Building robust methods for model explainability for healthcare

随着人工智能(AI)医疗应用的兴起，决策者现在要求预测模型具有更高的透明度。可解释性(XAI)是一项源于各种技术领域的复杂挑战。其主要目标是建立解释模型，使模型决策易于解释。我们区分了两种类型的XAI方法：(I)局部模型近似，其中简单的模型g(X)被拟合来预测预测点x附近的黑盒模型f(X)，以及(Ii)附加特征属性方法，其中无模型估计器描述了当从参考分布中移除和采样模型的一些特征时，模型在点x的结果如何变化。到目前为止，在为用例找到正确的方法方面，XAI领域还没有达成共识。此外，由于方法的不稳定性和缺乏稳健性，方法是不可靠的。归根结底，尽管临床医生经常寻求因果解释，但有限数量的XAI方法是基于因果推理。我们的目标是找到方法上的改进，以弥合统计学家和临床医生之间的差距，他们希望经常使用透明、公平的人工智能工具进行预测。我们利用统计学习理论、稳健的统计数据和医疗保健应用程序的知识来构建新的创新方法。我们的第一个研究工作的重点是解决本地解释模型中的局部性问题，并建立一个更稳健的方法来处理Shapley值，从而能够抵抗对手的攻击。与此同时，我们一直在开发在多结果因果模型中理解多受害者的方法。同时研究模型的可解释性和因果推理，有望使我们能够设计因果XAI方法。从长远来看，我们希望弥合这两个子领域之间的差距。这种在模型可解释性和因果推断方面的技术进步可以产生很高的社会影响，因为它们可以改进制定风险评分的方法，特别是医疗风险评分。这样的测量是根据预测性、非因果模型中的特征属性来构建的。最终，我们的目标是研究评估XAI方法的各种替代方案。这项任务从定义上讲是具有挑战性的，因为没有基本事实来评估这些方法。我们的目标是借用无监督学习中的想法和概念，并使其适应模型可解释性的目的。该项目属于EPSRC的两个研究领域：“人工智能和机器人”和“医疗保健技术”。

With the recent rise in medical applications of artificial intelligence (AI), decision makers are now demanding more transparency from predictive models. Explainability (XAI) is a complex challenge that stems from various technical fields. Its main goal is to build explanation model that make model decisions readily interpretable. We distinguish two types of XAI approaches: (i) local model approximations where a simple model, g(x), is fitted to predict the black boxmodel, f(x), in a neighborhood around the prediction point x, and (ii) additive feature attribution methods where a model-free estimator describes how the model outcome at a point x changes when some of its features are removed and sampled from a reference distribution. To this day, there is no consensus in the field of XAI when it comes to finding the right method for a use case. Further, methods are not reliable due to their instability and lack of robustness. Ultimately, a limited number of XAI methods are based on a causal reasoning, even though clinicians often seek causal explanations. Our aim is to find methodological improvements to bridge the gap between statisticians and clinicians who want to routinely use transparent, fair AI tools for prediction. We make use of statistical learning theory, robust statistics and knowledge of healthcare applications to build new, innovative approaches. The focus of our first research endeavor was to tackle the issue of locality in local explanation models and build a more robust approach to Shapley values that can resist adversarial attacks. In parallel, we have been developing methods for understanding poly-victimization in multi-outcome causal models. Working on both model explainability and causal inference will hopefully enable us to design causal XAI methods. Long term, we hope to bridge the gap between the two subfields. Such technical advances in model explainability and causal inference can have high social impact, as they can improve the methodology for developing risk scores, and in particularly medical risk scores. Such measures are built according to feature attributions in predictive, non-causal models. Ultimately, we aim to study various alternatives to evaluating XAI methods. This task is challenging by definition, as there is no ground truth for evaluating these methods. Our aim is to borrow ideas and concepts from unsupervised learning and adapt them to the purpose of model explainability. This project falls within two EPSRC research areas: "Artificial Intelligence and robotics" and "Healthcare technologies".