{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T11:17:49Z","timestamp":1787915869432,"version":"build-2784847793"},"reference-count":61,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T00:00:00Z","timestamp":1787875200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000265","name":"Medical Research Council","doi-asserted-by":"publisher","award":["UKRI3650"],"award-info":[{"award-number":["UKRI3650"]}],"id":[{"id":"10.13039\/501100000265","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oncol."],"abstract":"<jats:p>Normal tissue complication probability (NTCP) modelling is central to balancing tumour control and toxicity risk in radiotherapy (RT) for head and neck cancer (HNC). Despite major advances in radiation delivery and imaging, toxicity remains a major determinant of long-term quality of life in survivors. Classical NTCP models based on dose\u2013volume histograms (DVHs) and phenomenological equations such as the Lyman\u2013Kutcher\u2013Burman model have provided clinically valuable guidance for decades but oversimplify the complex, multidimensional nature of the normal tissue radiation response. Recent developments in machine learning (ML) and deep learning (DL) have enabled the integration of large-scale clinical, imaging, dosimetric and biological data to generate more accurate, patient-specific toxicity predictions. However, data scarcity, endpoint variability, and limited external generalisability have restricted clinical translation. This mini-review summarises the current status of NTCP modelling in HNC, focusing on evolving multimodal DL approaches and data fusion strategies. A structured literature review approach identified 10 contemporary studies of multimodal DL models for radiotherapy-related toxicity prediction in HNC. Across included studies, fusion architectures were inconsistently reported and model development procedures were also variably described regarding feature selection, hyperparameter tuning, model selection and validation. Current multimodal DL NTCP models are promising but not yet ready for routine clinical use, with robust external validation, calibration assessment, reproducibility, clinical utility evaluation and prospective testing required before integration into RT decision-support workflows.<\/jats:p>","DOI":"10.3389\/fonc.2026.1893002","type":"journal-article","created":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T10:44:46Z","timestamp":1787913886000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Current status and future directions of multimodal deep learning normal tissue complication probability modelling in head and neck cancer radiotherapy"],"prefix":"10.3389","volume":"16","author":[{"given":"Victoria","family":"Butterworth","sequence":"first","affiliation":[{"name":"School of Cancer & Pharmaceutical Sciences, King\u2019s College London","place":["London, United Kingdom"]},{"name":"Radiotherapy, Guy\u2019s and St Thomas\u2019 NHS Foundation Trust","place":["London, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tom","family":"Young","sequence":"additional","affiliation":[{"name":"School of Cancer & Pharmaceutical Sciences, King\u2019s College London","place":["London, United Kingdom"]},{"name":"Radiotherapy, Guy\u2019s and St Thomas\u2019 NHS Foundation Trust","place":["London, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrew P.","family":"King","sequence":"additional","affiliation":[{"name":"School of Biomedical Engineering & Imaging Sciences, King\u2019s College London","place":["London, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Teresa","family":"Guerrero Urbano","sequence":"additional","affiliation":[{"name":"School of Cancer & Pharmaceutical Sciences, King\u2019s College London","place":["London, United Kingdom"]},{"name":"Radiotherapy, Guy\u2019s and St Thomas\u2019 NHS Foundation Trust","place":["London, United Kingdom"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,8,28]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"399","DOI":"10.1007\/978-3-030-83047-2_17","article-title":"Modelling of radiotherapy response (TCP\/NTCP)","volume-title":"Machine and Deep Learning in Oncology, Medical Physics and Radiology","author":"Gulliford","year":"2022"},{"key":"B2","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2021.01.024","article-title":"Comprehensive