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

• URL: http://arxiv.org/abs/2605.03998v1
• Date: Tue, 05 May 2026 17:20:55 GMT
• Title: EQUITRIAGE: A Fairness Audit of Gender Bias in LLM-Based Emergency Department Triage
• Abstract summary: We present EQUITRIAGE, a fairness audit of large language models (LLMs) in emergency departments.<n>All five models produced flip rates above a pre-registered 5% threshold.<n>Group parity, counterfactual invariance, and gender calibration are distinct fairness properties.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Not All Relations Are Equal: Relation-Balanced and Calibrated Graph Learning for Provenance-Based Intrusion Detection [66.44527094471619]
  We present RECAL, an unsupervised framework using relation-balanced masked graph learning to better capture rare interaction patterns.<n>On three DARPA E3 datasets, RECAL achieves F1 scores of 99.99%, 99.93%, and 99.99%, outperforming the best baseline on each dataset by 0.88, 0.82, and 0.42 percentage points, respectively.
  arXiv  Detail & Related papers  (2026-09-15T00:31:01Z)
• RareLens: Towards End-to-End Rare Disease Care via Aligning Divergent Large Language Model Reasoning [42.80742579670377]
  RareLens is a system that supports clinical decision-making across the entire rare disease trajectory.<n>Developed and evaluated on RareBench, a real-world dataset of 157,525 cases spanning all 33 Orphanet categories and more than 7,000 conditions.<n>It achieved an area under the curve of 0.917 for screening and top-1 accuracies of 65.5% and 89.8% for diagnosis and treatment.
  arXiv  Detail & Related papers  (2026-07-25T16:58:10Z)
• A Controlled Audit of Pretraining Contamination in Public Medical Vision-Language Benchmarks [46.43161388634735]
  Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely downloadable for years.<n>We audit open VLMs on SLAKE-En, PathVQA, VQA-RAD, and an auxiliary public OmniMedVQA mirror using four detector families.
  arXiv  Detail & Related papers  (2026-06-08T18:40:10Z)
• Gender-Dependent Diagnostic Substitution in LLM Medical Triage: Same Symptoms, Unequal Urgency [0.0]
  We investigate whether large language models produce different medical triage recommendations for identical neurological symptoms when only the patient's gender and age vary.<n>We present a standardized symptom profile across seven demographic conditions.<n>We find a stark, systemic gender-dependent triage disparity.
  arXiv  Detail & Related papers  (2026-06-02T13:35:12Z)
• Compared to What? Baselines and Metrics for Counterfactual Prompting [39.56472929066589]
  We observe prediction flip rates on MedQA of 14.9% when we surgically change patient gender.<n>We propose a framework in which we compare differences observed under target interventions to those induced by paraphrasing inputs.<n>We find that these effects largely dissipate when we account for general model sensitivity.
  arXiv  Detail & Related papers  (2026-05-01T19:23:33Z)
• PsychBench: Auditing Epidemiological Fidelity in Large Language Model Mental Health Simulations [0.0]
  Large language models are increasingly deployed to simulate patients for clinical training, research, and mental health tools.<n>We introduce PsychBench, the first epidemiological audit of LLM patient simulation.<n>We show that models produce clinically plausible individuals while misrepresenting the populations they are drawn from.
  arXiv  Detail & Related papers  (2026-04-19T10:05:25Z)
• How Independent are Large Language Models? A Statistical Framework for Auditing Behavioral Entanglement and Reweighting Verifier Ensembles [46.63622714488747]
  Shared pretraining data, distillation, and alignment pipelines can induce hidden behavioral dependencies, latent entanglement.<n>In practice, this manifests as correlated reasoning patterns and synchronized failures.<n>We develop a statistical framework for auditing behavioral entanglement among black-box language models.
  arXiv  Detail & Related papers  (2026-04-08T23:32:06Z)
• Robust Fair Disease Diagnosis in CT Images [6.957497306200416]
  Class imbalance and group underrepresentation often coincide, creating compound failure modes.<n>We introduce a two-level objective that targets both axes of this problem.<n>We evaluate on the Fair Disease Diagnosis benchmark using a 3D ResNet-18 pretrained on Kinetics-400.
  arXiv  Detail & Related papers  (2026-04-08T03:37:44Z)
• FairMed-XGB: A Bayesian-Optimised Multi-Metric Framework with Explainability for Demographic Equity in Critical Healthcare Data [1.7915158401181968]
  Machine learning models deployed in critical care settings exhibit demographic biases, particularly gender disparities.<n>This paper introduces FairMed-XGB, a novel framework that systematically detects and mitigates gender-based prediction bias.<n>FairMed-XGB offers a robust, interpretable, and ethically aligned solution for equitable clinical decision-making.
  arXiv  Detail & Related papers  (2026-03-16T07:57:40Z)
• Evaluating the Presence of Sex Bias in Clinical Reasoning by Large Language Models [0.5872014229110214]
  Large language models (LLMs) are increasingly embedded in healthcare for documentation, education, and clinical decision support.<n>We examined whether contemporary LLMs exhibit sex-specific biases in clinical reasoning and how model configuration influences these behaviours.
  arXiv  Detail & Related papers  (2026-02-04T10:21:38Z)
• Transparent Early ICU Mortality Prediction with Clinical Transformer and Per-Case Modality Attribution [42.85462513661566]
  We present a lightweight, transparent multimodal ensemble that fuses physiological time-series measurements with unstructured clinical notes from the first 48 hours of an ICU stay.<n>A logistic regression model combines predictions from two modality-specific models: a bidirectional LSTM for vitals and a finetuned ClinicalModernBERT transformer for notes.<n>On the MIMIC-III benchmark, our late-fusion ensemble improves discrimination over the best single model while maintaining well-calibrated predictions.
  arXiv  Detail & Related papers  (2025-11-19T20:11:49Z)
• MeCaMIL: Causality-Aware Multiple Instance Learning for Fair and Interpretable Whole Slide Image Diagnosis [40.3028468133626]
  Multiple instance learning (MIL) has emerged as the dominant paradigm for whole slide image (WSI) analysis in computational pathology.<n>textbfMeCaMIL, a causality-aware MIL framework, explicitly models demographic confounders through structured causal graphs.<n>MeCaMIL achieves superior fairness -- demographic disparity variance drops by over 65% relative reduction on average across attributes.
  arXiv  Detail & Related papers  (2025-11-14T06:47:21Z)
• MEDEQUALQA: Evaluating Biases in LLMs with Counterfactual Reasoning [7.167933033102407]
  We introduce MEDEQUALQA, a counterfactual benchmark that perturbs only patient pronouns while holding critical symptoms and conditions constant.<n>We evaluate a GPT-4.1 model and compute Semantic Textual Similarity (STS) between reasoning traces to measure stability across pronoun variants.<n>Our results show overall high similarity (mean STS >0.80), but reveal consistent localized divergences in cited risk factors, guideline anchors, and differential ordering.
  arXiv  Detail & Related papers  (2025-10-09T22:12:58Z)
• Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation [116.86965910589775]
  We show that even minimal perturbations, such as masking just 10% of objects or weakly blurring backgrounds, can dramatically alter bias scores.<n>This suggests that current bias evaluations reflect model responses to spurious features rather than gender bias.
  arXiv  Detail & Related papers  (2025-09-09T11:14:11Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.