Diagnostic and comparative performance for the prediction of tuberculous pleural effusion using machine learning algorithms.

OBJECTIVE: Early diagnosis and differential diagnosis of tuberculous pleural effusion (TPE) remains challenging and is critical to the patients' prognosis. The present study aimed to develop nine machine learning (ML) algorithms for early diagnosis of TPE and compare their performance. METHODS: A total of 1435 untreated patients with pleural effusions (PEs) were retrospectively included and divided into the training set (80%) and the test set (20%). The demographic and laboratory variables were collected, preprocessed, and analyzed to select features, which were fed into nine ML algorithms to develop an optimal diagnostic model for TPE. The proposed model was validated by an independently external data. The decision curve analysis (DCA) and the SHapley Additive exPlanations (SHAP) were also applied. RESULTS: Support vector machine (SVM) was the best model in discriminating TPE from non-TPE, with a balanced accuracy of 87.7%, precision of 85.3%, area under the curve (AUC) of 0.914, sensitivity of 94.7%, specificity of 80.7%, and F1-score of 86.0% among the nine ML algorithms. The excellent diagnostic performance was also validated by the external data (a balanced accuracy of 87.7%, precision of 85.2%, and AUC of 0.898). Neural network (NN) and K-nearest neighbor (KNN) had better net benefits in clinical usefulness. Besides, PE adenosine deaminase (ADA), PE carcinoembryonic antigen (CEA), and serum CYFRA21-1 were identified as the top three important features for diagnosing TPE. CONCLUSIONS: This study developed and validated a SVM model for the early diagnosis of TPE, which might help clinicians provide better diagnosis and treatment for TPE patients.

Construction of a multi-classified decision tree model for identifying malignant pleural effusion and tuberculous pleural effusion.

OBJECTIVE: Pleural effusion (PE) is a common clinical complication associated with various disorders. We aimed to utilize laboratory variables and their corresponding ratios in serum and PE for the differential diagnosis of multiple types of PE based on a decision tree (DT) algorithm. METHODS: A total of 1435 untreated patients with PE admitted to The First Affiliated Hospital of Ningbo University were enrolled. The demographic and laboratory variables were collected and compared. The receiver operating characteristic curve was used to select important variables for diagnosing malignant pleural effusion (MPE) or tuberculous pleural effusion (TPE) and included in the DT model. The data were divided into the training set and the test set at a ratio of 7:3. The training data was used to develop the DT model, and the test data was for evaluating the model. Independent data was collected as external validation. RESULTS: Three PE indicators (carcinoembryonic antigen, adenosine deaminase [ADA], and total protein), two serum indicators (neuron-specific enolase and cytokeratin 19 fragments), and two ratios [high-sensitivity C-reactive protein (hsCRP)/ PE lymphocyte and hsCRP/PE ADA] were used to construct the DT model. The area under the curve (AUC), sensitivity, and specificity for diagnosing MPE were 0.963, 84.0%, 91.6% in the training set, 0.976, 84.1%, 88.6% in the test set, and 0.955,83.3%, 86.7% in the external validation set. The AUC, sensitivity, and specificity of diagnosing TPE were 0.898, 86.8%, 92.3% in the training set, 0.888, 88.8%, 92.7% in the test set, and 0.778, 84.8%, 94.3% in the external validation set. CONCLUSION: The DT model showed good diagnostic efficacy and could be applied for the differential diagnosis of MPE and TPE in clinical settings.

Development and validation of a prediction model for tuberculous pleural effusion: a large cohort study and external validation.

