Domain-Knowledge Informed Deep Learning for Early Detection of Pancreatic Cancer

项目摘要 该项目的目标是利用电子健康记录（EHR）的深度学习算法， 胰腺导管腺癌（PDAC）是一种死亡率高恶性肿瘤， 发病率。虽然已经确定了许多风险因素，但PDAC最常出现在晚期， 有效的治疗是不可行的，或者它们的生存益处是有限的。在这个R21中，我们的目标是开发新的 用于系统地结合来自专家领域的特征分组策略的结构化方法 将知识引入深度学习算法的训练过程，以改善PDAC诊断。的 这项研究的首要假设是，高度相关的变量组将联合收割机形成 与单个临床变量相比，具有上级和可解释的预测因子（当前提案）。 此外，由相关数据组表示的这些新的预测因子将对其他应用有用。 下游任务，如通过因果发现确定风险因素（未来研究）。 拟议中的研究提出了一种统一人类和人工智能的创新方法， 使用可解释的算法来构建可解释的预测模型，而不是传统的深度学习 由于其黑盒性质，人类无法追踪的算法。 创建复合（分组）变量的最佳策略还应最大化预测能力 as human-interpretability人类可解释性.因此，我们将探索各种严重依赖人类专家的分组策略 知识（例如临床工作流程）以及自相关测试。有效的分组策略将允许 我们的预测模型，以了解个人测量的相对重要性，以及可解释的 在预测PDAC中的测量组。文献中的例子表明，这种分组预测 通常具有上级预测能力，这可以归因于 组内共享信息。不同类型的可解释（注意力）神经网络也可能 根据群体特征进行应用，以进一步提高可解释性和预测性 精度 我们认为，类似的方法应用于医疗保健数据的预测建模有可能 通过改进的模型可解释性从根本上推进临床决策。的成功 一项提案将在一个更大的正在进行的项目中得到利用，该项目旨在建立新的因果关系 与PDAC相关的各种风险因素之间的关系。这涉及一种先进的基于图形的方法， 建立可解释的模型。我们在未来的研究中直接应用因果发现将是一个 收集患者生成的健康数据（PGHD）用于PDAC早期诊断的程序。

PROJECT SUMMARY The goal of this project is to leverage deep-learning algorithms on Electronic Health Records (EHRs) to improve early detection of pancreatic ductal adenocarcinoma (PDAC), a malignancy with high mortality and morbidity. Although numerous risk factors have been identified, PDAC is most often found in later stages when effective treatments are not feasible or their survival benefit is limited. In this R21, we aim to develop novel structured methodologies for systematically incorporating feature grouping strategy from expert domain knowledge into the training procedure of deep-learning algorithms for improving PDAC diagnosis. The overarching hypothesis for this study is that the groups of highly correlated variables will combine to form superior and interpretable predictors compared to individual clinical variables (current proposal). Furthermore, these new predictors represented by the group of related data will be useful for other downstream tasks such as risk factor identification via causal discovery (future research). The proposed research presents an innovative approach towards unifying human and artificial intelligence, using explainable algorithms to build interpretable prediction models, in contrast to conventional deep-learning algorithms which are non-traceable by humans due to their black-box nature. An optimal strategy for creating composite (grouped) variables should maximize both predictive power as well as human-interpretability. We will thus explore a variety of grouping strategies relying heavily on human-expert knowledge (e.g. clinical workflows) as well as auto-correlation tests. An effective grouping strategy will allow our prediction model to learn the relative importance of both individual measurements as well as interpretable groups of measurements in predicting PDAC. Examples in the literature show that such grouped predictors often have superior predictive power compared to their individual components, which can be attributed to the mutual information shared within the group. Different types of explainable (attention) neural networks may also be applied depending on the group characteristics to further improve interpretability as well as prediction accuracy. We believe that similar methodologies applied to predictive modeling in healthcare data have the potential to fundamentally advance clinical decision making with improved model interpretability. The success of this proposal will be leveraged in a larger ongoing project which aims to establish new causal relationships between various risk factors associated with PDAC. This involves an advanced graph-based approach for building interpretable models. Our direct application of causal discoveries in the future research will be a program for collecting patient-generated health data (PGHD) for PDAC early diagnosis.