Living systematic reviews

2. Combining human and machine effort

James Thomas, Anna Noel-Storr, Iain Marshall, Byron Wallace, Steven McDonald, Chris Mavergames, Paul Glasziou, Ian Shemilt, Anneliese Synnot, Tari Turner, Julian Elliott

Research output: Contribution to journalArticleResearchpeer-review

38 Citations (Scopus)

Abstract

New approaches to evidence synthesis, which use human effort and machine automation in mutually reinforcing ways, can enhance the feasibility and sustainability of living systematic reviews. Human effort is a scarce and valuable resource, required when automation is impossible or undesirable, and includes contributions from online communities ("crowds") as well as more conventional contributions from review authors and information specialists. Automation can assist with some systematic review tasks, including searching, eligibility assessment, identification and retrieval of full-text reports, extraction of data, and risk of bias assessment. Workflows can be developed in which human effort and machine automation can each enable the other to operate in more effective and efficient ways, offering substantial enhancement to the productivity of systematic reviews. This paper describes and discusses the potential-and limitations-of new ways of undertaking specific tasks in living systematic reviews, identifying areas where these human/machine "technologies" are already in use, and where further research and development is needed. While the context is living systematic reviews, many of these enabling technologies apply equally to standard approaches to systematic reviewing.

Original languageEnglish
Pages (from-to)31-37
Number of pages7
JournalJournal of Clinical Epidemiology
Volume91
DOIs
Publication statusPublished - Nov 2017

Keywords

  • Automation
  • Citizen science
  • Crowdsourcing
  • Machine learning
  • Systematic review
  • Text mining

Cite this

Thomas, James ; Noel-Storr, Anna ; Marshall, Iain ; Wallace, Byron ; McDonald, Steven ; Mavergames, Chris ; Glasziou, Paul ; Shemilt, Ian ; Synnot, Anneliese ; Turner, Tari ; Elliott, Julian. / Living systematic reviews : 2. Combining human and machine effort. In: Journal of Clinical Epidemiology. 2017 ; Vol. 91. pp. 31-37.
@article{ce18d4a6417b43c8861fe3f5c154761d,
title = "Living systematic reviews: 2. Combining human and machine effort",
abstract = "New approaches to evidence synthesis, which use human effort and machine automation in mutually reinforcing ways, can enhance the feasibility and sustainability of living systematic reviews. Human effort is a scarce and valuable resource, required when automation is impossible or undesirable, and includes contributions from online communities ({"}crowds{"}) as well as more conventional contributions from review authors and information specialists. Automation can assist with some systematic review tasks, including searching, eligibility assessment, identification and retrieval of full-text reports, extraction of data, and risk of bias assessment. Workflows can be developed in which human effort and machine automation can each enable the other to operate in more effective and efficient ways, offering substantial enhancement to the productivity of systematic reviews. This paper describes and discusses the potential-and limitations-of new ways of undertaking specific tasks in living systematic reviews, identifying areas where these human/machine {"}technologies{"} are already in use, and where further research and development is needed. While the context is living systematic reviews, many of these enabling technologies apply equally to standard approaches to systematic reviewing.",
keywords = "Automation, Citizen science, Crowdsourcing, Machine learning, Systematic review, Text mining",
author = "James Thomas and Anna Noel-Storr and Iain Marshall and Byron Wallace and Steven McDonald and Chris Mavergames and Paul Glasziou and Ian Shemilt and Anneliese Synnot and Tari Turner and Julian Elliott",
year = "2017",
month = "11",
doi = "10.1016/j.jclinepi.2017.08.011",
language = "English",
volume = "91",
pages = "31--37",
journal = "Journal of Clinical Epidemiology",
issn = "0895-4356",
publisher = "Elsevier",

}

Living systematic reviews : 2. Combining human and machine effort. / Thomas, James; Noel-Storr, Anna; Marshall, Iain; Wallace, Byron; McDonald, Steven; Mavergames, Chris; Glasziou, Paul; Shemilt, Ian; Synnot, Anneliese; Turner, Tari; Elliott, Julian.

In: Journal of Clinical Epidemiology, Vol. 91, 11.2017, p. 31-37.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Living systematic reviews

T2 - 2. Combining human and machine effort

AU - Thomas, James

AU - Noel-Storr, Anna

AU - Marshall, Iain

AU - Wallace, Byron

AU - McDonald, Steven

AU - Mavergames, Chris

AU - Glasziou, Paul

AU - Shemilt, Ian

AU - Synnot, Anneliese

AU - Turner, Tari

AU - Elliott, Julian

PY - 2017/11

Y1 - 2017/11

N2 - New approaches to evidence synthesis, which use human effort and machine automation in mutually reinforcing ways, can enhance the feasibility and sustainability of living systematic reviews. Human effort is a scarce and valuable resource, required when automation is impossible or undesirable, and includes contributions from online communities ("crowds") as well as more conventional contributions from review authors and information specialists. Automation can assist with some systematic review tasks, including searching, eligibility assessment, identification and retrieval of full-text reports, extraction of data, and risk of bias assessment. Workflows can be developed in which human effort and machine automation can each enable the other to operate in more effective and efficient ways, offering substantial enhancement to the productivity of systematic reviews. This paper describes and discusses the potential-and limitations-of new ways of undertaking specific tasks in living systematic reviews, identifying areas where these human/machine "technologies" are already in use, and where further research and development is needed. While the context is living systematic reviews, many of these enabling technologies apply equally to standard approaches to systematic reviewing.

AB - New approaches to evidence synthesis, which use human effort and machine automation in mutually reinforcing ways, can enhance the feasibility and sustainability of living systematic reviews. Human effort is a scarce and valuable resource, required when automation is impossible or undesirable, and includes contributions from online communities ("crowds") as well as more conventional contributions from review authors and information specialists. Automation can assist with some systematic review tasks, including searching, eligibility assessment, identification and retrieval of full-text reports, extraction of data, and risk of bias assessment. Workflows can be developed in which human effort and machine automation can each enable the other to operate in more effective and efficient ways, offering substantial enhancement to the productivity of systematic reviews. This paper describes and discusses the potential-and limitations-of new ways of undertaking specific tasks in living systematic reviews, identifying areas where these human/machine "technologies" are already in use, and where further research and development is needed. While the context is living systematic reviews, many of these enabling technologies apply equally to standard approaches to systematic reviewing.

KW - Automation

KW - Citizen science

KW - Crowdsourcing

KW - Machine learning

KW - Systematic review

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=85028965305&partnerID=8YFLogxK

U2 - 10.1016/j.jclinepi.2017.08.011

DO - 10.1016/j.jclinepi.2017.08.011

M3 - Article

VL - 91

SP - 31

EP - 37

JO - Journal of Clinical Epidemiology

JF - Journal of Clinical Epidemiology

SN - 0895-4356

ER -