CoChat

Making progress with the automation of systematic reviews: principles of the International Collaboration for the Automation of Systematic Reviews (ICASR)

Open access

The DOI matches its Crossref record; 23 of the 24 references it cites were found in a registry or an index; 6 of the 20 sources its claims cite were checked for support.

Abstract

Systematic reviews (SR) are vital to health care, but have become complicated and time-consuming, due to the rapid expansion of evidence to be synthesised. Fortunately, many tasks of systematic reviews have the potential to be automated or may be assisted by automation. Recent advances in natural language processing, text mining and machine learning have produced new algorithms that can accurately mimic human endeavour in systematic review activity, faster and more cheaply. Automation tools need to be able to work together, to exchange data and results. Therefore, we initiated the International Collaboration for the Automation of Systematic Reviews (ICASR), to successfully put all the parts of automation of systematic review production together. The first meeting was held in Vienna in October 2015. We established a set of principles to enable tools to be developed and integrated into toolkits.This paper sets out the principles devised at that meeting, which cover the need for improvement in efficiency of SR tasks, automation across the spectrum of SR tasks, continuous improvement, adherence to high quality standards, flexibility of use and combining components, the need for a collaboration and varied skills, the desire for open source, shared code and evaluation, and a requirement for replicability through rigorous and open evaluation.Automation has a great potential to improve the speed of systematic reviews. Considerable work is already being done on many of the steps involved in a review. The 'Vienna Principles' set out in this paper aim to guide a more coordinated effort which will allow the integration of work by separate teams and build on the experience, code and evaluations done by the many teams working across the globe.

Overview

CoChat Summary

TL;DR

This paper reports the “Vienna Principles” from the first meeting of the International Collaboration for the Automation of Systematic Reviews (ICASR), arguing that systematic review tasks are amenable to automation and that tools should be interoperable, openly shared, and rigorously evaluated. It is a consensus/meeting report rather than an empirical evaluation of automation tools.

Key findings

  • The paper identifies four main systematic review tasks amenable to automation—retrieving evidence, evaluating studies, synthesising evidence, and publishing the review—which have been broken down into 15 distinct tasks; automation should cover all tasks from scoping reviews to dissemination.
  • It notes that most systematic reviews are outdated on publication (median age of 8 months since last search; Cochrane recommends the last search within 6 months), and that a typical systematic review takes 6 months to 2 years or more, while rapid reviews take around half the time.
  • The Vienna Principles comprise eight principles: improve every SR task; automate across the spectrum of SR tasks; continuously improve processes; adhere to high standards such as PRISMA and Cochrane MECIR; allow flexible combining of components; require collaboration across varied expertise; share code, evaluation data, and corpora, preferably open source; and evaluate all tools with replicable methods and reported data.
  • The first meeting showcased tools including Covidence, RevMan HAL, eSuRFr, Rayyan, EPPI-Reviewer, Evidence Pipeline, Systematic Review Accelerator, and Systematic Review Toolbox; ICASR is developing a repository of test data sets and testing results.

Methods

  • Before the meeting, a focused literature search was conducted to identify potential topics for principles; these were incorporated into a discussion document circulated in advance.
  • The first meeting was by invitation in Vienna in October 2015, attended by 24 people, ran for a full day adjacent to the Cochrane Colloquium, and had no sponsor; topics were presented, small groups self-selected by expertise refined principles and drafted wording, and the wider group debated and agreed on them.
  • Subsequent ICASR meetings were held in Philadelphia in 2016 and London in 2017, focusing on technical aspects of testing automation tools, test data sets, and interoperability; those results are reported elsewhere.

Limitations

  • The paper states that the principles do not address some technical aspects: the need to manually review and manipulate results between tools, audit trails of tools used and data changes, handling large datasets, and use of web-based/stand-alone versions or large commercial data services.
  • The paper states that the principles do not address integration of systematic reviews into knowledge translation, such as GRADE assessment and automated production of clinical practice guidelines.
  • The paper states tensions remain between commercial and non-commercial development, individual academic credit and the common good, and different approaches to the overall problem; the principles attempt to address but do not completely resolve these.
  • Evident from the text: this is a consensus/meeting report based on one initial meeting and subsequent discussions, with no empirical evaluation of automation tool effectiveness or impact reported here.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1186/s13643-018-0740-7

Cites

23 of 23 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Automatable systematic review processes and example automation tools
Fig. 1 Automatable systematic review processes and example automation toolsCC BY · PubMed Central

Verification

Claims the paper makes

5 Valid · 0 Not valid · 9 Not checked · 12 Own results and interpretations

5 more claims

Create a free account to see all 26 claims and to verify the 14 references still open.

