Identification and management of pleural effusions of multiple aetiologies

Walker, Steven; Maskell, Nick A

doi:10.1097/mcp.0000000000000388

Cited by 18 publications

(11 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, it is increasingly recognised that a significant proportion of patients presenting with a pleural effusion will have dual pathology driving their presentation and this bears consideration. In a prospective study of 126 patients with pleural effusion of unknown aetiology, 30% (38/126) were found to have more than one cause for their effusion, of which the commonest secondary cause was congestive cardiac failure [5,14].…”

Section: Pleural Fluidmentioning

confidence: 99%

Diagnostics in Pleural Disease

2020

View full text Add to dashboard Cite

Pleural disease diagnostics represent a sprawling topic that has enjoyed a renaissance in recent years from humble beginnings. Whilst pleural patients are heterogeneous as a population and in the aetiology of the disease with which they present, we provide an overview of the typical diagnostic approach. Pleural fluid analysis is the cornerstone of the diagnostic pathway; however, it has many shortcomings. Strong cases have been made for more invasive upfront investigations, including image-guided biopsies or local anaesthetic thoracoscopy, in selected populations. Imaging can guide the diagnostic process as well as act as a vehicle to facilitate therapies, and this is never truer than with the recent advances in thoracic ultrasound.

show abstract

Section: Pleural Fluidmentioning

confidence: 99%

Diagnostics in Pleural Disease

2020

View full text Add to dashboard Cite

show abstract

“…PE is related to more than 50 etiologies and could be divided into benign pleural effusion (BPE) and malignant pleural effusion (MPE) [ 7 ]. BPE is mainly caused by tuberculosis, pneumonia and chronic heart failure in China [ 8 ]. Sometimes, MPE presents as the initial or even only sign in patients with cancer, but this does not mean that MPE is a warning sign for early stage of cancer.…”

Section: Introductionmentioning

confidence: 99%

Driverless artificial intelligence framework for the identification of malignant pleural effusion

Tian

Huang

et al. 2021

Translational Oncology

View full text Add to dashboard Cite

Our study aimed to explore the applicability of deep learning and machine learning techniques to distinguish MPE from BPE. We initially used a retrospective cohort with 726 PE patients to train and test the predictive performances of the driverless artificial intelligence (AI), and then stacked with a deep learning and five machine learning models, namely gradient boosting machine (GBM), extreme gradient boosting (XGBoost), extremely randomized trees (XRT), distributed random forest (DRF), and generalized linear models (GLM). Furthermore, a prospective cohort with 172 PE patients was applied to detect the external validity of the predictive models. The area under the curve (AUC) in the training, test and validation set were deep learning (0.995, 0.848, 0.917), GBM (0.981, 0.910, 0.951), XGBoost (0.933, 0.916, 0.935), XRT (0.927, 0.909, 0.963), DRF (0.906, 0.809, 0.969), and GLM (0.898, 0.866, 0.892), respectively. Although the Deep Learning model had the highest AUC in the training set (AUC = 0.995), GBM demonstrated stable and high predictive efficiency in three data sets. The final AI model by stacked ensemble yielded optimal diagnostic performance with AUC of 0.991, 0.912 and 0.953 in the training, test and validation sets, respectively. Using the driverless AI framework based on the routinely collected clinical data could significantly improve diagnostic performance in distinguishing MPE from BPE.

show abstract

“…In patients with known congestive cardiac failure (CCF) and bilateral effusions, it is highly likely that this is the cause of the effusions. 3 Unless there is a suspicion of dual pathologies, which are more common than previously thought, 4 diuresis should be undertaken rather than ABSTRACT Authors: Rachel M Mercer , A John P Corcoran , B Jose M Porcel , C Najib M Rahman D and Ioannis Psallidas E…”

Section: Introductionmentioning

confidence: 99%

Interpreting pleural fluid results

et al. 2019

View full text Add to dashboard Cite

Interpreting pleural fluid results correctly requires an awareness of the possible aetiologies of a pleural effusion and an understanding of the reliability of the outcome of each investigation. All results must be interpreted within each different clinical context and knowledge of the pitfalls for each test is necessary when the diagnosis is unclear. This review aims to discuss the common aetiologies of a pleural effusion and some of the pitfalls in interpretation that can occur when the diagnosis is unclear.

show abstract

Identification and management of pleural effusions of multiple aetiologies

Cited by 18 publications

References 38 publications

Diagnostics in Pleural Disease

Diagnostics in Pleural Disease

Driverless artificial intelligence framework for the identification of malignant pleural effusion

Interpreting pleural fluid results

Contact Info

Product

Resources

About