# EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department Triage

arXiv: https://arxiv.org/abs/2605.03998 · HTML: https://mlsanity.com/paper/2605.03998/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 62 references that are in the map.
- First posted on arXiv 5 May 2026.

## Builds on (most cited first, 25 of 25)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Men Also Like Shopping: Reducing Gender Bias Amplification using Corpus-level Constraints](https://mlsanity.com/paper/1707.09457/) (2017)
- [Non-Determinism of "Deterministic" LLM Settings](https://mlsanity.com/paper/2408.04667/) (2024)
- [Hurtful Words: Quantifying Biases in Clinical Contextual Word Embeddings](https://mlsanity.com/paper/2003.11515/) (2020)
- [What's in a Name? Auditing Large Language Models for Race and Gender Bias](https://mlsanity.com/paper/2402.14875/) (2024)
- [Evaluating Gender Bias in Large Language Models via Chain-of-Thought Prompting](https://mlsanity.com/paper/2401.15585/) (2024)
- [ER-Reason: A Benchmark Dataset for LLM Clinical Reasoning in the Emergency Room](https://mlsanity.com/paper/2505.22919/) (2025)
- [Locating and Mitigating Gender Bias in Large Language Models](https://mlsanity.com/paper/2403.14409/) (2024)
- [Development of a Large Language Model-based Multi-Agent Clinical Decision Support System for Korean Triage and Acuity Scale (KTAS)-Based Triage and Treatment Planning in Emergency Departments](https://mlsanity.com/paper/2408.07531/) (2024)
- [Bias in Large Language Models Across Clinical Applications: A Systematic Review](https://mlsanity.com/paper/2504.02917/) (2025)
- [AI Agents for Conversational Patient Triage: Preliminary Simulation-Based Evaluation with Real-World EHR Data](https://mlsanity.com/paper/2506.04032/) (2025)
- [From Promising Capability to Pervasive Bias: Assessing Large Language Models for Emergency Department Triage](https://mlsanity.com/paper/2504.16273/) (2025)
- [How Can We Diagnose and Treat Bias in Large Language Models for Clinical Decision-Making?](https://mlsanity.com/paper/2410.16574/) (2024)
- [MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning](https://mlsanity.com/paper/2510.12818/) (2025)
- [Fair Machine Learning for Healthcare Requires Recognizing the Intersectionality of Sociodemographic Factors, a Case Study](https://mlsanity.com/paper/2407.15006/) (2024)
- [Fairness at Every Intersection: Uncovering and Mitigating Intersectional Biases in Multimodal Clinical Predictions](https://mlsanity.com/paper/2412.00606/) (2024)
- [mFARM: Towards Multi-Faceted Fairness Assessment based on HARMs in Clinical Decision Support](https://mlsanity.com/paper/2509.02007/) (2025)
- [Uncovering Latent Bias in LLM-Based Emergency Department Triage Through Proxy Variables](https://mlsanity.com/paper/2601.15306/) (2026)
- [Multi-Modal Perceiver Language Model for Outcome Prediction in Emergency Department](https://mlsanity.com/paper/2304.01233/) (2023)
- [Bias Detection in Emergency Psychiatry: Linking Negative Language to Diagnostic Disparities](https://mlsanity.com/paper/2509.02651/) (2025)
- [Gender Bias in Large Language Models for Healthcare: Assignment Consistency and Clinical Implications](https://mlsanity.com/paper/2510.08614/) (2025)
- [Dr. Bias: Social Disparities in AI-Powered Medical Guidance](https://mlsanity.com/paper/2510.09162/) (2025)
- [Auditing Sex/Gender Disparities in Emergency Triage with LLM-based Paired Comparisons](https://mlsanity.com/paper/2511.17124/) (2025)

## Built on by (most cited first, 3 of 3)

- [AgentFairBench: Do LLM Agents Discriminate When They Act?](https://mlsanity.com/paper/2606.16723/) (2026)
- [Proxy reliance in large language model decisions is uncalibrated to predictive evidence](https://mlsanity.com/paper/2608.22887/) (2026)
- [Instability Floors: Separating Bias from Noise in Fairness Audits of Clinical LLM Agents with FairMedAgent](https://mlsanity.com/paper/2609.03221/) (2026)

## Abstract (arXiv)

Emergency department triage assigns patients an acuity score that determines treatment priority, and clinical evidence documents persistent gender disparities in human acuity assessment. As hospitals pilot large language models (LLMs) as triage decision support, a critical question is whether these models reproduce or mitigate known biases. We present EQUITRIAGE, a fairness audit of LLM-based ESI assignment evaluating five models (Gemini-3-Flash, Nemotron-3-Super, DeepSeek-V3.1, Mistral-Small-3.2, GPT-4.1-Nano) across 374,275 evaluations on 18,714 MIMIC-IV-ED vignettes under four prompt strategies. Of 9,368 originals, 9,346 are paired with a gender-swapped counterfactual. All five models produced flip rates above a pre-registered 5% threshold (9.9% to 43.8%). Two showed directional female undertriage (DeepSeek F/M 2.15:1, Gemini 1.34:1); two were near-parity; one had high sensitivity with weak male-direction asymmetry. DeepSeek's directional bias coexisted with a low outcome-linked calibration gap (0.013 against MIMIC-IV admission), a Chouldechova-style dissociation between within-group calibration and between-pair counterfactual invariance. Demographic blinding reduced Gemini's flip rate to 0.5%; an age-preserving blind variant left DeepSeek with residual F/M 1.25, implicating age as a residual channel. Chain-of-thought prompting degraded accuracy for all five models. A two-model ablation reveals opposite underlying mechanisms for the same directional phenotype: in Gemini the signal is emergent in the combined name+gender swap, while in DeepSeek the gender token alone carries it. EQUITRIAGE shows that group parity, counterfactual invariance, and gender calibration are distinct fairness properties, that intervention effectiveness is model-dependent, and that per-model counterfactual auditing should precede clinical deployment.