Machine learning-based model for acute asthma exacerbation detection using routine blood parameters

Background: Acute asthma exacerbations (AAEs) are a leading cause of asthma-related morbidity and mortality, especially in resource-limited settings where pulmonary function tests are unavailable or when patients are unable to cooperate with testing. This study aimed to develop and validate a diagno...

Full description

Saved in:
Bibliographic Details
Main Authors: Youpeng Chen, Junquan Sun, Yabang Chen, Enzhong Li, Jiancai Lu, Huanhua Tang, Yifei Xie, Jiana Zhang, Lesi Peng, Haojie Wu, Zhangkai J. Cheng, Baoqing Sun
Format: Article
Language:English
Published: Elsevier 2025-07-01
Series:World Allergy Organization Journal
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S1939455125000511
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418762886840320
author Youpeng Chen
Junquan Sun
Yabang Chen
Enzhong Li
Jiancai Lu
Huanhua Tang
Yifei Xie
Jiana Zhang
Lesi Peng
Haojie Wu
Zhangkai J. Cheng
Baoqing Sun
author_facet Youpeng Chen
Junquan Sun
Yabang Chen
Enzhong Li
Jiancai Lu
Huanhua Tang
Yifei Xie
Jiana Zhang
Lesi Peng
Haojie Wu
Zhangkai J. Cheng
Baoqing Sun
author_sort Youpeng Chen
collection DOAJ
description Background: Acute asthma exacerbations (AAEs) are a leading cause of asthma-related morbidity and mortality, especially in resource-limited settings where pulmonary function tests are unavailable or when patients are unable to cooperate with testing. This study aimed to develop and validate a diagnostic model for AAE using routine blood parameters through machine learning techniques. Methods: We developed a machine learning-based diagnostic model using routine blood test parameters. Data from 23,013 asthma patients treated at the First Affiliated Hospital of Guangzhou Medical University were analyzed. Significant variables were identified through logistic regression, and 12 machine learning algorithms were used to construct diagnostic models, which were evaluated using Receiver Operating Characteristic (ROC) analysis, calibration, and Decision Curve Analysis (DCA). Results: The Generalized Linear Model Boosting combined with Random Forest (glmBoost + RF) algorithm using 14 variables achieved comparable performance (Area Under the Curve [AUC] = 0.981) to the more complex Least Absolute Shrinkage and Selection Operator combined with Random Forest (Lasso + RF) algorithm using 25 variables (AUC = 0.985). Both models demonstrated excellent calibration and consistent performance across different demographic subgroups. DCA confirmed superior clinical utility compared to conventional strategies. Conclusions: This machine learning model provides an efficient and practical tool for detecting AAE using routine blood parameters, offering potential value in clinical practice, especially in resource-limited settings. Clinical trial number: Not applicable.
format Article
id doaj-art-50b1ff7f971541c28a1fa5ba1ea7c889
institution Kabale University
issn 1939-4551
language English
publishDate 2025-07-01
publisher Elsevier
record_format Article
series World Allergy Organization Journal
spelling doaj-art-50b1ff7f971541c28a1fa5ba1ea7c8892025-08-20T03:32:20ZengElsevierWorld Allergy Organization Journal1939-45512025-07-0118710107410.1016/j.waojou.2025.101074Machine learning-based model for acute asthma exacerbation detection using routine blood parametersYoupeng Chen0Junquan Sun1Yabang Chen2Enzhong Li3Jiancai Lu4Huanhua Tang5Yifei Xie6Jiana Zhang7Lesi Peng8Haojie Wu9Zhangkai J. Cheng10Baoqing Sun11Department of Clinical Laboratory, State Key Laboratory of Respiratory Disease, National Center for Respiratory Medicine, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China; Guangzhou National Laboratory, Guangzhou, Guangdong Province, China; Guangdong Provincial Clinical Research Center for Laboratory Medicine, Guangzhou, Guangdong Province, ChinaFirst Affiliated Hospital of Guangzhou Medical University, Guangzhou, ChinaFirst Affiliated Hospital of Guangzhou Medical University, Guangzhou, ChinaFirst Affiliated Hospital of Guangzhou Medical University, Guangzhou, ChinaDepartment of Clinical Laboratory, State Key Laboratory of Respiratory Disease, National Center for Respiratory Medicine, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China; Guangzhou National Laboratory, Guangzhou, Guangdong Province, China; Guangdong Provincial Clinical Research Center for Laboratory Medicine, Guangzhou, Guangdong Province, ChinaGuangzhou Medical University, Guangzhou, ChinaGuangzhou Medical University, Guangzhou, ChinaGuangzhou Medical University, Guangzhou, ChinaGuangzhou Medical University, Guangzhou, ChinaDepartment of Clinical Laboratory, State Key Laboratory of Respiratory Disease, National Center for Respiratory Medicine, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China; Guangzhou