Deep learning for diagnosis of malign pleural effusion on computed tomography images

Machine learning-based Diagnostic model for determining the etiology of pleural effusion using Age, ADA and LDH

BACKGROUND

Classification of the etiologies of pleural effusion is a critical challenge in clinical practice. Traditional diagnostic methods rely on a simple cut-off method based on the laboratory tests. However, machine learning (ML) offers a novel approach based on artificial intelligence to improving diagnostic accuracy and capture the non-linear relationships.

METHOD

A retrospective study was conducted using data from patients diagnosed with pleural effusion. The dataset was divided into training and test set with a ratio of 7:3 with 6 machine learning algorithms implemented to diagnosis pleural effusion. Model performances were assessed by accuracy, precision, recall, F1 scores and area under the receiver operating characteristic curve (AUC). Feature importance and average prediction of age, Adenosine (ADA) and Lactate dehydrogenase (LDH) was analyzed. Decision tree was visualized.

RESULTS

A total of 742 patients were included (training cohort: 522, test cohort: 220), 397 (53.3%) diagnosed with malignant pleural effusion (MPE) and 253 (34.1%) with tuberculous pleural effusion (TPE) in the cohort. All of the 6 models performed well in the diagnosis of MPE, TPE and transudates. Extreme Gradient Boosting and Random Forest performed better in the diagnosis of the MPE, with F1 scores above 0.890, while K-Nearest Neighbors and Tabular Transformer performed better in the diagnosis of the TPE, with F1 scores above 0.870. ADA was identified as the most important feature. The ROC of machine learning model outperformed those of conventional diagnostic thresholds.

CONCLUSIONS

This study demonstrates that ML models using age, ADA, and LDH can effectively classify the etiologies of pleural effusion, suggesting that ML-based approaches may enhance diagnostic decision-making.

A Thorough Review of the Clinical Applications of Artificial Intelligence in Lung Cancer

According to data from the World Health Organization (WHO), lung cancer is becoming a global epidemic. It is particularly high in the list of the leading causes of death not only in developed countries, but also worldwide; furthermore, it holds the leading place in terms of cancer-related mortality. Nevertheless, many breakthroughs have been made the last two decades regarding its management, with one of the most prominent being the implementation of artificial intelligence (AI) in various aspects of disease management. We included 473 papers in this thorough review, most of which have been published during the last 5-10 years, in order to describe these breakthroughs. In screening programs, AI is capable of not only detecting suspicious lung nodules in different imaging modalities-such as chest X-rays, computed tomography (CT), and positron emission tomography (PET) scans-but also discriminating between benign and malignant nodules as well, with success rates comparable to or even better than those of experienced radiologists. Furthermore, AI seems to be able to recognize biomarkers that appear in patients who may develop lung cancer, even years before this event. Moreover, it can also assist pathologists and cytologists in recognizing the type of lung tumor, as well as specific histologic or genetic markers that play a key role in treating the disease. Finally, in the treatment field, AI can guide in the development of personalized options for lung cancer patients, possibly improving their prognosis.

Cross-modal similar clinical case retrieval using a modular model based on contrastive learning and k-nearest neighbor search

OBJECTIVE

Electronic health record systems have made it possible for clinicians to use previously encountered similar cases to support clinical decision-making. However, most studies for similar case retrieval were based on single-modal data. The existing studies on cross-modal clinical case retrieval were limited. We aimed to develop a CRoss-Modal Retrieval (CRMR) model to retrieve similar clinical cases recorded in different data modalities.

MATERIALS AND METHODS

The publically available Medical Information Mart for Intensive Care-Chest X-ray (MIMIC-CXR) dataset was used for model development and testing. The CRMR model was designed as a modular model containing two feature extraction models, two feature transformation models, one feature transformation optimization model, and one case retrieval model. The ability to retrieve similar clinical cases recorded in different data modalities was facilitated by the use of contrastive deep learning and k-nearest neighbor search.

RESULTS

The average retrieval precision, denoted as AP@k, of the developed CRMR model, were 76.9 %@5, 76.7 %@10, 76.5 %@20, 76.3 %@50, and 77.9 %@100, respectively. Here k is the number of similar cases returned after retrieval. The average retrieval time varied from 0.013 ms to 0.016 ms with k varying from 5 to 100. Moreover, the model can retrieve similar cases with the same multiple radiographic manifestations as the query case.

