An Integrated Clinical and Computerized Tomography-Based Radiomic Feature Model to Separate Benign from Malignant Pleural Effusion

Fangqi Cai; Liwei Cheng; Xiaoling Liao; Yuping Xie; Wu Wang; Haofeng Zhang; Jinhua Lu; Ru Chen; Chunxia Chen; Xing Zhou; Xiaoyun Mo; Guoping Hu; Luying Huang

doi:10.1159/000536517

An Integrated Clinical and Computerized Tomography-Based Radiomic Feature Model to Separate Benign from Malignant Pleural Effusion

Respiration. 2024 Feb 29:1-11. doi: 10.1159/000536517. Online ahead of print.

Authors

Fangqi Cai¹, Liwei Cheng², Xiaoling Liao³, Yuping Xie³, Wu Wang³, Haofeng Zhang³, Jinhua Lu³, Ru Chen³, Chunxia Chen⁴, Xing Zhou⁴, Xiaoyun Mo³, Guoping Hu³, Luying Huang³

Affiliations

¹ Department of Respiratory and Critical Care Medicine, The People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, China, caifangqi1122@163.com.
² Department of Spine Osteopathia, The First Affiliated Hospital of Guangxi Medical University, Nanning, China.
³ Department of Respiratory and Critical Care Medicine, The People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, China.
⁴ Department of Clinical Medicine, The People's Hospital of Guangxi Zhuang Autonomous Region, Nanning, China.

PMID: 38422997
DOI: 10.1159/000536517

Abstract

Introduction: Distinguishing between malignant pleural effusion (MPE) and benign pleural effusion (BPE) poses a challenge in clinical practice. We aimed to construct and validate a combined model integrating radiomic features and clinical factors using computerized tomography (CT) images to differentiate between MPE and BPE.

Methods: A retrospective inclusion of 315 patients with pleural effusion (PE) was conducted in this study (training cohort: n = 220; test cohort: n = 95). Radiomic features were extracted from CT images, and the dimensionality reduction and selection processes were carried out to obtain the optimal radiomic features. Logistic regression (LR), support vector machine (SVM), and random forest were employed to construct radiomic models. LR analyses were utilized to identify independent clinical risk factors to develop a clinical model. The combined model was created by integrating the optimal radiomic features with the independent clinical predictive factors. The discriminative ability of each model was assessed by receiver operating characteristic curves, calibration curves, and decision curve analysis (DCA).

Results: Out of the total 1,834 radiomic features extracted, 15 optimal radiomic features explicitly related to MPE were picked to develop the radiomic model. Among the radiomic models, the SVM model demonstrated the highest predictive performance [area under the curve (AUC), training cohort: 0.876, test cohort: 0.774]. Six clinically independent predictive factors, including age, effusion laterality, procalcitonin, carcinoembryonic antigen, carbohydrate antigen 125 (CA125), and neuron-specific enolase (NSE), were selected for constructing the clinical model. The combined model (AUC: 0.932, 0.870) exhibited superior discriminative performance in the training and test cohorts compared to the clinical model (AUC: 0.850, 0.820) and the radiomic model (AUC: 0.876, 0.774). The calibration curves and DCA further confirmed the practicality of the combined model.

Conclusion: This study presented the development and validation of a combined model for distinguishing MPE and BPE. The combined model was a powerful tool for assisting in the clinical diagnosis of PE patients.

Keywords: Clinical risk factors; Machine learning; Pleural effusion; Radiomics.