toxicity risk profiling in radiation therapy for head and neck cancer: A new concept for individually optimised treatment","volume":"157","author":"Van den Bosch","year":"2021","journal-title":"Radiotherapy Oncol"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2021.12.002","article-title":"Deep learning for radiotherapy outcome prediction using dose data \u2013 a review","volume":"34","author":"Appelt","year":"2022","journal-title":"Clin Oncol"},{"key":"B4","first-page":"61","article-title":"Physics of radiation therapy for the radiobiologist","volume-title":"Basic Clinical Radiobiology","author":"Joiner","year":"2019"},{"key":"B5","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1016\/j.canrad.2023.05.001","article-title":"Prediction of toxicity outcomes following radiotherapy using deep learning-based models: A systematic review","volume":"27","author":"Tan","year":"2023","journal-title":"Cancer\/Radioth\u00e9rapie"},{"key":"B6","doi-asserted-by":"publisher","DOI":"10.3389\/fonc.2020.01178","article-title":"Image based data mining using per-voxel Cox regression","volume":"10","author":"Green","year":"2020","journal-title":"Front Oncol"},{"key":"B7","doi-asserted-by":"publisher","DOI":"10.1016\/j.semradonc.2023.03.010","article-title":"Normal tissue toxicity prediction: Clinical translation on the horizon","volume":"33","author":"Kerns","year":"2023","journal-title":"Semin Radiat Oncol"},{"key":"B8","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110689","article-title":"Predictive biomarkers of radiotherapy- related dermatitis, xerostomia, mucositis and dysphagia in head and neck cancer: A systematic review","volume":"203","author":"Koch","year":"2025","journal-title":"Radiotherapy Oncol"},{"key":"B9","doi-asserted-by":"publisher","DOI":"10.1038\/nrc.2016.18","article-title":"Radiation oncology in the era of precision medicine","volume":"16","author":"Baumann","year":"2016","journal-title":"Nat Rev Cancer"},{"key":"B10","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.07.1754","article-title":"Use of normal tissue complication probability models in the clinic","volume":"76","author":"Marks","year":"2010","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B11","doi-asserted-by":"publisher","DOI":"10.1016\/0360-3016(91)90171-Y","article-title":"Tolerance of normal tissue to therapeutic irradiation","volume":"21","author":"Emami","year":"1991","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B12","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2009.09.040","article-title":"Quantitative analyses of normal tissue effects in the clinic (QUANTEC): An introduction to the scientific issues","volume":"76","author":"Bentzen","year":"2010","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ctro.2023.100590","article-title":"Artificial intelligence to predict outcomes of head and neck radiotherapy","volume":"39","author":"Bang","year":"2023","journal-title":"Clin Transl Radiat Oncol"},{"key":"B14","doi-asserted-by":"publisher","first-page":"95","DOI":"10.14338\/20-00092","article-title":"NTCP modeling of late effects for head and neck cancer: A systematic review","volume":"8","author":"Stieb","year":"2021","journal-title":"Int J Part Ther"},{"key":"B15","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2019.03.004","article-title":"Rapid advances in auto-segmentation of organs at risk and target volumes in head and neck cancer","volume":"135","author":"Kosmin","year":"2019","journal-title":"Radiotherapy Oncol"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.1002\/1878-0261.12751","article-title":"Image guidance in radiation therapy for better cure of cancer","volume":"14","author":"Gr\u00e9goire","year":"2020","journal-title":"Mol Oncol"},{"key":"B17","doi-asserted-by":"publisher","first-page":"13","DOI":"10.1016\/j.phro.2021.05.007","article-title":"Machine learning applications in radiation oncology","volume":"19","author":"Field","year":"2021","journal-title":"Phys Imaging Radiat Oncol"},{"key":"B18","doi-asserted-by":"publisher","first-page":"106386","DOI":"10.1016\/j.oraloncology.2023.106386","article-title":"Machine learning for the prediction of toxicities from head and neck