A simple and efficient clinical prediction scoring system to identify malignant pleural effusion

Abstract

Background: Early diagnosis of malignant pleural effusion (MPE) is of great significance. Current prediction models are not simple enough to be widely used in heavy clinical work.

Objectives: We aimed to develop a simple and efficient clinical prediction scoring system to distinguish MPE from benign pleural effusion (BPE).

Design: This retrospective study involved patients with MPE or BPE who were admitted in West China Hospital from December 2010 to September 2016.

Methods: Patients were divided into training, testing, and validation set. Prediction model was developed from training set and modified to a scoring system. The diagnostic efficacy and clinical benefits of the scoring system were estimated in all three sets.

Results: Finally, 598 cases of MPE and 1094 cases of BPE were included. Serum neuron-specific enolase, serum cytokeratin 19 fragment (CYFRA21-1), pleural carcinoembryonic antigen (CEA), and ratio of pleural CEA to serum CEA were selected to establish the prediction models in training set, which were modified to the scoring system with scores of 6, 8, 10, and 9 points, respectively. Patients with scores >12 points have high MPE risk while ⩽12 points have low MPE risk. The scoring system has a high predictive value and good clinical benefits to differentiate MPE from BPE or lung-specific MPE from BPE.

Conclusion: This study developed a simple clinical prediction scoring system and was proven to have good clinical benefits, and it may help clinicians to separate MPE from BPE.

Keywords: clinical prediction model; diagnosis; malignant pleural effusion; scoring system.

Figure 1.

Establishment of MPE scoring system in training set: (a) Nomograph shows the relationship between four variables and MPE risk; (b) simplified scoring system and corresponding scores of each variable; (c) ROC analysis curve shows AUC 0.916, sensitivity 0.859, and specificity 0.892 at the cutoff score of 12 points for the simplified scoring system; (d) bar chart shows total score >12 points have high risk of MPE, and ⩽12 points have low risk of MPE. AUC, area under the curve; MPE, malignant pleural effusion; ROC, receiver operating characteristic.

Figure 2.

Evaluation of MPE scoring system in three sets: (a) ROC analyses show the AUC of training set, testing set, and validation set were 0.916, 0.923, and 0.936, respectively; (b) calibration curves show the gap between the predicted probability and the actual probability; (c) DCA curves show the benefits of patients with clinical intervention of MPE scoring system; (d) CIC curves show the gap between the predicted and actual number of patients under different probabilities with clinical intervention of MPE scoring system. AUC, area under the curve; CIC, clinical impact curve; DCA, decision curve analysis; MPE, malignant pleural effusion; ROC, receiver operating characteristic.

Figure 3.

Evaluation of MPE scoring system for identifying lung cancer-related MPE from BPE in three sets: (a) ROC analyses show the AUC of lung cancer-related MPE and BPE patients (lung/BPE) in training set, testing set, and validation set were 0.936, 0.962, and 0.930, respectively; (b) calibration curves show the gap between the predicted probability and the actual probability of lung/BPE patients; (c) DCA curves show the benefits of lung/BPE patients using the MPE scoring system; (d) CIC curves show the gap between the predicted and actual number of lung/BPE patients under different probabilities using the MPE scoring system. AUC, area under the curve; BPE, benign pleural effusion; CIC, clinical impact curve; DCA, decision curve analysis; MPE, malignant pleural effusion; ROC, receiver operating characteristic.