A Comparative Evaluation of Three Time-to-Event Models Predicting 5-Year Osteoporosis Risk in Thyroid Cancer Survivors: A Nationwide Cohort Study
Endocrinology and Metabolism · 2026
DOI: 10.3803/enm.2025.2478 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Endocrinology and Metabolism, 2026. Verfasst von Young Bin Cho und 1 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medicine, Graduate School of Konkuk University, Seoul, Korea. Hauptthemen laut MEDLINE: Osteoporosis, Thyroid Neoplasms, Cancer Survivors. Die Arbeit nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Konkuk University.
Abstract (Originalsprache)
Background
Osteoporosis is a common complication among thyroid cancer survivors; however, predictive tools for this condition remain inadequate. This study aimed to develop time-to-event prediction models for assessing osteoporosis risk in thyroid cancer patients.
Methods
Using the Korean National Health Insurance Service claims database, we identified 3,089 patients newly diagnosed with thyroid cancer between 2004 and 2014. Patients were randomly divided into training and test datasets in a 7:3 ratio. Three time-toevent models were constructed: random survival forest, Boruta-Cox proportional hazards, and least absolute shrinkage and selection operator (LASSO)-penalized Cox models, with feature selection and five-fold cross-validation. Model performance was evaluated using time-dependent area under the curve, Harrell’s concordance index (C-index), and risk stratification analysis.
Results
Among thyroid cancer survivors with a median follow-up of 4.2 years, the 5-year cumulative incidence of osteoporosis was 21%. The Boruta-Cox proportional hazards model achieved the highest C-index of 0.72 (95% confidence interval [CI], 0.68 to 0.75), outperforming the random survival forest (0.68 [95% CI, 0.65 to 0.71]) and the LASSO-penalized Cox model (0.64 [95% CI, 0.61 to 0.68]). Risk stratification analysis showed that all three models significantly distinguished between low- and high-risk groups (P
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medicine, Graduate School of Konkuk University, Seoul, Korea.
- Department of Surgery, Konkuk University Medical Center, Konkuk University School of Medicine, Seoul, Korea. kspark@kuh.ac.kr.
- Department of Surgery, Konkuk University Medical Center, Seoul, Korea. kspark@kuh.ac.kr.
Förderung
- Konkuk University
Zitieren
APA
Cho, Y. B., & Park, K. S. (2026). A Comparative Evaluation of Three Time-to-Event Models Predicting 5-Year Osteoporosis Risk in Thyroid Cancer Survivors: A Nationwide Cohort Study. Endocrinology and Metabolism. https://doi.org/10.3803/enm.2025.2478
Vancouver
Cho YB, Park KS. A Comparative Evaluation of Three Time-to-Event Models Predicting 5-Year Osteoporosis Risk in Thyroid Cancer Survivors: A Nationwide Cohort Study. Endocrinology and Metabolism. 2026. doi:10.3803/enm.2025.2478
BibTeX
@article{Cho2026,
author = {Cho, Young Bin and Park, Kyoung Sik},
title = {A Comparative Evaluation of Three Time-to-Event Models Predicting 5-Year Osteoporosis Risk in Thyroid Cancer Survivors: A Nationwide Cohort Study},
journal = {Endocrinology and Metabolism},
year = {2026},
doi = {10.3803/enm.2025.2478}
}
EUVIMED