BACKGROUND: Distinguishing tuberculous pleural effusion (TPE) from non-tuberculosis (TB) benign pleural effusion (BPE) remains to be a challenge in clinical practice. The aim of the present study was to develop and validate a novel nomogram for diagnosing TPE. METHODS: In this retrospective analysis, a total of 909 consecutive patients with TPE and non-TB BPE from Ningbo First Hospital were divided into the training set and the internal validation set at a ratio of 7:3, respectively. The clinical and laboratory features were collected and analyzed by logistic regression analysis. A diagnostic model incorporating selected variables was developed and was externally validated in a cohort of 110 patients from another hospital. RESULTS: Six variables including age, effusion lymphocyte, effusion adenosine deaminase (ADA), effusion lactatedehy drogenase (LDH), effusion LDH/effusion ADA, and serum white blood cell (WBC) were identified as valuable parameters used for developing a nomogram. The nomogram showed a good diagnostic performance in the training set. A novel scoring system was then established based on the nomogram to distinguish TPE from non-TB BPE. The scoring system showed good diagnostic performance in the training set [area under the curve (AUC) (95% confidence interval (CI)), 0.937 (0.917-0.957); sensitivity, 89.0%, and specificity, 89.5%], the internal validation set [AUC (95%CI), 0.934 (0.902-0.966); sensitivity, 88.7%, and specificity, 90.3%], and the external validation set [(AUC (95%CI), 0.941 (0.891-0.991); sensitivity, 93.6%, and specificity, 87.5%)], respectively. CONCLUSIONS: The study developed and validated a novel scoring system based on a nomogram originated from six clinical parameters. The novel scoring system showed a good diagnostic performance in distinguishing TPE from non-TB BPE and can be conveniently used in clinical settings.

Development and Validation of a Scoring System for Early Diagnosis of Malignant Pleural Effusion Based on a Nomogram.

BACKGROUND: The diagnostic value of clinical and laboratory features to differentiate between malignant pleural effusion (MPE) and benign pleural effusion (BPE) has not yet been established. OBJECTIVES: The present study aimed to develop and validate the diagnostic accuracy of a scoring system based on a nomogram to distinguish MPE from BPE. METHODS: A total of 1,239 eligible patients with PE were recruited in this study and randomly divided into a training set and an internal validation set at a ratio of 7:3. Logistic regression analysis was performed in the training set, and a nomogram was developed using selected predictors. The diagnostic accuracy of an innovative scoring system based on the nomogram was established and validated in the training, internal validation, and external validation sets (n = 217). The discriminatory power and the calibration and clinical values of the prediction model were evaluated. RESULTS: Seven variables [effusion carcinoembryonic antigen (CEA), effusion adenosine deaminase (ADA), erythrocyte sedimentation rate (ESR), PE/serum CEA ratio (CEA ratio), effusion carbohydrate antigen 19-9 (CA19-9), effusion cytokeratin 19 fragment (CYFRA 21-1), and serum lactate dehydrogenase (LDH)/effusion ADA ratio (cancer ratio, CR)] were validated and used to develop a nomogram. The prediction model showed both good discrimination and calibration capabilities for all sets. A scoring system was established based on the nomogram scores to distinguish MPE from BPE. The scoring system showed favorable diagnostic performance in the training set [area under the curve (AUC) = 0.955, 95% confidence interval (CI) = 0.942-0.968], the internal validation set (AUC = 0.952, 95% CI = 0.932-0.973), and the external validation set (AUC = 0.973, 95% CI = 0.956-0.990). In addition, the scoring system achieved satisfactory discriminative abilities at separating lung cancer-associated MPE from tuberculous pleurisy effusion (TPE) in the combined training and validation sets. CONCLUSIONS: The present study developed and validated a scoring system based on seven parameters. The scoring system exhibited a reliable diagnostic performance in distinguishing MPE from BPE and might guide clinical decision-making.

Application of Holistic Nursing in Uremic Patients with Hematodialysis Related Malnutrition.

BACKGROUND: We aimed to observe the effect of holistic nursing on patients undergoing hematodialysis for uremia who simultaneously were suffering from moderate to severe malnutrition. METHODS: Eighty patients with uremia on maintenance hematodialysis with malnutrition between June 2014 and June 2015 from Yantaishan Hospital, Yantai, Shandong, China were included and equally and randomly were divided into the control group (n=43) and observation group (n=43). Routine nursing was used in the control group while holistic nursing was used in observation group (before, during and after dialysis) and the clinical effects in the two groups were compared after 3 months. RESULTS: At follow-up visits, serum creatinine and urea nitrogen levels of the patients in the two groups were decreased, whereas hemoglobin and albumin levels were increased. In addition, these improvements were greater in the observation group and the differences were statistically significant (P<0.05). Furthermore, during follow-up visits, MQSGA and MIS scores of the two groups were lower and the scores of the observation group were lower than those in the control group were, and the differences were statistically significant (P<0.05). CONCLUSION: Holistic nursing is able to improve significantly malnutrition in patients with uremia on hematodialysis.