Back

Accuracy and efficiency of using artificial intelligence for data extraction in systematic reviews. A noninferiority study within reviews

2026-02-27 public and global health Title + abstract only
View on medRxiv
Show abstract

BackgroundSystematic reviews are important for informing public health policies and program selection; however, they are time- and resource-intensive. Artificial intelligence (AI) offers a solution to reduce these labour-intensive requirements for various aspects of systematic review production, including data extraction. To date, there is limited robust evidence evaluating the accuracy and efficiency of AI for data extraction. This study within a review (SWAR) aimed to determine whether human d...

Predicted journal destinations

1
BMJ Open
553 training papers
Top 4% 24.2%
2
Research Synthesis Methods
17 training papers
#1 19.3%
3
PLOS ONE
1737 training papers
Top 35% 19.3%
4
BMJ Global Health
95 training papers
Top 5% 4.2%
5
Journal of Medical Internet Research
81 training papers
Top 8% 2.1%
6
PLOS Global Public Health
287 training papers
Top 18% 2.1%
7
BMC Public Health
148 training papers
Top 19% 1.7%
8
BMC Medicine
155 training papers
Top 15% 1.7%
9
Journal of Clinical Epidemiology
29 training papers
Top 0.8% 1.7%
10
Frontiers in Public Health
135 training papers
Top 21% 1.5%
11
PLOS Medicine
95 training papers
Top 15% 1.0%
12
npj Digital Medicine
85 training papers
Top 16% 1.0%
13
Vaccine
140 training papers
Top 8% 1.0%
14
Trials
24 training papers
Top 2% 1.0%
15
Scientific Reports
701 training papers
Top 94% 0.8%
16
eLife
262 training papers
Top 51% 0.8%
17
JAMA Network Open
125 training papers
Top 28% 0.8%
18
International Journal of Environmental Research and Public Health
116 training papers
Top 31% 0.8%
19
JMIR Formative Research
31 training papers
Top 9% 0.5%
20
JMIR Public Health and Surveillance
45 training papers
Top 14% 0.5%
21
BMC Medical Research Methodology
41 training papers
Top 12% 0.5%
22
Public Health
34 training papers
Top 10% 0.5%
23
PLOS Digital Health
88 training papers
Top 24% 0.5%