Exploring the diagnostic markers of essential tremor: A study based on machine learning algorithms.

Essential tremor (ET) is a common neurological disorder with a difficult clinical diagnosis, primarily due to the lack of relevant biomarkers. The current study aims to identify possible biomarkers for ET by screening miRNAs using machine learning algorithms. In this investigation, public datasets and our own datasets were used to examine the ET disorder. The ET datasets originated from public sources. To generate our own dataset, high-throughput sequencing analyses were performed on ET and control samples from the First People's Hospital of Yunnan Province. Functional enrichment analysis was employed to identify the potential function of differentially expressed genes (DEGs). Using datasets from the Gene Expression Omnibus database, Lasso regression analysis and support vector machine recursive feature elimination were used to screen potential diagnostic genes for ET. To identify the genes responsible for the final diagnosis, area under the curves (AUCs) of the receiver operating characteristic was examined. Finally, an ssGSEA representing an ET immune landscape was created. The sample exhibited expression profiles that corresponded with six genes in the public database. Three diagnostic genes were discovered with AUCs >0.7 that can distinguish ET from normal data: APOE, SENP6, and ZNF148. Single-gene GSEA indicated that these diagnostic genes were closely associated with the cholinergic, GABAergic, and dopaminergic synapse networks. The immune microenvironment of ET was also affected by these diagnostic genes. According to the findings, these three DEGs (, , and ) may successfully differentiate between samples from ET patients and normal controls, serving as a helpful diagnostic tool. This effort provided a theoretical foundation for elucidating the pathogenesis of ET and raised hopes of overcoming the diagnostic difficulty of ET clinically.