EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Clinically Aligned Two‐Stage Machine Learning Framework for Predicting Hungry Bone Syndrome After Parathyroidectomy

Shih-Min Yin iD, Yu-Chieh Lin, Tzu-Hsun Hung, Shen-En Chou, Shun-Yu Chi, Fong-Fu Chou, Yi-Ju Wu, Si-Yuan Wu iD, Jenn-Jier James Lien, Po-Chih Kuo iD, Yi-Chia Chan iD

Endocrinology, Diabetes & Metabolism · 2026-09 · 9 (5)

DOI: 10.1002/edm2.70297 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Endocrinology, Diabetes & Metabolism, online erschienen am 30.07.2026. Verfasst von Shih-Min Yin und 10 weiteren Autor:innen. Beteiligte Einrichtung: Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan. Hauptthemen laut MEDLINE: Parathyroidectomy, Hypocalcemia, Hyperparathyroidism, Secondary, Machine Learning. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 39 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Hungry bone syndrome (HBS) is a frequent and clinically significant complication following parathyroidectomy (PTX) in patients with secondary hyperparathyroidism (SHPT), often leading to prolonged hypocalcaemia and increased healthcare burden. Existing prediction models are limited by small sample sizes and inability to capture complex clinical interactions. This study aimed to develop and validate a clinically aligned, two‐stage machine learning (ML) framework to predict HBS after PTX. Materials and Methods A retrospective cohort of patients undergoing PTX for SHPT between 2008 and 2025 at a tertiary centre was analysed. A two‐stage ML framework was constructed: stage 1 used preoperative variables to generate a risk score, and stage 2 integrated this score with intraoperative features. Multiple ML models were evaluated using area under the receiver operating characteristic curve (AUROC), calibration metrics and resampling techniques.

Results

A total of 882 patients were included, with an HBS incidence of 69.9%. EasyEnsemble and logistic regression demonstrated the highest discrimination (AUROC 0.712), outperforming the k ‐nearest neighbours baseline. EasyEnsemble achieved the best overall performance (accuracy 0.707, F1 score 0.666) and calibration (Brier score 0.186). Key predictors included elevated preoperative alkaline phosphatase, higher intact parathyroid hormone levels and lower serum calcium.

Conclusion

This two‐stage ML framework demonstrated acceptable predictive performance and aligns with clinical decision‐making processes. It enables early identification of high‐risk patients and may support individualised perioperative management to mitigate HBS and its complications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ParathyroidectomyHypocalcemiaHyperparathyroidism, SecondaryMachine LearningPostoperative ComplicationsHumansFemaleRetrospective StudiesMaleMiddle AgedPredictive Learning ModelsAged

Stichwörter der Autor:innen

hungry bone syndromemachine learningparathyroidectomyrisk predictionsecondary hyperparathyroidism

Autor:innen und Institutionen

  • Department of General Surgery, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung, Taiwan.
  • Department of Computer Science and Information Engineering, National Cheng Kung University, Tainan, Taiwan.
  • Department of Computer Science, National Tsing Hua University, Hsinchu, Taiwan.
  • Institute of Electrical Engineering, National Tsing Hua University, Hsinchu, Taiwan.
  • Division of General Surgery, Department of Surgery, Tri-Service General Hospital, National Defense Medical University, Taipei, Taiwan.
  • Kaohsiung Municipal Fong Shan Hospital of Chang Gung Medical Foundation, Kaohsiung, Taiwan.

ORCID-Profile: Shih-Min Yin, Si-Yuan Wu, Po-Chih Kuo, Yi-Chia Chan

Zitieren

APA

Yin, S. M., Lin, Y. C., Hung, T. H., Chou, S. E., Chi, S. Y., Chou, F. F., Wu, Y. J., Wu, S. Y., Lien, J. J., Kuo, P. C., & Chan, Y. C. (2026). A Clinically Aligned Two‐Stage Machine Learning Framework for Predicting Hungry Bone Syndrome After Parathyroidectomy. Endocrinology, Diabetes & Metabolism, 9(5). https://doi.org/10.1002/edm2.70297

Vancouver

Yin SM, Lin YC, Hung TH, Chou SE, Chi SY, Chou FF, et al. A Clinically Aligned Two‐Stage Machine Learning Framework for Predicting Hungry Bone Syndrome After Parathyroidectomy. Endocrinology, Diabetes & Metabolism. 2026;9(5). doi:10.1002/edm2.70297

BibTeX
@article{Yin2026,
  author = {Yin, Shih-Min and Lin, Yu-Chieh and Hung, Tzu-Hsun and Chou, Shen-En and Chi, Shun-Yu and Chou, Fong-Fu and Wu, Yi-Ju and Wu, Si-Yuan and Lien, Jenn-Jier James and Kuo, Po-Chih and Chan, Yi-Chia},
  title = {A Clinically Aligned Two‐Stage Machine Learning Framework for Predicting Hungry Bone Syndrome After Parathyroidectomy},
  journal = {Endocrinology, Diabetes & Metabolism},
  year = {2026},
  volume = {9},
  number = {5},
  doi = {10.1002/edm2.70297}
}
Kostenlos starten →