cancer treatment: A systematic review with meta-analysis","volume":"140","author":"Ara\u00fajo","year":"2023","journal-title":"Oral Oncol"},{"key":"B19","doi-asserted-by":"publisher","DOI":"10.1016\/S0895-4356(96)00236-3","article-title":"A simulation study of the number of events per variable in logistic regression analysis","volume":"49","author":"Peduzzi","year":"1996","journal-title":"J Clin Epidemiol"},{"key":"B20","doi-asserted-by":"publisher","first-page":"12TR01","DOI":"10.1088\/1361-6560\/ac0681","article-title":"Spatial descriptions of radiotherapy dose: normal tissue complication models and statistical associations","volume":"66","author":"Ebert","year":"2021","journal-title":"Phys Med Biol"},{"key":"B21","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2020.02.013","article-title":"Generalizability assessment of head and neck cancer NTCP models based on the TRIPOD criteria","volume":"146","author":"Sharabiani","year":"2020","journal-title":"Radiotherapy Oncol"},{"key":"B22","doi-asserted-by":"publisher","first-page":"111350","DOI":"10.1016\/j.radonc.2025.111350","article-title":"The actual performance of ML\/AI models in predicting radiation-induced toxicity in head and neck cancer: a systematic review and meta-analysis","volume":"216","author":"Ugwu","year":"2026","journal-title":"Radiotherapy Oncol"},{"key":"B23","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1038\/s41746-020-00341-z","article-title":"Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines","volume":"3","author":"Huang","year":"2020","journal-title":"NPJ Digit Med"},{"key":"B24","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","article-title":"Deep multimodal learning: A survey on recent advances and trends","volume":"34","author":"Ramachandram","year":"2017","journal-title":"IEEE Signal Process Mag"},{"key":"B25","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2019.06.009","article-title":"A deep learning model for predicting xerostomia due to radiation therapy for head and neck squamous cell carcinoma in the RTOG 0522 clinical trial","volume":"105","author":"Men","year":"2019","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijrobp.2024.07.2334","article-title":"Three-dimensional deep learning normal tissue complication probability model to predict late xerostomia in patients with head and neck cancer","volume":"121","author":"Chu","year":"2025","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B27","doi-asserted-by":"publisher","first-page":"305ra147","DOI":"10.1126\/scitranslmed.aac4441","article-title":"Sparing the region of the salivary gland containing stem cells preserves saliva production after radiotherapy for head and neck cancer","volume":"7","author":"van Luijk","year":"2015","journal-title":"Sci Transl Med"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.1016\/j.meddos.2021.03.005","article-title":"Convolutional neural network and transfer learning for dose volume histogram prediction for prostate cancer radiotherapy","volume":"46","author":"Ambroa","year":"2021","journal-title":"Med Dosim"},{"key":"B29","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2022.04.016","article-title":"Use of deep learning to predict the need for aggressive nutritional supplementation during head and neck radiotherapy","volume":"171","author":"Dohopolski","year":"2022","journal-title":"Radiotherapy Oncol"},{"key":"B30","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2025.110951","article-title":"Deep learning dosiomics for the pretreatment prediction of radiation dermatitis in nasopharyngeal carcinoma patients treated with radiotherapy","volume":"209","author":"Xiang","year":"2025","journal-title":"Radiotherapy Oncol"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2025.111312","article-title":"Dynamic prediction of radiotherapy toxicities in head and neck cancer using clinical and imaging data","volume":"214","author":"Bang","year":"2026","journal-title":"Radiotherapy Oncol"},{"key":"B32","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2025.111169","article-title":"Deep learning NTCP model for late dysphagia after radiotherapy for head and neck cancer patients based on 3D dose, CT and segmentations","volume":"213","author":"de Vette","year":"2025","journal-title":"Radiotherapy