Collaborative Research: SCH: Trustworthy and Explainable AI for Neurodegenerative Diseases

由于其性能准确性，机器学习（ML）已广泛用于医疗保健领域的各种应用。尽管它的表现很有希望，但研究人员和公众已经对这些原本有用和强大的模型的两个令人不安的缺陷感到震惊。首先，缺乏可信度——尽管在训练阶段有良好的实践，但ML模型在处理看不见的数据时容易受到干扰或欺骗，并表现出不稳定的行为。其次，缺乏可解释性——机器学习模型被描述为“黑盒子”，因为几乎没有解释为什么模型会做出预测。这引发了人们对机器学习在关键场景（如基于图像的疾病诊断或医疗建议）决策中的适用性的质疑。该项目的最终目标是为可信赖和可解释的人工智能（AI）开发计算基础，并为神经退行性疾病的早期诊断提供一种低成本、无创的基于ml的方法。具体来说，该项目旨在开发计算理论、机器学习算法和原型系统。该项目包括为值得信赖的机器学习开发原则性解决方案，并使机器学习预测过程对最终用户透明。后者将专注于解释机器学习模型如何以及为什么做出这样的预测，同时剖析其底层结构以获得更深入的理解。提出的模型进一步扩展到多模态和时空框架，这是将ML模型应用于医疗保健的一个重要方面。定义了与终端用户的验证框架，这将进一步提高原型系统的可信度。该项目将在可解释性、可信赖性和可验证性方面受益于各种高影响力的基于ai的应用程序。它不仅推动了深度学习和人工智能的研究前沿，而且还支持了神经退行性疾病诊断的转变。该项目将通过几项创新为可信赖和可解释的人工智能开发计算基础。首先，该项目将系统地研究机器学习系统的可信度。这将通过新的指标来衡量，如对抗鲁棒性和语义显著性，并将用于建立ML算法可信度的理论基础和实践限制。其次，该项目为可解释的人工智能提供了一个范式转变，解释了机器学习模型如何以及为什么做出预测，而不是特别的解释（即什么特征对预测很重要）。将设计一种基于证明的方法，该方法探测给定模型的所有隐藏层，以从局部角度识别涉及预测的关键层和神经元。第三，将设计一个验证框架，用户可以通过证据验证模型的性能和解释，以进一步提高系统的可信度。最后，该项目还通过以下方式推进了多模态成像和纵向数据的神经退行性疾病早期诊断的前沿：(i)在生物标志物图网络中使用基于证据的探测来识别视网膜血管生物标志物；（ii）通过跨模态可解释的人工智能模型连接视网膜和脑血管的生物标志物；并且，（iii）通过时空可解释模型识别血管生物标志物的纵向轨迹。计算机科学和医学之间的这种协同努力将使医疗保健领域的可信赖和可解释的人工智能得到广泛的应用。该项目的成果将融入研究团队开发的课程和暑期项目中，并通过专门设计的项目培养学生具有可信赖和可解释的人工智能。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Driven by its performance accuracy, machine learning (ML) has been used extensively for various applications in the healthcare domain. Despite its promising performance, researchers and the public have grown alarmed by two unsettling deficiencies of these otherwise useful and powerful models. First, there is a lack of trustworthiness - ML models are prone to interference or deception and exhibit erratic behaviors when in action dealing with unseen data, despite good practice during the training phase. Second, there is a lack of interpretability - ML models have been described as 'black-boxes' because there is little explanation for why the models make the predictions they do. This has called into question the applicability of ML to decision-making in critical scenarios such as image-based disease diagnostics or medical treatment recommendation. The ultimate goal of this project is to develop computational foundation for trustworthy and explainable Artificial Intelligence (AI), and offer a low-cost and non-invasive ML-based approach to early diagnosis of neurodegenerative diseases. In particular, the project aims to develop computational theories, ML algorithms, and prototype systems. The project includes developing principled solutions to trustworthy ML and making the ML prediction process transparent to end-users. The later will focus on explaining how and why an ML model makes such a prediction, while dissecting its underlying structure for deeper understanding. The proposed models are further extended to a multi-modal and spatial-temporal framework, an important aspect of applying ML models to healthcare. A verification framework with end-users is defined, which will further enhance the trustworthiness of the prototype systems. This project will benefit a variety of high-impact AI-based applications in terms of their explainability, trustworthy, and verifiability. It not only advances the research fronts of deep learning and AI, but also supports transformations in diagnosing neurodegenerative diseases. This project will develop the computational foundation for trustworthy and explainable AI with several innovations. First, the project will systematically study the trustworthiness of ML systems. This will be measured by novel metrics such as, adversarial robustness and semantic saliency, and will be carried out to establish the theoretical basis and practical limits of trustworthiness of ML algorithms. Second, the project provides a paradigm shift for explainable AI, explaining how and why a ML model makes its prediction, moving away from ad-hoc explanations (i.e. what features are important to the prediction). A proof-based approach, which probes all the hidden layers of a given model to identify critical layers and neurons involved in a prediction from a local point of view, will be devised. Third, a verification framework, where users can verify the model's performance and explanations with proofs, will be designed to further enhance the trustworthiness of the system. Finally, the project also advances the frontier of neurodegenerative diseases early diagnosis from multimodal imaging and longitudinal data by: (i) identifying retinal vasculature biomarkers using proof-based probing in biomarker graph networks; (ii) connecting biomarkers of the retina and the brain vasculature via cross- modality explainable AI model; and, (iii) recognizing the longitudinal trajectory of vasculature biomarkers via a spatio-temporal recurrent explainable model. This synergistic effort between computer science and medicine will enable a wide range of applications to trustworthy and explainable AI for healthcare. The results of this project will be assimilated into the courses and summer programs that the research team have developed with specially designed projects to train students with trustworthy and explainable AI.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.