111614
论文已发表
注册即可获取德孚的最新动态
IF 收录期刊
- 3.4 Breast Cancer (Dove Med Press)
- 3.2 Clin Epidemiol
- 2.6 Cancer Manag Res
- 2.9 Infect Drug Resist
- 3.7 Clin Interv Aging
- 5.1 Drug Des Dev Ther
- 3.1 Int J Chronic Obstr
- 6.6 Int J Nanomed
- 2.6 Int J Women's Health
- 2.9 Neuropsych Dis Treat
- 2.8 OncoTargets Ther
- 2.0 Patient Prefer Adher
- 2.2 Ther Clin Risk Manag
- 2.5 J Pain Res
- 3.0 Diabet Metab Synd Ob
- 3.2 Psychol Res Behav Ma
- 3.4 Nat Sci Sleep
- 1.8 Pharmgenomics Pers Med
- 2.0 Risk Manag Healthc Policy
- 4.1 J Inflamm Res
- 2.0 Int J Gen Med
- 3.4 J Hepatocell Carcinoma
- 3.0 J Asthma Allergy
- 2.2 Clin Cosmet Investig Dermatol
- 2.4 J Multidiscip Healthc
已发表论文
开发用于预测肺结核后慢性肺曲霉病复发风险的模型：一项回顾性观察研究
Authors Wu M , Yang YN, Wang F , Yan JR, Yang R, Yang C, Ren Y
Received 2 June 2025
Accepted for publication 21 November 2025
Published 3 December 2025 Volume 2025:18 Pages 7243—7254
DOI https://doi.org/10.2147/IJGM.S544265
Checked for plagiarism Yes
Review by Single anonymous peer review
Peer reviewer comments 5
Editor who approved publication: Professor Héctor Mora-Montes
Ming Wu,1 Yan Na Yang,1 Fei Wang,1 Ju Rong Yan,1 Rui Yang,2 ChengQing Yang,3 Yi Ren1
1Department of Clinical Laboratory, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China; 2Department of Orthopedics, People’s Hospital of Dongxihu District, Wuhan, Hubei Province, 430040, People’s Republic of China; 3Respiratory Ward Two, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China
Correspondence: ChengQing Yang, Respiratory Ward Two, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China, Email clarify719@163.com Yi Ren, Department of Clinical Laboratory, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China, Tel +86-13807196283, Email menease@sina.com
Objective: The recurrence rate of post-tuberculosis chronic pulmonary aspergillosis (post-TB CPA) is alarmingly high. This study aims to establish a risk prediction model utilizing machine learning algorithms to forecast the one-year recurrence risk of post-TB CPA.
Methods: This retrospective study included all patients diagnosed with pulmonary tuberculosis complicated by chronic pulmonary aspergillosis at Wuhan Pulmonary Hospital in 2022. Ultimately, 220 patients were included for the significance analysis.The Least Absolute Shrinkage and Selection Operator LASSO regression analysis was utilized to select 8 variables associated with the recurrence of tuberculosis complicated by chronic pulmonary aspergillosis. Four machine learning algorithms were compared to predict the recurrence risk in patients with this complication, with their performance evaluated using the receiver operating characteristic curve, area under the curve (AUC), calibration curve analysis, and decision curve analysis.
Results: LASSO regression analysis identified chronic obstructive pulmonary disease (COPD), chronic fibrotic pulmonary aspergillosis (CFPA), progressive pleural hypertrophy, fungal culture results, age, disease duration, emphysema and treatment duration as factors related to the recurrence risk of tuberculosis complicated by chronic pulmonary aspergillosis. The logistic regression model demonstrated the best performance, it outperformed the other three models by achieving the highest AUC of 0.779 on the internal validation set and 0.819 in the test cohort. The calibration curve indicated a strong correlation between the actual and predicted probabilities, while the decision curve analysis revealed significant clinical benefits.
Discussion: In this study, we developed a disease recurrence prediction model using machine learning techniques. This model aims to assist clinicians in identifying the most relevant risk factors associated with the recurrence of tuberculosis complicated by chronic pulmonary aspergillus. It facilitates the formulation of targeted and effective re-examination plans for discharged patients, ultimately reducing the recurrence rate after discharge and enhancing the quality of life for these patients.
Keywords: post-TB CPA, machine learning, predictive model, risk factors, recurrence risk, AUC
1Department of Clinical Laboratory, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China; 2Department of Orthopedics, People’s Hospital of Dongxihu District, Wuhan, Hubei Province, 430040, People’s Republic of China; 3Respiratory Ward Two, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China
Correspondence: ChengQing Yang, Respiratory Ward Two, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China, Email clarify719@163.com Yi Ren, Department of Clinical Laboratory, Wuhan Pulmonary Hospital, Wuhan, Hubei Province, 430030, People’s Republic of China, Tel +86-13807196283, Email menease@sina.com
Objective: The recurrence rate of post-tuberculosis chronic pulmonary aspergillosis (post-TB CPA) is alarmingly high. This study aims to establish a risk prediction model utilizing machine learning algorithms to forecast the one-year recurrence risk of post-TB CPA.
Methods: This retrospective study included all patients diagnosed with pulmonary tuberculosis complicated by chronic pulmonary aspergillosis at Wuhan Pulmonary Hospital in 2022. Ultimately, 220 patients were included for the significance analysis.The Least Absolute Shrinkage and Selection Operator LASSO regression analysis was utilized to select 8 variables associated with the recurrence of tuberculosis complicated by chronic pulmonary aspergillosis. Four machine learning algorithms were compared to predict the recurrence risk in patients with this complication, with their performance evaluated using the receiver operating characteristic curve, area under the curve (AUC), calibration curve analysis, and decision curve analysis.
Results: LASSO regression analysis identified chronic obstructive pulmonary disease (COPD), chronic fibrotic pulmonary aspergillosis (CFPA), progressive pleural hypertrophy, fungal culture results, age, disease duration, emphysema and treatment duration as factors related to the recurrence risk of tuberculosis complicated by chronic pulmonary aspergillosis. The logistic regression model demonstrated the best performance, it outperformed the other three models by achieving the highest AUC of 0.779 on the internal validation set and 0.819 in the test cohort. The calibration curve indicated a strong correlation between the actual and predicted probabilities, while the decision curve analysis revealed significant clinical benefits.
Discussion: In this study, we developed a disease recurrence prediction model using machine learning techniques. This model aims to assist clinicians in identifying the most relevant risk factors associated with the recurrence of tuberculosis complicated by chronic pulmonary aspergillus. It facilitates the formulation of targeted and effective re-examination plans for discharged patients, ultimately reducing the recurrence rate after discharge and enhancing the quality of life for these patients.
Keywords: post-TB CPA, machine learning, predictive model, risk factors, recurrence risk, AUC