调研医生对四种可解释AI技术的偏好，助力临床决策可信化。
Explainable AI for Clinical Outcome Prediction: A Survey of Clinician Perceptions and Preferences
- 对比LIME、注意力提示、病历检索和大模型生成理由四类解释方法
- 32名医生参与，发现自由文本解释最受青睐，但存在幻觉风险
- 为不同临床场景推荐适配的解释方式，指导AI系统设计
可解释人工智能（XAI）技术对于帮助临床医生理解AI预测结果并融入诊疗流程至关重要。本文针对基于电子健康记录（EHR）文本数据的预后预测模型，评估了四种XAI技术（LIME、基于注意力的片段高亮、示例患者检索、由大语言模型生成的自由文本理由）在重症监护室入院记录上预测住院死亡率时的表现。我们基于这些实现设计并开展了面向32名执业医生的问卷调查，收集其对各类解释方法的反馈与偏好。研究综合结果提出了一系列建议，说明不同XAI技术在何种情况下更适用、潜在局限性及改进方向。
原文摘要 · Abstract (English)
Explainable AI (XAI) techniques are necessary to help clinicians make sense of AI predictions and integrate predictions into their decision-making workflow. In this work, we conduct a survey study to understand clinician preference among different XAI techniques when they are used to interpret model predictions over text-based EHR data. We implement four XAI techniques (LIME, Attention-based span highlights, exemplar patient retrieval, and free-text rationales generated by LLMs) on an outcome prediction model that uses ICU admission notes to predict a patient's likelihood of experiencing in-hospital mortality. Using these XAI implementations, we design and conduct a survey study of 32 practicing clinicians, collecting their feedback and preferences on the four techniques. We synthesize our findings into a set of recommendations describing when each of the XAI techniques may be more appropriate, their potential limitations, as well as recommendations for improvement.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。