Interpretable noninvasive diagnosis of tuberculous pleural effusion using LGBM and SHAP: development and clinical application of a machine learning model.

Journal: PeerJ
Published Date: May 20, 2025

Abstract

BACKGROUND: Tuberculous pleural effusion (TPE) is a prevalent tuberculosis complication, with diagnosis presenting considerable challenges. Timely and precise identification of TPE is vital for effective patient management and prognosis, yet existing diagnostic methods tend to be invasive, lengthy, and often lack sufficient accuracy. This study seeks to design and validate an interpretable machine learning model based on routine laboratory data to enable noninvasive and rapid TPE diagnosis.

Authors

  • Bihua Yao
    Laboratory Medicine Center, Department of Clinical Laboratory, The First People's Hospital of Jiashan affiliated to Jiaxing University, Jiashan, Zhejiang, China.
  • Xingyu Yu
    Zhejiang Sci-Tech University, Hangzhou, Zhejiang, China.
  • Liannv Qiu
    Department of Laboratory Medicine, Zhejiang Provincial People's Hospital, Hangzhou, Zhejiang, China.
  • Er-Min Gu
    Department of Science and Education, The First People's Hospital of Jiashan affiliated to Jiaxing University, Jiaxing, Zhejiang, China.
  • Siyu Mao
    Laboratory Medicine Center, Department of Clinical Laboratory, The First People's Hospital of Jiashan affiliated to Jiaxing University, Jiashan, Zhejiang, China.
  • Lei Jiang
    Department of Thoracic Surgery, Shanghai Pulmonary Hospital, Tongji University, Shanghai 200433, China.
  • Jijun Tong
    Zhejiang Sci-Tech University, Hangzhou, China.
  • Jianguo Wu
    School of Life Sciences, Arizona State University, Tempe, AZ, 85281, USA; School of Sustainability, Julie A. Wrigley Global Institute of Sustainability, Arizona State University, Tempe, AZ, 85281, USA; Center for Human-Environment System Sustainability (CHESS), State Key Laboratory of Earth Surface Processes and Resource Ecology, Beijing Normal University, Beijing, 100875, China.

Keywords

External Resources

Popular Topics
Recent Journals