EUVIMEDEUVIMED entdecken
Crossref

Personalized Obesity Hypoventilation Syndrome Risk Assessment Among Bariatric Surgery Candidates Through Explainable Machine Learning

Min Ni, Yangyang Tang, Junzheng Zhang, Yujin Lu, Jiankun Liao, Zhiyong Dong, Cunchuan Wang, Jia Feng, Wenhui Chen

CHEST · 2026-09

DOI: 10.1016/j.chest.2026.09.013 ↗

Kurz gefasst

Fachartikel in der Zeitschrift CHEST, 2026-09. Verfasst von Min Ni und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Gastrointestinal Surgery, The Second People's Hospital of Nanning, Guangxi, China. Die Arbeit nennt 46 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND: Obesity hypoventilation syndrome (OHS) frequently is underdiagnosed, which substantially increases risk of perioperative complications. Limited provider awareness and the need for cumbersome diagnostic testing may hinder timely diagnosis. Machine learning (ML) may facilitate individualized OHS risk assessment by integrating multiple clinical and laboratory variables. RESEARCH QUESTION: Can an explainable ML model using readily available clinical and laboratory variables accurately identify bariatric surgery candidates at risk of OHS. STUDY DESIGN AND METHODS: This retrospective cross-sectional cohort study included 673 bariatric surgery candidates from the Chinese Obesity and Metabolic Surgery Database, randomly divided into training (70% [n = 471]) and internal testing (30% [n = 202]) cohorts. An independent cohort of 175 patients from another tertiary hospital was collected for external validation. Feature selection was performed using least absolute shrinkage and selection operator regression and Boruta, with bootstrap resampling used to assess selection stability. Ten ML models were constructed and evaluated using discrimination, calibration, and clinical usefulness measures. Shapley additive explanation (SHAP) analysis was performed to enhance model interpretability, and a publicly accessible web-based calculator was deployed for clinical application. RESULTS: The final logistic regression model included 7 predictors: serum bicarbonate, type 2 diabetes, mean corpuscular hemoglobin concentration, tiredness, BMI, observed apnea, and neck circumference. The model demonstrated good discrimination in the training, internal testing, and external validation cohorts, with areas under the receiver operating characteristic curve of 0.884 (95% CI, 0.844-0.917), 0.863 (95% CI, 0.784-0.935), and 0.870 (95% CI, 0.806-0.926), respectively. SHAP analysis identified serum bicarbonate as the most important predictor. The model showed favorable calibration and clinical usefulness as well as being implemented as an online calculator. INTERPRETATION: Our explainable ML model integrating 7 readily available clinical variables demonstrated good predictive performance for OHS in bariatric surgery candidates. This model may facilitate earlier risk stratification and targeted diagnostic evaluation.

Schlagwörter

Stichwörter der Autor:innen

Shapley additive explanationbariatric surgerymachine learningobesityobesity hypoventilation syndrome

Autor:innen und Institutionen

  • Department of Gastrointestinal Surgery, The Second People's Hospital of Nanning, Guangxi, China.
  • Department of General Surgery, The Fourth Affiliated Hospital of Guangxi Medical University, Liuzhou, China.
  • Bariatric Surgery Center, Department of Gastrointestinal Surgery, The First Affiliated Hospital of Jinan University, Guangzhou, China.
  • Department of Weight Management and Obesity Metabolic Surgery, The Second People's Hospital of Nanning, Guangxi, China.
  • The First Affiliated Hospital, Jinan University, Guangzhou, Guangdong, China; Institute of Biomedicine, Department of Cellular Biology, National Engineering Research Center of Genetic Medicine, Jinan University, Guangzh…
  • Bariatric Surgery Center, Department of Gastrointestinal Surgery, The First Affiliated Hospital of Jinan University, Guangzhou, China. Electronic address: jnucwh2019@163.com.

Zitieren

APA

Ni, M., Tang, Y., Zhang, J., Lu, Y., Liao, J., Dong, Z., Wang, C., Feng, J., & Chen, W. (2026). Personalized Obesity Hypoventilation Syndrome Risk Assessment Among Bariatric Surgery Candidates Through Explainable Machine Learning. CHEST. https://doi.org/10.1016/j.chest.2026.09.013

Vancouver

Ni M, Tang Y, Zhang J, Lu Y, Liao J, Dong Z, et al. Personalized Obesity Hypoventilation Syndrome Risk Assessment Among Bariatric Surgery Candidates Through Explainable Machine Learning. CHEST. 2026. doi:10.1016/j.chest.2026.09.013

BibTeX
@article{Ni2026,
  author = {Ni, Min and Tang, Yangyang and Zhang, Junzheng and Lu, Yujin and Liao, Jiankun and Dong, Zhiyong and Wang, Cunchuan and Feng, Jia and Chen, Wenhui},
  title = {Personalized Obesity Hypoventilation Syndrome Risk Assessment Among Bariatric Surgery Candidates Through Explainable Machine Learning},
  journal = {CHEST},
  year = {2026},
  doi = {10.1016/j.chest.2026.09.013}
}
Kostenlos starten →