{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T13:48:15Z","timestamp":1792590495496,"version":"4.5.0"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T00:00:00Z","timestamp":1792540800000},"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. Oncol."],"abstract":"<jats:sec>\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Osteoradionecrosis is one of the most severe late adverse effects of head and neck radiotherapy. Predictive models may help identify patients at increased risk and support personalized treatment. This exploratory study aimed to develop a machine learning\u2013based prediction model for osteoradionecrosis in a real-world cohort, following the TRIPOD+AI statement.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Clinical variables and mandibular dose\u2013volume histogram parameters were collected from head and neck cancer patients treated with radiotherapy. Forward Stepwise Logistic Regression was used for predictor selection. Six machine learning algorithms, Logistic Regression, Random Forest, Support Vector Machine, CatBoost, XGBoost, and TabPFN, were evaluated under class-weighted baseline modelling, threshold optimization, and data augmentation with repeated stratified 5-fold cross-validation. Performance was primarily assessed using sensitivity. Pairwise comparisons used the Nadeau\u2013Bengio corrected paired t-test with Holm adjustment.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Ninety-seven patients were included, of whom 8 developed osteoradionecrosis (8.25%). Of the 80 available variables, V60Gy and tumor location in the oral cavity were selected as predictors. Without augmentation, Logistic Regression achieved the highest sensitivity (0.74 [95% CI: 0.40\u20131.00]), while several algorithms showed poor sensitivity. With data augmentation, sensitivity ranged from 0.72 to 0.77 across models, with TabPFN, CatBoost, Logistic Regression and Support Vector Machine reaching the highest sensitivity. Logistic Regression achieved the highest AUC under both strategies (0.87). However, F1 scores remained modest, reaching a maximum of 0.48.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Machine learning models demonstrated exploratory potential for ORN risk assessment within an internal validation framework. Class-imbalance strategies were associated with greater minority-class detection in this cohort, but their generalizability remains uncertain. Larger multicenter cohorts and external validation are needed before clinical implementation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fonc.2026.1955800","type":"journal-article","created":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T13:23:57Z","timestamp":1792589037000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Machine learning to predict osteoradionecrosis in head and neck cancer"],"prefix":"10.3389","volume":"16","author":[{"given":"Vitoria Tavares","family":"Castro","sequence":"first","affiliation":[{"name":"University of Brasilia, Laboratory of Oral Histopathology, School of Health Sciences","place":["Bras\u00edlia, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luan Matheus Trindade","family":"Dalmazo","sequence":"additional","affiliation":[{"name":"Department of Informatics, Federal University of Parana","place":["Curitiba, Paran\u00e1, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paula Elaine Diniz Dos","family":"Reis","sequence":"additional","affiliation":[{"name":"University of Brasilia, Interdisciplinary Laboratory of Research Applied to Clinical Practice in Oncology, Nursing Department, School of Health Sciences","place":["Bras\u00edlia, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenzel Castro","family":"de Abreu","sequence":"additional","affiliation":[{"name":"High-Complexity Oncology Care Center, University Hospital of Brasilia","place":["Bras\u00edlia, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ricardo Gomes","family":"dos Reis","sequence":"additional","affiliation":[{"name":"High-Complexity Oncology Care Center, University Hospital of Brasilia","place":["Bras\u00edlia, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ana Carolina","family":"Prado-Ribeiro","sequence":"additional","affiliation":[{"name":"Dental Oncology Service, Instituto Do C\u00e2ncer Do Estado de S\u00e3o Paulo, Faculdade de Medicina da Universidade de S\u00e3o Paulo","place":["S\u00e3o Paulo, Brazil"]},{"name":"Bioengineering Graduate Program, Scientific and Technological Institute, Brazil University","place":["S\u00e3o Paulo, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andr\u00e9 Ferreira","family":"Leite","sequence":"additional","affiliation":[{"name":"University of Brasilia, Laboratory of Oral Histopathology, School of Health Sciences","place":["Bras\u00edlia, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabiana T.","family":"Almeida","sequence":"additional","affiliation":[{"name":"Mike Petryk School of Dentistry, Faculty of Medicine and Dentistry, University of Alberta","place":["Edmonton, AB, Canada"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Eliete Neves Silva","family":"Guerra","sequence":"additional","affiliation":[{"name":"University of Brasilia, Laboratory of Oral Histopathology, School of Health