Pneumoconiosis remains one of the most serious global occupational diseases. However, effective treatments are lacking, and early detection is crucial for disease prevention. This study aimed to explore serum biomarkers of occupational coal workers' pneumoconiosis (CWP) by high-throughput metabolomics, combining with machine learning strategy for precision screening. A case-control study was conducted in Beijing, China, involving 150 pneumoconiosis patients with different stages and 120 healthy controls. Metabolomics found a total of 68 differential metabolites between the CWP group and the control group. Then, potential biomarkers of CWP were screened from these differential metabolites by three machine learning methods. The four most important differential metabolites were identified as benzamide, terazosin, propylparaben and N-methyl-2-pyrrolidone. However, after adjusting for the influence of confounding factors, including age, smoking, drinking and chronic diseases, only one metabolite, propylparaben, was significantly correlated with CWP. The more severe CWP was, the higher the content of propylparaben in serum. Moreover, the receiver operating characteristic curve (ROC) of propylparaben showed good sensitivity and specificity as a biomarker of CWP. Therefore, it was demonstrated that the serum metabolite profiles in CWP patients changed significantly and that the serum metabolites represented by propylparaben were good biomarkers of CWP.
Keywords: biomarkers; case–control study; machine learning; metabolomics; pneumoconiosis.