{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T22:46:36Z","timestamp":1776379596374,"version":"3.51.2"},"reference-count":43,"publisher":"Oxford University Press (OUP)","issue":"4","license":[{"start":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T00:00:00Z","timestamp":1771804800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"funder":[{"name":"Pudong New Area Health Commission of Shanghai","award":["2026-PWDL-03"],"award-info":[{"award-number":["2026-PWDL-03"]}]},{"name":"Pudong New Area Commission of Science and Economy of Shanghai","award":["10-PKJ2024-Y56"],"award-info":[{"award-number":["10-PKJ2024-Y56"]}]},{"DOI":"10.13039\/501100008750","name":"Shanghai Shenkang Hospital Development Center","doi-asserted-by":"publisher","award":["7-2025SKMR-39"],"award-info":[{"award-number":["7-2025SKMR-39"]}],"id":[{"id":"10.13039\/501100008750","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>Temporal drift, defined as changes over time in underlying data distributions, can degrade the performance of clinical prediction models. In head and neck cancer (HNC) radiotherapy, evolving proton and carbon ion therapies may shift the risk of oral mucositis over time. This study aimed to compare machine learning (ML) strategies for mitigating temporal drift in predicting grade \u22652 oral mucositis among patients treated with particle therapy.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>This retrospective cohort included 1751 adults with HNC treated with particle therapy between May 2015 and December 2022 at a single proton and heavy-ion center. Acute oral mucositis was graded twice weekly using Radiation Therapy Oncology Group criteria. Thirty-five demographic, clinical, and laboratory variables were extracted from electronic health records. Three complementary strategies were examined, including standard ML with inclusion of recent data, temporal modeling, and transfer learning, and each benchmarked using 14 machine-learning algorithms. Model performance was assessed using Area Under the Receiver Operating Characteristic Curve (AUC), F1-score, accuracy, precision, recall, and SHAP-based interpretability.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The incidence of grade \u22652 oral mucositis increased from 27.3% in 2015 to 60.4% in 2022, paralleling evolving dose and modality patterns. Models trained on 2015-2020 data declined in AUC from 0.81 internally to 0.74 and 0.68 on 2021 and 2022 data. A Extras Trees transfer-learning ensemble achieved the best temporal robustness (AUC 0.87, F1 0.82) on 2022 data, demonstrating improved adaptability to drift.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Temporal drift significantly reduced oral mucositis prediction accuracy over time. Transfer-learning ensembles improved adaptability and maintained reliable, clinically relevant performance for particle-therapy toxicity prediction.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/jamia\/ocag025","type":"journal-article","created":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T12:31:06Z","timestamp":1770121866000},"page":"890-900","source":"Crossref","is-referenced-by-count":0,"title":["Adapting machine learning models to temporal drift: oral mucositis prediction in head and neck cancer patients receiving proton and carbon ion therapy"],"prefix":"10.1093","volume":"33","author":[{"given":"Yiqiao","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Nursing, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital; Shanghai Key Laboratory of Radiation Oncology; and Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy , Shanghai 201315,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhihong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Columbia University Data Science Institute, , New York City, NY 10027,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhu","sequence":"additional","affiliation":[{"name":"Department of Nursing, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital; Shanghai Key Laboratory of Radiation Oncology; and Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy , Shanghai 201315,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziying","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Nursing, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital; Shanghai Key Laboratory of Radiation Oncology; and Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy , Shanghai 201315,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renli","family":"Ning","sequence":"additional","affiliation":[{"name":"Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital; Shanghai Key Laboratory of Radiation Oncology; and Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy, Department of Research and Development, Shanghai 201315,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Nursing, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital; Shanghai Key Laboratory of Radiation