Related Experiment Video
Updated: Aug 8, 2026
03:38
Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
Published on: June 20, 2025
Prediction of Post-COVID-19 Pulmonary Fibrosis: An Integrated Approach Combining CT Radiomics and Clinical
Mujuan Wang1,2, Pei Huang1,2, Min Jiang
1Department of Radiology, Jiangxi Provincial People's Hospital, The First Affiliated Hospital of Nanchang Medical College, Nanchang, China.
Summary
A new nomogram model combining CT radiomics and clinical data shows promise for predicting post-COVID-19 pulmonary fibrosis (PCPF), aiding early intervention.
Area of Science:
- Medical Imaging
- Pulmonology
- Data Science
Background:
- COVID-19 can lead to long-term respiratory complications.
- Post-COVID-19 pulmonary fibrosis (PCPF) is a significant concern.
- Early identification of PCPF is crucial for effective management.
Purpose of the Study:
- To develop and validate a predictive model for PCPF.
- Integrate CT radiomics features with clinical characteristics.
- Facilitate early identification and intervention for PCPF.
Main Methods:
- An observational study involving 223 COVID-19 patients.
- Collected chest CT images and clinical data.
- Developed a combined nomogram model using radiomics scores and clinical predictors (age, lesion location, hospital stay, LDH).
Main Results:
- The combined nomogram model demonstrated superior predictive performance (AUC = 0.833) compared to clinical (AUC = 0.687) and radiomic (AUC = 0.811) models.
- The nomogram significantly outperformed the clinical model (p < 0.05).
- Calibration and decision curve analyses confirmed the nomogram's excellent fit and clinical utility.
Conclusions:
- The nomogram model integrating CT radiomics and clinical features is a promising tool for predicting PCPF.
- This model can aid in the early detection and management of PCPF.
- Further validation is recommended for broader clinical application.
