Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosis

Abstract Background The lack of reliable biomarkers for the early detection and risk stratification of post-COVID-19 pulmonary fibrosis (PCPF) underscores the urgency advanced predictive tools. This study aimed to develop a machine learning-based predictive model integrating quantitative CT (qCT) ra...

Full description

Saved in:
Bibliographic Details
Main Authors: Qianqian Zhao, Yijie Li, Chunliu Zhao, Ran Dong, Jiaxin Tian, Ze Zhang, Lin Huang, Jingwen Huang, Junhai Yan, Zhitao Yang, Jiangnan Ruan, Ping Wang, Li Yu, Jieming Qu, Min Zhou
Format: Article
Language:English
Published: BMC 2025-07-01
Series:Respiratory Research
Subjects:
Online Access:https://doi.org/10.1186/s12931-025-03305-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849401959640989696
author Qianqian Zhao
Yijie Li
Chunliu Zhao
Ran Dong
Jiaxin Tian
Ze Zhang
Lin Huang
Jingwen Huang
Junhai Yan
Zhitao Yang
Jiangnan Ruan
Ping Wang
Li Yu
Jieming Qu
Min Zhou
author_facet Qianqian Zhao
Yijie Li
Chunliu Zhao
Ran Dong
Jiaxin Tian
Ze Zhang
Lin Huang
Jingwen Huang
Junhai Yan
Zhitao Yang
Jiangnan Ruan
Ping Wang
Li Yu
Jieming Qu
Min Zhou
author_sort Qianqian Zhao
collection DOAJ
description Abstract Background The lack of reliable biomarkers for the early detection and risk stratification of post-COVID-19 pulmonary fibrosis (PCPF) underscores the urgency advanced predictive tools. This study aimed to develop a machine learning-based predictive model integrating quantitative CT (qCT) radiomics and clinical features to assess the risk of lung fibrosis in COVID-19 patients. Methods A total of 204 patients with confirmed COVID-19 pneumonia were included in the study. Of these, 93 patients were assigned to the development cohort (74 for training and 19 for internal validation), while 111 patients from three independent hospitals constituted the external validation cohort. Chest CT images were analyzed using qCT software. Clinical data and laboratory parameters were obtained from electronic health records. Least absolute shrinkage and selection operator (LASSO) regression with 5-fold cross-validation was used to select the most predictive features. Twelve machine learning algorithms were independently trained. Their performances were evaluated by receiver operating characteristic (ROC) curves, area under the curve (AUC) values, sensitivity, and specificity. Results Seventy-eight features were extracted and reduced to ten features for model development. These included two qCT radiomics signatures: (1) whole lung_reticulation (%) interstitial lung disease (ILD) texture analysis, (2) interstitial lung abnormality (ILA)_Num of lung zones ≥ 5%_whole lung_ILA. Among 12 machine learning algorithms evaluated, the support vector machine (SVM) model demonstrated the best predictive performance, with AUCs of 0.836 (95% CI: 0.830–0.842) in the training cohort, 0.796 (95% CI: 0.777–0.816) in the internal validation cohort, and 0.797 (95% CI: 0.691–0.873) in the external validation cohort. Conclusions The integration of CT radiomics, clinical and laboratory variables using machine learning provides a robust tool for predicting pulmonary fibrosis progression in COVID-19 patients, facilitating early risk assessment and intervention.
format Article
id doaj-art-ececc471fe0d4fa686c4b45b255839de
institution Kabale University
issn 1465-993X
language English
publishDate 2025-07-01
publisher BMC
record_format Article
series Respiratory Research
spelling doaj-art-ececc471fe0d4fa686c4b45b255839de2025-08-20T03:37:40ZengBMCRespiratory Research1465-993X2025-07-0126111010.1186/s12931-025-03305-7Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosisQianqian Zhao0Yijie Li1Chunliu Zhao2Ran Dong3Jiaxin Tian4Ze Zhang5Lin Huang6Jingwen Huang7Junhai Yan8Zhitao Yang9Jiangnan Ruan10Ping Wang11Li Yu12Jieming Qu13Min Zhou14Department of Pulmonary and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Pulmonary and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Respiratory Medicine, Luwan Branch, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Pulmonary and Critical Care Medicine, Tongji Hospital, School of Medicine, Tongji UniversityDepartment of Pulmonary and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Respiratory Medicine, Shanghai Ninth People’s Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Pulmonary and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Pulmonary and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Respiratory Medicine, Luwan Branch, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Emergency, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineHangzhou Smart