Viability of machine learning to reduce workload in systematic review\n screenings in the health sciences: a working paper

Abstract

Systematic reviews, which summarize and synthesize all the current research\nin a specific topic, are a crucial component to academia. They are especially\nimportant in the biomedical and health sciences, where they synthesize the\nstate of medical evidence and conclude the best course of action for various\ndiseases, pathologies, and treatments. Due to the immense amount of literature\nthat exists, as well as the output rate of research, reviewing abstracts can be\na laborious process. Automation may be able to significantly reduce this\nworkload. Of course, such classifications are not easily automated due to the\npeculiar nature of written language. Machine learning may be able to help. This\npaper explored the viability and effectiveness of using machine learning\nmodelling to classify abstracts according to specific exclusion/inclusion\ncriteria, as would be done in the first stage of a systematic review. The\nspecific task was performing the classification of deciding whether an abstract\nis a randomized control trial (RCT) or not, a very common classification made\nin systematic reviews in the healthcare field. Random training/testing splits\nof an n=2042 dataset of labelled abstracts were repeatedly created (1000 times\nin total), with a model trained and tested on each of these instances. A Bayes\nclassifier as well as an SVM classifier were used, and compared to non-machine\nlearning, simplistic approaches to textual classification. An SVM classifier\nwas seen to be highly effective, yielding a 90% accuracy, as well as an F1\nscore of 0.84, and yielded a potential workload reduction of 70%. This shows\nthat machine learning has the potential to significantly revolutionize the\nabstract screening process in healthcare systematic reviews.\n

Ähnliche Arbeiten