Women’s health is a growing public health crisis. 1 out of 10 women will experience some type of chronic gynecological disease in their lifetime, yet confirmative diagnosis can take up to 5-7 years, due to the dismissal of the symptoms, lack of access to adequate resources, and social stigma. MicroRNAs are segments of non-coding RNA that play a vital role in gene expression and have been shown as a noninvasive diagnostic candidate detected in bodily fluids. The goal of this study is to evaluate serum miRNA expression levels to predict gynecologic conditions, specifically ovarian cancer, breast cancer, and endometriosis. A predictive machine-learning model will be trained on public miRNA datasets to generate unique miRNA profiles for each condition. Significant miRNAs in the predictive model willbe extracted through feature selection techniques and inserted in pathway modeling software to determine the pathways most affected in each disease. By identifying the unique and shared pathology of ovarian breast cancer, and endometriosis, miRNA prevalence can be used as a noninvasive diagnostic tool, potentially reduce waiting periods, and guide future therapeutic development.