Back

Accuracy and reliability of data extraction for systematic reviews using large language models: A protocol for a prospective study

2024-05-22 health informatics Title + abstract only
View on medRxiv
Show abstract

BackgroundSystematic reviews require extensive time and effort to manually extract and synthesize data from numerous screened studies. This study aims to investigate the ability of large language models (LLMs) to automate data extraction with high accuracy and minimal bias, using clinical questions (CQs) of the Japanese Clinical Practice Guidelines for Management of Sepsis and Septic Shock (J-SSCG) 2024. the study will evaluate the accuracy of three LLMs and optimize their command prompts to enh...

Predicted journal destinations

1
Research Synthesis Methods
17 training papers
#1 17.5%
2
BMJ Open
553 training papers
Top 13% 10.8%
3
Journal of the American Medical Informatics Association
53 training papers
Top 2% 8.9%
4
PLOS ONE
1737 training papers
Top 62% 8.9%
5
Journal of Medical Internet Research
81 training papers
Top 3% 5.9%
6
JAMIA Open
35 training papers
Top 4% 5.5%
7
BMC Medical Informatics and Decision Making
36 training papers
Top 3% 5.5%
8
BMC Medical Research Methodology
41 training papers
Top 0.3% 5.0%
9
Journal of Clinical Epidemiology
29 training papers
Top 0.3% 5.0%
10
PLOS Digital Health
88 training papers
Top 7% 3.8%
11
Journal of Biomedical Informatics
37 training papers
Top 4% 2.7%
12
JMIR Medical Informatics
16 training papers
Top 2% 1.9%
13
International Journal of Medical Informatics
25 training papers
Top 3% 1.9%
14
Scientific Reports
701 training papers
Top 87% 1.5%
15
JMIR Formative Research
31 training papers
Top 3% 1.2%
16
npj Digital Medicine
85 training papers
Top 17% 0.9%
17
Frontiers in Digital Health
18 training papers
Top 4% 0.7%
18
International Journal of Environmental Research and Public Health
116 training papers
Top 33% 0.7%
19
Computers in Biology and Medicine
39 training papers
Top 10% 0.7%
20
Frontiers in Public Health
135 training papers
Top 34% 0.7%
21
BMJ
49 training papers
Top 7% 0.7%