Back
#1
24.8%
Top 44%
16.3%
Top 18%
10.1%
Top 1%
8.7%
Top 1%
6.6%
Top 3%
4.3%
Top 5%
4.3%
Top 34%
2.2%
Top 6%
2.2%
Top 26%
1.7%
Top 12%
1.3%
Top 6%
1.3%
Top 8%
1.3%
Top 61%
1.1%
Top 5%
1.1%
Top 25%
1.1%
Top 5%
0.5%
Top 5%
0.5%
Top 24%
0.5%
Top 7%
0.5%
Top 10%
0.5%
Evaluating the Influence of Demographic Identity in the Medical Use of Large Language Models
2025-07-11
medical ethics
Title + abstract only
View on medRxiv
Show abstract
As large language models (LLMs) are increasingly adopted in medical decision-making, concerns about demographic biases in AIgenerated recommendations remain unaddressed. In this study, we systematically investigate how demographic attributes--specifically race and gender--affect the diagnostic, medication, and treatment decisions of LLMs. Using the MedQA dataset, we construct a controlled evaluation framework comprising 20,000 test cases with systematically varied doctor-patient demographic pair...
Predicted journal destinations
1
npj Digital Medicine
85 training papers
2
PLOS ONE
1737 training papers
3
Scientific Reports
701 training papers
4
PLOS Digital Health
88 training papers
5
Journal of Biomedical Informatics
37 training papers
6
JAMA Network Open
125 training papers
7
Journal of Medical Internet Research
81 training papers
8
Nature Communications
483 training papers
9
PLOS Computational Biology
141 training papers
10
eLife
262 training papers
11
Cureus
64 training papers
12
Computers in Biology and Medicine
39 training papers
13
Nature Medicine
88 training papers
14
BMJ Open
553 training papers
15
Royal Society Open Science
49 training papers
16
BMC Medicine
155 training papers
17
Trials
24 training papers
18
Journal of Clinical Epidemiology
29 training papers
19
Proceedings of the National Academy of Sciences
100 training papers
20
Journal of the American Medical Informatics Association
53 training papers
21
Communications Medicine
63 training papers