Early Detection of Pancreatic Cancer with Human-in-the-Loop Deep Learning

该项目的目标是利用电子健康记录(EHR)上的深度学习算法来 提高高死亡率恶性肿瘤--胰腺导管腺癌的早期诊断率 和发病率。与美国其他主要类型的癌症(如结直肠癌、前列腺癌、乳腺癌、肺癌)相比， PDAC具有独特的高死亡率，5年存活率仅为3%，主要是由于诊断的晚期。 以及恶性疾病的侵袭性。在这个K25应用中，我们的目标是开发新的结构化 系统地将人类专家领域知识纳入培训程序的方法 深度学习算法(“人在回路”方法)，以提高PDAC的早期检测。这个 这项研究的主要假设是，已经在许多其他背景下得到证明的是 专家参与PDAC预测模型的深度学习 领域知识(例如，临床工作流、统计知识)，以改进模型性能，如 以及结果的可解释性。 拟议的研究将实现三个目标。在目标1中，我们将构建以下预处理管道 可用于分析来自不同数据收集系统(国家、州和 机构)。由此产生的管道将提供针对深度优化的多模式EHR深度嵌入 在目标2和目标3中的学习应用。在目标2中，我们将研究依赖于 从临床工作流程中获取信息，并将其纳入深度学习预测模型。这个 所提出的模型将提供由单变量或复合变量表示的新的临床预测因子 分组策略。文献中的例子表明，这样的分组预测者一致地具有 与它们各自的组件相比，具有更强的预测能力。在目标3中，我们将研究因果关系 患者变量(包括在AIM 2中发现的复合变量)与PDAC风险之间的关系。我们将使用 人在环路方法，其中可能的因果关系从深度学习中暗示 模型将由人类专家(例如，临床医生、统计学家)进行评估和校正，以构建可信的 因果贝叶斯网络(CBN)可视化从患者变量到PDAC风险的因果路径。这个 由此产生的CBN将被用作开发风险评估问卷的框架，以收集患者- 生成的运行状况数据(PGHD)，它将在我未来的R01中进行进一步评估和优化，重点是 开发移动调查应用程序，以有效收集PGHD并提高早期发现 PDAC。 这项提议可能会导致新的标准来识别PDAC的高危患者并告知 有针对性的筛查做法，很可能会推广到其他类型的癌症。

The goal of this project is to leverage deep-learning algorithms on Electronic Health Records (EHRs) to improve the early detection of pancreatic ductal adenocarcinoma (PDAC), a malignancy with high mortality and morbidity. Compared to other major types of cancer in the U.S. (e.g., colorectal, prostate, breast, lung), PDAC has a uniquely high mortality with a 5-year survival of only 3%, largely due to the late stage of diagnosis and the aggressiveness of the malignancy. In this K25 application, we aim to develop novel structured methodologies for systematically incorporating human expert domain knowledge into the training procedure of deep-learning algorithms (“Human-in-the-Loop” approach) for improving the early detection of PDAC. The overarching hypothesis for this study, which has already been demonstrated in numerous other contexts, is that the “Human-in-the-Loop” approach imbues the deep learning in the PDAC prediction model with expert domain knowledge (e.g., clinical work-flows, statistical knowledge) to result in improved model performance as well as interpretability of results. The proposed research will accomplish three aims. In Aim 1, we will build preprocessing pipelines that are generalizable for analyzing multimodal data from different data collection systems (national, state, and institutional). The resultant pipelines will provide multimodal EHR deep embeddings optimized for deep learning applications in Aim 2 & 3. In Aim 2, we will investigate feature grouping strategies relying on information from clinical workflows and incorporate them into the deep learning prediction model. The proposed model will provide new clinical predictors represented by single or composite variables according to the grouping strategies. Examples in the literature show that such grouped predictors consistently have superior predictive power compared to their individual components. In Aim 3 we will study causal relationships between patient variables (including composite variables discovered in Aim 2) and the PDAC risk. We will use the Human-in-the-Loop approach where the possible causal relationships suggested from the deep learning model will be evaluated and corrected by human experts (e.g., clinicians, statisticians), to construct faithful Causal Bayesian Networks (CBNs) visualizing causal pathways from patient variables to PDAC risk. The resultant CBNs will be used as a framework for developing a risk assessment questionnaire to collect Patient- Generated Health Data (PGHD), which will be further evaluated and optimized in my future R01 focused on the development of a mobile survey application to efficiently collect PGHD and improve the early detection of PDAC. This proposal can potentially lead to new criteria for identifying high-risk patients for PDAC and inform targeted screening practices, that will likely be generalizable to other types of cancer.