Abstract
OBJECTIVE: This study aims to identify potential lipid biomarkers and metabolic pathways associated with oral cancer (OC). Then to establish and evaluate disease classification models capable of distinguishing OC patients from healthy controls. METHODS: A total of 41 OC patients and 41 controls were recruited from a hospital in Southeast China to examine the serum lipidomics by Ultra-high Performance Liquid Chromatography Q Exactive Mass Spectrometry (UHPLC-QE-MS). RESULTS: The total serum lipid profile showed that triglycerides accounted for the highest proportion of total metabolites, reaching 35.90% of the total. A total of 74 different metabolites were screened (12 up-regulated and 62 down-regulated), mainly enriched in the glycerophospholipid metabolism pathway. The three most significant changes in lipid metabolites were phosphatidylcholine (PC(18:3e/17:2)), acylcarnitine (ACar(14:2)), and glucuronosyldiacylglycerol (GlcADG(14:1/14:1)). The disease classification model, constructed using a KNN algorithm with 13 metabolites selected through LASSO screening, achieved the best performance, with an AUC of 0.978 (0.955-1.000). CONCLUSION: Lipid metabolic biomarkers identified in this study exhibit potential as candidate biomarkers for OC diagnosis. Further validation through prospective studies is required to confirm their clinical utility in early detection.