Case Prompting to Mitigate Large Language Model Bias for ICU Mortality Prediction

• URL: http://arxiv.org/abs/2512.19735v2
• Date: Wed, 24 Dec 2025 08:34:41 GMT
• Title: Case Prompting to Mitigate Large Language Model Bias for ICU Mortality Prediction
• Authors: Gangxiong Zhang, Yongchao Long, Yong Zhang, Yuxi Zhou, Shenda Hong,
• Abstract summary: Large language models (LLMs) show promise in predicting outcomes from structured medical data.<n>LLMs may exhibit demographic biases related to sex, age, and race, limiting their trustworthy use in clinical practice.<n>We propose a training-free, clinically adaptive prompting framework to simultaneously improve fairness and performance.
• Score: 17.91443453604627
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Accurate mortality risk prediction for intensive care unit (ICU) patients is essential for clinical decision-making. Although large language models (LLMs) show promise in predicting outcomes from structured medical data, their predictions may exhibit demographic biases related to sex, age, and race, limiting their trustworthy use in clinical practice. Existing debiasing methods often reduce predictive performance, making it difficult to jointly optimize fairness and accuracy. In this study, we systematically examine bias in LLM-based ICU mortality prediction and propose a training-free, clinically adaptive prompting framework to simultaneously improve fairness and performance. We first develop a multi-dimensional bias assessment scheme for comprehensive model diagnosis. Building on this analysis, we introduce CAse Prompting (CAP), a novel prompting framework that integrates conventional debiasing prompts with case-based reasoning. CAP guides the model to learn from similar historical misprediction cases and their correct outcomes, enabling correction of biased reasoning patterns. Experiments on the MIMIC-IV dataset show that CAP substantially improves both predictive accuracy and fairness. CAP increases AUROC from 0.806 to 0.873 and AUPRC from 0.497 to 0.694, while reducing sex- and race-related disparities by over 90%. Feature reliance analysis further indicates highly consistent attention patterns across demographic groups, with similarity scores exceeding 0.98. These results demonstrate that LLMs exhibit measurable bias in ICU mortality prediction, and that a carefully designed prompting framework can effectively co-optimize fairness and performance without retraining, offering a transferable paradigm for equitable clinical decision support.

Related papers

• Adaptive-CaRe: Adaptive Causal Regularization for Robust Outcome Prediction [16.391352325575763]
  Supervised machine learning algorithms are commonly used for outcome prediction in the medical domain.<n>We propose a novel model-agnostic regularization strategy, Adaptive-CaRe, for generalized outcome prediction in the medical domain.
  arXiv  Detail & Related papers  (2026-02-06T11:14:03Z)
• Early Mortality Prediction in ICU Patients with Hypertensive Kidney Disease Using Interpretable Machine Learning [3.4335475695580127]
  Hypertensive kidney disease (HKD) patients in intensive care units (ICUs) face high short-term mortality.<n>We developed a machine learning framework to predict 30-day in-hospital mortality among ICU patients with HKD.
  arXiv  Detail & Related papers  (2025-07-25T00:48:23Z)
• Mitigating Spurious Correlations in LLMs via Causality-Aware Post-Training [57.03005244917803]
  Large language models (LLMs) often fail on out-of-distribution (OOD) samples due to spurious correlations acquired during pre-training.<n>Here, we aim to mitigate such spurious correlations through causality-aware post-training (CAPT)<n> Experiments on the formal causal inference benchmark CLadder and the logical reasoning dataset PrOntoQA show that 3B-scale language models fine-tuned with CAPT can outperform both traditional SFT and larger LLMs on in-distribution (ID) and OOD tasks.
  arXiv  Detail & Related papers  (2025-06-11T06:30:28Z)
• Explainable AI for Mental Health Emergency Returns: Integrating LLMs with Predictive Modeling [2.466324275447403]
  Emergency department (ED) returns for mental health conditions pose a major healthcare burden, with 24-27% of patients returning within 30 days.<n>To assess whether integrating large language models (LLMs) with machine learning improves predictive accuracy and clinical interpretability of ED mental health return risk models.
  arXiv  Detail & Related papers  (2025-01-21T15:41:20Z)
• Debias-CLR: A Contrastive Learning Based Debiasing Method for Algorithmic Fairness in Healthcare Applications [0.17624347338410748]
  We proposed an implicit in-processing debiasing method to combat disparate treatment. We used clinical notes of heart failure patients and used diagnostic codes, procedure reports and physiological vitals of the patients. We found that Debias-CLR was able to reduce the Single-Category Word Embedding Association Test (SC-WEAT) effect size score when debiasing for gender and ethnicity.
  arXiv  Detail & Related papers  (2024-11-15T19:32:01Z)
• SepsisLab: Early Sepsis Prediction with Uncertainty Quantification and Active Sensing [67.8991481023825]
  Sepsis is the leading cause of in-hospital mortality in the USA. Existing predictive models are usually trained on high-quality data with few missing information. For the potential high-risk patients with low confidence due to limited observations, we propose a robust active sensing algorithm.
  arXiv  Detail & Related papers  (2024-07-24T04:47:36Z)
• Using Pre-training and Interaction Modeling for ancestry-specific disease prediction in UK Biobank [69.90493129893112]
  Recent genome-wide association studies (GWAS) have uncovered the genetic basis of complex traits, but show an under-representation of non-European descent individuals. Here, we assess whether we can improve disease prediction across diverse ancestries using multiomic data.
  arXiv  Detail & Related papers  (2024-04-26T16:39:50Z)
• Clinical Outcome Prediction from Admission Notes using Self-Supervised Knowledge Integration [55.88616573143478]
  Outcome prediction from clinical text can prevent doctors from overlooking possible risks. Diagnoses at discharge, procedures performed, in-hospital mortality and length-of-stay prediction are four common outcome prediction targets. We propose clinical outcome pre-training to integrate knowledge about patient outcomes from multiple public sources.
  arXiv  Detail & Related papers  (2021-02-08T10:26:44Z)
• Increasing the efficiency of randomized trial estimates via linear adjustment for a prognostic score [59.75318183140857]
  Estimating causal effects from randomized experiments is central to clinical research. Most methods for historical borrowing achieve reductions in variance by sacrificing strict type-I error rate control.
  arXiv  Detail & Related papers  (2020-12-17T21:10:10Z)
• A Knowledge Distillation Ensemble Framework for Predicting Short and Long-term Hospitalisation Outcomes from Electronic Health Records Data [5.844828229178025]
  Existing outcome prediction models suffer from a low recall of infrequent positive outcomes. We present a highly-scalable and robust machine learning framework to automatically predict adversity represented by mortality and ICU admission.
  arXiv  Detail & Related papers  (2020-11-18T15:56:28Z)
• UNITE: Uncertainty-based Health Risk Prediction Leveraging Multi-sourced Data [81.00385374948125]
  We present UNcertaInTy-based hEalth risk prediction (UNITE) model. UNITE provides accurate disease risk prediction and uncertainty estimation leveraging multi-sourced health data. We evaluate UNITE on real-world disease risk prediction tasks: nonalcoholic fatty liver disease (NASH) and Alzheimer's disease (AD) UNITE achieves up to 0.841 in F1 score for AD detection, up to 0.609 in PR-AUC for NASH detection, and outperforms various state-of-the-art baselines by up to $19%$ over the best baseline.
  arXiv  Detail & Related papers  (2020-10-22T02:28:11Z)

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.