Intelligent Co., LtdHangzhou Smart Intelligent Co., LtdDepartment of Pulmonary and Critical Care Medicine, Tongji Hospital, School of Medicine, Tongji UniversityDepartment of Pulmonary and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineDepartment of Pulmonary and Critical Care Medicine, Ruijin Hospital, Shanghai Jiao Tong University School of MedicineAbstract Background The lack of reliable biomarkers for the early detection and risk stratification of post-COVID-19 pulmonary fibrosis (PCPF) underscores the urgency advanced predictive tools. This study aimed to develop a machine learning-based predictive model integrating quantitative CT (qCT) radiomics and clinical features to assess the risk of lung fibrosis in COVID-19 patients. Methods A total of 204 patients with confirmed COVID-19 pneumonia were included in the study. Of these, 93 patients were assigned to the development cohort (74 for training and 19 for internal validation), while 111 patients from three independent hospitals constituted the external validation cohort. Chest CT images were analyzed using qCT software. Clinical data and laboratory parameters were obtained from electronic health records. Least absolute shrinkage and selection operator (LASSO) regression with 5-fold cross-validation was used to select the most predictive features. Twelve machine learning algorithms were independently trained. Their performances were evaluated by receiver operating characteristic (ROC) curves, area under the curve (AUC) values, sensitivity, and specificity. Results Seventy-eight features were extracted and reduced to ten features for model development. These included two qCT radiomics signatures: (1) whole lung_reticulation (%) interstitial lung disease (ILD) texture analysis, (2) interstitial lung abnormality (ILA)_Num of lung zones ≥ 5%_whole lung_ILA. Among 12 machine learning algorithms evaluated, the support vector machine (SVM) model demonstrated the best predictive performance, with AUCs of 0.836 (95% CI: 0.830–0.842) in the training cohort, 0.796 (95% CI: 0.777–0.816) in the internal validation cohort, and 0.797 (95% CI: 0.691–0.873) in the external validation cohort. Conclusions The integration of CT radiomics, clinical and laboratory variables using machine learning provides a robust tool for predicting pulmonary fibrosis progression in COVID-19 patients, facilitating early risk assessment and intervention.https://doi.org/10.1186/s12931-025-03305-7Post-acute COVID-19 sequelaePulmonary fibrosisQuantitative CTRadiomicsMachine learning
spellingShingle Qianqian Zhao
Yijie Li
Chunliu Zhao
Ran Dong
Jiaxin Tian
Ze Zhang
Lin Huang
Jingwen Huang
Junhai Yan
Zhitao Yang
Jiangnan Ruan
Ping Wang
Li Yu
Jieming Qu
Min Zhou
Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosis
Respiratory Research
Post-acute COVID-19 sequelae
Pulmonary fibrosis
Quantitative CT
Radiomics
Machine learning
title Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosis
title_full Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosis
title_fullStr Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosis
title_full_unstemmed Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosis
title_short Integrating CT radiomics and clinical features using machine learning to predict post-COVID pulmonary fibrosis
title_sort integrating ct radiomics and clinical features using machine learning to predict post covid pulmonary fibrosis
topic Post-acute COVID-19 sequelae
Pulmonary fibrosis
Quantitative CT
Radiomics
Machine learning
url https://doi.org/10.1186/s12931-025-03305-7
work_keys_str_mv AT qianqianzhao integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT yijieli integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT chunliuzhao integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT randong integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT jiaxintian integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT zezhang integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT linhuang integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT jingwenhuang integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT junhaiyan integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT zhitaoyang integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT jiangnanruan integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT pingwang integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT liyu integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT jiemingqu integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis
AT minzhou integratingctradiomicsandclinicalfeaturesusingmachinelearningtopredictpostcovidpulmonaryfibrosis