This study aims to develop a novel saliva-based microRNA (miRNA) signature for the early diagnosis and prediction of oral cancer (OC) and oral potentially malignant disorders (OPMD). The researchers utilized The Cancer Genome Atlas (TCGA) miRNA sequencing data and small RNA sequencing data from saliva samples to identify differentially expressed miRNAs. Eight miRNAs (miR-7-5p, miR-10b-5p, miR-182-5p, miR-215-5p, miR-431-5p, miR-486-3p, miR-3614-5p, and miR-4707-3p) were identified and validated in saliva samples from OC, OPMD, and control groups using quantitative real-time PCR. The eight-miRNA signature showed high diagnostic efficiency, with an area under the curve (AUC) of 0.954, sensitivity of 86%, specificity of 90%, positive predictive value (PPV) of 87.8%, and negative predictive value (NPV) of 88.5%. Additionally, a risk probability score was developed to predict the presence or risk of OC in OPMD patients, with a significant difference in scores between high-grade dysplasia and controls. The study highlights the potential of using salivary miRNAs as a non-invasive biomarker for early detection and management of OC and OPMD.This study aims to develop a novel saliva-based microRNA (miRNA) signature for the early diagnosis and prediction of oral cancer (OC) and oral potentially malignant disorders (OPMD). The researchers utilized The Cancer Genome Atlas (TCGA) miRNA sequencing data and small RNA sequencing data from saliva samples to identify differentially expressed miRNAs. Eight miRNAs (miR-7-5p, miR-10b-5p, miR-182-5p, miR-215-5p, miR-431-5p, miR-486-3p, miR-3614-5p, and miR-4707-3p) were identified and validated in saliva samples from OC, OPMD, and control groups using quantitative real-time PCR. The eight-miRNA signature showed high diagnostic efficiency, with an area under the curve (AUC) of 0.954, sensitivity of 86%, specificity of 90%, positive predictive value (PPV) of 87.8%, and negative predictive value (NPV) of 88.5%. Additionally, a risk probability score was developed to predict the presence or risk of OC in OPMD patients, with a significant difference in scores between high-grade dysplasia and controls. The study highlights the potential of using salivary miRNAs as a non-invasive biomarker for early detection and management of OC and OPMD.