Search

Background: The reliable and usable (semi)automation of data extraction can support the field of systematic review by reducing the workload required to gather information about the conduct and results of the included studies. This living systematic review examines published approaches for data extraction from reports of clinical studies. Methods: We systematically and continually search PubMed, ACL Anthology, arXiv, OpenAlex via EPPI-Reviewer, and the dblp computer science bibliography. Full text screening and data extraction are conducted within an open-source living systematic review application created for the purpose of this review. This living review update includes publications up to December 2022 and OpenAlex content up to March 2023. Results: 76 publications are included in this review. Of these, 64 (84%) of the publications addressed extraction of data from abstracts, while 19 (25%) used full texts. A total of 71 (93%) publications developed classifiers for randomised controlled trials. Over 30 entities were extracted, with PICOs (population, intervention, comparator, outcome) being the most frequently extracted. Data are available from 25 (33%), and code from 30 (39%) publications. Six (8%) implemented publicly available tools Conclusions: This living systematic review presents an overview of (semi)automated data-extraction literature of interest to different types of literature review. We identified a broad evidence base of publications describing data extraction for interventional reviews and a small number of publications extracting epidemiological or diagnostic accuracy data. Between review updates, trends for sharing data and code increased strongly: in the base-review, data and code were available for 13 and 19% respectively, these numbers increased to 78 and 87% within the 23 new publications. Compared with the base-review, we observed another research trend, away from straightforward data extraction and towards additionally extracting relations between entities or automatic text summarisation. With this living review we aim to review the literature continually.

Background: The COVID-19 pandemic has caused considerable morbidity, mortality and disruption to people’s lives around the world. There are concerns that rates of suicide and suicidal behaviour may rise during and in its aftermath. Our living systematic review synthesises findings from emerging literature on incidence and prevalence of suicidal behaviour as well as suicide prevention efforts in relation to COVID-19, with this iteration synthesising relevant evidence up to 19th October 2020. Method: Automated daily searches feed into a web-based database with screening and data extraction functionalities. Eligibility criteria include incidence/prevalence of suicidal behaviour, exposure-outcome relationships and effects of interventions in relation to the COVID-19 pandemic. Outcomes of interest are suicide, self-harm or attempted suicide and suicidal thoughts. No restrictions are placed on language or study type, except for single-person case reports. We exclude one-off cross-sectional studies without either pre-pandemic measures or comparisons of COVID-19 positive vs. unaffected individuals. Results: Searches identified 6,226 articles. Seventy-eight articles met our inclusion criteria. We identified a further 64 relevant cross-sectional studies that did not meet our revised inclusion criteria. Thirty-four articles were not peer-reviewed (e.g. research letters, pre-prints). All articles were based on observational studies. There was no consistent evidence of a rise in suicide but many studies noted adverse economic effects were evolving. There was evidence of a rise in community distress, fall in hospital presentation for suicidal behaviour and early evidence of an increased frequency of suicidal thoughts in those who had become infected with COVID-19. Conclusions: Research evidence of the impact of COVID-19 on suicidal behaviour is accumulating rapidly. This living review provides a regular synthesis of the most up-to-date research evidence to guide public health and clinical policy to mitigate the impact of COVID-19 on suicide risk as the longer term impacts of the pandemic on suicide risk are researched.

Background: The reliable and usable (semi)automation of data extraction can support the field of systematic review by reducing the workload required to gather information about the conduct and results of the included studies. This living systematic review examines published approaches for data extraction from reports of clinical studies. Methods: We systematically and continually search MEDLINE, Institute of Electrical and Electronics Engineers (IEEE), arXiv, and the dblp computer science bibliography databases. Full text screening and data extraction are conducted within an open-source living systematic review application created for the purpose of this review. This iteration of the living review includes publications up to a cut-off date of 22 April 2020. Results: In total, 53 publications are included in this version of our review. Of these, 41 (77%) of the publications addressed extraction of data from abstracts, while 14 (26%) used full texts. A total of 48 (90%) publications developed and evaluated classifiers that used randomised controlled trials as the main target texts. Over 30 entities were extracted, with PICOs (population, intervention, comparator, outcome) being the most frequently extracted. A description of their datasets was provided by 49 publications (94%), but only seven (13%) made the data publicly available. Code was made available by 10 (19%) publications, and five (9%) implemented publicly available tools. Conclusions: This living systematic review presents an overview of (semi)automated data-extraction literature of interest to different types of systematic review. We identified a broad evidence base of publications describing data extraction for interventional reviews and a small number of publications extracting epidemiological or diagnostic accuracy data. The lack of publicly available gold-standard data for evaluation, and lack of application thereof, makes it difficult to draw conclusions on which is the best-performing system for each data extraction target. With this living review we aim to review the literature continually.

