Identifying tuberculous pleural effusion using artificial intelligence machine learning algorithms

Abstract

Background The differential diagnosis of tuberculous pleural effusion (TPE) is challenging. In recent years, artificial intelligence (AI) machine learning algorithms have started being used to an increasing extent in disease diagnosis due to the high level of efficiency, objectivity, and accuracy that they offer. Methods Data samples on 192 patients with TPE, 54 patients with parapneumonic pleural effusion (PPE), and 197 patients with malignant pleural effusion (MPE) were retrospectively collected. Based on 28 different features obtained via statistical analysis, TPE diagnostic models using four machine learning algorithms (MLAs), namely logistic regression, k-nearest neighbors (KNN), support vector machine (SVM) and random forest (RF) were established and their respective diagnostic performances were calculated. The respective diagnostic performances of each of the four algorithmic models were compared with that of pleural fluid adenosine deaminase (pfADA). Based on 12 features with the most significant impacts on the accuracy of the RF model, a new RF model was designed for clinical application. To demonstrate its external validity, a prospective study was conducted and the diagnostic performance of the RF model was calculated. Results The respective sensitivity and specificity of each of the four TPE diagnostic models were as follows: logistic regression – 80.5 and 84.8%; KNN– 78.6 and 86.6%; SVM – 83.2 and 85.9%; and RF – 89.1 and 93.6%. The sensitivity and specificity of pfADA were 85.4 and 84.1%, respectively, at the best cut-off value of 17.5 U/L. RF was the superior method among the four MLAs, and was also superior to pfADA. The newly designed RF model (based on 12 out of 28 features) exhibited an acceptable performance rate for the diagnosis of TPE with a sensitivity and specificity of 90.6 and 92.3%, respectively. In the prospective study, its sensitivity and specificity were 100.0 and 90.0%, respectively. Conclusions Establishing a model for the diagnosis of TPE using RF resulted in a more effective, economical, and faster diagnostic method. This method could enable clinicians to diagnose and treat TPE more effectively.

Driverless artificial intelligence framework for the identification of malignant pleural effusion

“…Their predictive model obtained 98.3% specificity, 92.2% sensitivity, and AUC of the ROC curve was 0.976 for identifying TPE. Moreover, Ren et al [ 41 ] applied 12 clinical features to design a random forest model, and this model exhibited favorable diagnostic performance for the identification of TPE with a sensitivity of 90.6% and a specificity of 92.3%. They also verified the diagnostic model in the prospective study, and the results indicated that the specificity and sensitivity were 90.0% and 100.0% respectively.…”

“…It is worth noting that DL demonstrated the highest AUC of 0.995 in the train set whereas the prediction efficiency was less satisfactory in the test and validation set. DL method is more sensitive to changes of sample size than ML technique [ 41 ], and DL algorithm requires sufficient samples to obtain high predictive accuracy. The sample sizes in the test and validation sets were relatively small compared with that in the training set.…”

Development and validation of a novel scoring system developed from a nomogram to identify malignant pleural effusion

“…Although pleural biopsy has a relatively higher diagnostic accuracy [13] , it is invasive and associated with more complications, as well as higher costs. Hence, it is important to design a cost-effective method that is more accurate and less invasive to identify MPE [14] .…”

“…Of course, some studies have also attempted to differentiate MPE from BPE using various indexes. In addition to the limited sample sizes, most clinical studies have not established a quick and novel scoring system for physicians to use in clinical practice [14] . More importantly, no investigations used another independent cohort to externally validate their predictive model [ 17 , 18 ].…”

Pleural biomarkers in diagnostics of malignant pleural effusion: a narrative review

“…We can hence conclude that the diagnostic accuracy of each single cancer biomarker is relatively modest so that it seems reasonable to suggest that a multi-marker strategy may be a much better approach in MPE diagnostics. Although the development of such algorithms is indeed challenging, artificial intelligence approaches could be an option (139,140). Further studies, such as SIMPLE (141) and DIAPHRAGM (5), are attempting to use this approach for improving the diagnostic accuracy of cancer biomarkers in MPE.…”