• An Interpretable AdaBoost Mode...

Treffer: An Interpretable AdaBoost Model for 1-Year Readmission Risk Prediction in AECOPD Patients with Hypertension.

Title:
An Interpretable AdaBoost Model for 1-Year Readmission Risk Prediction in AECOPD Patients with Hypertension.
Authors:
Zhang X; Department of Pulmonary and Critical Care Medicine, The First Affiliated Hospital of Shihezi University, Shihezi, People's Republic of China., He M; Department of Pulmonary and Critical Care Medicine, The First Affiliated Hospital of Shihezi University, Shihezi, People's Republic of China., Zhang J; Shihezi University School of Medicine, Shihezi, People's Republic of China., Zhao L; Department of Pulmonary and Critical Care Medicine, The First Affiliated Hospital of Shihezi University, Shihezi, People's Republic of China., Liu D; Department of Pulmonary and Critical Care Medicine, The First Affiliated Hospital of Shihezi University, Shihezi, People's Republic of China.
Source:
International journal of chronic obstructive pulmonary disease [Int J Chron Obstruct Pulmon Dis] 2026 Jan 08; Vol. 21, pp. 1-14. Date of Electronic Publication: 2026 Jan 08 (Print Publication: 2026).
Publication Type:
Journal Article; Validation Study
Language:
English
Journal Info:
Publisher: DOVE Medical Press Country of Publication: New Zealand NLM ID: 101273481 Publication Model: eCollection Cited Medium: Internet ISSN: 1178-2005 (Electronic) Linking ISSN: 11769106 NLM ISO Abbreviation: Int J Chron Obstruct Pulmon Dis Subsets: MEDLINE
Imprint Name(s):
Original Publication: Auckland, N.Z. : DOVE Medical Press,
MeSH Terms:
Patient Readmission* , Hypertension*/diagnosis , Hypertension*/complications , Hypertension*/physiopathology , Hypertension*/therapy , Hypertension*/epidemiology , Pulmonary Disease, Chronic Obstructive*/diagnosis , Pulmonary Disease, Chronic Obstructive*/therapy , Pulmonary Disease, Chronic Obstructive*/complications , Pulmonary Disease, Chronic Obstructive*/physiopathology , Pulmonary Disease, Chronic Obstructive*/epidemiology , Machine Learning* , Decision Support Techniques*, Humans ; Female ; Male ; Retrospective Studies ; Risk Assessment ; Aged ; Risk Factors ; Middle Aged ; Time Factors ; Predictive Value of Tests ; Reproducibility of Results ; Disease Progression ; Prognosis ; Boosting Machine Learning Algorithms
References:
JAMA. 2022 May 10;327(18):1806-1811. (PMID: 35536260)
Int J Chron Obstruct Pulmon Dis. 2016 Oct 04;11:2475-2496. (PMID: 27785005)
Biomedicines. 2025 Jun 30;13(7):. (PMID: 40722673)
Lancet Respir Med. 2024 May;12(5):345-348. (PMID: 38437859)
Eur Respir J. 2006 Dec;28(6):1245-57. (PMID: 17138679)
J Stat Softw. 2017;76:. (PMID: 36568334)
JAMA Netw Open. 2023 Dec 1;6(12):e2346598. (PMID: 38060225)
Chest. 2008 Feb;133(2):343-9. (PMID: 17951621)
Eur Respir Rev. 2025 Dec 10;34(178):. (PMID: 41371715)
Am J Respir Crit Care Med. 2012 Jul 15;186(2):155-61. (PMID: 22561964)
Expert Rev Cardiovasc Ther. 2024 Apr-May;22(4-5):177-191. (PMID: 38529639)
Arch Bronconeumol. 2016 Aug;52(8):425-31. (PMID: 27207325)
Eur J Intern Med. 2021 Jul;89:3-9. (PMID: 34016514)
Arch Bronconeumol. 2024 Apr;60(4):226-237. (PMID: 38383272)
Eur Respir J. 2023 Aug 31;62(2):. (PMID: 37385658)
Ther Adv Respir Dis. 2018 Jan-Dec;12:1753465817750524. (PMID: 29355081)
Contributed Indexing:
Keywords: 1-year readmission; acute exacerbation of chronic obstructive pulmonary disease; hypertension; machine learning; web calculator
Entry Date(s):
Date Created: 20260113 Date Completed: 20260113 Latest Revision: 20260124
Update Code:
20260124
PubMed Central ID:
PMC12790769
DOI:
10.2147/COPD.S557298
PMID:
41527668
Database:
MEDLINE

Weitere Informationen

Background: Chronic obstructive pulmonary disease (COPD) complicated by hypertension imposes a substantial global health burden, with acute exacerbation of chronic obstructive pulmonary disease (AECOPD) significantly increasing 1-year readmission risk. This study aimed to develop and validate an interpretable machine learning (ML) model that predicts 1-year readmission risk in AECOPD patients complicated by hypertension using real-world data.
Methods: This retrospective cohort study enrolled 2042 patients with AECOPD complicated by hypertension from the First Affiliated Hospital of Shihezi University between 2015 and 2024. The data were split into training and test sets at a 7:3 ratio. Feature selection was performed based on machine learning methods. Eight ML models were trained and tested to construct predictive models. Model performance was evaluated by the area under the receiver operating characteristic curve (AUC), accuracy, recall, specificity, and F1-score. The Shapley additive explanation method (SHAP) was used to rank the feature importance and explain the final model. An online risk prediction tool was developed based on the optimal model to facilitate clinical application.
Results: The 1-year readmission rate of patients with AECOPD complicated by hypertension was 37.5%. Seven independent predictors, including times of inhospitalization, procalcitonin, total protein, international normalized ratio (INR), prothrombin time, D-dimer, and hypoproteinemia, were identified as the most valuable features for establishing the models. The AdaBoost model showed optimal performance, with an AUC of 0.884 in the test set and an average AUC of 0.889 in 5-fold cross-validation. SHAP analysis confirmed that times of inhospitalization were the strongest predictor, followed by INR and total protein. An online calculator was deployed (https://fast.statsape.com/tool/detail?id=17) for clinical use.
Conclusion: This study developed an interpretable AdaBoost-based online calculator for 1-year readmission risk assessment in AECOPD patients by hypertension. The tool highlight the importance of addressing hypercoagulability and nutritional status to reduce readmission risk. Further external multi-center validation is needed to enhance its generalizability.
(© 2026 Zhang et al.)

The authors declare no competing interests.