Development and Evaluation of the New Predictive Models in Tuberculous Pleuritis

Enhanced differential evolution algorithm for feature selection in tuberculous pleural effusion clinical characteristics analysis

Tuberculous pleural effusion poses a significant threat to human health due to its potential for severe disease and mortality. Without timely treatment, it may lead to fatal consequences. Therefore, early identification and prompt treatment are crucial for preventing problems such as chronic lung disease, respiratory failure, and death. This study proposes an enhanced differential evolution algorithm based on colony predation and dispersed foraging strategies. A series of experiments conducted on the IEEE CEC 2017 competition dataset validated the global optimization capability of the method. Additionally, a binary version of the algorithm is introduced to assess the algorithm's ability to address feature selection problems. Comprehensive comparisons of the effectiveness of the proposed algorithm with 8 similar algorithms were conducted using public datasets with feature sizes ranging from 10 to 10,000. Experimental results demonstrate that the proposed method is an effective feature selection approach. Furthermore, a predictive model for tuberculous pleural effusion is established by integrating the proposed algorithm with support vector machines. The performance of the proposed model is validated using clinical records collected from 140 tuberculous pleural effusion patients, totaling 10,780 instances. Experimental results indicate that the proposed model can identify key correlated indicators such as pleural effusion adenosine deaminase, temperature, white blood cell count, and pleural effusion color, aiding in the clinical feature analysis of tuberculous pleural effusion and providing early warning for its treatment and prediction.

Diagnostic scoring systems for tuberculous pleural effusion in patients with lymphocyte-predominant exudative pleural profile: A development study

Background

Diagnosing tuberculous pleural effusion (TPE) in patients presenting with Lymphocyte-Predominant Exudative pleural effusion (LPE) is challenging, due to the poor clinical utility of TB culture. Adenosine deaminase (ADA) has been recommended for diagnosis, but its high cost and limited availability hinder its clinical utility. We aim to develop diagnostic prediction tools for Thai patients with LPE in scenarios where pleural fluid ADA is available but yields negative results and in situations where pleural fluid ADA is not available.

Methods

Two diagnostic prediction tools were developed using retrospective data from patients with LPE at Surin Hospital. Model 1 is for ADA-negative results, and Model 2 is for situations where pleural fluid ADA testing is unavailable. The models were derived using multivariable logistic regression and presented as two clinical scoring systems: round-up and count scoring. The score cut-point that achieves a positive predictive value (PPV) comparable to the post-test probability of a pleural fluid ADA at a cut-point of 40 U/L was used as a threshold for initiating anti-TB treatment.

Results

A total of 359 patients were eligible for analysis, with 166 diagnosed with TPE and 193 diagnosed with non-TPE. Age <40 years, fever, pleural fluid protein ≥5 g/dL, male gender, pleural fluid color, and pleural fluid ADA ≥20 U/L were identified as final predictors. Both models demonstrated excellent discriminative ability (AuROC: 0.85 to 0.89). The round-up scoring demonstrated PPV above 90% at cut-off points of 4 and 4.5, while the count scoring achieved cut-off points of 3 and 4 for Model 1 (Lex-2P2A) and Model 2 (Lex-2P-MAC), respectively.

Conclusion

These diagnostic tools offer valuable assistance in differentiating between TPE and non-TPE in LPE patients with negative pleural fluid ADA (Lex-2P2A) and in settings where pleural fluid ADA testing is not available (Lex-2P-MAC). Implementing these diagnostic scores may have the potential to improve TPE diagnosis and facilitate prompt initiation of treatment.

Tuberculous pleural effusion prediction using ant colony optimizer with grade-based search assisted support vector machine

Introduction

Although tuberculous pleural effusion (TBPE) is simply an inflammatory response of the pleura caused by tuberculosis infection, it can lead to pleural adhesions and cause sequelae of pleural thickening, which may severely affect the mobility of the chest cavity.

Methods

In this study, we propose bGACO-SVM, a model with good diagnostic power, for the adjunctive diagnosis of TBPE. The model is based on an enhanced continuous ant colony optimization (ACOR) with grade-based search technique (GACO) and support vector machine (SVM) for wrapped feature selection. In GACO, grade-based search greatly improves the convergence performance of the algorithm and the ability to avoid getting trapped in local optimization, which improves the classification capability of bGACO-SVM.

Results

To test the performance of GACO, this work conducts comparative experiments between GACO and nine basic algorithms and nine state-of-the-art variants as well. Although the proposed GACO does not offer much advantage in terms of time complexity, the experimental results strongly demonstrate the core advantages of GACO. The accuracy of bGACO-predictive SVM was evaluated using existing datasets from the UCI and TBPE datasets.

Discussion

In the TBPE dataset trial, 147 TBPE patients were evaluated using the created bGACO-SVM model, showing that the bGACO-SVM method is an effective technique for accurately predicting TBPE.