Sciences","place":["Bras\u00edlia, Brazil"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,10,21]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21834","article-title":"Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries","volume":"74","author":"Bray","year":"2024","journal-title":"CA: A Cancer J For Clin"},{"key":"B2","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1615\/CritRevOncog.2022044635","article-title":"Improving radiotherapy response in the treatment of head and neck cancer","volume":"27","author":"Wicker","year":"2022","journal-title":"Crit Rev Oncog"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.3390\/jcm12083025","article-title":"Review of osteoradionecrosis of the jaw: radiotherapy modality, technique, and dose as risk factors","volume":"12","author":"Topkan","year":"2023","journal-title":"J Clin Med"},{"key":"B4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.12.017","article-title":"International expert-based consensus definition, classification criteria, and minimum data elements for osteoradionecrosis of the jaw: an interdisciplinary modified delphi study","volume":"122","author":"Moreno","year":"2025","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B5","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.23.02750","article-title":"Prevention and management of osteoradionecrosis in patients with head and neck cancer treated with radiation therapy: ISOO-MASCC-ASCO guideline","volume":"42","author":"Peterson","year":"2024","journal-title":"J Clin Oncol"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.1007\/s11864-021-00915-3","article-title":"Overview and emerging trends in the treatment of osteoradionecrosis","volume":"22","author":"Meleca","year":"2021","journal-title":"Curr Treat Options Oncol"},{"key":"B7","doi-asserted-by":"publisher","first-page":"891","DOI":"10.1007\/s12663-015-0762-9","article-title":"Osteoradionecrosis of the jaws: clinico-therapeutic management: A literature review and update","volume":"14","author":"Nadella","year":"2015","journal-title":"J Maxillofac Oral Surg"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1002\/hed.27927","article-title":"Prevention of osteoradionecrosis in patients with head and neck cancer treated with radiation therapy","volume":"47","author":"Naseer","year":"2025","journal-title":"Head Neck"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1111\/scd.12910","article-title":"Osteoradionecrosis treatment in head and neck cancer patients: An overview of systematic reviews","volume":"44","author":"Schroter","year":"2024","journal-title":"Special Care Dentistry"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1002\/prca.201900040","article-title":"Radiomics and machine learning in oral healthcare","volume":"14","author":"Leite","year":"2020","journal-title":"Proteomics Clin Appl"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1111\/joim.13483","article-title":"Predictive models for clinical decision making: Deep dives in practical machine learning","volume":"292","author":"Eloranta","year":"2022","journal-title":"J Internal Med"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.02.021","article-title":"Cluster-based toxicity estimation of osteoradionecrosis via unsupervised machine learning: Moving beyond single dose-parameter normal tissue complication probability by using whole dose-volume histograms for cohort risk stratification","volume":"119","author":"Hosseinian","year":"2024","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2024.100668","article-title":"External validation of a multimodality deep-learning normal tissue complication probability model for mandibular osteoradionecrosis trained on 3D radiation distribution maps and clinical variables","volume":"32","author":"Humbert-Vidan","year":"2024","journal-title":"Phys Imaging Radiat Oncol"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.1016\/j.jormas.2025.102432","article-title":"Imaging-based maxillomandibular changes after head and neck radiotherapy: A systematic review and meta-analysis","volume":"126","author":"Castro","year":"2025","journal-title":"J Stomatology Oral Maxillofac Surg"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2020.12.043","article-title":"Osteoradionecrosis: exposing the evidence not the bone","volume":"109","author":"Frankart","year":"2021","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2025.12.044","article-title":"Multi-institutional normal tissue complication probability (NTCP) prediction model for mandibular osteoradionecrosis: results from the PREDMORN study","volume":"125","author":"Humbert-Vidan","year":"2026","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B17","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10884-2","article-title":"Handling imbalanced medical datasets: review of a decade of research","volume":"57","author":"Salmi","year":"2024","journal-title":"Artif Intell Rev"},{"key":"B18","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110415","article-title":"A broad review on class imbalance learning techniques","volume":"143","author":"Rezvani","year":"2023","journal-title":"Appl Soft Comput"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2023-078378","article-title":"TRIPOD+AI statement: Updated guidance for reporting clinical prediction models that use regression or machine learning methods","volume":"385","author":"Collins","year":"2024","journal-title":"BMJ"},{"key":"B20","article-title":"Head and neck tumours","volume-title":"WHO Classification of