Advanced analytics for the automation of medical systematic reviews
Abstract
While systematic reviews (SRs) are positioned as an essential element of modern evidence-based medical practice, the creation and update of these reviews is resource intensive. In this research, we propose to leverage advanced analytics techniques for automatically classifying articles for inclusion and exclusion for systematic reviews. Specifically, we used soft-margin polynomial Support Vector Machine (SVM) as a classifier, exploited Unified Medical Language Systems (UMLS) for medical terms extraction, and examined various techniques to resolve the class imbalance issue. Through an empirical study, we demonstrated that soft-margin polynomial SVM achieves better classification performance than the existing algorithms used in current research, and the performance of the classifier can be further improved by using UMLS to identify medical terms in articles and applying re-sampling methods to resolve the class imbalance issue.