Background: The COVID-19 pandemic has caused morbidity and mortality, as well as, widespread disruption to people’s lives and livelihoods around the world. Given the health and economic threats posed by the pandemic to the global community, there are concerns that rates of suicide and suicidal behaviour may rise during and in its aftermath. Our living systematic review (LSR) focuses on suicide prevention in relation to COVID-19, with this iteration synthesising relevant evidence up to June 7th 2020. Method: Automated daily searches feed into a web-based database with screening and data extraction functionalities. Eligibility criteria include incidence/prevalence of suicidal behaviour, exposure-outcome relationships and effects of interventions in relation to the COVID-19 pandemic. Outcomes of interest are suicide, self-harm or attempted suicide and suicidal thoughts. No restrictions are placed on language or study type, except for single-person case reports. Results: Searches identified 2070 articles, 29 (28 studies) met our inclusion criteria, of which 14 articles were research letters or pre-prints awaiting peer review. All articles reported observational data: 12 cross-sectional; eight case series; five modelling; and three service utilisation studies. No studies reported on changes in rates of suicidal behaviour. Case series were largely drawn from news reporting in low/middle income countries and factors associated with suicide included fear of infection, social isolation and economic concerns. Conclusions: A marked improvement in the quality of design, methods, and reporting in future studies is needed. There is thus far no clear evidence of an increase in suicide, self-harm, suicidal behaviour, or suicidal thoughts associated with the pandemic. However, suicide data are challenging to collect in real time and economic effects are evolving. Our LSR will provide a regular synthesis of the most up-to-date research evidence to guide public health and clinical policy to mitigate the impact of COVID-19 on suicide. PROSPERO registration: CRD42020183326 01/05/2020

Background: Researchers in evidence-based medicine cannot keep up with the amounts of both old and newly published primary research articles. Support for the early stages of the systematic review process – searching and screening studies for eligibility – is necessary because it is currently impossible to search for relevant research with precision. Better automated data extraction may not only facilitate the stage of review traditionally labelled ‘data extraction’, but also change earlier phases of the review process by making it possible to identify relevant research. Exponential improvements in computational processing speed and data storage are fostering the development of data mining models and algorithms. This, in combination with quicker pathways to publication, led to a large landscape of tools and methods for data mining and extraction. Objective: To review published methods and tools for data extraction to (semi)automate the systematic reviewing process. Methods: We propose to conduct a living review. With this methodology we aim to do constant evidence surveillance, bi-monthly search updates, as well as review updates every 6 months if new evidence permits it. In a cross-sectional analysis we will extract methodological characteristics and assess the quality of reporting in our included papers. Conclusions: We aim to increase transparency in the reporting and assessment of automation technologies to the benefit of data scientists, systematic reviewers and funders of health research. This living review will help to reduce duplicate efforts by data scientists who develop data mining methods. It will also serve to inform systematic reviewers about possibilities to support their data extraction.

Background: The reliable and usable (semi)automation of data extraction can support the field of systematic review by reducing the workload required to gather information about the conduct and results of the included studies. This living systematic review examines published approaches for data extraction from reports of clinical studies. Methods: We systematically and continually search PubMed, ACL Anthology, arXiv, OpenAlex via EPPI-Reviewer, and the dblp computer science bibliography. Full text screening and data extraction are conducted within an open-source living systematic review application created for the purpose of this review. This living review update includes publications up to December 2022 and OpenAlex content up to March 2023. Results: 76 publications are included in this review. Of these, 64 (84%) of the publications addressed extraction of data from abstracts, while 19 (25%) used full texts. A total of 71 (93%) publications developed classifiers for randomised controlled trials. Over 30 entities were extracted, with PICOs (population, intervention, comparator, outcome) being the most frequently extracted. Data are available from 25 (33%), and code from 30 (39%) publications. Six (8%) implemented publicly available tools Conclusions: This living systematic review presents an overview of (semi)automated data-extraction literature of interest to different types of literature review. We identified a broad evidence base of publications describing data extraction for interventional reviews and a small number of publications extracting epidemiological or diagnostic accuracy data. Between review updates, trends for sharing data and code increased strongly: in the base-review, data and code were available for 13 and 19% respectively, these numbers increased to 78 and 87% within the 23 new publications. Compared with the base-review, we observed another research trend, away from straightforward data extraction and towards additionally extracting relations between entities or automatic text summarisation. With this living review we aim to review the literature continually.

