Differentiation of malignant from benign pleural effusions based on artificial intelligence

Differential Diagnosis of Pleural Effusion Using Machine Learning

Rationale: Differential diagnosis of pleural effusion is challenging in clinical practice. Objectives: We aimed to develop a machine learning model to classify the five common causes of pleural effusions. Methods: This retrospective study collected 49 features from clinical information, blood, and pleural fluid of adult patients who underwent diagnostic thoracentesis between October 2013 and December 2018. Pleural effusions were classified into the following five categories: transudative, malignant, parapneumonic, tuberculous, and other. The performance of five different classifiers, including multinomial logistic regression, support vector machine, random forest, extreme gradient boosting, and light gradient boosting machine (LGB), was evaluated in terms of accuracy and area under the receiver operating characteristic curve through fivefold cross-validation. Hybrid feature selection was applied to determine the most relevant features for classifying pleural effusion. Results: We analyzed 2,253 patients (training set, n = 1,459; validation set, n = 365; extra-validation set, n = 429) and found that the LGB model achieved the best performance in both validation and extra-validation sets. After feature selection, the accuracy of the LGB model with the selected 18 features was equivalent to that with all 49 features (mean ± standard deviation): 0.818 ± 0.012 and 0.777 ± 0.007 in the validation and extra-validation sets, respectively. The model's mean area under the receiver operating characteristic curve was as high as 0.930 ± 0.042 and 0.916 ± 0.044 in the validation and extra-validation sets, respectively. In our model, pleural lactate dehydrogenase, protein, and adenosine deaminase levels were the most important factors for classifying pleural effusions. Conclusions: Our LGB model showed satisfactory performance for differential diagnosis of the common causes of pleural effusions. This model could provide clinicians with valuable information regarding the major differential diagnoses of pleural diseases.

IR808@MnO nano-near infrared fluorescent dye's diagnostic value for malignant pleural effusion

BACKGROUND

Malignant pleural effusion is mostly a complication of advanced malignant tumors. However, the cancer markers such as carbohydrate antigen 125 (CA 125), carbohydrate antigen 15-3 (CA 15-3), carbohydrate antigen 19-9 (CA 19-9), and cytokeratin fragment 21-1 (CYFRA 21-1) have low sensitivity and organ specificity for detecting malignant pleural effusion.

RESEARCH QUESTION

Is IR808@MnO nano-near infrared fluorescent dye worthy for the diagnosis in differentiating benign and malignant pleural effusions.

STUDY DESIGN AND METHODS

This experiment was carried out to design and characterize the materials for in vitro validation of the new dye in malignant tumor cells in the A549 cell line and in patients with adenocarcinoma pleural effusion. The dye was verified to possess tumor- specific targeting capabilities. Subsequently, a prospective hospital-based observational study was conducted, enrolling 106 patients and excluding 28 patients with unknown diagnoses. All patients underwent histopathological analysis of thoracoscopic biopsies, exfoliative cytological analysis of pleural fluid, and analysis involving the new dye. Statistical analyses were performed using Microsoft Excel, GraphPad Prism, and the R language.

RESULTS

The size of IR808@MnO was 136.8 ± 2.9 nm, with peak emission at 808 nm, and it has near-infrared fluorescence properties. Notably, there was a significant difference in fluorescence values between benign and malignant cell lines (p < 0.0001). The malignant cell lines tested comprised CL1-5, A549, MDA-MB-468, U-87MG, MKN-7, and Hela, while benign cell lines were BEAS-2B, HUVEC, HSF, and VE. The most effective duration of action was identified as 30 min at a concentration of 5 μl. This optimal duration of action and concentration were consistent in patients with lung adenocarcinoma accompanied by pleural effusion and 5 μl. Of the 106 patients examined, 28 remained undiagnosed, 39 were diagnosed with malignant pleural effusions, and the remaining 39 with benign pleural effusions. Employing the new IR808@MnO staining method, the sensitivity stood at 74.4%, specificity at 79.5%, a positive predictive value of 69.2%, and a negative predictive value of 82.1%. The area under the ROC curve was recorded as 0.762 (95% CI: 0.652-0.872). The confusion matrix revealed a positive predictive value of 75.7%, a negative predictive value of 75.6%, a false positive rate of 22.5%, and a false negative rate of 26.3%.

INTERPRETATION

The IR808@MnO fluorescent probe represents an efficient, sensitive, and user-friendly diagnostic tool for detecting malignant pleural fluid, underscoring its significant potential for clinical adoption.

Automated detection and segmentation of pleural effusion on ultrasound images using an Attention U-net

BACKGROUND

Ultrasonic for detecting and evaluating pleural effusion is an essential part of the Extended Focused Assessment with Sonography in Trauma (E-FAST) in emergencies. Our study aimed to develop an Artificial Intelligence (AI) diagnostic model that automatically identifies and segments pleural effusion areas on ultrasonography.

METHODS

An Attention U-net and a U-net model were used to detect and segment pleural effusion on ultrasound images of 848 subjects through fully supervised learning. Sensitivity, specificity, precision, accuracy, F1 score, the receiver operating characteristic (ROC) curve, and the area under the curve (AUC) were used to assess the model's effectiveness in classifying the data. The dice coefficient was used to evaluate the segmentation performance of the model.

RESULTS

In 10 random tests, the Attention U-net and U-net 's average sensitivity of 97% demonstrated that the pleural effusion was well detectable. The Attention U-net performed better at identifying negative images than the U-net, which had an average specificity of 91% compared to 86% for the U-net. Additionally, the Attention U-net was more accurate in predicting the pleural effusion region because its average dice coefficient was 0.86 as opposed to the U-net's average dice coefficient of 0.82.

CONCLUSIONS

The Attention U-net showed excellent performance in detecting and segmenting pleural effusion on ultrasonic images, which is expected to enhance the operation and application of E-FAST in clinical work.

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.