获取途径

作者

Wang, Yan Tan, Jie Li, Xinjun Sun, Liang Yu, Zhaoyan

作者单位

³Binzhou Peoples Hospital, Department of Pathology, No. 515 Huanghe 7th Road, Bincheng District, Shandong, Binzhou 250000, China 010050, China ⁴Shandong First Medical University, Shandong Academy of Medical Sciences, First Affiliated Hospital, Biomedical Sciences College, Shandong Medicinal Biotechnology Centre, Shandong, Jinan ⁵Shandong First Medical University, Shandong Academy of Medical Sciences, Binzhou Peoples Hospital Affiliated to Shandong First Medical University, College of Medical Information and Artificial Intelligence, Shandong, Jinan 256610, China ¹Shandong First Medical University, School of Pharmacy, Shandong, Jinan ²Affiliated Hospital of Inner Mongolia Medical University, Department of Respiratory and Critical Care Medicine, Inner Mongolia, Hohhot

刊名

SSRN

年份

2025

ISSN

1556-5068

摘要

Background: Differential diagnosis of pneumonia, tuberculosis, and lung cancer is highly challenging due to overlapping clinical presentations and high comorbidity rates. To overcome the limitations of traditional diagnostic methods, this study developed and validated an explainable machine learning model using proteomic data for multi-label classification of these three diseases.Methods: Bronchoalveolar lavage fluid proteomic data were collected from 358 patients with confirmed lung diseases at...更多

Background: Differential diagnosis of pneumonia, tuberculosis, and lung cancer is highly challenging due to overlapping clinical presentations and high comorbidity rates. To overcome the limitations of traditional diagnostic methods, this study developed and validated an explainable machine learning model using proteomic data for multi-label classification of these three diseases.Methods: Bronchoalveolar lavage fluid proteomic data were collected from 358 patients with confirmed lung diseases at the Shandong Provincial Public Health Clinical Center. We constructed a voting ensemble model integrating XGBoost, Random Forest,and Gradient Boosting algorithms based on clinical features, global proteomic statistical features, differentially expressed derived features, and disease-specific biomarker scores. Considering insufficient cancer samples and risk of missed diagnoses, a 1·5-fold weighting strategy was applied to the cancer class to enhance sensitivity. The model was evaluated using 5-fold stratified cross-validation and an independent external cohort of 20 cases. Feature contributions were interpreted using the Shapley Additive exPlanations method and biological significance of key proteins was determined using Gene Ontology functional enrichment analysis.Findings: The AUC and PR-AUC values were 0·910±0·042 and 0·906 for tuberculosis detection and 0·817±0·024 and 0·709 for cancer detection, respectively. Thus, the ensemble model demonstrated excellent performance, significantly outperforming seven baseline models including logistic regression and support vector machines. SHAP analysis identified key protein biomarkers. Furthermore, the model achieved an overall accuracy of 70% with the independent external validation cohort.Interpretation: This study established an explainable, multi-label classification model based on proteomics that can provide a valuable reference for the differential diagnosis of complex lung diseases, especially those with comorbidities. The model shows good performance and interpretability, suggesting potential for precise diagnosis of lung diseases.收起

文献类型

期刊