Background: The reliable and usable (semi)automation of data extraction can support the field of systematic review by reducing the workload required to gather information about the conduct and results of the included studies. This living systematic review examines published approaches for data extraction from reports of clinical studies. Methods: We systematically and continually search MEDLINE, Institute of Electrical and Electronics Engineers (IEEE), arXiv, and the dblp computer science bibliography databases. Full text screening and data extraction are conducted within an open-source living systematic review application created for the purpose of this review. This iteration of the living review includes publications up to a cut-off date of 22 April 2020. Results: In total, 53 publications are included in this version of our review. Of these, 41 (77%) of the publications addressed extraction of data from abstracts, while 14 (26%) used full texts. A total of 48 (90%) publications developed and evaluated classifiers that used randomised controlled trials as the main target texts. Over 30 entities were extracted, with PICOs (population, intervention, comparator, outcome) being the most frequently extracted. A description of their datasets was provided by 49 publications (94%), but only seven (13%) made the data publicly available. Code was made available by 10 (19%) publications, and five (9%) implemented publicly available tools. Conclusions: This living systematic review presents an overview of (semi)automated data-extraction literature of interest to different types of systematic review. We identified a broad evidence base of publications describing data extraction for interventional reviews and a small number of publications extracting epidemiological or diagnostic accuracy data. The lack of publicly available gold-standard data for evaluation, and lack of application thereof, makes it difficult to draw conclusions on which is the best-performing system for each data extraction target. With this living review we aim to review the literature continually.

Background: The COVID-19 pandemic has caused widespread morbidity and mortality as well as disruption to people’s lives and livelihoods around the world; this has occurred as a result of both infection with the virus itself and the health protection measures taken to curb its spread. There are concerns that rates of suicide, suicidal behaviours and self-harm may rise during and in the aftermath of the pandemic. Given the likely rapidly expanding research evidence base on the pandemic’s impact on rates of suicide, suicidal behaviours and self-harm and emerging evidence about how best to mitigate such effects, it is important that the best available knowledge is made readily available to policymakers, public health specialists and clinicians as soon as is possible. To facilitate this, we plan to undertake a living systematic review focusing on suicide prevention in relation to COVID-19. Method: Regular automated searches will feed into a web-based screening system which will also host the data extraction form for included articles. Our eligibility criteria are wide and include aspects of incidence and prevalence of suicidal behaviour, effects of exposures and effects of interventions in relation to the COVID-19 pandemic, with minimal restrictions on the types of study design to be included. The outcomes assessed will be death by suicide; self-harm or attempted suicide (including hospital attendance and/or admission for these reasons); and suicidal thoughts/ideation. There will be no restriction on study type, except for single case reports. There will be no restriction on language of publication. The review will be updated at three-monthly intervals if a sufficient volume of new evidence justifies doing so. Conclusions: Our living review will provide a regular synthesis of the most up-to-date research evidence to guide public health and clinical policy to mitigate the impact of COVID-19 on suicide. Protocol registration: PROSPERO CRD42020183326 01/05/2020

Background: Researchers in evidence-based medicine cannot keep up with the amounts of both old and newly published primary research articles. Conducting and updating of systematic reviews is time-consuming. In practice, data extraction is one of the most complex tasks in this process. Exponential improvements in computational processing speed and data storage are fostering the development of data extraction models and algorithms. This, in combination with quicker pathways to publication, led to a large landscape of tools and methods for data extraction tasks. Objective: To review published methods and tools for data extraction to (semi)automate the systematic reviewing process. Methods: We propose to conduct a living review. With this methodology we aim to do monthly search updates, as well as bi-annual review updates if new evidence permits it. In a cross-sectional analysis we will extract methodological characteristics and assess the quality of reporting in our included papers. Conclusions: We aim to increase transparency in the reporting and assessment of machine learning technologies to the benefit of data scientists, systematic reviewers and funders of health research. This living review will help to reduce duplicate efforts by data scientists who develop data extraction methods. It will also serve to inform systematic reviewers about possibilities to support their data extraction.