Oncology; and Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy , Shanghai 201315,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongwei","family":"Wan","sequence":"additional","affiliation":[{"name":"Department of Nursing, Shanghai Proton and Heavy Ion Center, Fudan University Cancer Hospital; Shanghai Key Laboratory of Radiation Oncology; and Shanghai Engineering Research Center of Proton and Heavy Ion Radiation Therapy , Shanghai 201315,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2026,2,23]]},"reference":[{"key":"2026041617413973000_ocag025-B1","first-page":"345","article-title":"From development to deployment: dataset shift, causality, and shift-stable models in health AI","volume":"21","author":"Subbaswamy","year":"2020","journal-title":"Biostatistics."},{"key":"2026041617413973000_ocag025-B2","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1056\/NEJMc2104626","article-title":"The clinician and dataset shift in artificial intelligence","volume":"385","author":"Finlayson","year":"2021","journal-title":"N Engl J Med."},{"key":"2026041617413973000_ocag025-B3","doi-asserted-by":"crossref","first-page":"1386760","DOI":"10.3389\/fphys.2024.1386760","article-title":"Predictive modeling of biomedical temporal data in healthcare applications: review and future directions","volume":"15","author":"Patharkar","year":"2024","journal-title":"Front Physiol."},{"key":"2026041617413973000_ocag025-B4","doi-asserted-by":"crossref","first-page":"e38053","DOI":"10.2196\/38053","article-title":"A transfer learning approach to correct the temporal performance drift of clinical prediction models: retrospective cohort study","volume":"10","author":"Zhang","year":"2022","journal-title":"JMIR Med Inform."},{"key":"2026041617413973000_ocag025-B5","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1186\/s12916-019-1426-2","article-title":"Key challenges for delivering clinical impact with artificial intelligence","volume":"17","author":"Kelly","year":"2019","journal-title":"BMC Med."},{"key":"2026041617413973000_ocag025-B6","doi-asserted-by":"crossref","first-page":"e252724","DOI":"10.1001\/jamahealthforum.2025.2724","article-title":"Understanding model drift and its impact on health care policy","volume":"6","author":"Wong","year":"2025","journal-title":"JAMA Health Forum."},{"key":"2026041617413973000_ocag025-B7","doi-asserted-by":"crossref","first-page":"e000046","DOI":"10.1136\/bmjdhai-2025-000046","article-title":"Importance of model governance in clinical AI models: case study on the relevance of data drift detection","volume":"1","author":"van der Vorst","year":"2025","journal-title":"BMJ Digit Health."},{"key":"2026041617413973000_ocag025-B8","doi-asserted-by":"crossref","first-page":"1767","DOI":"10.1007\/s12094-024-03706-y","article-title":"The prevalence of oral mucositis after radiotherapy in patients with head and neck cancer and its associated factors: a meta-analysis","volume":"27","author":"Li","year":"2025","journal-title":"Clin Transl Oncol."},{"key":"2026041617413973000_ocag025-B9","doi-asserted-by":"publisher","author":"Pacheco","year":"2021","DOI":"10.3390\/msf2021005023"},{"key":"2026041617413973000_ocag025-B10","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.semradonc.2025.02.011","article-title":"Oral mucositis in head and neck cancer patients","volume":"35","author":"Anderson","year":"2025","journal-title":"Semin Radiat Oncol."},{"key":"2026041617413973000_ocag025-B11","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.oraloncology.2019.05.013","article-title":"Oral mucositis in head and neck cancer: evidence-based management and review of clinical trial data","volume":"95","author":"Blakaj","year":"2019","journal-title":"Oral Oncol."},{"key":"2026041617413973000_ocag025-B12","doi-asserted-by":"crossref","first-page":"e2337265","DOI":"10.1001\/jamanetworkopen.2023.37265","article-title":"Severe oral mucositis after intensity-modulated radiation therapy for head and neck cancer","volume":"6","author":"Iovoli","year":"2023","journal-title":"JAMA Netw Open."},{"key":"2026041617413973000_ocag025-B13","doi-asserted-by":"crossref","DOI":"10.1259\/bjr.20200247","article-title":"Heavy charged particle beam therapy and related new radiotherapy technologies: the clinical potential, physics and technical developments required to deliver benefit for patients with cancer","volume":"93","author":"Kirkby","year":"2020","journal-title":"Br J Radiol."},{"key":"2026041617413973000_ocag025-B14","doi-asserted-by":"crossref","first-page":"34","DOI":"10.1038\/s44303-024-00039-x","article-title":"Real-time tracking of the Bragg peak during proton therapy via 3D protoacoustic imaging in a clinical scenario","volume":"2","author":"Wang","year":"2024","journal-title":"Npj Imaging."},{"key":"2026041617413973000_ocag025-B15","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1001\/jamaoncol.2019.4889","article-title":"Comparative effectiveness of proton vs photon therapy as part of concurrent chemoradiotherapy for locally advanced cancer","volume":"6","author":"Baumann","year":"2020","journal-title":"JAMA Oncol."