Back

Fully Automated Systematic Review Generation via Large Language Models: Quality Assessment and Implications for Scientific Publishing

2026-02-23 health informatics Title + abstract only
View on medRxiv
Show abstract

Large language models (LLMs) are increasingly transforming scientific workflows, yet their application to rigorous evidence synthesis remains underexplored. Through the execution of a single Python script, we present a fully automated pipeline leveraging the Claude API to generate systematic reviews from literature search through manuscript completion without human intervention. Our pipeline processes hundreds of papers through iterative API calls for inclusion evaluation, information extraction...

Predicted journal destinations

1
Journal of the American Medical Informatics Association
53 training papers
#1 23.2%
2
JAMIA Open
35 training papers
Top 1% 6.7%
3
Journal of Biomedical Informatics
37 training papers
Top 2% 6.2%
4
PLOS Digital Health
88 training papers
Top 4% 6.2%
5
npj Digital Medicine
85 training papers
Top 5% 5.3%
6
BMC Medical Informatics and Decision Making
36 training papers
Top 4% 4.4%
7
BMC Medical Research Methodology
41 training papers
Top 0.5% 4.0%
8
Journal of Medical Internet Research
81 training papers
Top 5% 4.0%
9
Scientific Reports
701 training papers
Top 64% 4.0%
10
Nature Communications
483 training papers
Top 26% 4.0%
11
PLOS ONE
1737 training papers
Top 89% 3.3%
12
International Journal of Medical Informatics
25 training papers
Top 3% 2.0%
13
Research Synthesis Methods
17 training papers
Top 0.3% 2.0%
14
JMIR Medical Informatics
16 training papers
Top 1% 2.0%
15
BMJ Open
553 training papers
Top 47% 2.0%
16
Journal of Clinical Epidemiology
29 training papers
Top 0.6% 2.0%
17
BMC Medicine
155 training papers
Top 15% 1.6%
18
Scientific Data
30 training papers
Top 2% 1.2%
19
JAMA Network Open
125 training papers
Top 23% 1.0%
20
Patterns
15 training papers
Top 3% 0.7%
21
Nature Medicine
88 training papers
Top 16% 0.7%
22
JMIR Formative Research
31 training papers
Top 7% 0.7%
23
Bioinformatics
24 training papers
Top 3% 0.7%
24
Communications Medicine
63 training papers
Top 6% 0.7%
25
Computers in Biology and Medicine
39 training papers
Top 9% 0.7%
26
The Lancet Digital Health
25 training papers
Top 2% 0.7%
27
Frontiers in Digital Health
18 training papers
Top 3% 0.7%
28
Biology Methods and Protocols
19 training papers
Top 1% 0.7%