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

On behalf of the founding members of the ICASR group

Research output: Contribution to journalComment/debate

9 Citations (Scopus)

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.

Original languageEnglish
Article number77
JournalSystematic Reviews
Volume7
Issue number1
DOIs
Publication statusPublished - 19 May 2018

Fingerprint

Automation
Natural Language Processing
Data Mining
Delivery of Health Care

Keywords

  • Automation
  • Collaboration
  • Systematic review

ASJC Scopus subject areas

  • Medicine (miscellaneous)

Cite this

Making progress with the automation of systematic reviews : Principles of the International Collaboration for the Automation of Systematic Reviews (ICASR). / On behalf of the founding members of the ICASR group.

In: Systematic Reviews, Vol. 7, No. 1, 77, 19.05.2018.

Research output: Contribution to journalComment/debate

@article{18b68ea1715e42b2870d2fa046853b96,
title = "Making progress with the automation of systematic reviews: Principles of the International Collaboration for the Automation of Systematic Reviews (ICASR)",
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.",
keywords = "Automation, Collaboration, Systematic review",
author = "{On behalf of the founding members of the ICASR group} and Elaine Beller and Justin Clark and Guy Tsafnat and Clive Adams and Heinz Diehl and Hans Lund and Mourad Ouzzani and Kristina Thayer and James Thomas and Tari Turner and Jun Xia and Karen Robinson and Paul Glasziou and Olga Ahtirschi and Robin Christensen and Julian Elliott and Sergio Graziosi and Joel Kuiper and Rasmus Moustgaard and Annette O'Connor and Jacob Riis and Karla Soares-Weiser and Camilo Vergara and Ida Wedel-Heinen",
year = "2018",
month = "5",
day = "19",
doi = "10.1186/s13643-018-0740-7",
language = "English",
volume = "7",
journal = "Systematic Reviews",
issn = "2046-4053",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Making progress with the automation of systematic reviews

T2 - Principles of the International Collaboration for the Automation of Systematic Reviews (ICASR)

AU - On behalf of the founding members of the ICASR group

AU - Beller, Elaine

AU - Clark, Justin

AU - Tsafnat, Guy

AU - Adams, Clive

AU - Diehl, Heinz

AU - Lund, Hans

AU - Ouzzani, Mourad

AU - Thayer, Kristina

AU - Thomas, James

AU - Turner, Tari

AU - Xia, Jun

AU - Robinson, Karen

AU - Glasziou, Paul

AU - Ahtirschi, Olga

AU - Christensen, Robin

AU - Elliott, Julian

AU - Graziosi, Sergio

AU - Kuiper, Joel

AU - Moustgaard, Rasmus

AU - O'Connor, Annette

AU - Riis, Jacob

AU - Soares-Weiser, Karla

AU - Vergara, Camilo

AU - Wedel-Heinen, Ida

PY - 2018/5/19

Y1 - 2018/5/19

N2 - 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.

AB - 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.

KW - Automation

KW - Collaboration

KW - Systematic review

UR - http://www.scopus.com/inward/record.url?scp=85047153123&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047153123&partnerID=8YFLogxK

U2 - 10.1186/s13643-018-0740-7

DO - 10.1186/s13643-018-0740-7

M3 - Comment/debate

C2 - 29778096

AN - SCOPUS:85047153123

VL - 7

JO - Systematic Reviews

JF - Systematic Reviews

SN - 2046-4053

IS - 1

M1 - 77

ER -