A question of trust: can we build an evidence base to gain trust in systematic review automation technologies?
Top Cited Papers
Open Access
- 18 June 2019
- journal article
- review article
- Published by Springer Nature in Systematic Reviews
- Vol. 8 (1) , 1-8
Abstract
Although many aspects of systematic reviews use computational tools, systematic reviewers have been reluctant to adopt machine learning tools. We discuss that the potential reason for the slow adoption of machine learning tools into systematic reviews is multifactorial. We focus on the current absence of trust in automation and set-up challenges as major barriers to adoption. It is important that reviews produced using automation tools are considered non-inferior or superior to current practice. However, this standard will likely not be sufficient to lead to widespread adoption. As with many technologies, it is important that reviewers see “others” in the review community using automation tools. Adoption will also be slow if the automation tools are not compatible with workflows and tasks currently used to produce reviews. Many automation tools being developed for systematic reviews mimic classification problems. Therefore, the evidence that these automation tools are non-inferior or superior can be presented using methods similar to diagnostic test evaluations, i.e., precision and recall compared to a human reviewer. However, the assessment of automation tools does present unique challenges for investigators and systematic reviewers, including the need to clarify which metrics are of interest to the systematic review community and the unique documentation challenges for reproducible software experiments. We discuss adoption barriers with the goal of providing tool developers with guidance as to how to design and report such evaluations and for end users to assess their validity. Further, we discuss approaches to formatting and announcing publicly available datasets suitable for assessment of automation technologies and tools. Making these resources available will increase trust that tools are non-inferior or superior to current practice. Finally, we identify that, even with evidence that automation tools are non-inferior or superior to current practice, substantial set-up challenges remain for main stream integration of automation into the systematic review process.Keywords
This publication has 33 references indexed in Scilit:
- Vision for SLR tooling infrastructure: Prioritizing value-added requirementsInformation and Software Technology, 2017
- Reproducibility of studies on text mining for citation screening in systematic reviews: Evaluation and checklistJournal of Biomedical Informatics, 2017
- A primer on systematic reviews in toxicologyArchives of Toxicology, 2017
- A literature review on the levels of automation during the years. What are the different taxonomies that have been proposed?Applied Ergonomics, 2016
- Applicability and Feasibility of Systematic Review for Performing Evidence-Based Risk Assessment in Food and Feed SafetyCritical Reviews in Food Science and Nutrition, 2015
- Estimation of diagnostic test accuracy without full verification: a review of latent class methodsStatistics in Medicine, 2014
- A systematic review of interactive information retrieval evaluation studies, 1967–2006Journal of the American Society for Information Science and Technology, 2013
- Lessons from applying the systematic literature review process within the software engineering domainJournal of Systems and Software, 2007
- Insights into latent class analysis of diagnostic test performanceBiostatistics, 2006
- Replicating software engineering experiments: a poisoned chalice or the Holy GrailInformation and Software Technology, 2005