Classification of pleural effusions using deep learning visual models: contrastive-loss

Abstract

Blood and fluid analysis is extensively used for classifying the etiology of pleural effusion. However, most studies focused on determining the presence of a disease. This study classified pleural effusion etiology employing deep learning models by applying contrastive-loss. Patients with pleural effusion who underwent thoracentesis between 2009 and 2019 at the Asan Medical Center were analyzed. Five different models for categorizing the etiology of pleural effusion were compared. The performance metrics were top-1 accuracy, top-2 accuracy, and micro-and weighted-AUROC. UMAP and t-SNE were used to visualize the contrastive-loss model’s embedding space. Although the 5 models displayed similar performance in the validation set, the contrastive-loss model showed the highest accuracy in the extra-validation set. Additionally, the accuracy and micro-AUROC of the contrastive-loss model were 81.7% and 0.942 in the validation set, and 66.2% and 0.867 in the extra-validation set. Furthermore, the embedding space visualization in the contrastive-loss model exhibited typical and atypical effusion results by comparing the true and false positives of the rule-based criteria. Therefore, classifying the etiology of pleural effusion was achievable using the contrastive-loss model. Conclusively, visualization of the contrastive-loss model will provide clinicians with valuable insights for etiology diagnosis by differentiating between typical and atypical disease types.

Conditional diagnostic accuracy according to inflammation status and age for diagnosing tuberculous effusion

“…In a previous study, the deep learning model classified the etiology of pleural effusion based on laboratory results and showed the class probabilities [ 8 ]. The visualization map revealed that several tuberculosis pleurisy patients were misclassified as bacterial infections.…”

Man versus Machine in Pleural Diagnostics: Does Artificial Intelligence Provide the Solution?

“…The authors should be congratulated for their robust approach to developing a machine learning algorithm for pleural diagnostics and achieving accuracies of >80% in one of the largest datasets to date in the field of pleural medicine ( 9 ). This area is of great interest to pleural physicians, with the potential to stratify patients into one of five diagnostic groups earlier in their pathway, with fewer invasive procedures and reduced visits to hospitals or inpatient stays.…”