Automation of clinical evidence identification and synthesis
Centre for health informatics
Research stream
Project members
Dr Didi Surian
Dr Ying Wang
Satya Vedantam
Professor Enrico Coiera
Project contact
Dr Didi Surian
E: didi.surian@mq.edu.au
Project main description
Systematic reviews are considered as the highest-level evidence for use in clinical decision-making and practice guidelines and policy development. With new evidence is accumulating at unprecedented rates in many domains, systematic reviews need to be up to date to remain current, especially to support clinical practice. However, performing systematic reviews is resource-intensive and efforts are inefficiently allocated.
The goals of this project are:
- To develop new methods to efficiently predict if systematic reviews need to be updated
- To develop new methods to link between systematic reviews and clinical evidence such as clinical trials and published articles
- To investigate automated tools and develop new methods to support the process of the evidence synthesis
We have developed methods to automatically extract data from published systematic reviews and their updates and to predict whether a systematic review needs to be updated or not. We also have designed and developed novel methods that aim to improve the quality and efficiency in the reporting of clinical trials for systematic review updates. We have developed various novel methods to link relevant published clinical trials from ClinicalTrials.gov to systematic reviews. Our results suggest that existing included clinical trials in a systematic review can be used to predict new clinical trials to be included in systematic review updates. We collaborate with experts from various institutions and universities investigating automation tools to accelerate the process of systematic reviews.
References
- Surian D, Bourgeois FT, Dunn AG. The automation of relevant trial registration screening for systematic review updates: an evaluation study on a large dataset of ClinicalTrial.gov registrations. BMC Medical Research Methodology. 2021 21:281.
- Bashir R, Dunn AG, Surian D. A rule‐based approach for automatically extracting data from systematic reviews and their updates to model the risk of conclusion change. Research Synthesis Methods. 2021 12(2):216-225.
- Bashir R, Surian D, Dunn AG. The risk of conclusion change in systematic review updates can be estimated by learning from a database of published examples. Journal of Clinical Epidemiology. 2019 (110):42-49.
- Martin P, Surian D, Bashir R, Bourgeois FT, Dunn AG. Trial2rev: combining machine learning and crowd-sourcing to create a shared space for updating systematic reviews. JAMIA Open. 2019 2(1):15-22.
- Bashir R, Surian D, Dunn AG. Time-to-update of systematic reviews relative to the availability of new evidence. Systematic Reviews. 2018 7(1):195.
- Bashir R, Surian D, Dunn AG. An empirically defined decision tree to predict systematic reviews at risk of change in conclusion. Cochrane Database of Systematic Reviews 9 (Supplement 1). 2018:122-123.
- Surian D, Dunn AG, Orenstein L, Bashir R, Coiera E, Bourgeois FT. A shared latent space matrix factorisation method for recommending new trial evidence for systematic review updates. Journal of Biomedical Informatics. 2018 (79):32-40.
- G Tsafnat, P Glasziou, MK Choong, A Dunn, F Galgani, E Coiera. Systematic review automation technologies. Systematic reviews. 2014 3 (1), 1-15
- G Tsafnat, A Dunn, P Glasziou, E Coiera. The automation of systematic reviews. BMJ. 2013 346
- AG Dunn, E Coiera, KD Mandl, FT Bourgeois. Conflict of interest disclosure in biomedical research: a review of current practices, biases, and the role of public registries in improving transparency. Research integrity and peer review. 2016 1 (1), 1-8
- MK Choong, F Galgani, AG Dunn, G Tsafnat. Automatic evidence retrieval for systematic reviews. Journal of Medical Internet Research. 2014 16 (10), e223
- R Bashir, FT Bourgeois, AG Dunn. A systematic review of the processes used to link clinical trial registrations to their published results. Systematic reviews. 2017 6 (1), 1-17
- KA Robinson, AG Dunn, G Tsafnat, P Glasziou. Citation networks of related trials are often disconnected: implications for bidirectional citation searches. Journal of Clinical Epidemiology. 2014 67 (7), 793-799
- AG Dunn, RO Day, KD Mandl, E Coiera. Learning from hackers: open-source clinical trials. Science translational medicine. 2012 4 (132), 132cm5-132cm5
- AG Dunn, E Coiera, FT Bourgeois. Unreported links between trial registrations and published articles were identified using document similarity measures in a cross-sectional analysis of ClinicalTrials.gov. Journal of Clinical Epidemiology. 2018 95, 94-101
- R Bashir, AG Dunn. Systematic review protocol assessing the processes for linking clinical trial registries and their published results. 2016. BMJ open 6 (10), e013048
- AG Dunn, L Orenstein, E Coiera, KD Mandl, FT Bourgeois. The timing and frequency of trial inclusion in systematic reviews of type 2 diabetes drugs was associated with trial characteristics. Journal of Clinical Epidemiology. 2019 109, 62-69
- Identifying clinical study types from PubMed metadata: the active (machine) learning approach
- AG Dunn, D Arachi, FT Bourgeois. 2015. Amsterdam: IOS Press
- R Bashir, FT Bourgeois, AG Dunn. A systematic review of the processes used to link clinical trial registrations to their published results. Systematic reviews. 2017 6 (1), 1-17
- KA Robinson, AG Dunn, G Tsafnat, P Glasziou. Citation networks of related trials are often disconnected: implications for bidirectional citation searches. Journal of Clinical Epidemiology. 2014 67 (7), 793-799
- L Trinquart, AG Dunn, FT Bourgeois. Registration of published randomized trials: a systematic review and meta-analysis. BMC medicine. 2018 16 (1), 1-13
- AG Dunn, RO Day, KD Mandl, E Coiera. Learning from hackers: open-source clinical trials. Science translational medicine. 2012 4 (132), 132cm5-132cm5
Project sponsors
- The Agency for Healthcare Research and Quality (R03HS024798)
- National Library of Medicine, National Institutes of Health (R01LM012976)
Collaborative partners
- Prof Paul Glasziou, Bond University
- A/Prof Adam Dunn, the University of Sydney
- A/Prof Florence T. Bourgeois, Dr Kenneth Mandl, Boston Children’s Hospital, Boston, MA, United States, Harvard Medical School, Boston, MA, United States
- Dr Guy Tsafnat, Evidentli
Project status
Current
Centres related to this project
Content owner: Australian Institute of Health Innovation Last updated: 11 Mar 2024 6:49pm