Machine Learning of Physiological Waveforms and Electronic Health Record Data to Predict, Diagnose, and Treat Hemodynamic Instability in Surgical Patients

生理波形和电子健康记录数据的机器学习可预测、诊断和治疗手术患者的血流动力学不稳定

• 批准号: 10330420
• 负责人: Maxime Cannesson
• 金额: $ 74.66万
• 依托单位: UNIVERSITY OF CALIFORNIA LOS ANGELES
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-01-07 至 2023-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10330420
• 关键词: Acute; Adopted; Air; Algorithms; American; Anesthesia procedures; Animals; Architecture; Calibration; California; Caring; Cessation of life; Characteristics; Classification; Clinical; Clinical Decision Support Systems; Clinical Management; Clinical Research; Complex; Critical Care; Data; Data Set; Databases; Development; Diagnosis; Disease; Documentation; Effectiveness; Electronic Health Record; Environment; Etiology; Evaluation; Frequencies; Goals; Health; Healthcare; Healthcare Systems; Homeostasis; Hospital Mortality; Hospitals; Hypotension; Insufflation; Intensive Care Units; Intervention; Intra-abdominal; Intraoperative Care; Intraoperative Period; Intubation; Knowledge; Lead; Los Angeles; Machine Learning; Measures; Medical center; Modeling; Monitor; Nature; Operating Rooms; Operative Surgical Procedures; Outcome; Pathologic Processes; Patient Care; Patients; Pattern; Perioperative; Phase; Physiological; Postoperative Complications; Postoperative Period; Process; Recommendation; Registries; Resources; Resuscitation; Reverse engineering; Running; Sampling; Shock; Signal Transduction; Skin; Specificity; Stress; Surgical incisions; System; Techniques; Testing; Time; Titrations; Training; Universities; Validation; Variant; Work; base; clinical care; clinical decision support; clinical risk; cohort; data integration; data streams; data structure; database structure; deep neural network; demographics; density; diagnostic accuracy; effectiveness evaluation; electronic data; graphical user interface; hemodynamics; high risk; improved; information display; insight; interoperability; iterative design; large datasets; machine learning algorithm; machine learning model; model development; mortality; neural network algorithm; novel; organ injury; patient population; personalized medicine; preconditioning; predictive modeling; predictive tools; pressure; prospective; prototype; relational database; response; risk prediction; simulation environment; stressor; support tools; surgical risk; tool; treatment response

Project Summary / Abstract If one could accurately predict who, when and why patients develop cardiorespiratory instability (CRI) during surgery, then effective preemptive treatments could be given to improve postoperative outcome and more effectively use healthcare resources. But signs of shock often occur late once organ injury is already present. The goal of this proposal is to develop, validate, and test real-time intraoperative risk prediction tools based on electronic health record (EHR) data and high-fidelity physiological waveforms to predict CRI and make the databases of intraoperative data and waveforms used for these developments freely accessible. This is extremely relevant because although 5.7 million Americans are admitted to an Intensive Care Units (ICU) in one year, more than 42 millions undergo surgery annually. Previous and ongoing studies conducted in the ICU and in the step down unit have built the architecture to collect real-time high-fidelity physiological waveform data streams and integrate them with patient demographics from the EHR to build large data sets, and derive actionable fused parameters based on machine learning (ML) analytics as well as display information in real time at the bedside to drive clinical decision support (CDS) in the critical care setting. The goal of this proposal is to apply these ML approaches to the complex and time compressed environment of high-risk surgery where greater patient and disease variability exist and shorter period of time is available to deliver truly personalized medicine approaches. The work will be initiated using an already existing annotated intraoperative database from the University of California Irvine including EHR and high-fidelity waveform data. This operating room database already exists and needs only to be extracted. This data will be used for the initial training and development of the ML model that will then be tested on prospectively collected University of California Los Angeles and University of Pittsburgh Medical Center databases. Simultaneously, this approach will use existing knowledge of CRI patterns derived from previous step down unit / intensive care unit cohorts, MIMIC II data, University of California Irvine data, and animal studies to create smart alarms and graphic user interface for clinical decision support based on functional hemodynamic monitoring principles. The next step will then leverage the focus on the issues and strengths of the intraoperative environment, some of which can be listed as: 1) Known patients characteristics before surgery to define pre-stress baseline, allowing functional hemodynamic monitoring stress evaluations, preconditioning, and other preoperative calibrations, 2) High degree of direct observation and data density during most phases of surgery allowing close semi-autonomous monitoring and titration of novel treatment algorithms early, 3) Defined stages in the initial part of surgery (induction, intubation, skin incision) allowing ML approaches to build large common relational database registries, and 4) Defined surgical procedure and stressors (anesthesia induction, intra-abdominal air insufflation, and other surgery-specific interventions), which will alter the impact of CRI on measured variables.

项目概要/摘要 如果能够准确预测谁、何时以及为何患者在治疗过程中出现心肺不稳定 (CRI) 手术，然后可以给予有效的预防性治疗以改善术后结果等 有效利用医疗资源。但是，一旦器官损伤已经存在，休克的迹象通常会出现得很晚。 该提案的目标是开发、验证和测试基于以下内容的实时术中风险预测工具： 电子健康记录 (EHR) 数据和高保真生理波形来预测 CRI 并制定 用于这些开发的术中数据和波形数据库可免费访问。这是 极其相关，因为尽管一年内就有 570 万美国人住进重症监护病房 (ICU) 每年有超过 4200 万人接受手术。之前和正在进行的在 ICU 进行的研究 在降压单元中构建了采集实时高保真生理波形数据的架构 将其与 EHR 中的患者人口统计数据进行流处理，以构建大型数据集，并得出 基于机器学习 (ML) 分析的可操作融合参数以及真实显示信息 在重症监护环境中，在床边推动临床决策支持 (CDS) 的时间。本提案的目标 就是将这些机器学习方法应用于高风险手术的复杂且时间压缩的环境中 存在更大的患者和疾病变异性，并且可以在更短的时间内提供真正的个性化服务 医学方法。这项工作将使用现有的带注释的术中数据库启动 来自加州大学欧文分校，包括 EHR 和高保真波形数据。这个手术室 数据库已经存在，只需提取即可。该数据将用于初始训练和 开发 ML 模型，然后在预期收集的加州大学洛杉矶分校上进行测试 安吉利斯和匹兹堡大学医学中心数据库。同时，该方法将利用现有的 来自先前降压病房/重症监护病房队列的 CRI 模式知识、MIMIC II 数据、 加州大学欧文分校数据和动物研究创建智能警报和图形用户界面 基于功能性血流动力学监测原则的临床决策支持。然后下一步将 重点关注术中环境的问题和优势，其中一些可以列出 如下： 1) 手术前已知患者特征，以确定预应力基线，允许功能性评估 血流动力学监测、压力评估、预处理和其他术前校准，2) 高 在手术的大多数阶段直接观察的程度和数据密度允许接近的半自主 早期监测和调整新的治疗算法，3) 手术初始阶段的明确阶段 （诱导、插管、皮肤切开）允许机器学习方法构建大型通用关系数据库 登记处，以及 4) 明确的手术程序和压力源（麻醉诱导、腹腔内吹气、 和其他手术特定的干预措施），这将改变 CRI 对测量变量的影响。