Introduction to the WISEST (Which Systematic Evidence Synthesis is best) Project: Developing an automated clinical decision-support algorithm to choose amongst systematic review(s) on the same topic

Article type
Authors
Lunny C1, Veroniki AA1, Shea B2, Hutton B2, Hamel C3, Pieper D4, Bagheri E5, Reid E6, Zhang JH7, Watt J8, Lavis J9, Downie L10, Tunis M11, Dobbins M12, Ferri N13, Kanjii S2, Whitelaw S14, Strauss S15, Chi Y16, Stevens A17, Pilic A18, Harder T18, Pham B8, Dormuth C19, Bassett K19, Baxter D11, Wright J20, McFarlane J21, Waddell L11, Moja L22, Mittmann N23, Lorenz R24, Iyer S25, Minogue V26, Zarin W27, Gerrish S28, Bryan S29, Tricco AC8
1Knowledge Translation Program, St Michael's Hospital, Unity Health Toronto
2Ottawa Hospital Research Institute
3Canadian Association of Radiologists
4Institute for Health Services and Health Systems Research, Center for Health Services Research, Brandenburg Medical School
5Department of Electrical and Computer Engineering, Toronto Metropolitan University (TMU)
6Nova Scotia Health
7The University of British Columbia
8Knowledge Translation Program, Li Ka Shing Knowledge Institute, St. Michael’s Hospital, Unity Health Toronto
9McMasterPlus, McMaster University
10CrowdCARE, University of Melbourne
11Public Health Agency of Canada
12National Collaborating Centre for Methods and Tools & Health Evidence
13Università di Bologna
14McGill University
15University of Toronto
16Beijing Yealth Technology
17National Advisory Committee on Immunization (NACI)
18Robert Koch Institute
19Therapeutics Initiative, The University of British Columbia (UBC)
20Cochrane Hypertension Group, The University of British Columbia
21British Columbia Ministry of Health
22World Health Organisation
23Canadian Agency for Drugs and Technology in Health
24The Federal Joint Committee (G-BA)
25Agency for Healthcare Research and Quality (AHRQ)
26Cochrane Consumer Network
27SPOR Evidence Alliance
28SFU
29BC Support Unit
Abstract
Background: Knowledge users (KUs) need the highest-quality studies to make decisions about which interventions and policies should be used. The most reliable way to answer questions is with a systematic review (SR). AMSTAR and ROBIS tools are used to assess quality/bias in SRs. However, no automated tool currently exists to assess the quality/biases in SRs (Figure 1).

Objectives: (1) Develop a set of features to extract from SRs related to quality/bias; (2) develop a labelled dataset of 10,000 SRs; and (3) test, train and validate models and compare their accuracy.

Methods: A structure was proposed by the international steering group, and features were collected using a methods review and a survey. We used the results of a previous study comparing the tools which mapped an item’s concept across the three tools. A core team reviewed them and determined their feasibility in being automatically identifiable and predictable by our model (rather than through a manual process). A flowchart of activities is proposed (Figure 2). Five organisations with databases of preappraised SRs will supply the SRs. Duplicates will be removed and topics will be mapped. If topic fields, settings or conditions are missing, we will fill these gaps with a search for SRs. We will use ML Random Forests and DL Neural Network classification models such as Facebook’s StarSpace and Fasttext. We will use a ‘supervised’ learning model which learns by making predictions given examples of data.

Results: The proposed structure is found in Figure 1. The 21 items mapped from AMSTAR 1 and 2 and ROBIS will be used as the quality features. Other features chosen include PROGRESS-Plus items related to sex, gender and equity, 20 methods features (e.g., number of databases searched, PICO, and meta-analysis model used) and 10 results features (e.g., effect estimates and adverse events). SRs were collected and cleaned and the other features were extracted in duplicate. Testing will begin in March 2024.

Conclusions: An artificial intelligence tool that critically appraises SRs would dramatically reduce the financial and human resources currently needed to appraise SRs and update SR databases (e.g., McMasterPlus, HealthEvidence and SysVac).

Patient, public and/or healthcare consumer involvement: None.