摘要
由一名新闻记者-机器人与机器学习每日新闻编辑-调查人员讨论人工智能的新发现。根据News Rx记者来自意大利罗马的新闻报道，研究表明：“获得临床医生的信任将释放人工智能(AI)在医学上的全部潜力，解释人工智能被视为建立可信系统的途径。然而，解释人工智能(XAI)在医学上的方法往往缺乏适当的评估。”这项研究的财政支持来自HORIZON EUROPE Health。我们的新闻记者引用了San Raffaele Roma O Pen University的研究，“在本文中，我们提出了我们使用前向模拟的XAI方法的评估方法，我们定义了前向模拟得分(FSS)，并分析了它在临床预测方面的局限性，然后我们将FSS应用于我们定义的ML-RO上的XAI方法。”基于多核支持向量机(SVM)算法的随机优化的机器学习临床预测器.为了比较解释阶段前后的FSS值,我们在乳腺癌、VTE和偏头痛三个临床DAT ASET上测试了我们对XAI方法的评价方法. ML-RO系统是检验基于FSS的XAI评价策略的良好模型.ML-RO在THRE数据集上执行了另外两个基本模型-决策树(DT)和普通SVM，并给出了定义不同XAI模型的可能性：TOPK，MIG F和F4G。FSS评分表明，ML-RO的解释方法F4G在三个测试数据集中最有效。本研究旨在为医学领域XAI方法的评价提供一个标准实践。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-Investigators discuss new findings in Artificial Intelligence. According to news originating from Rome, Italy, by News Rx correspondents, research stated, "Gaining clinicians' trust will unleash the full potential of artificial intelligence (AI) in medicine, and explaining AI de cisions is seen as the way to build trustworthy systems. However, explainable ar tificial intelligence (XAI) methods in medicine often lack a proper evaluation." Financial support for this research came from HORIZON EUROPE Health. Our news journalists obtained a quote from the research from San Raffaele Roma O pen University, "In this paper, we present our evaluation methodology for XAI me thods using forward simulatability. We define the Forward Simulatability Score ( FSS) and analyze its limitations in the context of clinical predictors. Then, we applied FSS to our XAI approach defined over an ML-RO, a machine learning clini cal predictor based on random optimization over a multiple kernel support vector machine (SVM) algorithm.To Compare FSS values before and after the explanation phase, we test our evaluation methodology for XAI methods on three clinical dat asets, namely breast cancer, VTE, and migraine. The ML-RO system is a good model on which to test our XAI evaluation strategy based on the FSS. Indeed, ML-RO ou tperforms two other base models-a decision tree (DT) and a plain SVM-in the thre e datasets and gives the possibility of defining different XAI models: TOPK, MIG F, and F4G. The FSS evaluation score suggests that the explanation method F4G fo r the ML-RO is the most effective in two datasets out of the three tested, and i t shows the limits of the learned model for one dataset. Our study aims to intro duce a standard practice for evaluating XAI methods in medicine."
NETL
NSTL