Oral squamous cell carcinoma (OSCC) has the highest incidence among all the oral neoplasms, thus widely affects people’s life. Genetics has an important effect on the OSCC’s etiopathogenesis. However, OSCC’s molecular mechanism has not been completely investigated yet. We propose a novel method to detect genes that are associated to OSCC, where mean difference and variance difference are compared between cases and controls. This method can discover knowledge from gene data by processing multi-format information and can identify disease-associated genes for many complex human diseases, like melanoma, head and neck squamous cell carcinoma (HNSCC), lung adenocarcinoma, and serous ovarian cancer. Based on Gene Expression Omnibus, two OSCC datasets are obtained, and gene probes are then identified, typed as differentially variable (DV) and differentially expressed (DE), with numbers of 456 and 2375, respectively. Those probes can be further discriminated as DE-only, DV-only, and then DE-and-DV probes, with numbers of 2193, 274, and 182, respectively. Kyoto Encyclopedia of Genes and Genomes (KEGG) pathway enrichment analysis is performed to separately analyze the genes that are relevant to these three kinds of specific probes, as per the DAVID functional analysis, implying they have diverse functions in OSCC. In the future, our novel method also can be applied to investigate other complex human diseases’ genetic risk factors.