DISCUSSION

The CRMR model has shown promising cross-modal retrieval performance in clinical case analysis, with the potential for future scalability and improvement in handling diverse disease types and data modalities. The CRMR model has promising potential to aid clinicians in making optimal and explainable clinical decisions.

The Use of "Cancer Ratio" in Differentiating Malignant and Tuberculous Pleural Effusions: Protocol for a Prospective Observational Study

BACKGROUND

Differentiating between tuberculosis and malignancy as the cause of an exudative lymphocyte predominant pleural effusion is difficult due to similarities in the cellular and biochemical characteristics of the pleural fluid in both conditions. Microbiological tests in tubercular pleural effusions have a poor diagnostic yield, and the long turnaround time for results prevents an early diagnosis. The diagnosis of malignant pleural effusion (MPE) is hampered by a variable yield of pleural fluid cytology and closed pleural biopsy and the fact that thoracoscopy may not be readily available or feasible in each patient. A key gap in the existing knowledge is the performance of the serum lactate dehydrogenase to pleural adenosine deaminase ratio (ie, "cancer ratio"; CR) in differentiating between tuberculous and MPE in a high tuberculosis prevalence country like India, although its use has been well established in Western literature. The CR may find a practical application in the community health care settings in low-income countries without ready access to biopsy.

OBJECTIVE

This study aimed to evaluate the CR as a test to differentiate tubercular and malignant etiology in patients with an exudative lymphocyte predominant pleural effusion. Secondary objectives to be assessed include a comparison of CR to pleural fluid carcinoembryonic antigen in MPE and the association of histologic type of lung carcinoma to the CR positivity.

METHODS

This hospital-based, prospective, observational study will include patients admitted with pleural effusion whose pleural fluid reports indicate a lymphocyte-predominant exudate. The ability of the CR to discriminate between tuberculous and MPE will be evaluated as a primary objective of this study. The performance of CR and pleural fluid carcinoembryonic antigen in the diagnosis of MPE will be compared using the receiver operating characteristics and area under the curve for both tests as a secondary objective. The association between a positive CR and histologic type of lung cancer will be analyzed as well.

RESULTS

Data collection began in June 2022. As of March 24, 2024, we have recruited 22 patients. Outcomes of the study are expected at the end of 2024.

CONCLUSIONS

The results of this study will provide an objective basis for the use of CR in differentiating between tuberculosis and malignancy as the cause of an exudative lymphocyte predominant pleural effusion.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/56592.

Local Anesthetic Thoracoscopy: A Focus on Indications, Techniques and Complications

The main purpose of this narrative review is to educate general practitioners about a crucial pleural procedure, namely local anesthetic thoracoscopy (LAT), and to provide established respiratory physicians with an expert opinion-based summary of the literature. This narrative review focuses on the indications, technical aspects and complications of LAT, highlighting its safety and high degree of diagnostic sensitivity for patients who present with an unexplained pleural effusion and have a high pre-test probability of cancer.

Comparative Evaluation of Chest Ultrasonography and Computed Tomography as Predictors of Malignant Pleural Effusion: A Prospective Study

Malignant pleural effusion (MPE) is a manifestation of advanced cancer that requires a prompt and accurate diagnosis. Ultrasonography (US) and computed tomography (CT) are valuable imaging techniques for evaluating pleural effusions; however, their relative predictive ability for a malignant origin remains debatable. This prospective study aimed to compare chest US with CT findings as predictors of malignancy in patients with undiagnosed exudative pleural effusion. Fifty-four adults with undiagnosed exudative pleural effusions underwent comprehensive clinical evaluation including chest US, CT, and histopathologic biopsy. Blinded radiologists evaluated the US and CT images for features suggestive of malignancy, based on predefined criteria. Diagnostic performance measures were calculated using histopathology as a reference standard. Of the 54 patients, 33 (61.1%) had MPEs confirmed on biopsy. No significant differences between US and CT were found in detecting parietal pleural abnormalities, lung lesions, chest wall invasion, or liver metastasis. US outperformed CT in identifying diaphragmatic pleural thickening ≥10 mm (33.3% vs. 6.1%, p < 0.001) and nodularity (45.5% vs. 3%, p < 0.001), whereas CT was superior for mediastinal thickening (48.5% vs. 15.2%, p = 0.002). For diagnosing MPE, diaphragmatic nodularity detected by US had 45.5% sensitivity and 100% specificity, whereas CT mediastinal thickening had 48.5% sensitivity and 90.5% specificity. Both US and CT demonstrate reasonable diagnostic performance for detecting MPE, with particular imaging findings favoring a malignant origin. US may be advantageous for evaluating diaphragmatic pleural involvement, whereas CT is more sensitive to mediastinal abnormalities.

