Key result
LightGBM model differentiates malignant from benign pericardial effusion with ~0.93 AUC.
Why the study?
Real-time, accurate decision support based on routine clinical data was needed to distinguish malignant pericardial effusion from benign pericardial effusion.
Does a machine learning diagnostic model using routine clinical data accurately differentiate malignant pericardial effusion from benign pericardial effusion in patients with pericardial effusion?
Cohort (n=296)
Does a machine learning diagnostic model using routine clinical data accurately differentiate malignant pericardial effusion from benign pericardial effusion in patients with pericardial effusion?
An interpretable LightGBM machine learning model using five routine clinical indicators (with fluid lactate dehydrogenase having the highest importance) can differentiate malignant from benign pericardial effusion with an AUC of 0.930.
Answers are grounded in this paper and cite their sources.
May support pericardial effusion evaluation but should not change practice; leaves open prospective validation of machine learning models.
Objectives: This study aimed to develop and validate a machine learning model based on routine clinical data to provide real-time, accurate decision support for distinguishing malignant pericardial effusion (MPE) from benign pericardial effusion (BPE). Methods: In total, 296 patients were retrospectively enrolled, comprising 168 with BPE and 128 with MPE. The dataset was randomly divided into training and test sets in a 7:3 ratio. Six machine learning algorithms were trained to construct predictive models, with their predictive accuracy assessed using the Area Under the Curve (AUC) and Decision Curve Analysis (DCA). Furthermore, SHapley Additive exPlanations (SHAP) analysis was utilized to interpret model outputs and identify key predictive variables. Results: All six machine learning models achieved favorable diagnostic performance. Among them, the LightGBM (LGB) model demonstrated the highest predictive accuracy; the LGB test set under the receiver operating characteristic curve (AUC) was 0.930 (95% CI 0.871–0.979), with a sensitivity of 86.8%, a specificity of 94.0%, and an accuracy of 90.9%. XGBoost (XGB) had a lower score than LGB (0.111 versus 0.142). LGB calibration intercept and slope were 0.246 and 3.328. The combined serum D-dimer/carbohydrate antigen 125 (CA125) model had AUC 0.876; its difference from LGB was uncertain (ΔAUC 0.054, 95% CI −0.011 to 0.125; Holm-adjusted p = 0.382). Mean LGB out-of-fold AUC was 0.888 (SD 0.008). Fluid lactate dehydrogenase had the highest SHAP importance. Conclusions: This study developed and validated an interpretable machine learning model incorporating five readily available clinical indicators that enables accurate and rapid differentiation between MPE and BPE, enhancing diagnostic decision-making for pericardial effusion.
No takes yet. Share an insight, caveat, or question.
Sun et al. (2026) conducted a cohort in Pericardial effusion (malignant vs benign) (n=296). LightGBM (LGB) machine learning diagnostic model using five routine clinical indicators vs. Combined serum D-dimer/carbohydrate antigen 125 (CA125) model and other machine learning algorithms (including XGBoost) was evaluated on Diagnostic accuracy for distinguishing malignant pericardial effusion (MPE) from benign pericardial effusion (BPE) assessed by Area Under the Curve (AUC) (AUC 0.930, 95% CI 0.871-0.979, p=0.382). The LightGBM machine learning model differentiated malignant from benign pericardial effusion with a test set AUC of 0.930, 86.8% sensitivity, and 94.0% specificity.
Synapse has enriched 10 related papers. Consider them for comparative context: