{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:59:52Z","timestamp":1772866792690,"version":"3.50.1"},"reference-count":34,"publisher":"American Society of Clinical Oncology (ASCO)","issue":"3","content-domain":{"domain":["ascopubs.org"],"crossmark-restriction":true},"short-container-title":["JCO Precis Oncol"],"published-print":{"date-parts":[[2026,3]]},"abstract":"<jats:sec>\n                    <jats:title>PURPOSE<\/jats:title>\n                    <jats:p>To develop and validate machine learning (ML) models for postoperative risk stratification in oral cavity squamous cell carcinoma (OCSCC) and to examine whether ML-derived risk groups modify the association between adjuvant therapy and overall survival (OS).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>METHODS<\/jats:title>\n                    <jats:p>Using the National Cancer Database, we identified adults with invasive OCSCC treated with primary surgery. The surgery-alone cohort (n = 18,543) was split 70\/30 for training\/testing to develop DeepSurv, Neural Multi-Task Logistic Regression (NMTLR), and Random Survival Forest (RSF) models. Risk scores were generated for the full cohort (n = 35,625) and converted to low, intermediate, and high groups. Within groups, treatment effects of adjuvant radiotherapy (RT) and chemoradiotherapy (CRT) were estimated using multivariable Cox models.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>RESULTS<\/jats:title>\n                    <jats:p>The best performance was achieved by DeepSurv (C-index 0.73), with similar discrimination for NMTLR\/RSF (C-index 0.71-0.72). For DeepSurv, the full cohort was partitioned into low- (50.0%), intermediate- (32.0%), and high-risk (18.0%) groups with distinct 5-year OS rates: 77.6%, 53.0%, and 29.3%, respectively. In the low-risk group, adjuvant RT (adjusted hazard ratios [aHR], 0.94 [95% CI, 0.87 to 1.02]) and CRT (aHR, 1.03 [95% CI, 0.91 to 1.17]) did not improve OS. In the intermediate-risk group, OS improved with RT (aHR, 0.61 [95% CI, 0.57 to 0.65]) and CRT (aHR, 0.56 [95% CI, 0.52 to 0.61]). In the high-risk group, both adjuvant RT (aHR, 0.47 [95% CI, 0.43 to 0.51]) and CRT (aHR, 0.39 [95% CI, 0.36 to 0.41]) were associated with improved OS compared with surgery alone. CRT was associated with a modest benefit compared with RT. NMTLR and RSF yielded concordant patterns. Top features included pT4a stage, age \u226570 years, and extranodal extension.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>CONCLUSION<\/jats:title>\n                    <jats:p>ML-derived risk stratification identifies patients with OCSCC most likely to benefit from adjuvant therapy, supporting intensification for intermediate-\/high-risk patients and potential deintensification for low-risk patients. External prospective validation is warranted to enable clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1200\/po-25-00914","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T20:59:30Z","timestamp":1772485170000},"update-policy":"https:\/\/doi.org\/10.1200\/crossmark","source":"Crossref","is-referenced-by-count":0,"title":["Machine Learning\u2013Driven Risk Stratification and Adjuvant Treatment Guidance in Oral Cavity Cancer"],"prefix":"10.1200","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5551-7785","authenticated-orcid":true,"given":"Andrea","family":"Costantino","sequence":"first","affiliation":[{"name":"Otorhinolaryngology Unit, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2178-8971","authenticated-orcid":true,"given":"Nir","family":"Tsur","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, AdventHealth Orlando, Celebration, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-1979-0624","authenticated-orcid":true,"given":"Daniel","family":"Uralov","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, Thomas Jefferson University, Philadelphia, PA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4716-6628","authenticated-orcid":true,"given":"Jianbin","family":"Zhu","sequence":"additional","affiliation":[{"name":"Center for Academic Research Excellence, AdventHealth Research Institute, Orlando, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1585-5357","authenticated-orcid":true,"given":"Uthman","family":"Alamoudi","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, AdventHealth Orlando, Celebration, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Giuseppe","family":"Spriano","sequence":"additional","affiliation":[{"name":"Otorhinolaryngology Unit, IRCCS Humanitas Research Hospital, Rozzano, Milan, Italy"},{"name":"Department of Biomedical Sciences, Humanitas University, Pieve Emanuele, Milan, Italy"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"J. Scott","family":"Magnuson","sequence":"additional","affiliation":[{"name":"Department of Otolaryngology\u2014Head and Neck Surgery, AdventHealth