发表机构
Technological University Dublin; Aalborg University; Health Management Institute; Trinity College Dublin（都柏林理工大学; 奥尔堡大学; 健康管理研究所; 都柏林圣三一学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本研究针对缺血性卒中结局预测，探究将连续预测因子替换为符合指南的类别编码的效果，发现多数队列性能无显著差异，该分类方式是模型设计的可行选择。
AI 中文摘要
机器学习模型在急性缺血性卒中的90天结局预测中实现了较强的预测准确率，但模型解释与临床医生推理的不一致限制了其临床应用。受一项呼吁采用符合临床指南的临界值的临床医生用户研究的推动，本研究探究能否用临床信息驱动的类别编码替代连续预测因子且不损失性能。在分层为三个治疗队列的多中心欧洲登记数据上，研究者对比了标准梯度提升模型与完全分类的梯度提升模型，后者采用符合卒中指南的、针对不同治疗的阈值。结果显示，在两个治疗队列中，完全分类模型与其连续模型的预测性能无统计学差异，仅在一个队列中预测准确率显著下降。全局特征重要性排名保持一致，表明将连续预测因子离散化为基于指南的类别可在所有治疗组中保留预后因素的核心层级。因此，基于指南的分类是卒中结局模型的可行设计选择。
英文摘要
Machine learning models achieve strong predictive accuracy for 90-day outcome prediction in acute ischaemic stroke, yet clinical adoption is limited by the misalignment of model explanations with clinicians' reasoning. Motivated by a clinician user study calling for clinical guideline-aligned cut-offs, we ask whether continuous predictors can be replaced by clinically informed categorical encodings without sacrificing performance. On a multi-centre European registry stratified into three treatment cohorts, we compare standard and fully categorised gradient-boosted models, the latter using stroke guideline-aligned, treatment-specific thresholds. The fully categorised models are statistically indistinguishable from their continuous counterparts in two of the treatment cohorts, with a significant drop in predictive accuracy in one cohort. Global feature importance rankings remain consistent, suggesting that discretising continuous predictors into guideline-based categories preserves the core hierarchy of prognostic factors across all treatment groups. Guideline-based categorisation is thus a viable design choice for stroke-outcome models.
Comments9 pages, 2 figures
