English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Systematic reviews, which summarize and synthesize all the current researchin a specific topic, are a crucial component to academia. They are especiallyimportant in the biomedical and health sciences, where they synthesize thestate of medical evidence and conclude the best course of action for variousdiseases, pathologies, and treatments. Due to the immense amount of literaturethat exists, as well as the output rate of research, reviewing abstracts can bea laborious process. Automation may be able to significantly reduce thisworkload. Of course, such classifications are not easily automated due to thepeculiar nature of written language. Machine learning may be able to help. Thispaper explored the viability and effectiveness of using machine learningmodelling to classify abstracts according to specific exclusion/inclusioncriteria, as would be done in the first stage of a systematic review. Thespecific task was performing the classification of deciding whether an abstractis a randomized control trial (RCT) or not, a very common classification madein systematic reviews in the healthcare field. Random training/testing splitsof an n=2042 dataset of labelled abstracts were repeatedly created (1000 timesin total), with a model trained and tested on each of these instances. A Bayesclassifier as well as an SVM classifier were used, and compared to non-machinelearning, simplistic approaches to textual classification. An SVM classifierwas seen to be highly effective, yielding a 90% accuracy, as well as an F1score of 0.84, and yielded a potential workload reduction of 70%. This showsthat machine learning has the potential to significantly revolutionize theabstract screening process in healthcare systematic reviews.

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