A nonlinear model for diagnosing malignancy in patients with exudative plural effusion using routine plural fluid findings

Abstract

Background: There is a challenge in diagnosing cancer in patients with exudative plural effusion using anoninvasive and accurate method. Objective: We developed artificial neural network (ANN), as a nonlinear model, to discriminate malignant exudativeplural effusion from nonmalignant based on routine pleural fluid findings. Methods: The plural fluid parameters including total and differential cell counts, total proteins, lactatedehydrogenase (LDH), glucose, adenosine deaminase (ADA), as well as age and sex of 114 patients withexudative plural effusion were applied by models as input. The output was supposed to be the presence orabsence of the cancer. Results: The accuracy, sensitivity and specificity of ANN for predicting malignancy were 89.7%, 86.7%, and91.7%, respectively. In addition, the neural network significantly outperformed the logistic regression model, asa linear model, (AUC: 0.892 vs. 0.633, respectively, p Conclusion: The ANN is a novel accurate and noninvasive method that can be used clinically to diagnosemalignancy in patients with exudative plural effusion. Keywords: Artificial neural network, exudative plural effusion, malignancy