# Improving Fairness of Large Language Model-Based ICU Mortality Prediction via Case-Based Prompting

arXiv: https://arxiv.org/abs/2512.19735 · HTML: https://mlsanity.com/paper/2512.19735/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 20 of its 78 references that are in the map.
- First posted on arXiv 17 Dec 2025.

## Builds on (most cited first, 20 of 20)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Large Language Models Encode Clinical Knowledge](https://mlsanity.com/paper/2212.13138/) (2022)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning](https://mlsanity.com/paper/2301.11916/) (2023)
- [Fairness-guided Few-shot Prompting for Large Language Models](https://mlsanity.com/paper/2303.13217/) (2023)
- [Thinking Fair and Slow: On the Efficacy of Structured Prompts for Debiasing Language Models](https://mlsanity.com/paper/2405.10431/) (2024)
- [Prompting Techniques for Reducing Social Bias in LLMs through System 1 and System 2 Cognitive Processes](https://mlsanity.com/paper/2404.17218/) (2024)
- [Prompting Fairness: Integrating Causality to Debias Large Language Models](https://mlsanity.com/paper/2403.08743/) (2024)
- [Co2PT: Mitigating Bias in Pre-trained Language Models through Counterfactual Contrastive Prompt Tuning](https://mlsanity.com/paper/2310.12490/) (2023)
- [Aligning (Medical) LLMs for (Counterfactual) Fairness](https://mlsanity.com/paper/2408.12055/) (2024)
- [FairMedQA: Benchmarking Bias in Large Language Models for Medical Question Answering](https://mlsanity.com/paper/2505.19562/) (2025)
- [Metric-Fair Prompting: Treating Similar Samples Similarly](https://mlsanity.com/paper/2512.07608/) (2025)
- [Dual-Teacher De-biasing Distillation Framework for Multi-domain Fake News Detection](https://mlsanity.com/paper/2312.01006/) (2023)
- [Monitoring fairness in machine learning models that predict patient mortality in the ICU](https://mlsanity.com/paper/2411.00190/) (2024)
- [FAST-CAD: A Fairness-Aware Framework for Non-Contact Stroke Diagnosis](https://mlsanity.com/paper/2511.08887/) (2025)
- [FunnyNodules: A Customizable Medical Dataset Tailored for Evaluating Explainable AI](https://mlsanity.com/paper/2511.15481/) (2025)

## Abstract (arXiv)

Accurately predicting mortality risk in intensive care unit (ICU) patients is critical for clinical decision-making. Large language models (LLMs) are increasingly explored for clinical prediction using structured medical data, but their outputs may exhibit demographic disparities. Mitigating such disparities without degrading predictive performance remains challenging. We systematically investigate demographic bias in LLM-based ICU mortality prediction and propose Case-Based Prompting (CAP), a training-free framework designed to improve the empirical balance between predictive performance and subgroup fairness. CAP retrieves clinically similar historical misprediction and demographic-sensitive cases with known outcomes and incorporates them as case-level contextual evidence. We further evaluate model discrimination, subgroup fairness, and feature-dependence consistency. On MIMIC-IV, CAP improved AUROC from 0.806 to 0.873 and AUPRC from 0.497 to 0.694 compared with the Baseline Prompt. CAP also reduced several subgroup disparities, particularly for sex and White-Black comparisons, although age-related disparities remained non-negligible. Controlled demographic-information ablations showed that removing demographic information did not uniformly improve both predictive performance and subgroup fairness, indicating distinct performance-fairness patterns rather than a uniform benefit from demographic suppression. Feature-dependence analysis showed generally consistent expressed clinical factor patterns across demographic subgroups. These findings suggest that CAP is a promising inference-time strategy for LLM-based clinical prediction under the evaluated retrospective setting. Further validation across additional LLMs, external datasets, and prospective clinical scenarios is required before deployment.