National Laboratory, Guangzhou, Guangdong Province, China; Guangdong Provincial Clinical Research Center for Laboratory Medicine, Guangzhou, Guangdong Province, ChinaDepartment of Clinical Laboratory, State Key Laboratory of Respiratory Disease, National Center for Respiratory Medicine, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China; Guangzhou National Laboratory, Guangzhou, Guangdong Province, China; Guangdong Provincial Clinical Research Center for Laboratory Medicine, Guangzhou, Guangdong Province, China; Corresponding author.Department of Clinical Laboratory, State Key Laboratory of Respiratory Disease, National Center for Respiratory Medicine, National Clinical Research Center for Respiratory Disease, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China; Guangzhou National Laboratory, Guangzhou, Guangdong Province, China; Guangdong Provincial Clinical Research Center for Laboratory Medicine, Guangzhou, Guangdong Province, China; Corresponding author.Background: Acute asthma exacerbations (AAEs) are a leading cause of asthma-related morbidity and mortality, especially in resource-limited settings where pulmonary function tests are unavailable or when patients are unable to cooperate with testing. This study aimed to develop and validate a diagnostic model for AAE using routine blood parameters through machine learning techniques. Methods: We developed a machine learning-based diagnostic model using routine blood test parameters. Data from 23,013 asthma patients treated at the First Affiliated Hospital of Guangzhou Medical University were analyzed. Significant variables were identified through logistic regression, and 12 machine learning algorithms were used to construct diagnostic models, which were evaluated using Receiver Operating Characteristic (ROC) analysis, calibration, and Decision Curve Analysis (DCA). Results: The Generalized Linear Model Boosting combined with Random Forest (glmBoost + RF) algorithm using 14 variables achieved comparable performance (Area Under the Curve [AUC] = 0.981) to the more complex Least Absolute Shrinkage and Selection Operator combined with Random Forest (Lasso + RF) algorithm using 25 variables (AUC = 0.985). Both models demonstrated excellent calibration and consistent performance across different demographic subgroups. DCA confirmed superior clinical utility compared to conventional strategies. Conclusions: This machine learning model provides an efficient and practical tool for detecting AAE using routine blood parameters, offering potential value in clinical practice, especially in resource-limited settings. Clinical trial number: Not applicable.http://www.sciencedirect.com/science/article/pii/S1939455125000511AsthmaMachine learningBlood chemical analysisDiagnosis
spellingShingle Youpeng Chen
Junquan Sun
Yabang Chen
Enzhong Li
Jiancai Lu
Huanhua Tang
Yifei Xie
Jiana Zhang
Lesi Peng
Haojie Wu
Zhangkai J. Cheng
Baoqing Sun
Machine learning-based model for acute asthma exacerbation detection using routine blood parameters
World Allergy Organization Journal
Asthma
Machine learning
Blood chemical analysis
Diagnosis
title Machine learning-based model for acute asthma exacerbation detection using routine blood parameters
title_full Machine learning-based model for acute asthma exacerbation detection using routine blood parameters
title_fullStr Machine learning-based model for acute asthma exacerbation detection using routine blood parameters
title_full_unstemmed Machine learning-based model for acute asthma exacerbation detection using routine blood parameters
title_short Machine learning-based model for acute asthma exacerbation detection using routine blood parameters
title_sort machine learning based model for acute asthma exacerbation detection using routine blood parameters
topic Asthma
Machine learning
Blood chemical analysis
Diagnosis
url http://www.sciencedirect.com/science/article/pii/S1939455125000511
work_keys_str_mv AT youpengchen machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT junquansun machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT yabangchen machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT enzhongli machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT jiancailu machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT huanhuatang machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT yifeixie machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT jianazhang machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT lesipeng machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT haojiewu machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT zhangkaijcheng machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters
AT baoqingsun machinelearningbasedmodelforacuteasthmaexacerbationdetectionusingroutinebloodparameters