},{"issue":"282","key":"pone.0257949.ref033","doi-asserted-by":"crossref","first-page":"457","DOI":"10.1080\/01621459.1958.10501452","article-title":"Nonparametric estimation from incomplete observations","volume":"53","author":"EL Kaplan","year":"1958","journal-title":"J Am Stat Assoc"},{"issue":"4","key":"pone.0257949.ref034","doi-asserted-by":"crossref","first-page":"685","DOI":"10.1002\/sim.6370","article-title":"Comparing two correlated C indices with right\u2010censored survival outcome: a one\u2010shot nonparametric approach","volume":"34","author":"L Kang","year":"2015","journal-title":"Stat Med."},{"key":"pone.0257949.ref035","volume-title":"Biostatistics: a foundation for analysis in the health sciences","author":"WW Daniel","year":"1999","edition":"7"},{"issue":"5","key":"pone.0257949.ref036","doi-asserted-by":"crossref","first-page":"471","DOI":"10.2217\/fon-2017-0500","article-title":"Evaluation of the eighth American Joint Committee on Cancer staging system for malignant melanoma of the skin","volume":"14","author":"O Abdel-Rahman","year":"2018","journal-title":"Future Oncol"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0257949","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,30]],"date-time":"2021-09-30T18:21:35Z","timestamp":1633026095000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0257949"}},"subtitle":[],"editor":[{"given":"Sandro","family":"Pasquali","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,9,30]]},"references-count":36,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0257949","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,30]]}}}