Oncol"},{"key":"B33","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1186\/s12880-025-01848-1","article-title":"A deep learning model for predicting radiation-induced xerostomia in patients with head and neck cancer based on multi-channel fusion","volume":"25","author":"Lin","year":"2025","journal-title":"BMC Med Imaging"},{"key":"B34","doi-asserted-by":"publisher","first-page":"20NT01","DOI":"10.1088\/1361-6560\/ad8290","article-title":"Comparison of deep-learning multimodality data fusion strategies in mandibular osteoradionecrosis NTCP modelling using clinical variables and radiation dose distribution volumes","volume":"69","author":"Humbert-Vidan","year":"2024","journal-title":"Phys Med Biol"},{"key":"B35","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":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2026.111486","article-title":"A multi-toxicity deep learning approach for normal tissue complication probability modelling in head and neck cancer patients receiving radiotherapy","volume":"219","author":"MacRae","year":"2026","journal-title":"Radiotherapy Oncol"},{"key":"B37","doi-asserted-by":"publisher","DOI":"10.1002\/mp.16972","article-title":"RADCURE: An open\u2010source head and neck cancer CT dataset for clinical radiation therapy insights","volume":"51","author":"Welch","year":"2024","journal-title":"Med Phys"},{"key":"B38","doi-asserted-by":"publisher","first-page":"100162","DOI":"10.1016\/j.esmorw.2025.100162","article-title":"Data-centric artificial intelligence and cancer research: Construction of a real-world head and neck treatment data repository","volume":"9","author":"Butterworth","year":"2025","journal-title":"ESMO Real World Data and Digital Oncology"},{"key":"B39","doi-asserted-by":"publisher","DOI":"10.1016\/j.clon.2025.103935","article-title":"RT-HaND_C: A multi-source, validated real-world head and neck cancer dataset for research","volume":"47","author":"Young","year":"2025","journal-title":"Clin Oncol"},{"key":"B40","unstructured":"NIHR Supports Study to Predict the Side Effects of Radiotherapy: Hamlet.Rt\n          \n          2024"},{"key":"B41","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/j.radonc.2022.09.014","article-title":"Protocol letter: A multi-institutional retrospective case-control cohort investigating PREDiction models for mandibular osteoradionecrosis in head and neck cancer (PREDMORN)","volume":"176","author":"Humbert-Vidan","year":"2022","journal-title":"Radiotherapy Oncol"},{"key":"B42","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":"B43","doi-asserted-by":"publisher","DOI":"10.1007\/s00439-008-0500-1","article-title":"Evidence for significant heritability of apoptotic and cell cycle responses to ionising radiation","volume":"123","author":"Finnon","year":"2008","journal-title":"Hum Genet"},{"key":"B44","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/S0360-3016(01)02690-6","article-title":"Deterministic rather than stochastic factors explain most of the variation in the expression of skin telangiectasia after radiotherapy","volume":"52","author":"Safwat","year":"2002","journal-title":"Int J Radiat Oncol Biol Phys"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2014.02.012","article-title":"A genome wide association study (GWAS) providing evidence of an association between common genetic variants and late radiotherapy toxicity","volume":"111","author":"Barnett","year":"2014","journal-title":"Radiotherapy Oncol"},{"key":"B46","doi-asserted-by":"publisher","DOI":"10.1038\/s41416-021-01670-w","article-title":"A genome-wide association study of radiotherapy induced toxicity in head and neck cancer patients identifies a susceptibility locus associated with mucositis","volume":"126","author":"Schack","year":"2022","journal-title":"Br J Cancer"},{"key":"B47","doi-asserted-by":"publisher","first-page":"pkad088","DOI":"10.1093\/jncics\/pkad088","article-title":"Large-scale meta\u2013genome-wide association study reveals common genetic factors linked to radiation-induced acute toxicities across cancer types","volume":"7","author":"Naderi","year":"2023","journal-title":"JNCI Cancer Spectr"},{"key":"B48","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2022.09.016","article-title":"Meta-GWAS identifies