},{"key":"2026041617413973000_ocag025-B16","doi-asserted-by":"crossref","first-page":"567","DOI":"10.1111\/jop.13426","article-title":"Toxicity with proton therapy for oral and\/or oropharyngeal cancers: a scoping review","volume":"52","author":"Sethi","year":"2023","journal-title":"J Oral Pathol Med."},{"key":"2026041617413973000_ocag025-B17","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.ctrv.2010.08.004","article-title":"Systematic review and meta-analysis of radiotherapy in various head and neck cancers: comparing photons, carbon-ions and protons","volume":"37","author":"Ramaekers","year":"2011","journal-title":"Cancer Treat Rev."},{"key":"2026041617413973000_ocag025-B18","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.radonc.2015.12.008","article-title":"Proton beam radiation therapy results in significantly reduced toxicity compared with intensity-modulated radiation therapy for head and neck tumors that require ipsilateral radiation","volume":"118","author":"Romesser","year":"2016","journal-title":"Radiother Oncol"},{"key":"2026041617413973000_ocag025-B19","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1186\/s12903-025-07369-1","article-title":"Prediction models of severe radiation-induced oral mucositis: a systematic review and meta-analysis","volume":"26","author":"Zhang","year":"2025","journal-title":"BMC Oral Health."},{"key":"2026041617413973000_ocag025-B20","first-page":"96","article-title":"Machine learning prediction model for oral mucositis risk in head and neck radiotherapy: a preliminary study","volume":"33","author":"Kauark-Fontes","year":"2025","journal-title":"Support Care Cancer."},{"key":"2026041617413973000_ocag025-B21","doi-asserted-by":"crossref","first-page":"e24866","DOI":"10.1016\/j.heliyon.2024.e24866","article-title":"Predicting severe radiation-induced oral mucositis in head and neck cancer patients using integrated baseline CT radiomic, dosimetry, and clinical features: a machine learning approach","volume":"10","author":"Agheli","year":"2024","journal-title":"Heliyon."},{"key":"2026041617413973000_ocag025-B22","doi-asserted-by":"crossref","first-page":"110709","DOI":"10.1016\/j.radonc.2025.110709","article-title":"Normal tissue complication probability model for acute oral mucositis in patients with head and neck cancer undergoing carbon ion radiation therapy based on dosimetry, radiomics, and dosiomics","volume":"204","author":"Meng","year":"2025","journal-title":"Radiother Oncol."},{"key":"2026041617413973000_ocag025-B23","doi-asserted-by":"crossref","first-page":"181","DOI":"10.4103\/crst.crst_332_22","article-title":"Artificial intelligence-based prediction of oral mucositis in patients with head-and-neck cancer: a prospective observational study utilizing a thermographic approach","volume":"6","author":"Thukral","year":"2023","journal-title":"Cancer Res Stat Treatment"},{"key":"2026041617413973000_ocag025-B24","doi-asserted-by":"publisher","first-page":"104902","DOI":"10.1016\/j.jbi.2025.104902","article-title":"Strategies for detecting and mitigating dataset shift in machine learning for health predictions: a systematic review","volume":"170","author":"Silva","year":"2025","journal-title":"J Biomed Inform."},{"key":"2026041617413973000_ocag025-B25","doi-asserted-by":"crossref","first-page":"313","DOI":"10.1007\/s41666-023-00143-4","article-title":"Assessment of prediction tasks and time window selection in temporal modeling of electronic health record data: a systematic review","volume":"7","author":"Pungitore","year":"2023","journal-title":"J Healthc Inform Res."},{"key":"2026041617413973000_ocag025-B26","doi-asserted-by":"crossref","first-page":"1711","DOI":"10.1007\/s10462-023-10561-w","article-title":"Machine and deep learning for longitudinal biomedical data: a review of methods and applications","volume":"56","author":"Cascarano","year":"2023","journal-title":"Artif Intell Rev"},{"key":"2026041617413973000_ocag025-B27","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","article-title":"A comprehensive survey on transfer learning","volume":"109","author":"Zhuang","year":"2021","journal-title":"Proc IEEE."},{"key":"2026041617413973000_ocag025-B28","doi-asserted-by":"crossref","first-page":"e52730","DOI":"10.2196\/52730","article-title":"Using domain adaptation and inductive transfer learning to improve patient outcome prediction in the intensive care unit: retrospective observational study","volume":"26","author":"Mutnuri","year":"2024","journal-title":"J Med Internet Res"},{"key":"2026041617413973000_ocag025-B29","doi-asserted-by":"crossref","first-page":"2215","DOI":"10.7150\/jca.24313","article-title":"Salvage carbon ion radiation therapy for locally recurrent or radiation-induced second primary sarcoma of the head and neck","volume":"9","author":"Yang","year":"2018","journal-title":"J Cancer."