Skip to content
DraconiticResearch
Search Sources API
194,161 studies31 sourcesUpdated 7 min ago
Peer-reviewedCC BY-NC-NDClinical and Translational Radiation Oncology

Development and validation of a cumulative risk model and assessment tool for radiation-induced hypothyroidism in head and neck cancer: a multicentre study

  • Jiaming Wu1
  • Jie Gong2
  • Jiang Zhang1
  • Xinzhi Teng1
  • Xinyu Zhang1
  • Jeffrey C.F. Lui3
  • Ka Man Cheung4
  • Kwok Hung Au4
  • Kenneth C.W. Wong5
  • Dave K.W. Yeung5
  • Victor H.F. Lee6
  • Jing Cai1
3 more authors
  • Tian Li7
  • Jian Zang8
  • James C.H. Chow9
9 affiliations
  1. 1Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China
  2. 2Xijing Hospital, The Fourth Military Medical University, Xi'an, China
  3. 3Department of Clinical Oncology, Queen Elizabeth Hospital, Hong Kong SAR, China; Department of Clinical Oncology, The University of Hong Kong, Hong Kong SAR, China
  4. 4Department of Clinical Oncology, Queen Elizabeth Hospital, Hong Kong SAR, China
  5. 5Department of Clinical Oncology, Prince of Wales Hospital, Hong Kong SAR, China
  6. 6Department of Clinical Oncology, The University of Hong Kong, Hong Kong SAR, China
  7. 7Department of Health Technology and Informatics, The Hong Kong Polytechnic University, Hung Hom, Kowloon, Hong Kong SAR, China; Corresponding authors.
  8. 8Xijing Hospital, The Fourth Military Medical University, Xi'an, China; Corresponding authors.
  9. 9Department of Clinical Oncology, Queen Elizabeth Hospital, Hong Kong SAR, China; Corresponding author at: Department of Clinical Oncology, Queen Elizabeth Hospital, Kowloon, Hong Kong SAR, China.
Read full textPDFDOICite

Abstract

Objectives: Radiation-induced hypothyroidism (RIHT) is a common late toxicity after head and neck radiotherapy. We aimed to develop and externally validate a multimodal Cox model for patient-specific cumulative RIHT risk assessment. Materials & methods: This retrospective multicentre study included 1407 patients across four cohorts. The model was developed in the training cohort and externally validated in three independent cohorts. Candidate predictors included CT radiomics, dosiomics, dose-volume histogram parameters, and clinical variables. A multimodal Cox model was developed and used to estimate cumulative risks across time horizons. Temporal risk groups were derived from predicted 3- and 7-year risks. Results: A total of 1407 patients (mean age, 55.4 ± 13.8 years; 1027 men) were evaluated and RIHT occurred in 694 (49.3%). The final model integrated three CT radiomics features, four dosiomics features, mean thyroid dose, age and N stage. It achieved C-index/overall AUC values of 0.714/0.765 in the development cohort and 0.725/0.800, 0.680/0.754, and 0.627/0.690 in the three external validation cohorts. Four temporal risk groups had RIHT event rates of 21.7%, 46.1%, 58.3%, and 71.8%, with significant differences in RIHT-free survival (log-rank p < 0.001). The model was packaged as an open-source software tool for individualised risk assessment. Conclusion: The externally validated multimodal Cox model provided time-resolved, patient-specific RIHT risk estimates and temporal risk stratification using routinely available radiotherapy-planning data.

