Abstract
The use of microRNAs as biomarkers has been proposed for many diseases, including the diagnosis of melanoma. Although hundreds of microRNAs have been identified as differentially expressed in melanomas as compared to benign melanocytic lesions, a limited consensus has been achieved across studies, constraining the effective use of these potentially useful markers. In this study, we applied a machine learning-based pipeline to a dataset consisting of genetic features, clinical features, and next-generation microRNA sequencing from micro-dissected formalin-fixed paraffin embedded melanomas and their adjacent benign precursor nevi. We identified patient age and tumor cellularity as variables that frequently confound the measured expression of potentially diagnostic microRNAs. By employing the ratios of microRNAs that were either enriched or depleted in melanoma compared to the nevi as a normalization strategy, we developed a model that classified all the available published cohorts with an area under the receiver operating characteristic curve of 0.98. External validation on an independent cohort classified lesions with 81% sensitivity and 88% specificity and was uninfluenced by the tumor content of the sample or patient age.