Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences.
Ada-WHIPS: explaining AdaBoost classification with applications in the health sciences.
复制标题
DOI：
10.1186/s12911-020-01201-2
复制
发表时间：
2020-10-02
影响因子：
3.5
通讯作者：
Atif Azad RM
中科院分区：
文献类型：
--
作者：
Hatwell J;Gaber MM;Atif Azad RM
计算机辅助诊断（CAD）可以帮助医生对病人的病情做出关键的决定。从业人员需要了解CAD背后的推理链，以建立对CAD建议的信任，并补充自己的专业知识。然而，CAD系统可能基于黑箱机器学习模型和高维数据源，如电子健康记录、磁共振成像扫描、心脏图等。这些基础使得对CAD建议的解释和解释非常具有挑战性。这一挑战在整个机器学习研究界都得到了认可。可解释人工智能（XAI）是近年来最重要的研究领域之一，因为它解决了关键决策者（包括临床和医疗实践中的决策者）的可解释性和信任问题。在这项工作中，我们专注于AdaBoost，一个在CAD文献中被广泛采用的黑盒模型。我们用一种从AdaBoost模型中提取简单逻辑规则的新算法来解决这一挑战——解释AdaBoost分类。我们的算法，自适应加权高重要性路径片段（ada - whps），利用AdaBoost的自适应分类器权重。ada - whps使用一种新颖的公式，在AdaBoost模型内部决策树的各个决策节点之间唯一地重新分配权重。然后，对加权节点进行简单的启发式搜索，找到支配模型决策的单个规则。在一项实验研究中，我们比较了由我们的新方法产生的解释和最新的解释。我们通过简单的统计测试来评估推导出的解释，这些测试包括众所周知的质量测量、精度和覆盖率，以及更适合XAI设置的新测量稳定性。对9个cad相关数据集的实验表明，Ada-WHIPS的解释始终优于现有的解释（平均覆盖率为15%-68%），同时在特异性方面仍具有竞争力（平均精度为80%-99%）。在特异性上的一个很小的权衡被证明可以防止过度拟合，这是目前最先进的方法中一个已知的问题。实验结果表明，使用我们的新算法来解释文献中广泛发现的CAD AdaBoost分类器的好处。我们的紧密耦合、adaboost特定的方法优于与模型无关的解释方法，应该被为这类模型寻找XAI解决方案的实践者考虑。
Computer Aided Diagnostics (CAD) can support medical practitioners to make critical decisions about their patients’ disease conditions. Practitioners require access to the chain of reasoning behind CAD to build trust in the CAD advice and to supplement their own expertise. Yet, CAD systems might be based on black box machine learning models and high dimensional data sources such as electronic health records, magnetic resonance imaging scans, cardiotocograms, etc. These foundations make interpretation and explanation of the CAD advice very challenging. This challenge is recognised throughout the machine learning research community. eXplainable Artificial Intelligence (XAI) is emerging as one of the most important research areas of recent years because it addresses the interpretability and trust concerns of critical decision makers, including those in clinical and medical practice. In this work, we focus on AdaBoost, a black box model that has been widely adopted in the CAD literature. We address the challenge – to explain AdaBoost classification – with a novel algorithm that extracts simple, logical rules from AdaBoost models. Our algorithm, Adaptive-Weighted High Importance Path Snippets (Ada-WHIPS), makes use of AdaBoost’s adaptive classifier weights. Using a novel formulation, Ada-WHIPS uniquely redistributes the weights among individual decision nodes of the internal decision trees of the AdaBoost model. Then, a simple heuristic search of the weighted nodes finds a single rule that dominated the model’s decision. We compare the explanations generated by our novel approach with the state of the art in an experimental study. We evaluate the derived explanations with simple statistical tests of well-known quality measures, precision and coverage, and a novel measure stability that is better suited to the XAI setting. Experiments on 9 CAD-related data sets showed that Ada-WHIPS explanations consistently generalise better (mean coverage 15%-68%) than the state of the art while remaining competitive for specificity (mean precision 80%-99%). A very small trade-off in specificity is shown to guard against over-fitting which is a known problem in the state of the art methods. The experimental results demonstrate the benefits of using our novel algorithm for explaining CAD AdaBoost classifiers widely found in the literature. Our tightly coupled, AdaBoost-specific approach outperforms model-agnostic explanation methods and should be considered by practitioners looking for an XAI solution for this class of models.
登录
查看更多内容
影响因子：
3.9
作者：
El-Sappagh, Shaker;Alonso, Jose M.;Kwak, Kyung-Sup
通讯作者：
Kwak, Kyung-Sup
影响因子：
3.9
作者：
Adadi, Amina;Berrada, Mohammed
通讯作者：
Berrada, Mohammed
影响因子：
4.5
作者：
Friedman, J;Hastie, T;Tibshirani, R
通讯作者：
Tibshirani, R
影响因子：
8.8
作者：
Acharya, U. Rajendra;Sudarshan, Vidya K.;Sankaranarayanan, Meena
通讯作者：
Sankaranarayanan, Meena
影响因子：
1.1
作者：
Freund, Y;Schapire, RE
通讯作者：
Schapire, RE