See all claims — free account
  • It may state two separate claims as one. 8
  • Probably not a substantial claim. 12

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

1 more claim about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Citations

Cites

Show all 23 references

Research works printed but not linked: 2

  1. Cockburn A. Using both incremental and iterative development. STSC CrossTalk. 2008;21(5):27–30.
  2. Fielding RT. Architectural styles and the design of network-based software architectures (dissertation). University of California, Irvine. https://www.ics.uci.edu/~fielding/pubs/dissertation/top.htm . Accessed 18 Apr 2017.

Cited by

See all 203

Metadata

Authors
On behalf of the founding members of the ICASR group, Beller, E., Clark, J., Tsafnat, G., Adams, C., Diehl, H., Lund, H., Ouzzani, M., Thayer, K., Thomas, J., Turner, T., Xia, J., Robinson, K., & Glasziou, P.
Affiliations
  • Bond University (AU)
  • University of Nottingham (GB)
  • Western Norway University of Applied Sciences (NO)
  • Pennsylvania State University (US)
  • University College London (GB)
Corresponding author
Beller, Elaine
Venue
Systematic Reviews
Published
2018-05-19
Volume
7
Issue
1
Pages
77-77
ISSN
2046-4053 (ISSN-L)
OpenAlex
W2805303998
Cited by
191
References
24
Citations by year
2026: 14 · 2025: 17 · 2024: 30 · 2023: 34 · 2022: 17 · 2021: 26 · 2020: 35 · 2019: 15 · 2018: 3
FWCI
3.89
Type
journal article
Language
en
Open access
Licence
  • cc-by
  • creativecommons.org/licenses/by/4.0/ (tdm)
Locations
  • Systematic Reviews (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, other-oa)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • Repository@Nottingham (University of Nottingham) (publishedVersion, cc-by)
  • Monash University Research Portal (Monash University) (submittedVersion, other-oa)
  • Repository@Nottingham (University of Nottingham) (submittedVersion, cc-by)
  • Bond University Research Portal (Bond University) (submittedVersion, cc-by)
  • NORA - Norwegian Open Research Archives (submittedVersion, cc-by)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
  • Nottingham ePrints (University of Nottingham) (submittedVersion, cc-by)
  • UCL Discovery (University College London) (submittedVersion)
  • Figshare (submittedVersion, cc-by)
Topics
  • Social Sciences › Decision Sciences › Statistics, Probability and Uncertainty › Meta-analysis and systematic reviews
  • Social Sciences › General Social Sciences › Computational and Text Analysis Methods
  • Health Sciences › Medicine › Health Informatics › Biomedical Text Mining and Ontologies
Keywords
systematic review automation, natural language processing, text mining, machine learning, tool integration, open source software, open evaluation, replicability, research collaboration, evidence synthesis
MeSH terms
Data Accuracy, Machine Learning, Systematic Reviews as Topic, Algorithms, Automation, Cooperative Behavior, Humans, Natural Language Processing, Data Mining

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Making progress with the automation of systematic reviews: principles of the International Collaboration for the Automation of Systematic Reviews (ICASR). https://app.cochat.ai/papers/10.1186/s13643-018-0740-7
The paper
On behalf of the founding members of the ICASR group, Beller, E., Clark, J., Tsafnat, G., Adams, C., Diehl, H., Lund, H., Ouzzani, M., Thayer, K., Thomas, J., Turner, T., Xia, J., Robinson, K., & Glasziou, P. (2018). Making progress with the automation of systematic reviews: principles of the International Collaboration for the Automation of Systematic Reviews (ICASR). Systematic Reviews. https://doi.org/10.1186/s13643-018-0740-7

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.