Machine-Learning Prediction of Pediatric Thyroid Nodule Malignancy Using Structured Nodule and Cervical Lymph-Node Ultrasonographic Features
Diagnostics · 14.11.2026 · 16 (22) · 3773
DOI: 10.3390/diagnostics16223773 ↗Kurz gefasst
Fachartikel in der Zeitschrift Diagnostics, online erschienen am 14.11.2026. Verfasst von Jiaojiao Ding und 7 weiteren Autor:innen. Die Arbeit nennt 20 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Beijing Municipal Science & Technology Commission, Administrative Commission of Zhongguancun Science Park.
Abstract (Originalsprache)
Background/Objectives: Pediatric thyroid nodules carry a higher malignancy risk and more frequent regional cervical lymph-node involvement than adult nodules, making individualized pre-biopsy risk assessment particularly important. We aimed to develop and temporally validate a machine-learning model integrating routinely available thyroid-nodule and cervical lymph-node ultrasonographic features for malignancy-risk estimation in children.
Methods
This retrospective single-center study at a tertiary pediatric referral center included consecutive patients aged 18 years or younger undergoing biopsy-based diagnostic evaluation between January 2019 and August 2025. The cohort comprised 195 patients with 221 nodules. Six candidate algorithms were evaluated using patient-grouped nested cross-validation. The selected XGBoost model integrated structured nodule and regional cervical lymph-node ultrasonographic features and was evaluated using discrimination, precision–recall performance, probability accuracy, calibration, and threshold-dependent operating characteristics. ACR TI-RADS served as a secondary standardized comparator.
Results
Overall, 151 of 221 nodules (68.3%) were malignant, including 32 of 48 nodules (66.7%) in the temporal validation cohort. The final model achieved an AUROC of 0.973 (95% CI, 0.919–1.000), an AUPRC of 0.986 (95% CI, 0.954–1.000), a Brier score of 0.071 (95% CI, 0.030–0.126), a sensitivity of 84.4%, and a specificity of 87.5%. For comparison, the ACR TI-RADS total score yielded an AUROC of 0.906, while the TR5-positive and TR4/5-positive strategies yielded sensitivities of 84.4% and 93.8% and specificities of 87.5% and 56.2%, respectively.
Conclusions
Integrating thyroid-nodule and cervical lymph-node ultrasonographic features enabled individualized malignancy-risk estimation in this selected pediatric biopsy-evaluation cohort. The continuous risk estimate may complement established sonographic assessment as an adjunct to comprehensive diagnostic evaluation. Prospective multicenter external validation is required before broader clinical application.
Förderung
- Beijing Municipal Science & Technology Commission
- Administrative Commission of Zhongguancun Science Park
Zitieren
APA
Ding, J., Zhang, X., Chang, Y., Tang, S., Wan, J., Liu, Q., Shi, W., & Ni, X. (2026). Machine-Learning Prediction of Pediatric Thyroid Nodule Malignancy Using Structured Nodule and Cervical Lymph-Node Ultrasonographic Features. Diagnostics, 16(22), 3773. https://doi.org/10.3390/diagnostics16223773
Vancouver
Ding J, Zhang X, Chang Y, Tang S, Wan J, Liu Q, et al. Machine-Learning Prediction of Pediatric Thyroid Nodule Malignancy Using Structured Nodule and Cervical Lymph-Node Ultrasonographic Features. Diagnostics. 2026;16(22):3773. doi:10.3390/diagnostics16223773
BibTeX
@article{Ding2026,
author = {Ding, Jiaojiao and Zhang, Xiao and Chang, Yue and Tang, Saikang and Wan, Jiabin and Liu, Qiaoyin and Shi, Wenyuan and Ni, Xin},
title = {Machine-Learning Prediction of Pediatric Thyroid Nodule Malignancy Using Structured Nodule and Cervical Lymph-Node Ultrasonographic Features},
journal = {Diagnostics},
year = {2026},
volume = {16},
number = {22},
pages = {3773},
doi = {10.3390/diagnostics16223773}
}
EUVIMED