Back
Top 0.3%
17.9%
Top 0.6%
11.1%
Top 0.2%
9.1%
Top 2%
7.9%
Top 0.4%
7.9%
Top 1%
6.5%
Top 3%
6.5%
Top 76%
6.0%
Top 63%
4.2%
Top 0.8%
3.9%
Top 0.8%
2.8%
Top 2%
2.0%
Top 1%
1.6%
Top 7%
1.2%
Top 2%
1.2%
Top 63%
1.0%
Top 4%
0.7%
Top 3%
0.7%
Top 14%
0.7%
Top 33%
0.7%
MedMatch: a first step for the automation of large language model performance benchmarking for medication-related tasks
2026-01-15
health informatics
Title + abstract only
View on medRxiv
Show abstract
BackgroundThe accuracy and safety of generating medication orders by large language models (LLMs) must be demonstrated. Without standardization, performance evaluation is limited to time and resource-intensive clinician grading. This evaluation aimed to develop a standardized medication format that supports automated performance evaluation (MedMatch). MethodsFirst, a survey of 40 medication prompts was given to clinicians to assess agreement in medication order communication. Second, a clinicia...
Predicted journal destinations
1
Journal of the American Medical Informatics Association
53 training papers
2
Journal of Medical Internet Research
81 training papers
3
JAMIA Open
35 training papers
4
PLOS Digital Health
88 training papers
5
BMC Medical Informatics and Decision Making
36 training papers
6
Journal of Biomedical Informatics
37 training papers
7
npj Digital Medicine
85 training papers
8
PLOS ONE
1737 training papers
9
Scientific Reports
701 training papers
10
International Journal of Medical Informatics
25 training papers
11
BMC Medical Research Methodology
41 training papers
12
JMIR Medical Informatics
16 training papers
13
JMIR Formative Research
31 training papers
14
Computers in Biology and Medicine
39 training papers
15
Frontiers in Digital Health
18 training papers
16
BMJ Open
553 training papers
17
JMIRx Med
29 training papers
18
Patterns
15 training papers
19
Heliyon
57 training papers
20
Frontiers in Public Health
135 training papers