Building robust methods for model explainability for healthcare

随着人工智能（AI）在医疗领域应用的兴起，决策者现在要求预测模型具有更高的透明度。可解释性（XAI）是一个复杂的挑战，源于各种技术领域。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，其中一个简单的模型g（x），在预测点x周围的邻域中拟合预测黑盒模型f（x），以及（ii）添加性特征归因方法，其中无模型估计量描述了当从参考分布中删除并采样一些特征时，点x处的模型结果如何变化。直到今天，在XAI领域，当涉及到为用例找到正确的方法时，还没有达成共识。此外，方法由于其不稳定性和缺乏鲁棒性而不可靠。最终，有限数量的XAI方法是基于因果推理的，尽管临床医生经常寻求因果解释。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，这些临床医生希望常规使用透明、公平的人工智能工具进行预测。我们利用统计学习理论，强大的统计和医疗保健应用的知识，建立新的，创新的方法。我们第一奋进的重点是解决局部解释模型中的局部性问题，并建立一种更强大的Shapley值方法，可以抵抗对抗性攻击。与此同时，我们一直在开发用于理解多结果因果模型中的多重受害的方法。研究模型的可解释性和因果推理将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。模型可解释性和因果推理方面的技术进步可能会产生很大的社会影响，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。这些措施是根据预测性，非因果模型中的特征属性构建的。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，因为没有用于评估这些方法的基本事实。我们的目标是从无监督学习中借用思想和概念，并使其适应模型可解释性的目的。该项目福尔斯EPSRC的两个研究领域：“人工智能和机器人技术”和“医疗技术”。

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".