Related Experiment Video
Updated: Jun 2, 2026
05:47
Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems
Published on: June 13, 2025
Implicit Gender, Racial, and Ethnic Biases in Large Language Models: An Audit Study of Automated Psychiatric
Sachin R Pendse1,2, Mini Jain1, Neha Kumar1
1School of Interactive Computing, Georgia Institute of Technology, Atlanta, GA.
Mayo Clinic Proceedings. Digital Health
|June 1, 2026
Summary
Large language models (LLMs) show implicit biases in psychiatric diagnoses, impacting AI fairness. Auditing AI for bias in mental health is crucial for accurate and equitable clinical decision support.
Area of Science:
- Artificial Intelligence in Healthcare
- Clinical Psychology
- Medical Ethics
Background:
- Large language models (LLMs) are increasingly used in healthcare.
- Potential for implicit biases in LLMs to affect clinical decision support.
- Need to evaluate AI fairness in psychiatric diagnostics.
Purpose of the Study:
- To assess gender, racial, and ethnic biases in LLM-generated psychiatric diagnoses.
- To determine the impact of these biases on AI-assisted clinical decision support accuracy and fairness.
Main Methods:
- Audit of 6 LLMs using 97 psychiatric training cases.
- Systematic alteration of case details to represent 39 demographic groups.
- Evaluation of diagnostic accuracy, missed/additional diagnoses, and reasoning language.
Main Results:
- Generative Pretrained Transformer 4o showed high accuracy but overdiagnosed.
- Diagnostic accuracy varied by gender, with lower performance for nonbinary individuals.
- Biased diagnostic patterns emerged, with specific diagnoses linked to race/ethnicity.
Conclusions:
- LLMs can reproduce and amplify existing clinical biases.
- AI tools require rigorous auditing for both accuracy and bias in mental health.
- Ensuring fairness in AI-driven mental health support is paramount.
Related Concept Videos
02:16Stereotype Content Model
The Stereotype Content Model (SCM) was first proposed by Susan Fiske and her colleagues (Fiske, Cuddy, Glick & Xu, 2002; see also Fiske, 2012 and Fiske, 2017). The SCM specifies that when someone encounters a new group, they will stereotype them based on two metrics: warmth—or that group’s perceived intent, and how likely they are to provide help or inflict harm—and competence—or their ability to carry out that objective. Depending on the warmth-competence categorization, a person will feel...
02:55Stereotypes, Prejudice, and Discrimination
Humans are very diverse and although we share many similarities, we also have many differences. The social groups we belong to help form our identities (Tajfel, 1974). These differences may be difficult for some people to reconcile, which may lead to prejudice toward people who are different. Prejudice is a negative attitude and feeling toward an individual based solely on one’s membership in a particular social group (Allport, 1954; Brown, 2010). Prejudice is common against people who are...
01:27Diagnostic and Statistical Manual of Mental Disorders (DSM)
The Diagnostic and Statistical Manual of Mental Disorders (DSM) serves as the primary classification system for mental health disorders, providing standardized diagnostic criteria for clinicians and researchers. First published by the American Psychiatric Association (APA) in 1952, the DSM has undergone several revisions to reflect evolving psychiatric understanding. The fifth edition, DSM-5, released in 2013, introduced key updates that expanded diagnostic categories and modified diagnostic...
01:25Motivational Bias
Cognitive bias results from limitations in thinking and information processing, leading to systematic errors in judgment. Conversely, motivational bias stems from personal desires or emotions, causing distortions in perception to align with self-interest. Motivational bias influences how individuals perceive and attribute causes to events, often shaped by personal needs, goals, and self-esteem preservation. This bias can distort judgment, leading to inaccurate assessments of success, failure,...
01:31Confirmation Biases
The confirmation bias is the tendency to focus on information that confirms our existing beliefs and ignore information that is inconsistent with our expectations. For example, if you think that your professor is not very nice, you notice all of the instances of rude behavior exhibited by the professor while ignoring the countless pleasant interactions he is involved in on a daily basis. Have you ever fallen prey to the confirmation bias, either as the source or target of such bias?
01:22Bias
Bias refers to any tendency that prevents a question from being considered unprejudiced. In research, bias occurs when one outcome or answer is selected or encouraged over others in sampling or testing. Bias can occur during any research phase, including study design, data collection, analysis, and publication.
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...
In statistics, a sampling bias is created when a sample is collected from a population, and some members of the population are not as likely to be chosen as others (remember, each member...