A decision tree for differentiating tuberculous from malignant pleural effusions
José M Porcel1, Carmen Alemán, Silvia Bielsa
1Pleural Disease Unit, Department of Internal Medicine, Arnau de Vilanova University Hospital, IRBLLEIDA, Avda Alcalde Rovira Roure 80, 25198 Lleida, Spain. jporcelp@yahoo.es
Insights
A new decision tree algorithm using simple clinical and laboratory data can effectively differentiate tuberculous from malignant pleural effusions, avoiding invasive pleural biopsy.
Area of Science:
- Pulmonology
- Medical Diagnostics
- Decision Science
Background:
- Distinguishing tuberculous from malignant pleural effusions is clinically challenging.
- Pleural biopsy is invasive and not always feasible.
Purpose of the Study:
- To develop a simple clinical algorithm for differentiating tuberculous from malignant pleural effusions.
- To avoid the need for pleural biopsy in diagnosis.
Main Methods:
- Retrospective analysis of clinical and pleural fluid features from 238 patients (tuberculosis vs. malignancy).
- Development of a decision tree model using the C4.5 algorithm.
- Validation of the model on an independent cohort of 367 patients.
Main Results:
- Four key predictors identified: age >35 years, pleural fluid adenosine deaminase >38 U/L, temperature >=37.8°C, and pleural fluid LDH >320 U/L.
- The algorithm achieved 92.2% sensitivity and 98.3% specificity in the derivation cohort (AUC=0.976).
- Validation cohort showed 85.1% sensitivity and 96.9% specificity (AUC=0.958).
Conclusions:
- A decision tree analysis incorporating straightforward clinical and laboratory data aids in the differential diagnosis of pleural effusions.
- This algorithm offers a non-invasive approach to improve diagnostic accuracy for tuberculous pleural effusion.
Objective:
To improve physicians' ability to discriminate tuberculous from malignant pleural effusions through a simple clinical algorithm that avoids pleural biopsy.
Design:
We retrospectively compared the clinical and pleural fluid features of 238 adults with pleural effusion who satisfied diagnostic criteria for tuberculosis (n=64) or malignancy (n=174) at one academic center (derivation cohort). Then, we built a decision tree model to predict tuberculosis using the C4.5 algorithm. The model was validated with an independent sample set from another center that included 74 tuberculous and 293 malignant effusions (validation cohort).
Results:
Among 12 potential predictor variables, the classification tree analysis selected four discriminant parameters (age>35 years, pleural fluid adenosine deaminase>38U/L, temperature>or=37.8 degrees C, and pleural fluid LDH>320U/L) from the derivation cohort. The generated flowchart had 92.2% sensitivity, 98.3% specificity, and an area under the ROC curve of 0.976 for diagnosing tuberculosis. The corresponding operating characteristics for the validation cohort were 85.1%, 96.9% and 0.958.
Conclusions:
Applying a decision tree analysis that contains simple clinical and laboratory data can help in the differential diagnosis of tuberculous and malignant pleural effusions.
Related Concept Videos
Pulmonary Tuberculosis IV
Several diagnostic approaches are used to detect TB. The conventional method is the Tuberculin Skin Test (TST), also known as the Mantoux test. However, this method has...
Pulmonary Tuberculosis III
The first classification is based on the development of the disease, and it includes the following categories:
Pulmonary Tuberculosis II
Here is a detailed explanation of its pathophysiology:
Transmission: The process begins when a person inhales droplet nuclei containing M. tuberculosis. These are typically released into the air when an individual with pulmonary or...
Pleural Effusion II: Symptoms and Management
A pleural effusion is the abnormal collection of fluid between the parietal and visceral pleura layers of tissue that form the lining of the lungs and chest cavity. It can occur independently or due to surrounding parenchymal diseases, such as infection, malignancy, or inflammatory conditions.
Clinical Manifestations:
Pulmonary Tuberculosis V
Latent tuberculosis infection occurs when TB bacteria are present in a person's body, but are not causing illness or symptoms. It is not contagious, and preventive treatment is crucial to avoid the progression...
Pulmonary Tuberculosis I
Causative Organism
The primary infectious agent causing tuberculosis is Mycobacterium tuberculosis, a slow-growing, acid-fast, aerobic rod that exhibits sensitivity to heat and ultraviolet light. Instances of Mycobacterium bovis and Mycobacterium avium contributing to the development of TB infection are rare.
Mode of...