Unveiling Insights: A Comprehensive Review of the Role of Medical Thoracoscopy in Pleural Effusion Assessment

Pleural effusion, characterized by abnormal fluid accumulation in the pleural cavity, poses diagnostic and therapeutic challenges across various medical conditions. This comprehensive review explores the role of medical thoracoscopy in assessing pleural effusions, providing insights into its historical context, procedural intricacies, diagnostic performance, safety considerations, and clinical applications. Medical thoracoscopy, a minimally invasive endoscopic procedure, offers advantages such as high diagnostic yield, therapeutic interventions, real-time assessment, and a minimally invasive nature. The review critically analyzes the procedure's advantages and disadvantages, including technical expertise, risk of complications, resource intensity, and patient selection criteria. Comparative analyses with alternative diagnostic modalities highlight the unique benefits of medical thoracoscopy in specific clinical scenarios. The diagnostic yield of medical thoracoscopy is examined, considering sensitivity and specificity in various contexts. Patient selection criteria, complications, and safety measures are discussed, emphasizing the importance of careful consideration in integrating thoracoscopy into clinical practice. The review further explores its clinical applications, including differentiating exudative and transudative effusions, identifying specific etiologies, and its role in treatment planning. In conclusion, medical thoracoscopy emerges as a valuable tool in the comprehensive management of pleural effusions, offering a nuanced approach to diagnosis and treatment. The evolving landscape of diagnostic modalities underscores the continued significance of medical thoracoscopy and potential advancements in the field.

Development and validation of a machine learning model for differential diagnosis of malignant pleural effusion using routine laboratory data

BACKGROUND

The differential diagnosis of malignant pleural effusion (MPE) and benign pleural effusion (BPE) presents a clinical challenge. In recent years, the use of artificial intelligence (AI) machine learning models for disease diagnosis has increased.

OBJECTIVE

This study aimed to develop and validate a diagnostic model for early differentiation between MPE and BPE based on routine laboratory data.

DESIGN

This was a retrospective observational cohort study.

METHODS

A total of 2352 newly diagnosed patients with pleural effusion (PE), between January 2008 and March 2021, were eventually enrolled. Among them, 1435, 466, and 451 participants were randomly assigned to the training, validation, and testing cohorts in a ratio of 3:1:1. Clinical parameters, including age, sex, and laboratory parameters of PE patients, were abstracted for analysis. Based on 81 candidate laboratory variables, five machine learning models, namely extreme gradient boosting (XGBoost) model, logistic regression (LR) model, random forest (RF) model, support vector machine (SVM) model, and multilayer perceptron (MLP) model were developed. Their respective diagnostic performances for MPE were evaluated by receiver operating characteristic (ROC) curves.

RESULTS

Among the five models, the XGBoost model exhibited the best diagnostic performance for MPE (area under the curve (AUC): 0.903, 0.918, and 0.886 in the training, validation, and testing cohorts, respectively). Additionally, the XGBoost model outperformed carcinoembryonic antigen (CEA) levels in pleural fluid (PF), serum, and the PF/serum ratio (AUC: 0.726, 0.699, and 0.692 in the training cohort; 0.763, 0.695, and 0.731 in the validation cohort; and 0.722, 0.729, and 0.693 in the testing cohort, respectively). Furthermore, compared with CEA, the XGBoost model demonstrated greater diagnostic power and sensitivity in diagnosing lung cancer-induced MPE.

CONCLUSION

The development of a machine learning model utilizing routine laboratory biomarkers significantly enhances the diagnostic capability for distinguishing between MPE and BPE. The XGBoost model emerges as a valuable tool for the diagnosis of MPE.