Orlando, Celebration, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"233","reference":[{"key":"e_1_3_6_2_2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21871"},{"key":"e_1_3_6_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2015.10.012"},{"key":"e_1_3_6_4_2","doi-asserted-by":"publisher","DOI":"10.1634\/theoncologist.2009-0289"},{"key":"e_1_3_6_5_2","volume-title":"Head and Neck Cancers (version 5.2025), 2025","author":"National Comprehensive Cancer Network","unstructured":"National Comprehensive Cancer Network: Head and Neck Cancers (version 5.2025), 2025. https:\/\/www.nccn.org"},{"key":"e_1_3_6_6_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa032641"},{"key":"e_1_3_6_7_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMoa032646"},{"key":"e_1_3_6_8_2","doi-asserted-by":"publisher","DOI":"10.1002\/lary.31148"},{"key":"e_1_3_6_9_2","doi-asserted-by":"publisher","DOI":"10.1002\/hed.20879"},{"key":"e_1_3_6_10_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2016.68.2336"},{"key":"e_1_3_6_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/S1470-2045(06)70580-0"},{"key":"e_1_3_6_12_2","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21689"},{"key":"e_1_3_6_13_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1606181"},{"key":"e_1_3_6_14_2","doi-asserted-by":"publisher","DOI":"10.1056\/NEJMp1702071"},{"key":"e_1_3_6_15_2","doi-asserted-by":"publisher","DOI":"10.7861\/futurehosp.6-2-94"},{"key":"e_1_3_6_16_2","doi-asserted-by":"publisher","DOI":"10.1002\/hed.27283"},{"key":"e_1_3_6_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2023.106643"},{"key":"e_1_3_6_18_2","doi-asserted-by":"publisher","DOI":"10.1245\/s10434-019-07213-1"},{"key":"e_1_3_6_19_2","volume-title":"International Classification of Diseases for Oncology","author":"Fritz AG","year":"2013","unstructured":"Fritz AG, Percy CL, Jack A: International Classification of Diseases for Oncology (ed 3). Washington, DC, World Health Organization, 2013","edition":"3"},{"key":"e_1_3_6_20_2","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2016.67.3863"},{"key":"e_1_3_6_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9681(87)90171-8"},{"key":"e_1_3_6_22_2","doi-asserted-by":"publisher","DOI":"10.1016\/0895-4356(92)90133-8"},{"key":"e_1_3_6_23_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12874-018-0482-1"},{"key":"e_1_3_6_24_2","first-page":"1845","volume-title":"Adv Neural Inf Process Syst","author":"Yu CN","year":"2011","unstructured":"Yu CN, Greiner R, Lin HC, et al: Learning patient-specific cancer survival distributions as a sequence of dependent regressors. Adv Neural Inf Process Syst 24:1845-1853, 2011"},{"key":"e_1_3_6_25_2","doi-asserted-by":"publisher","DOI":"10.1214\/08-AOAS169"},{"key":"e_1_3_6_26_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19960229)15:4<361::AID-SIM168>3.0.CO;2-4"},{"key":"e_1_3_6_27_2","doi-asserted-by":"publisher","DOI":"10.1002\/(SICI)1097-0258(19990915\/30)18:17\/18<2529::AID-SIM274>3.0.CO;2-5"},{"key":"e_1_3_6_28_2","first-page":"177","article-title":"All models are wrong, but many are useful: Learning a variable\u2019s importance by studying an entire class of prediction models simultaneously","volume":"20","author":"Fisher A","year":"2019","unstructured":"Fisher A, Rudin C, Dominici F: All models are wrong, but many are useful: Learning a variable\u2019s importance by studying an entire class of prediction models simultaneously. J Mach Learn Res 20:177, 2019","journal-title":"J Mach Learn Res"},{"key":"e_1_3_6_29_2","doi-asserted-by":"publisher","DOI":"10.1002\/1097-0142(1950)3:1<32::AID-CNCR2820030106>3.0.CO;2-3"},{"key":"e_1_3_6_30_2","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1988.10478612"},{"key":"e_1_3_6_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1974.1100705"},{"key":"e_1_3_6_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oraloncology.2021.105451"},{"key":"e_1_3_6_33_2","doi-asserted-by":"publisher","DOI":"10.2147\/JMDH.S410301"},{"key":"e_1_3_6_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2023.01.035"},{"key":"e_1_3_6_35_2","doi-asserted-by":"publisher","DOI":"10.1038\/s43018-021-00236-2"}],"container-title":["JCO Precision Oncology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ascopubs.org\/doi\/pdfdirect\/10.1200\/PO-25-00914","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T15:49:48Z","timestamp":1772812188000},"score":1,"resource":{"primary":{"URL":"https:\/\/ascopubs.org\/doi\/10.1200\/PO-25-00914"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":34,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,3]]}},"alternative-id":["10.1200\/PO-25-00914"],"URL":"https:\/\/doi.org\/10.1200\/po-25-00914","relation":{},"ISSN":["2473-4284"],"issn-type":[{"value":"2473-4284","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"2025-09-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-12-23","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-02","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e2500914"}}