Exploring the Value of Pleural Fluid Biomarkers for Complementary Pleural Effusion Disease Examination

Abstract

Background: Pleural fluid biomarkers are beneficial for the complementary diagnosis of pleural effusion diseases. This study focuses on using multidimensional evaluation based on deep learning to examine the clinical value of the pleural effusion biomarkers and the utility of combining these markers, in distinguishing pleural effusion diseases. Methods: Pleural effusion diseases were divided into three groups according to the diagnosis and treatment guidelines: malignant pleural effusion (MPE), parapneumonic effusion (PPE), and congestive heart failure (CHF). The levels of 11 pleural fluid biomarkers such as specific gravity (SG), transparency, color, pH level, total protein (TP), glucose (GLU), adenosine deaminase (ADA), lactate dehydrogenase (LDH), cytokeratin 19 fragment (CYFRA21-1), carcinoembryonic antigen (CEA), neuron-specific enolase (NSE), were detected. The four other biomarkers based on cytological morphology examination including white blood cell (WBC), percentage of mononuclear cell (MNC %), percentage of polymorphonuclear cell (PNC %), percentage of mesothelial cell (MTC %) were also determined. First, the diagnostic ability of biomarkers was analyzed by a receiver operating characteristic (ROC) curve. Then by utilizing deep learning and entropy weight method (EWM), the clinical value of biomarkers was computed multidimensionally for complementary diagnosis of pleural effusion diseases. Findings: There were significant differences in the six biomarkers, TP, ADA, CEA, CYFRA211, NSE, MNC% (p 0.05) among the three groups of pleural effusion diseases. The comprehensive test of pleural fluid biomarkers based on deep learning is of high accuracy. The clinical value of cytomorphology biomarkers WBC, MNC %, PNC %, MTC % was high among pleural fluid biomarkers. Conclusions: The clinical value of pleural fluid biomarkers analyzed multidimensionally by deep learning and entropy weight method is different from that by traditional statistics and ROC curve. In the process of clinical examination, it is suggested that more attention should be paid to the cytomorphological biomarkers, while the physical characteristic of pleural fluid have less clinical significance. Funding Statement: This work was totally supported by the National Natural Science Foundation of China (Grant Nos.61703304, 31600761). Declaration of Interests: The authors declare no conflict of interest. Ethics Approval Statement: All procedures were performed in accordance with the ethical standards of the institutional and national research committee. Informed consent was obtained from all patients included in the study.