First Steps Towards a Risk of Bias Corpus of Randomized Controlled Trials

Risk of bias (RoB) assessment of randomized clinical trials (RCTs) is vital to conducting systematic reviews. Manual RoB assessment for hundreds of RCTs is a cognitively demanding, lengthy process and is prone to subjective judgment. Supervised machine learning (ML) can help to accelerate this proce...

Full description

Saved in:
Bibliographic Details
Published inStudies in health technology and informatics Vol. 302; p. 586
Main Authors Dhrangadhariya, Anjani, Hilfiker, Roger, Sattelmayer, Martin, Giacomino, Katia, Caliesch, Rahel, Elsig, Simone, Naderi, Nona, Müller, Henning
Format Journal Article
LanguageEnglish
Published Netherlands 18.05.2023
Subjects
Bias
Judgment
Randomized Controlled Trials as Topic
Research Design
Risk Assessment
annotation
risk of bias
corpus
automation
systematic reviews
Online AccessGet more information

Cover

More Information
Summary:Risk of bias (RoB) assessment of randomized clinical trials (RCTs) is vital to conducting systematic reviews. Manual RoB assessment for hundreds of RCTs is a cognitively demanding, lengthy process and is prone to subjective judgment. Supervised machine learning (ML) can help to accelerate this process but requires a hand-labelled corpus. There are currently no RoB annotation guidelines for randomized clinical trials or annotated corpora. In this pilot project, we test the practicality of directly using the revised Cochrane RoB 2.0 guidelines for developing an RoB annotated corpus using a novel multi-level annotation scheme. We report inter-annotator agreement among four annotators who used Cochrane RoB 2.0 guidelines. The agreement ranges between 0% for some bias classes and 76% for others. Finally, we discuss the shortcomings of this direct translation of annotation guidelines and scheme and suggest approaches to improve them to obtain an RoB annotated corpus suitable for ML.
ISSN:1879-8365
DOI:10.3233/SHTI230210