Back

Biomedical Large Language Models and Prompt Engineering for Causality Assessment of Individual Case Safety Reports in Pharmacovigilance

2026-02-24 pharmacology and therapeutics Title + abstract only
View on medRxiv
Show abstract

BackgroundBiomedical Large Language Models (LLMs) combined with prompt engineering offer domain-specific reasoning, yet their application to individual-level causality assessment remains unexplored. This study evaluated five combinations of biomedical LLMs, prompting strategies, and causality algorithms by comparing their agreement with two human expert evaluators. Research design and methodsA total of 150 Individual Case Safety Reports (ICSRs) were analyzed: 140 reports from Food and Drug Admi...

Predicted journal destinations

1
Journal of the American Medical Informatics Association
53 training papers
Top 1% 12.4%
2
Clinical Pharmacology & Therapeutics
19 training papers
Top 0.2% 12.4%
3
PLOS ONE
1737 training papers
Top 60% 9.5%
4
British Journal of Clinical Pharmacology
21 training papers
Top 0.2% 8.2%
5
Scientific Reports
701 training papers
Top 25% 8.2%
6
Frontiers in Pharmacology
27 training papers
Top 0.2% 6.7%
7
npj Digital Medicine
85 training papers
Top 5% 5.3%
8
Frontiers in Medicine
99 training papers
Top 7% 2.0%
9
Journal of Medical Internet Research
81 training papers
Top 8% 2.0%
10
JAMA Network Open
125 training papers
Top 12% 1.6%
11
Journal of Biomedical Informatics
37 training papers
Top 5% 1.6%
12
Trials
24 training papers
Top 0.9% 1.4%
13
PLOS Digital Health
88 training papers
Top 14% 1.2%
14
Nature Communications
483 training papers
Top 52% 1.0%
15
Antimicrobial Agents and Chemotherapy
17 training papers
Top 0.5% 1.0%
16
JMIRx Med
29 training papers
Top 2% 1.0%
17
Clinical Infectious Diseases
219 training papers
Top 23% 1.0%
18
Scientific Data
30 training papers
Top 4% 0.8%
19
Cureus
64 training papers
Top 21% 0.8%
20
BMJ
49 training papers
Top 6% 0.8%
21
PLOS Medicine
95 training papers
Top 22% 0.8%
22
eLife
262 training papers
Top 53% 0.8%
23
Biology Methods and Protocols
19 training papers
Top 1% 0.8%