A pilot study examined the diagnostic accuracy of four machine learning algorithms—support vector machine (SVM), random forest (RF), artificial neural network (ANN), and logistic regression (LR)—in differentiating ovarian cancer from benign masses. Data from 50 patients with suspected epithelial ovarian cancer (group A) or benign tumor (group B) were tested using multimodal parameters. Statistical analysis was performed in STATA version 14.0. All algorithms achieved high accuracy, with the random forest (RF) having a maximum AUROC of 0.92 and an accuracy of 85.87%. The support vector machine (SVM) had an accuracy of 83.05%. The machine learning approach predicts malignancy with significantly high accuracy, similar to other studies in the field. ML algorithms detect ovarian cancers with high accuracy, but a large-scale prospective study on large datasets is needed before clinical use.