Scholarlink

<p>Survival analysis in healthcare can be plagued by demographic imbalances due to fairness-oblivious model assumptions or training data biases, especially in clinically consequential domains, such as allogeneic hematopoietic cell transplantation (HCT). To address this problem, we introduce Fair Survival Analysis Transformer (FairSurvTrans), a transformer model for survival forecasting that draws ideas from the design of a large language model (LLM). The model applies positional encoding and multi-head self-attention mechanisms to structured clinical data while incorporating a dynamic fairness-conscious loss function that penalizes performance inequality across the racial subgroups. When trained using synthetically balanced HCT data, FairSurvTrans demonstrated superior predictive performance with an overall C-index value of <InlineEquation ID="IEq1"> <EquationSource Format="TEX">\(0.6738 \pm 0.0031\)</EquationSource> </InlineEquation>, while achieving the lowest fairness penalty (<InlineEquation ID="IEq2"> <EquationSource Format="TEX">\(0.0002 \pm 0.0001\)</EquationSource> </InlineEquation>) among benchmark models such as CoxPH, DeepSurv, and XGBoost-AFT. The model also made well-calibrated risk predictions for 1-year survival while maintaining an accuracy consistent across the six predefined racial groups. These results demonstrate the utility of transformer models inspired by LLM architectures in equitably facilitating interpretable, clinically actionable survival modelling, enabling more responsible deployment of AI in healthcare.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Risk-aware feature-token attention with subgroup-calibrated fairness regularization for survival

  • 期刊论文

  • 出版模式：

    开放获取

  • 发表日期：

    2026年3月10日

查看全文
  • Vijay Kalmani,
  • Siddhi Patil,
  • Amol Adamuthe

摘要

Survival analysis in healthcare can be plagued by demographic imbalances due to fairness-oblivious model assumptions or training data biases, especially in clinically consequential domains, such as allogeneic hematopoietic cell transplantation (HCT). To address this problem, we introduce Fair Survival Analysis Transformer (FairSurvTrans), a transformer model for survival forecasting that draws ideas from the design of a large language model (LLM). The model applies positional encoding and multi-head self-attention mechanisms to structured clinical data while incorporating a dynamic fairness-conscious loss function that penalizes performance inequality across the racial subgroups. When trained using synthetically balanced HCT data, FairSurvTrans demonstrated superior predictive performance with an overall C-index value of \(0.6738 \pm 0.0031\) , while achieving the lowest fairness penalty ( \(0.0002 \pm 0.0001\) ) among benchmark models such as CoxPH, DeepSurv, and XGBoost-AFT. The model also made well-calibrated risk predictions for 1-year survival while maintaining an accuracy consistent across the six predefined racial groups. These results demonstrate the utility of transformer models inspired by LLM architectures in equitably facilitating interpretable, clinically actionable survival modelling, enabling more responsible deployment of AI in healthcare.