Neural language models for text classification in evidence-based medicine

TL;DR

This paper demonstrates that neural language models, particularly XLNet, significantly improve the accuracy of classifying scientific articles in evidence-based medicine, aiding clinicians in managing the overwhelming volume of COVID-19 research.

Contribution

It introduces an application of neural language models to automate and enhance the classification of medical literature for evidence-based medicine.

Findings

XLNet achieves a 93% improvement in F1-score over previous methods.

The approach reduces manual curation time for COVID-19 research articles.

Neural language models can effectively support evidence synthesis in medical research.

Abstract

The COVID-19 has brought about a significant challenge to the whole of humanity, but with a special burden upon the medical community. Clinicians must keep updated continuously about symptoms, diagnoses, and effectiveness of emergent treatments under a never-ending flood of scientific literature. In this context, the role of evidence-based medicine (EBM) for curating the most substantial evidence to support public health and clinical practice turns essential but is being challenged as never before due to the high volume of research articles published and pre-prints posted daily. Artificial Intelligence can have a crucial role in this situation. In this article, we report the results of an applied research project to classify scientific articles to support Epistemonikos, one of the most active foundations worldwide conducting EBM. We test several methods, and the best one, based on the XLNet neural language model, improves the current approach by 93\% on average F1-score, saving valuable time from physicians who volunteer to curate COVID-19 research articles manually.