Predicting Acute Exacerbation Phenotype in Chronic Obstructive Pulmonary Disease Patients Using VGG-16 Deep Learning

Shengchuan Feng; Ran Zhang; Wenxiu Zhang; Yuqiong Yang; Aiqi Song; Jiawei Chen; Fengyan Wang; Jiaxuan Xu; Cuixia Liang; Xiaoyun Liang; Rongchang Chen; Zhenyu Liang

doi:10.1159/000540383

Predicting Acute Exacerbation Phenotype in Chronic Obstructive Pulmonary Disease Patients Using VGG-16 Deep Learning

Respiration. 2024 Jul 24:1-14. doi: 10.1159/000540383. Online ahead of print.

Authors

Shengchuan Feng¹, Ran Zhang², Wenxiu Zhang³, Yuqiong Yang⁴, Aiqi Song⁵, Jiawei Chen⁶, Fengyan Wang⁴, Jiaxuan Xu⁴, Cuixia Liang², Xiaoyun Liang³, Rongchang Chen⁴, Zhenyu Liang⁴

Affiliations

¹ State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, National Center for Respiratory Medicine, Department of Respiratory Medicine, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China, fengsc2022@163.com.
² Neusoft Medical Systems Co., Ltd., Shenyang, China.
³ Institute of Research and Clinical Innovations, Neusoft Medical Systems Co., Ltd., Shanghai, China.
⁴ State Key Laboratory of Respiratory Disease, National Clinical Research Center for Respiratory Disease, National Center for Respiratory Medicine, Department of Respiratory Medicine, Guangzhou Institute of Respiratory Health, The First Affiliated Hospital of Guangzhou Medical University, Guangzhou, China.
⁵ Nanshan School, Guangzhou Medical University, Guangzhou, China.
⁶ First Clinical School, Guangzhou Medical University, Guangzhou, China.

PMID: 39047695
DOI: 10.1159/000540383

Abstract

Introduction: Exacerbations of chronic obstructive pulmonary disease (COPD) have a significant impact on hospitalizations, morbidity, and mortality of patients. This study aimed to develop a model for predicting acute exacerbation in COPD patients (AECOPD) based on deep-learning (DL) features.

Methods: We performed a retrospective study on 219 patients with COPD who underwent inspiratory and expiratory HRCT scans. By recording the acute respiratory events of the previous year, these patients were further divided into non-AECOPD group and AECOPD group according to the presence of acute exacerbation events. Sixty-nine quantitative CT (QCT) parameters of emphysema and airway were calculated by NeuLungCARE software, and 2,000 DL features were extracted by VGG-16 method. The logistic regression method was employed to identify AECOPD patients, and 29 patients of external validation cohort were used to access the robustness of the results.

Results: The model 3-B achieved an area under the receiver operating characteristic curve (AUC) of 0.933 and 0.865 in the testing cohort and external validation cohort, respectively. Model 3-I obtained AUC of 0.895 in the testing cohort and AUC of 0.774 in the external validation cohort. Model 7-B combined clinical characteristics, QCT parameters, and DL features achieved the best performance with an AUC of 0.979 in the testing cohort and demonstrating robust predictability with an AUC of 0.932 in the external validation cohort. Likewise, model 7-I achieved an AUC of 0.938 and 0.872 in the testing cohort and external validation cohort, respectively.

Conclusions: DL features extracted from HRCT scans can effectively predict acute exacerbation phenotype in COPD patients.

Keywords: Acute exacerbation; Chronic obstructive pulmonary disease; High-resolution computed tomography; Quantitative computed tomography; VGG-16.