},{"key":"2026041617413973000_ocag025-B30","doi-asserted-by":"crossref","first-page":"774","DOI":"10.7150\/jca.14399","article-title":"Phase I\/II trial evaluating carbon ion radiotherapy for salvaging treatment of locally recurrent nasopharyngeal carcinoma","volume":"7","author":"Kong","year":"2016","journal-title":"J Cancer."},{"key":"2026041617413973000_ocag025-B31","doi-asserted-by":"crossref","first-page":"4574","DOI":"10.1002\/cam4.2319","article-title":"Intensity-modulated proton and carbon-ion radiation therapy in the management of head and neck sarcomas","volume":"8","author":"Yang","year":"2019","journal-title":"Cancer Med."},{"key":"2026041617413973000_ocag025-B32","doi-asserted-by":"crossref","first-page":"7914","DOI":"10.1002\/cam4.3393","article-title":"Particle beam radiation therapy for sinonasal malignancies: single institutional experience at the Shanghai proton and heavy ion center","volume":"9","author":"Hu","year":"2020","journal-title":"Cancer Med."},{"key":"2026041617413973000_ocag025-B33","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1016\/0360-3016","article-title":"Toxicity criteria of the Radiation Therapy Oncology Group (RTOG) and the European organization for research and treatment of cancer (EORTC)","volume":"31","author":"Cox","year":"1995","journal-title":"Int J Radiat Oncol Biol Phys."},{"key":"2026041617413973000_ocag025-B34","article-title":"mice: multivariate imputation by chained equations in R","volume":"45","author":"van Buuren","year":"2011","journal-title":"J Stat Softw"},{"key":"2026041617413973000_ocag025-B35","first-page":"2825","article-title":"Scikit-learn: machine learning in python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J Machine Learning Res"},{"key":"2026041617413973000_ocag025-B36","doi-asserted-by":"crossref","first-page":"100159","DOI":"10.1016\/j.ibmed.2024.100159","article-title":"Predictive modeling of Alzheimer\u2019s disease progression: integrating temporal clinical factors and outcomes in time series forecasting","volume":"10","author":"Aqil","year":"2024","journal-title":"Intell Based Med"},{"key":"2026041617413973000_ocag025-B37","first-page":"1","article-title":"Imbalanced-learn: a python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"Lema\u00eetre","year":"2017","journal-title":"J Machine Learning Res"},{"key":"2026041617413973000_ocag025-B38","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J Artificial Intell Res"},{"key":"2026041617413973000_ocag025-B39","doi-asserted-by":"publisher","first-page":"2346-2363","DOI":"10.1109\/TKDE.2018.2876857","article-title":"Learning under concept drift: a review","volume":"31","author":"Lu","year":"2019","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"2026041617413973000_ocag025-B40","doi-asserted-by":"crossref","DOI":"10.1186\/s40537-016-0043-6","article-title":"A survey of transfer learning","volume":"3","author":"Weiss","year":"2016","journal-title":"J Big Data."},{"key":"2026041617413973000_ocag025-B41","doi-asserted-by":"crossref","first-page":"103611","DOI":"10.1016\/j.jbi.2020.103611","article-title":"Detection of calibration drift in clinical prediction models to inform model updating","volume":"112","author":"Davis","year":"2020","journal-title":"J Biomed Inform."},{"key":"2026041617413973000_ocag025-B42","doi-asserted-by":"crossref","first-page":"104930","DOI":"10.1016\/j.ijmedinf.2022.104930","article-title":"Assessing the effects of data drift on the performance of machine learning models used in clinical sepsis prediction","volume":"173","author":"Rahmani","year":"2023","journal-title":"Int J Med Inform."},{"key":"2026041617413973000_ocag025-B43","doi-asserted-by":"publisher","first-page":"20220878","DOI":"10.1259\/bjr.20220878","article-title":"Data drift in medical machine learning: implications and potential remedies","volume":"96","author":"Sahiner","year":"2023","journal-title":"Br J Radiol."}],"container-title":["Journal of the American Medical Informatics Association"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/jamia\/advance-article-pdf\/doi\/10.1093\/jamia\/ocag025\/67075335\/ocag025.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/4\/890\/67075335\/ocag025.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/jamia\/article-pdf\/33\/4\/890\/67075335\/ocag025.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T21:43:22Z","timestamp":1776375802000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/jamia\/article\/33\/4\/890\/8494987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,23]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2026,2,23]]},"published-print":{"date-parts":[[2026,4,1]]}},"URL":"https:\/\/doi.org\/10.1093\/jamia\/ocag025","relation":{},"ISSN":["1067-5027","1527-974X"],"issn-type":[{"value":"1067-5027","type":"print"},{"value":"1527-974X","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2026,4]]},"published":{"date-parts":[[2026,2,23]]}}}