Identifying potential circulating miRNA biomarkers for the diagnosis and prediction of ovarian cancer using machine-learning approach: application of Boruta

Introduction In gynecologic oncology, ovarian cancer is a great clinical challenge. Because of the lack typical symptoms and effective biomarkers for noninvasive screening, most patients develop advanced-stage by time diagnosis. MicroRNAs (miRNAs) are type non-coding RNA molecule that has been linked to human cancers. Specifying diagnostic determine non-cancer samples difficult. Methods By using Boruta, novel random forest-based feature selection in machine-learning techniques, we aimed identify associated with cancerous from Gene Expression Omnibus (GEO) database: GSE106817. this study, used two independent GEO data sets as external validation, including GSE113486 GSE113740. We utilized five state-of-the-art algorithms classification: logistic regression, forest, decision trees, artificial neural networks, XGBoost. Results Four models discovered had an AUC 100%, three GSE113740 over 94%, four 94%. identified 10 miRNAs distinguish cases normal controls: hsa-miR-1290, hsa-miR-1233-5p, hsa-miR-1914-5p, hsa-miR-1469, hsa-miR-4675, hsa-miR-1228-5p, hsa-miR-3184-5p, hsa-miR-6784-5p, hsa-miR-6800-5p, hsa-miR-5100. Our findings suggest could be possible intervention.