EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Development and external validation of machine-learning models for diagnosing malignant pleural effusion

Aihua Wu, Shanshan Wang, Hongying Ma, Songbo Yuan, Yanqing Liu

Frontiers in Oncology · 17.08.2026 · 16

DOI: 10.3389/fonc.2026.1880122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 17.08.2026. Verfasst von Aihua Wu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Department of Laboratory Medicine, The First Affiliated Hospital of Ningbo University, Ningbo, Zhejiang, China. Die Arbeit nennt 29 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Clinicians face challenges in diagnosing malignant pleural effusion (MPE) and distinguishing it from benign causes. This study aimed to develop and validate machine learning (ML) models for this purpose.

Methods

The retrospective study included 1,530 untreated patients with pleural effusion (PE) between January 2016 and December 2025. Clinical variables, including age, sex, smoking status, and laboratory indices were collected for analysis. The patients were randomly divided into the training and test sets at a ratio of 7:3. Six ML algorithms were developed and compared to determine the best diagnostic model for MPE using seven metrics, calibration curve, and decision curve. The SHapley Additive exPlanations (SHAP) values were used to interpret the model. An independent cohort of 244 PE patients was used for external validation.

Results

Based on the feature importance analysis, the XGBoost (extreme gradient boosting) model achieved the best diagnostic performance in the training set, with an AUC of 0.988 (95% CI: 0.982-0.993), the lowest brier score 0.037 (95% CI: 0.029-0.045), and high values for accuracy of 0.951, sensitivity of 0.891, specificity of 0.984, and F1 score of 0.928. Six features were included: fluid carcinoembryonic antigen (CEA), serum CEA, serum cytokeratin 19 fragment (CYFRA 21-1), fluid carbohydrate antigen 724 (CA724), fluid carbohydrate antigen CA199 (CA199), and fluid adenosine deaminase (ADA). SHAP analysis showed that fluid CEA, fluid ADA, and serum CYFRA21–1 were the three most important variables.

Conclusions

We developed and validated an accurate and interpretable XGBoost model for distinguishing MPE from BPE using routine laboratory data, which might be applied in clinical practice and decision-making.

Schlagwörter

Stichwörter der Autor:innen

area under the curvediagnostic performanceextreme gradient boostingmachine learningmalignant pleural effusion

Autor:innen und Institutionen

  • Department of Laboratory Medicine, The First Affiliated Hospital of Ningbo University, Ningbo, Zhejiang, China.
  • Department of Respiratory and Critical Care Medicine, The First Affiliated Hospital of Ningbo University, Ningbo, Zhejiang, China.
  • Department of Laboratory Medicine, The Affiliated People's Hospital of Ningbo University, Ningbo, Zhejiang, China.
  • School of Medicine, Ningbo University, Ningbo, China.

Zitieren

APA

Wu, A., Wang, S., Ma, H., Yuan, S., & Liu, Y. (2026). Development and external validation of machine-learning models for diagnosing malignant pleural effusion. Frontiers in Oncology, 16. https://doi.org/10.3389/fonc.2026.1880122

Vancouver

Wu A, Wang S, Ma H, Yuan S, Liu Y. Development and external validation of machine-learning models for diagnosing malignant pleural effusion. Frontiers in Oncology. 2026;16. doi:10.3389/fonc.2026.1880122

BibTeX
@article{Wu2026,
  author = {Wu, Aihua and Wang, Shanshan and Ma, Hongying and Yuan, Songbo and Liu, Yanqing},
  title = {Development and external validation of machine-learning models for diagnosing malignant pleural effusion},
  journal = {Frontiers in Oncology},
  year = {2026},
  volume = {16},
  doi = {10.3389/fonc.2026.1880122}
}
Kostenlos starten →