Back
Top 0.3%
17.8%
Top 12%
11.8%
#1
9.0%
Top 0.2%
6.4%
Top 3%
6.0%
Top 82%
5.0%
Top 0.3%
5.0%
Top 3%
5.0%
Top 4%
3.1%
Top 31%
3.1%
Top 8%
2.8%
Top 9%
1.9%
Top 10%
1.9%
Top 11%
1.9%
Top 13%
1.6%
Top 2%
1.5%
Top 4%
1.3%
Top 5%
1.3%
Top 90%
1.2%
Top 4%
0.7%
Top 2%
0.7%
Top 31%
0.5%
MR-KG: A knowledge graph of Mendelian randomization evidence powered by large language models
2025-12-15
health informatics
Title + abstract only
View on medRxiv
Show abstract
BackgroundThe exponential growth of Mendelian randomization (MR) literature has created challenges for systematically organising and synthesising evidence, with key information fragmented across heterogeneous publications. We present MR-KG, a knowledge graph resource using large language models (LLMs) to systematically extract and structure published MR evidence at scale. MethodsWe evaluated eight OpenAI and local LLMs for extracting structured information from MR study abstracts. Two reviewers...
Predicted journal destinations
1
Journal of the American Medical Informatics Association
53 training papers
2
BMJ Open
553 training papers
3
Research Synthesis Methods
17 training papers
4
Journal of Clinical Epidemiology
29 training papers
5
JAMIA Open
35 training papers
6
PLOS ONE
1737 training papers
7
BMC Medical Research Methodology
41 training papers
8
Journal of Biomedical Informatics
37 training papers
9
BMC Medical Informatics and Decision Making
36 training papers
10
Nature Communications
483 training papers
11
PLOS Digital Health
88 training papers
12
Journal of Medical Internet Research
81 training papers
13
npj Digital Medicine
85 training papers
14
BMC Medicine
155 training papers
15
JAMA Network Open
125 training papers
16
BMJ
49 training papers
17
JMIR Medical Informatics
16 training papers
18
International Journal of Medical Informatics
25 training papers
19
Scientific Reports
701 training papers
20
Frontiers in Digital Health
18 training papers
21
The Lancet Digital Health
25 training papers
22
PLOS Medicine
95 training papers