Predicting the Activity of Oral Lichen Planus with Glycolysis-related Molecules:A Scikit-learn-based Function  

作　　者：Yan YANG Pei HU Su-rong CHEN Wei-wei WU Pan CHEN Shi-wen WANG Jing-zhi MA Jing-yu HU 

机构地区：[1]Department of Stomatology,Tongji Hospital,Tongji Medical College,Huazhong University of Science and Technology,Wuhan 430030,China [2]School of Stomatology,Tongji Medical College,Huazhong University of Science and Technology,Wuhan 430030,China

出　　处：《Current Medical Science》2023年第3期602-608,共7页当代医学科学（英文）

基　　金：This work was supported by grants from the National Natural Science Foundation of China(No.62171193);the Natural Science Foundation of Hubei Province(No.2021CFB399);the Foundation of Health Commission of Hubei Province(No.WJ2021M125);the Key Research and Development Project of Hubei Province of China(No.2022BCA033).

摘　　要：Objective Oral lichen planus(OLP)is one of the most common oral mucosa diseases,and is mainly mediated by T lymphocytes.The metabolic reprogramming of activated T cells has been shown to transform from oxidative phosphorylation to aerobic glycolysis.The present study investigated the serum levels of glycolysis-related molecules(lactate dehydrogenase,LDH;pyruvic acid,PA;lactic acid,LAC)in OLP,and the correlation with OLP activity was assessed using the reticular,atrophic and erosive lesion(RAE)scoring system.Methods Univariate and multivariate linear regression functions based on scikit-learn were designed to predict the RAE scores in OLP patients,and the performance of these two machine learning functions was compared.Results The results revealed that the serum levels of PA and LAC were upregulated in erosive OLP(EOLP)patients,when compared to healthy volunteers.Furthermore,the LDH and LAC levels were significantly higher in the EOLP group than in the nonerosive OLP(NEOLP)group.All glycolysis-related molecules were positively correlated to the RAE scores.Among these,LAC had a strong correlation.The univariate function that involved the LAC level and the multivariate function that involved all glycolysis-related molecules presented comparable prediction accuracy and stability,but the latter was more time-consuming.Conclusion It can be concluded that the serum LAC level can be a user-friendly biomarker to monitor the OLP activity,based on the univariate function developed in the present study.The intervention of the glycolytic pathway may provide a potential therapeutic strategy.

关 键 词：oral lichen planus GLYCOLYSIS lactic acid linear regression machine learning 

分 类 号：R78[医药卫生—口腔医学]