ArticleDelaware journal of public health2026
Bias Patterns in the Application of LLMs for Clinical Decision Support: A Comprehensive Study.
Article in Delaware journal of public health, 2026. The graph could read no effect estimate from its abstract, so it casts no vote on the map. Cited by 12 papers.
What it found
Each row is one number read from the abstract, on the scale the paper reported it, with its interval. Left of the dashed line favours the treatment, right favours the comparator. Under each row is the sentence it came from. New to these charts? A ten-minute tutorial.
The abstract states no effect estimate the extractor could read, or names no intervention and outcome on the map, so this paper lights no cell and moves no belief. It is still indexed, cited and linked below.
The trial behind it
Trials whose registry record cites this paper, or whose number appears in the abstract. A trial that started after this paper was published is citing it as background, not reporting it.
Neither the registry nor the abstract names a trial number. If this is a trial report, that itself is worth knowing.
Who cites it
12 citing papers in PubMed.
- Prompt Engineering of Large Language Models for Medication Dose Calculation.Clinical pharmacology and therapeutics · 2026Article
- Large Language Models for Breast and Cervical Cancers Communication: Mixed Methods Evaluation Study Assessing Linguistic Quality, Safety, and Accessibility.JMIR cancer · 2026Article
- Susceptibility of Large Language Models to User-Driven Factors in Medical Queries.Journal of healthcare informatics research · 2026Article
- When Artificial Intelligence Fails the Future: How Unchecked Artificial Intelligence Could Amplify Inequality in Medical Education.Plastic and reconstructive surgery. Global open · 2026Article
- LLMs in Patient-Centric Program Evaluation: Addressing Concerns and Further Considerations.Pain reports · 2026Article
- Race, Ethnicity and Their Implication on Bias in Large Language Models.medRxiv : the preprint server for health sciences · 2026Article
- The rise and potential opportunities of large language model agents in bioinformatics and biomedicine.Briefings in bioinformatics · 2025Review
- A Review of Large Language Models in Medical Education, Clinical Decision Support, and Healthcare Administration.Healthcare (Basel, Switzerland) · 2025Review
- LLM-Guided Pain Management: Examining Socio-Demographic Gaps in Cancer vs non-Cancer cases.medRxiv : the preprint server for health sciences · 2025Article
- "Hospice Care Could Be a Compassionate Choice": ChatGPT Responses to Questions About Decision Making in Advanced Cancer.Journal of palliative medicine · 2024Article
- Bias in medical AI: Implications for clinical decision-making.PLOS digital health · 2024Review
- Review
Corrections and comments
PubMed lists nothing against this paper. Absence here is not a guarantee, only a check that was made.
Authors and funding
4 authors.
Funding
No grant is acknowledged in the PubMed record.
Abstract
Objectives: To investigate the extent to which Large Language Models (LLMs) exhibit social bias based on protected patient attributes and to determine how design choices, such as architecture and prompting strategies, influence these observed biases in clinical decision support. Methods: We evaluated eight popular LLMs, including general-purpose and clinically trained models, across three standardized question-answering datasets using clinical vignettes. We employed red-teaming strategies to analyze the impact of demographics on LLM outputs and compared various prompting techniques, including Zero-shot and Chain of Thought. Results: Our experiments reveal various disparities across protected groups. Notably, larger models were not necessarily less biased, and medical fine-tuning did not consistently outperform general-purpose models. Furthermore, specific prompt phrasing significantly influenced bias patterns, whereas reflection-type approaches like Chain of Thought effectively reduced biased outcomes. Conclusions: LLMs demonstrate significant social biases in clinical scenarios that are influenced by model architecture and prompt engineering. These findings highlight the critical need for rigorous evaluation and enhancement of LLMs before their integration into clinical decision support systems. Consistent with prior studies, we call for additional scrutiny to ensure equity in AI-driven healthcare applications. All code and data are available at https://github.com/healthylaife/FairCDSLLM.
Identifiers
What OpenQuestion holds
Registered trials
Read under generation 80e0d062 · epoch 390. Bibliography from PubMed, PubMed Central and OpenAlex; grants from NIH RePORTER; trial links from ClinicalTrials.gov; estimates, votes and beliefs from the OpenQuestion graph.