EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Explainable machine learning model for predicting acute exacerbations of COPD combining sarcopenia index and traditional risk factors: A retrospective single-center exploratory study

Ai-Bin Zhang, Li-Wen Zhou, Yu-Fen An, Qing-Qing Qin, Jian-Tong Wei, Hao Chen iD

Chronic Respiratory Disease · 2026

DOI: 10.1177/14799731261454690 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Chronic Respiratory Disease, 2026. Verfasst von Ai-Bin Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Pulmonology Respiratory and Critical Care Unit, Gansu Provincial Hospital of Traditional Chinese Medicine, Lanzhou, Gansu, China. Hauptthemen laut MEDLINE: Pulmonary Disease, Chronic Obstructive, Sarcopenia, Machine Learning. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 32 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Science and Technology Planning Project of Gansu Province, Healthcare Industry Research Projects of Gansu Province.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

Chronic obstructive pulmonary disease (COPD) is a common respiratory disorder. Acute exacerbation of COPD (AECOPD) severely affects patients’ quality of life and prognosis. This study aimed to identify novel risk factors and develop an effective predictive model for AECOPD using machine learning (ML) models.

Methods

In this retrospective single-center study, clinical data and biomarkers from 565 participants were analyzed using ML algorithms. Feature selection employed least absolute shrinkage and selection operator regression. Eight ML models were trained and evaluated using receiver operating characteristic (ROC) and clinical decision curve analysis. The Shapley Additive explanations (SHAP) framework assessed feature contributions. An online personalized risk calculator was developed based on the optimal model and individual SHAP values.

Results

The XGBoost model demonstrated excellent discriminative performance, with areas under the ROC curve of 0.818 and 0.838 for the training and test sets, respectively. Key predictors identified by SHAP analysis included age, current smoking status, frequency of exacerbations in the previous year, albumin levels, sarcopenia index, and COPD Assessment Test score. These variables were integrated into an online calculator for research to illustrate individualized AECOPD risk estimation. However, external validation is still required before its clinical application.

Conclusions

We developed a preliminary ML model for predicting AECOPD, which provides a valuable tool for clinical risk assessment. The results also highlighted the correlation between sarcopenia and AECOPD risk.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Pulmonary Disease, Chronic ObstructiveSarcopeniaMachine LearningHumansRetrospective StudiesPredictive Learning ModelsRisk FactorsAgedFemaleDisease ProgressionMaleBoosting Machine Learning AlgorithmsRisk AssessmentMiddle AgedROC CurvePrognosisPrediction Algorithms

Stichwörter der Autor:innen

acute exacerbationchronic obstructive pulmonary diseasemachine learningsarcopenia

Autor:innen und Institutionen

  • Pulmonology Respiratory and Critical Care Unit, Gansu Provincial Hospital of Traditional Chinese Medicine, Lanzhou, Gansu, China.
  • Department of Orthopedics, the First School of Clinical Medicine, Lanzhou University, Lanzhou, Gansu, China.

ORCID-Profile: Hao Chen

Förderung

  • Science and Technology Planning Project of Gansu Province
  • Healthcare Industry Research Projects of Gansu Province

Zitieren

APA

Zhang, A. B., Zhou, L. W., An, Y. F., Qin, Q. Q., Wei, J. T., & Chen, H. (2026). Explainable machine learning model for predicting acute exacerbations of COPD combining sarcopenia index and traditional risk factors: A retrospective single-center exploratory study. Chronic Respiratory Disease. https://doi.org/10.1177/14799731261454690

Vancouver

Zhang AB, Zhou LW, An YF, Qin QQ, Wei JT, Chen H. Explainable machine learning model for predicting acute exacerbations of COPD combining sarcopenia index and traditional risk factors: A retrospective single-center exploratory study. Chronic Respiratory Disease. 2026. doi:10.1177/14799731261454690

BibTeX
@article{Zhang2026,
  author = {Zhang, Ai-Bin and Zhou, Li-Wen and An, Yu-Fen and Qin, Qing-Qing and Wei, Jian-Tong and Chen, Hao},
  title = {Explainable machine learning model for predicting acute exacerbations of COPD combining sarcopenia index and traditional risk factors: A retrospective single-center exploratory study},
  journal = {Chronic Respiratory Disease},
  year = {2026},
  doi = {10.1177/14799731261454690}
}
Kostenlos starten →