Tumours","year":""},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1259\/bjr.20200026","article-title":"Comparison of machine learning methods for prediction of osteoradionecrosis incidence in patients with head and neck cancer","volume":"94","author":"Humbert-Vidan","year":"2021","journal-title":"Br J Radiol"},{"key":"B22","unstructured":"TabPFN: A transformer that solves small tabular classification problems in a second\n          \n          \n            \n              Hollmann\n              N\n            \n            \n              M\u00fcller\n              S\n            \n            \n              Eggensperger\n              K\n            \n            \n              Hutter\n              F\n            \n          \n          \n          2023"},{"key":"B23","doi-asserted-by":"publisher","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artif Intell Res"},{"key":"B24","doi-asserted-by":"publisher","DOI":"10.3389\/froh.2022.980786","article-title":"Osteoradionecrosis of the jaw: A mini review","volume":"3","author":"Singh","year":"2022","journal-title":"Front Oral Health"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1080\/0284186X.2019.1643037","article-title":"Osteoradionecrosis of the mandible after radiotherapy for head and neck cancer: risk factors and dose-volume correlations","volume":"58","author":"Aarup-Kristensen","year":"2019","journal-title":"Acta Oncol"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2023.109736","article-title":"Development of a local dose-response relationship for osteoradionecrosis within the mandible","volume":"186","author":"Sijtsema","year":"2023","journal-title":"Radiotherapy Oncol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1016\/j.oraloncology.2016.11.015","article-title":"The prevalence and risk factors associated with osteoradionecrosis of the jaw in oral and oropharyngeal cancer patients treated with intensity-modulated radiation therapy (IMRT): The Memorial Sloan Kettering Cancer Center experience","volume":"64","author":"Owosho","year":"2017","journal-title":"Oral Oncol"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2012.05.032","article-title":"Osteoradionecrosis and radiation dose to the mandible in patients with oropharyngeal cancer","volume":"85","author":"Tsai","year":"2013","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-022-12898-8","article-title":"Predictive performance of different NTCP techniques for radiation-induced esophagitis in NSCLC patients receiving proton radiotherapy","volume":"12","author":"Chen","year":"2022","journal-title":"Sci Rep"},{"key":"B30","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.oraloncology.2017.07.014","article-title":"Incidence of, and risk factors for, mandibular osteoradionecrosis in patients with oral cavity and oropharynx cancers","volume":"72","author":"Moon","year":"2017","journal-title":"Oral Oncol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1002\/hed.23949","article-title":"Osteoradionecrosis of mandible bone in patients with oral cancer - Associated factors and treatment outcomes","volume":"38","author":"Chen","year":"2016","journal-title":"Head Neck"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1136\/heartjnl-2025-325928","article-title":"Parsimonious machine learning model to predict 1-year mortality and procedural futility after transcatheter aortic valve replacement","volume":"112","author":"Bharucha","year":"2025","journal-title":"Heart"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.1016\/j.adro.2022.101163","article-title":"Comparison of machine-learning and deep-learning methods for the prediction of osteoradionecrosis resulting from head and neck cancer radiation therapy","volume":"8","author":"Reber","year":"2023","journal-title":"Adv Radiat Oncol"},{"key":"B34","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-024-01127-3","article-title":"Generalization\u2014a key challenge for responsible AI in patient-facing clinical applications","volume":"7","author":"Goetz","year":"2024","journal-title":"NPJ Digital Med"},{"key":"B35","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-17197-6","article-title":"Generalizing machine learning models from clinical free text","volume":"15","author":"Pandian","year":"2025","journal-title":"Sci Rep"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-14-137","article-title":"Modern modelling techniques are data hungry: A simulation study for predicting dichotomous endpoints","volume":"14","author":"Van Der Ploeg","year":"2014","journal-title":"BMC Med Res Methodol"},{"key":"B37","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.jclinepi.2019.02.004","article-title":"A systematic review shows no performance benefit of machine learning over logistic regression for clinical prediction models","volume":"110","author":"Christodoulou","year":"2019","journal-title":"J Clin Epidemiol"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1955800\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,21]],"date-time":"2026-10-21T13:23:58Z","timestamp":1792589038000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1955800\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,21]]},"references-count":37,"alternative-id":["10.3389\/fonc.2026.1955800"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1955800","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,21]]},"article-number":"1955800"}}