A rapid calprotectin test for the diagnosis of pleural effusion

In previous studies, measuring the levels of calprotectin in patients with pleural effusion (PE) was an exceptionally accurate way to predict malignancy. Here, we evaluated a rapid method for the measurement of calprotectin levels as a useful parameter in the diagnosis of malignant pleural effusion (MPE) in order to minimise invasive diagnostic tests. Calprotectin levels were measured with Quantum Blue^® sCAL (QB^®sCAL) and compared with the gold standard reference ELISA method. Calprotectin levels in patients with benign pleural effusion (BPE) were significantly higher (p < 0.0001) than for MPE patients. We measured the sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and positive and negative likelihood ratios (LRs) for a cut-off value of ≤ 14,150 ng/mL; the diagnostic accuracy was 64%. The odds ratio for PE calprotectin levels was 10.938 (95% CI [4.133 − 28.947]). The diagnostic performance of calprotectin concentration was better for predicting MPE compared to other individual parameters. Comparison of two assays showed a slope of 1.084, an intercept of 329.7, and a Pearson correlation coefficient of 0.798. The Bland–Altman test showed a positive bias for the QB^®sCAL method compared to ELISA fCAL^®. Clinical concordance between both these methods was 88.5% with a Cohen kappa index of 0.76 (95% CI [0.68 − 0.84]). We concluded that QB^®sCAL is a fast, reliable, and non-invasive diagnostic tool for diagnosing MPE and represents an alternative to ELISA that could be implemented in medical emergencies.

Influence of age on the diagnostic accuracy of soluble biomarkers for tuberculous pleural effusion: a post hoc analysis

BACKGROUND

Accurately diagnosing pleural effusion is a frequent and significant problem in clinical practice. Combining pleural biomarkers with patients' age may be a valuable method for diagnosing TPE. We sought to evaluate the influence of age on diagnostic values of pleural adenosine deaminase (ADA), interferon-gamma (IFN-γ), and interleukin 27 (IL-27) for tuberculous pleural effusion (TPE).

METHODS

Two hundred seventy-four consecutive adult patients with pleural effusion were selected from Beijing and Wuhan between January 1, 2014 and June 30, 2015, and their pleural fluid concentrations of ADA, IFN-γ, and IL-27 were tested. Biomarker performance was analyzed by standard receiver operating characteristic (ROC) curves according to different ages.

RESULTS

Data from the Beijing cohort showed that ADA, IFN-γ, and IL-27 could all accurately diagnose TPE in young patients (≤ 40 years of age). With a cutoff of 21.4 U/L, the area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of ADA for diagnosing TPE were 1.000 (95% confidence interval: 0.884-1.000), 100.0, 100.0%, 100.0, and 100.0, respectively. In older patients (> 40 years of age), IL-27 and IFN-γ were excellent biomarkers for discriminating TPE versus non-TPE cases. With a cutoff of 591.4 ng/L, the AUC, sensitivity, specificity, PPV, and NPV of IL-27 for diagnosing TPE were 0.976 (95% confidence interval: 0.932-0.995), 96.3, 99.0%, 96.3, and 99.0, respectively. Similar diagnostic accuracy among the three pleural biomarkers was validated in the Wuhan cohort.

CONCLUSIONS

Among young patients, ADA is reliable for diagnosing TPE. Conversely, in older patients, IL-27 and IFN-γ are excellent biomarkers to differentiate TPE versus non-TPE cases.

Risk factors for tuberculous empyema in pleural tuberculosis patients

Tuberculous empyema (TE) is associated with high mortality and morbidity. In the retrospective cohort study, we aimed to find risk factors for TE among pleural tuberculosis (TB) patients. Between July 2011 and September 2015, all culture-confirmed pleural TB patients (474 cases) were enrolled in our study. Empyema was defined as grossly purulent pleural fluid. Demographic and epidemiological data were collected for further analysis. Multivariate logistic regression analysis was used to evaluate risk factors of TE in pleural TB, age–adjusted odds ratio (OR) and 95% confidence interval (CI) were calculated to show the risk. The mean age was 35.7 ± 18.1 years old, males comprised 79.1% of the participants (375 cases). Forty-seven patients (9.9%) were multidrug-resistant TB (MDR-TB), 29 (6.1%) had retreatment TB, 26 (5.5%) had diabetes mellitus. The percentage of empyema patients was 8.9% (42 cases). Multivariate analysis revealed that male (adjusted OR = 4.431, 95% CI: 1.411, 13.919), pleural adenosine deaminase (ADA, >88 U/L) (adjusted OR = 3.367, 95% CI: 1.533, 7.395) and white blood cell (WBC, >9.52 10⁹/L) (adjusted OR = 5.763, 95% CI: 2.473, 13.431) were significant risk factors for empyema in pleural TB, while pulmonary TB (adjusted OR = 0.155, 95% CI: 0.072, 0.336) was the protective factor for the patients. TE remains a serious threat to public health in China. Male sex is a significant risk factor for TE while the presence of pulmonary TB is protective, and high levels of pleural ADA and WBC count could aid in early diagnosis of TE. This finding would help towards reducing the mortality and morbidity associated with TE.

