Back

Evaluating a Locally Deployed 20-Billion Parameter Large Language Model for Automated Abstract Screening in Systematic Reviews

2026-03-04 health informatics Title + abstract only
View on medRxiv
Show abstract

BackgroundSystematic reviews (SRs) are essential for evidence-based medicine but require extensive time and resources for abstract screening. Large language models (LLMs) offer potential for automating this process, yet concerns about data privacy, intellectual property protection, and reproducibility limit the use of cloud-based solutions in research settings. ObjectiveTo evaluate the performance of a locally deployed 20-billion parameter LLM for automated abstract screening in systematic revi...

Predicted journal destinations

1
Journal of the American Medical Informatics Association
53 training papers
#1 22.2%
2
PLOS Digital Health
88 training papers
Top 2% 7.8%
3
JAMIA Open
35 training papers
Top 0.6% 7.8%
4
Journal of Medical Internet Research
81 training papers
Top 2% 6.4%
5
BMJ Open
553 training papers
Top 29% 5.9%
6
npj Digital Medicine
85 training papers
Top 4% 5.9%
7
Journal of Biomedical Informatics
37 training papers
Top 2% 5.9%
8
BMC Medical Informatics and Decision Making
36 training papers
Top 3% 5.0%
9
PLOS ONE
1737 training papers
Top 86% 3.9%
10
Journal of Clinical Epidemiology
29 training papers
Top 0.4% 3.9%
11
BMC Medical Research Methodology
41 training papers
Top 0.8% 2.8%
12
Research Synthesis Methods
17 training papers
Top 0.3% 2.1%
13
JMIR Medical Informatics
16 training papers
Top 2% 1.9%
14
International Journal of Medical Informatics
25 training papers
Top 3% 1.9%
15
Scientific Reports
701 training papers
Top 86% 1.5%
16
JAMA Network Open
125 training papers
Top 20% 1.2%
17
JMIR Formative Research
31 training papers
Top 5% 1.0%
18
Nature Communications
483 training papers
Top 54% 1.0%
19
The Lancet Digital Health
25 training papers
Top 2% 0.7%
20
Annals of Internal Medicine
27 training papers
Top 1% 0.7%
21
Biology Methods and Protocols
19 training papers
Top 1% 0.7%
22
Frontiers in Digital Health
18 training papers
Top 4% 0.7%
23
BMC Medicine
155 training papers
Top 35% 0.7%
24
Computers in Biology and Medicine
39 training papers
Top 10% 0.7%
25
BMJ
49 training papers
Top 9% 0.5%