Summarizing Cardiac Data: An Automated Approach for Identifying Representative Heartbeats in the Clinical Setting

总结心脏数据：在临床环境中识别代表性心跳的自动方法

• 批准号: 10515222
• 负责人: Emily Hendryx Lyons
• 金额: $ 37.54万
• 依托单位: UNIVERSITY OF CENTRAL OKLAHOMA
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-08-02 至 2025-07-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10515222
• 关键词: 3-Dimensional; Address; Adult; Algorithm Design; Algorithms; Architecture; Area; Arrhythmia; Attention; Automated Clinical Decision Support; Cardiac; Cardiac health; Caring; Childhood; Classification; Clinical; Clinical Data; Collaborations; Communities; Computerized Medical Record; Coupled; Data; Data Analyses; Data Science; Data Set; Detection; Development; Electrocardiogram; Electrodes; Future; Goals; Hospitals; Hour; Human; Interdisciplinary Study; Lead; Learning; Literature; Mathematics; Medical; Medicine; Methods; Modeling; Monitor; Morphologic artifacts; Morphology; Movement; Noise; Oklahoma; Output; Pathology; Patient-Focused Outcomes; Patients; Pediatric Hospitals; Physiological; Population; Process; Recording of previous events; Research; Research Personnel; Scheme; Series; Signal Transduction; Sinus; Stream; Structure; Students; Techniques; Texas; Time; Training; Universities; Variant; Work; autoencoder; biomedical informatics; cardiac intensive care unit; clinical decision support; clinical decision-making; college; cost; deep learning; deep learning algorithm; experience; experimental study; heart rhythm; improved; innovation; insight; interest; mathematical model; metropolitan; novel; patient health information; patient population; pediatric patients; prediction algorithm; predictive modeling; statistics; support tools; trustworthiness; undergraduate student

Project Summary/Abstract With a constant stream of patient data generated at the hospital bedside, clinicians are asked to interpret this data along with patient medical records and lab results in real time. The proposed project offers an approach to automated clinical decision support (CDS) in parsing through some of this abundant data, focusing on the time series summarization (TSS) of the electrocardiogram (ECG) and approximations to the related vectorcardiogram (VCG) using techniques at the interface of data science and applied mathematics. Given the fact that bedside monitor signals can be corrupted by noise, it is important to distinguish between noise/artifact, cardiac arrhythmia, and normal cardiac rhythms; while the literature approaching such issues is growing, there is still a need for addressing this problem for the pediatric population – especially for pediatric patients with electrical conduction abnormalities as seen in the Cardiac Intensive Care Unit (CICU). Through collaboration between investigators at the University of Central Oklahoma (UCO) and at Baylor College of Medicine and Texas Children’s Hospital (TCH), this project combines the application of deep learning algorithms and subset selection techniques such as the discrete empirical interpolation method (DEIM) to classify and summarize data recorded from the pediatric CICU at TCH. Specifically, the objective of this project is two-fold: (1) apply variational autoencoders (VAEs) to differentiate between noise, arrhythmias, and normal sinus rhythm, and (2) evaluate both existing and newly developed subset selection algorithms, with an added emphasis on DEIM-related methods in application to cardiac data. Undergraduate students at UCO will evaluate VAE architectures for noise detection, performing model selection and then applying the chosen model to patient data for further analysis. Additional VAE models will be trained and selected for recognizing ECG and VCG waveforms containing pathologies. VAE results will be compared to those generated using existing methods in the literature and will inform the subsequent summarization of patient data. While DEIM has demonstrated viability in class- identification tasks in prior work, DEIM and its related methods were originally developed for applications such as mathematical model reduction, not class identification. For this reason, students will perform a necessary comparison of DEIM-related methods applied to a variety of data types, giving particular attention to experiments involving ECG waveforms; while doing so, students will also develop a novel extension of such methods tailored to this specific medical context. In addition, the comparison of these techniques for class identification purposes will offer valuable insight regarding DEIM-related methods to both the larger biomedical informatics and data science communities. Once established, this TSS framework will provide a means of presenting to clinicians a representation of a patient’s recent cardiac health history, information that can be used as-is and as input to other predictive models. If met, this long-term goal will provide CDS toward improving patient outcomes while giving undergraduate students an opportunity to participate in innovative interdisciplinary research.

项目总结/摘要 随着医院床边不断产生的患者数据流，临床医生被要求解释这一点 数据沿着患者医疗记录和实验室结果在真实的时间。拟议的项目提供了一种方法， 自动化临床决策支持（CDS）在分析这些丰富的数据，重点是时间 心电图（ECG）的系列摘要（TSS）和相关心电向量图的近似值 (VCG)使用数据科学和应用数学的接口技术。考虑到床边 监护仪信号可能被噪声破坏，因此区分噪声/伪影、心脏 心律失常和正常的心律;虽然接近这些问题的文献越来越多，但仍然存在一个 需要解决儿科人群的这个问题-特别是对于患有电气疾病的儿科患者 心脏重症监护室（CICU）中观察到的传导异常。通过合作， 中央俄克拉荷马州大学（UCO）、贝勒医学院和得克萨斯州的研究人员 儿童医院（TCH），这个项目结合了深度学习算法和子集选择的应用 离散经验插值法（DEIM）等技术对记录的数据进行分类和汇总 儿科重症监护室送来的具体而言，本项目的目标是双重的：（1）应用变分 自动编码器（VAE），以区分噪声、心律失常和正常窦性心律，以及（2）评估 现有的和新开发的子集选择算法，重点是DEIM相关的 应用于心脏数据的方法。UCO的本科生将评估VAE架构的噪声 检测，执行模型选择，然后将所选择的模型应用于患者数据以进行进一步分析。 将训练和选择额外的VAE模型，用于识别ECG和VCG波形， 病理学。VAE结果将与文献中使用现有方法生成的结果进行比较， 通知后续的患者数据汇总。虽然DEIM在课堂上展示了可行性- 在先前的工作中，DEIM及其相关方法最初是为以下应用开发的， 作为数学模型简化，而不是类识别。为此，学生将进行必要的 比较DEIM相关方法应用于各种数据类型，特别注意实验 涉及心电图波形;同时，学生还将开发一种新的扩展这种方法量身定制 这个特定的医学背景。此外，比较这些技术用于类别识别的目的 将为更大的生物医学信息学和数据提供有关DEIM相关方法的宝贵见解 科学界。一旦建立，该TSS框架将提供一种向临床医生呈现 患者最近的心脏健康史的表示，可以原样使用和作为输入的信息， 其他预测模型。如果实现，这一长期目标将为改善患者结局提供CDS， 让本科生有机会参与创新的跨学科研究。