Developing a new intelligent system for the diagnosis of tuberculous pleural effusion

BACKGROUND AND OBJECTIVE

In countries with high prevalence of tuberculosis (TB), clinicians often diagnose tuberculous pleural effusion (TPE) by using diagnostic tests, which have not only poor sensitivity, but poor availability as well. The aim of our study is to develop a new artificial intelligence based diagnostic model that is accurate, fast, non-invasive and cost effective to diagnose TPE. It is expected that a tool derived based on the model be installed on simple computer devices (such as smart phones and tablets) and be used by clinicians widely.

METHODS

For this study, data of 140 patients whose clinical signs, routine blood test results, blood biochemistry markers, pleural fluid cell type and count, and pleural fluid biochemical tests' results were prospectively collected into a database. An Artificial intelligence based diagnostic model, which employs moth flame optimization based support vector machine with feature selection (FS-MFO-SVM), is constructed to predict the diagnosis of TPE.

RESULTS

The optimal model results in an average of 95% accuracy (ACC), 0.9564 the area under the receiver operating characteristic curve (AUC), 93.35% sensitivity, and 97.57% specificity for FS-MFO-SVM.

CONCLUSIONS

The proposed artificial intelligence based diagnostic model is found to be highly reliable for diagnosing TPE based on simple clinical signs, blood samples and pleural effusion samples. Therefore, the proposed model can be widely used in clinical practice and further evaluated for use as a substitute of invasive pleural biopsies.

Diagnostic value of interferon-γ-induced protein of 10kDa for tuberculous pleurisy: A meta-analysis

BACKGROUND

The accurate diagnosis of tuberculous pleurisy is still a clinical challenge. Many studies reported that interferon-γ-induced protein of 10kDa (IP-10) plays a role in diagnosing tuberculous pleurisy, but with considerable variance of results. This meta-analysis aimed to evaluate the overall diagnostic accuracy of IP-10 for tuberculous pleurisy.

METHODS

PubMed, EMBASE, and other databases were searched for studies examining accuracy of pleural IP-10 for diagnosing tuberculous pleurisy. Related data were extracted and sensitivity/specificity, positive/negative likelihood ratio (PLR/NLR), and diagnostic odds ratio (DOR) were pooled. Summary receiver operating characteristic curve and area under the curve (AUC) were performed and calculated to summarize the overall test performance.

RESULTS

Fourteen studies involving 1382 subjects met inclusion criteria, including 715 cases of tuberculous pleurisy and 667 controls. Summary estimates of the diagnostic performance of the IP-10 for tuberculous pleurisy were listed as follows: sensitivity, 0.84 (95%CI 0.81 to 0.87); specificity, 0.90 (95% CI 0.88 to 0.92); PLR, 7.96 (95% CI 5.59 to 11.32); NLR, 0.19 (95% CI 0.15 to 0.24); DOR, 49.82 (95% CI 28.08 to 88.38); and AUC 0.94. No publication bias was detected.

CONCLUSION

Pleural IP-10 is a useful diagnostic marker for tuberculous pleurisy. Nevertheless, its result should be interpreted together with the results of conventional test and clinical information of patients.

Advances in the diagnosis of tuberculous pleuritis

Pleural tuberculosis (TB) remains difficult to diagnose. In about two-thirds of the cases the diagnosis is reliant upon clinical suspicion along with consistent fluid biochemistries (i.e., lymphocytic predominant exudates) and exclusion of other potential causes for the effusion. Microbiological methods for a confirmatory diagnosis of pleural TB, which include acid-fast smears (Ziehl-Nelseen), cultures on solid media (Lowenstein-Jensen) and polymerase chain reaction tests from either pleural fluid or sputum samples, remain suboptimal since they are positive in only a minority of patients. Liquid media, however, significantly increase sensitivity while shortening culture positivity as compared with solid cultures. A number of pleural fluid biomarkers such as adenosine deaminase (ADA), interferon-Ƴ, interferon-Ƴ-induced protein of 10 KDa (IP-10) and interleukin-27 (IL-27), have shown promise for the rapid diagnosis of TB, but only ADA combines the accuracy and simplicity required to be considered a mainstay investigative tool for clinical decisions, particularly in areas with medium to high TB prevalence. In countries where ADA is not available, pleural biopsies to evaluate for caseating granulomas are a standard diagnostic approach. They are now frequently performed under ultrasound guidance to optimize yield and patient safety.