Predicting the nature of pleural effusion in patients with lung adenocarcinoma based on 18F-FDG PET/CT

Abstract

Background: This study aims to establish a predictive model on the basis of ¹⁸F-FDG PET/CT for diagnosing the nature of pleural effusion (PE) in patients with lung adenocarcinoma.

Methods: Lung adenocarcinoma patients with PE who underwent ¹⁸F-FDG PET/CT were collected and divided into training and test cohorts. PET/CT parameters and clinical information in the training cohort were collected to estimate the independent predictive factors of malignant pleural effusion (MPE) and to establish a predictive model. This model was then applied to the test cohort to evaluate the diagnostic efficacy.

Results: A total of 413 lung adenocarcinoma patients with PE were enrolled in this study, including 245 patients with MPE and 168 patients with benign PE (BPE). The patients were divided into training (289 patients) and test (124 patients) cohorts. CEA, SUVmax of tumor and attachment to the pleura, obstructive atelectasis or pneumonia, SUVmax of pleura, and SUVmax of PE were identified as independent significant factors of MPE and were used to construct a predictive model, which was graphically represented as a nomogram. This predictive model showed good discrimination with the area under the curve (AUC) of 0.970 (95% CI 0.954-0.986) and good calibration. Application of the nomogram in the test cohort still gave good discrimination with AUC of 0.979 (95% CI 0.961-0.998) and good calibration. Decision curve analysis demonstrated that this nomogram was clinically useful.

Conclusions: Our predictive model based on ¹⁸F-FDG PET/CT showed good diagnostic performance for PE, which was helpful to differentiate MPE from BPE in patients with lung adenocarcinoma.

Keywords: 18F-FDG; Lung adenocarcinoma; PET/CT; Pleural effusion; Predictive model.

Fig. 1

Flowchart of the search strategy and study selection

Fig. 2

Nomogram predicting the probability of MPE

Fig. 3

ROC analysis of the predictive model in training (a) and test (b) cohorts, respectively, and calibration curves of the nomogram in the training (c) and test (d) cohorts, respectively

Fig. 4

Decision curve analysis for this model in predicting MPE for patients with lung adenocarcinoma. The y-axis measures the net benefit. The grey line represents the assumption that all lesions were malignant (the treat-all scheme). The black line represents the assumption that all lesions were benign (the treat-none scheme). If the threshold probability was more than 5%, using the nomogram to predict malignancy added more benefit than either the treat-all scheme or the treat-none scheme (red line)