the heritability of acute radiation-induced toxicities in head and neck cancer","volume":"176","author":"Naderi","year":"2022","journal-title":"Radiotherapy Oncol"},{"key":"B49","doi-asserted-by":"publisher","DOI":"10.1177\/03008916221078061","article-title":"Predicting acute severe toxicity for head and neck squamous cell carcinomas by combining dosimetry with a radiosensitivity biomarker: a pilot study","volume":"109","author":"Deneuve","year":"2023","journal-title":"Tumori J"},{"key":"B50","doi-asserted-by":"publisher","DOI":"10.1200\/JCO.2007.14.6647","article-title":"Impact of late treatment-related toxicity on quality of life among patients with head and neck cancer treated with radiotherapy","volume":"26","author":"Langendijk","year":"2008","journal-title":"J Clin Oncol"},{"key":"B51","doi-asserted-by":"publisher","DOI":"10.1080\/14796678.2026.2620956","article-title":"AI-assisted MI diagnosis from echocardiogram videos: does explainability enhance human-AI collaborative accuracy","volume":"22","author":"Khan","year":"2026","journal-title":"Future Cardiol"},{"key":"B52","doi-asserted-by":"publisher","DOI":"10.1136\/bmj-2024-082505","article-title":"PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods","volume":"388","author":"Moons","year":"2025","journal-title":"BMJ"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.240300","article-title":"Checklist for artificial intelligence in medical imaging (CLAIM): 2024 update","volume":"6","author":"Tejani","year":"2024","journal-title":"Radiol Artif Intell"},{"key":"B54","unstructured":"Open Science- Our Code Policy"},{"key":"B55","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcpo.2024.100537","article-title":"PRE-ACT: Prediction of radiotherapy side effects using explainable AI for patient communication and treatment modification","volume":"43","author":"Liang","year":"2025","journal-title":"J Cancer Policy"},{"key":"B56","doi-asserted-by":"publisher","DOI":"10.1016\/j.phro.2026.100978","article-title":"An evaluation of uncertainty quantification methods and measures for deep learning outcome prediction models in head and neck cancer radiotherapy","volume":"39","author":"MacRae","year":"2026","journal-title":"Phys Imaging Radiat Oncol"},{"key":"B57","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-83047-2_15","article-title":"Prediction of oncology treatment outcomes","volume-title":"Machine and Deep Learning in Oncology, Medical Physics and Radiology","author":"Cui","year":"2022"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.1016\/j.radonc.2024.110345","article-title":"A joint ESTRO and AAPM guideline for development, clinical validation and reporting of artificial intelligence models in radiation therapy","volume":"197","author":"Hurkmans","year":"2024","journal-title":"Radiotherapy Oncol"},{"key":"B59","doi-asserted-by":"publisher","first-page":"tzae039","DOI":"10.1093\/BJRO\/TZAE039","article-title":"Artificial intelligence research in radiation oncology: a practical guide for the clinician on concepts and methods","volume":"6","author":"Hoebers","year":"2023","journal-title":"BJR|Open"},{"key":"B60","doi-asserted-by":"publisher","DOI":"10.1016\/j.canlet.2016.05.033","article-title":"Big data and machine learning in radiation oncology: State of the art and future prospects","volume":"382","author":"Bibault","year":"2016","journal-title":"Cancer Lett"},{"key":"B61","doi-asserted-by":"publisher","DOI":"10.7326\/M18-0850","article-title":"PRISMA extension for scoping reviews (PRISMA-ScR): checklist and explanation","volume":"169","author":"Tricco","year":"2018","journal-title":"Ann Intern Med"}],"container-title":["Frontiers in Oncology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1893002\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,28]],"date-time":"2026-08-28T10:44:49Z","timestamp":1787913889000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fonc.2026.1893002\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,28]]},"references-count":61,"alternative-id":["10.3389\/fonc.2026.1893002"],"URL":"https:\/\/doi.org\/10.3389\/fonc.2026.1893002","relation":{},"ISSN":["2234-943X"],"issn-type":[{"value":"2234-943X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,28]]},"article-number":"1893002"}}