Related

  1. Development and internal validation of an oxygen saturation-based prehospital cardiac risk assessment index (P-CRAI) for predicting 30-day mortality in acute myocardial infarction: a multicentre registry study from the Mie ACS Registry, Japan
    Yosuke Kirii, Tairo Kurita, Hiromasa Ito +10
    BMJ OpenPeer-reviewedCC BY-NC 4.0Full textCardiovascular medicineCrossrefPMC
  2. An explainable artificial intelligence system for prognostic assessment and decision support in diabetic foot ulcer care: a multicentre derivation and validation study with prospective randomised evaluation
    Jia-Yu Zhang, Yangyang Zhuang, Qingping Cao +9
    eClinicalMedicinePeer-reviewedCC BY-NC-ND 4.0General medicineCrossref
  3. Development and validation of interpretable machine learning models for predicting cumulative live birth rates in assisted reproductive technology: a SHAP-based analysis.
    XiaoQian Fu, Yisi Qin, Qianyi Huang +3
    Frontiers in endocrinologyPeer-reviewedCC BYFull textObstetrics, gynaecology & paediatricsEurope PMCCrossref
  4. A Parsimonious Machine Learning Model for Predicting Invasive Coronary Angiography Referral After Coronary Computed Tomography Angiography: Development and Multicentre External Validation
    Alec Chunta, Caitlyn Gilbert, Dina Labib +10
    Journal of clinical medicinePeer-reviewedCC BYFull textMedical imaging & radiologyEurope PMCCrossref
  5. Development and validation of an artificial intelligence model for basal cell carcinoma detection and section completeness assessment in Mohs micrographic surgery in an Asian cohort
    Li Yang Loo, Wen-Bin Luo, Isaac Hong-Kei Lam +11
    JAAD internationalPeer-reviewedCC BYFull textGeneral medicineEurope PMC

Cite

BibTeXRIS
BibTeX
@article{wu2026development,
  title = {{Development and validation of a cumulative risk model and assessment tool for radiation-induced hypothyroidism in head and neck cancer: a multicentre study}},
  author = {Jiaming Wu and Jie Gong and Jiang Zhang and Xinzhi Teng and Xinyu Zhang and Jeffrey C.F. Lui and Ka Man Cheung and Kwok Hung Au and Kenneth C.W. Wong and Dave K.W. Yeung and Victor H.F. Lee and Jing Cai and Tian Li and Jian Zang and James C.H. Chow},
  journal = {Clinical and Translational Radiation Oncology},
  year = {2026},
  month = oct,
  doi = {10.1016/j.ctro.2026.101325},
  url = {https://doi.org/10.1016/j.ctro.2026.101325},
  note = {CC BY-NC-ND},
}
RIS
TY  - JOUR
TI  - Development and validation of a cumulative risk model and assessment tool for radiation-induced hypothyroidism in head and neck cancer: a multicentre study
AU  - Jiaming Wu
AU  - Jie Gong
AU  - Jiang Zhang
AU  - Xinzhi Teng
AU  - Xinyu Zhang
AU  - Jeffrey C.F. Lui
AU  - Ka Man Cheung
AU  - Kwok Hung Au
AU  - Kenneth C.W. Wong
AU  - Dave K.W. Yeung
AU  - Victor H.F. Lee
AU  - Jing Cai
AU  - Tian Li
AU  - Jian Zang
AU  - James C.H. Chow
PY  - 2026
DA  - 2026/10/16
JO  - Clinical and Translational Radiation Oncology
DO  - 10.1016/j.ctro.2026.101325
UR  - https://doi.org/10.1016/j.ctro.2026.101325
AB  - Objectives: Radiation-induced hypothyroidism (RIHT) is a common late toxicity after head and neck radiotherapy. We aimed to develop and externally validate a multimodal Cox model for patient-specific cumulative RIHT risk assessment. Materials & methods: This retrospective multicentre study included 1407 patients across four cohorts. The model was developed in the training cohort and externally validated in three independent cohorts. Candidate predictors included CT radiomics, dosiomics, dose-volume histogram parameters, and clinical variables. A multimodal Cox model was developed and used to estimate cumulative risks across time horizons. Temporal risk groups were derived from predicted 3- and 7-year risks. Results: A total of 1407 patients (mean age, 55.4 ± 13.8 years; 1027 men) were evaluated and RIHT occurred in 694 (49.3%). The final model integrated three CT radiomics features, four dosiomics features, mean thyroid dose, age and N stage. It achieved C-index/overall AUC values of 0.714/0.765 in the development cohort and 0.725/0.800, 0.680/0.754, and 0.627/0.690 in the three external validation cohorts. Four temporal risk groups had RIHT event rates of 21.7%, 46.1%, 58.3%, and 71.8%, with significant differences in RIHT-free survival (log-rank p < 0.001). The model was packaged as an open-source software tool for individualised risk assessment. Conclusion: The externally validated multimodal Cox model provided time-resolved, patient-specific RIHT risk estimates and temporal risk stratification using routinely available radiotherapy-planning data.
SN  - 2405-6308
ER  -