用谱熵量化XAI对心电图信号引入的噪声，提升解释可信度。
Quantifying Explainable AI-introduced signal noise on ECG data with Spectral Entropy
- 提出谱熵衡量XAI生成解释中的信号噪声
- 在心律失常分类任务中验证不同解释方法的噪声水平
- 适合关注医疗AI可解释性与信噪比的研究者
可解释性技术用于评估各类深度学习模型的输出，尤其在医疗领域，模型需具备可信赖性和决策可解释性。现有的可解释性（XAI）工具依赖启发式方法，常在解释结果中引入信号噪声。目前难以区分模型真实信号与XAI带来的噪声。本文提出使用谱熵作为衡量XAI输出中噪声程度的指标。在心电图数据集上，通过多种后处理可解释性技术对心律失常进行分类，验证了该方法的有效性。结果表明，谱熵能有效量化不同解释方法引入的噪声水平，有助于筛选更可靠的解释结果。
原文摘要 · Abstract (English)
Explainability techniques are used to assess the output of various deep learning models. This is especially true in healthcare, where models need to be trusted and decisions justified. Explainability (XAI) tools use heuristics which often add signal noise to the explanation "core". It is not always obvious what is signal from the model and what is noise from the XAI. We propose the use of spectral entropy as a measure of noise in XAI output. We demonstrate its usefulness in the context of classifying arrhythmias in an ECG dataset with different post hoc explainability techniques.
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。