Machine learning of physiological variables to predict diagnose and treat cardiorespiratory instability

机器学习生理变量来预测诊断和治疗心肺不稳定

• 批准号: 9029396
• 负责人: MICHAEL R PINSKY
• 金额: $ 66.25万
• 依托单位: UNIVERSITY OF PITTSBURGH AT PITTSBURGH
• 依托单位国家: 美国
• 财政年份: 2016
• 资助国家: 美国
• 起止时间: 2016-04-01 至 2020-03-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9029396
• 关键词: Accounting; Acute; Algorithms; Animals; Attention; Biological Neural Networks; California; Cardiovascular system; Caring; Classification; Clinical; Clinical Data; Clinical Decision Support Systems; Clinical Treatment; Complex; Coupled; Critical Illness; Data; Data Collection; Data Set; Development; Diagnosis; Disease; Effectiveness; Electronic Health Record; Engineering; Entropy; Environment; Etiology; Family suidae; Frequencies; Future; Health; Healthcare; Hemorrhage; Hemorrhagic Shock; Homeostasis; Hour; Human; Hypovolemia; Individual; Injury; Institution; Intensive Care Units; Intervention; Lead; Learning; Libraries; Machine Learning; Measures; Mechanical ventilation; Medical; Medical center; Modeling; Monitor; Normal Range; Organ; Organ failure; Pathologic Processes; Patient Monitoring; Patient-Focused Outcomes; Patients; Pattern; Physiologic Monitoring; Physiological; Principal Component Analysis; Process; Public Health; Recommendation; Refractory; Resolution; Resources; Resuscitation; Risk; Running; Sampling; Sensitivity and Specificity; Sepsis; Shock; Signal Transduction; Specificity; Stream; Stress; System; Techniques; Testing; Time; Trauma; Triage; Universities; Validation; Variant; Weaning; Work; abstracting; base; clinical care; clinically relevant; computerized data processing; cost; database structure; density; design; diagnostic accuracy; early onset; effective therapy; fitness; forest; graphical user interface; hemodynamics; high risk; improved; improved outcome; insight; iterative design; mortality; novel strategies; patient population; personalized medicine; predictive modeling; predictive tools; prospective; prototype; response; simulation; support tools; treatment response

Project Summary/Abstract: If one could accurately predict who, when and why patients develop cardiorespiratory instability (CRI), then effective preemptive treatments could be given to improve outcome and better use care resources. However, CRI is often unrecognized until it is well established and patients are more refractory to treatment, or progressed to organ injury. We have shown that an integrated monitoring system alert obtained from continuous noninvasively acquired monitoring parameters and coupled to a care algorithm improved step-down unit (SDU) patient outcomes. We also showed that advanced HR variability analysis (sample entropy) identified SDU patients at CRI risk within 2 minutes, and if monitored for 5 minutes differentiated between patients who would develop CRI or remain stable over the next 48 hours. We also applied machine learning (ML) modeling to our clinically-relevant porcine model of hemorrhagic shock to characterize responses to hypovolemia, hemorrhage, and resuscitation, predict which animals would or would not collapse during hypovolemia, and identify occult bleeding 5 minutes earlier than with traditional monitoring. We now propose to apply our work to vulnerable and invasively monitored ICU patients. We will develop multivariable models through ML data-driven classification techniques such as regression, Fourier and principal component analysis, artificial neural networks, random forest classification, etc. as well as more novel approaches (temporal rule learning developed by our team; Bayesian Aggregation) to predict CRI in ICU patients. We will first use our existing annotated high fidelity waveform MIMIC II clinical data set (4200 patients) to develop predictive models and differential signatures for various CRI drivers. We will also use our high-density data collection and processing platform (Bernoulli) to prospectively collect data from ICUs in three institutions: Univ. Pittsburgh (PITT), Univ. California (UC) Irvine and UC San Diego (initial algorithm development conducted at PITT and validated in the UC systems). We will identify the number and type of independent measures, sampling frequency, and lead time necessary to create robust algorithms to: 1) predict impending CRI, 2) select the most effective treatments, 3) monitor treatment response, and 4) determine when treatment has restored physiologic stability and can be stopped. We will also determine the smallest number and types of parameters coupled to the longest CRI lead time to achieve the above four targets with the best sensitivity and specificity (a concept we call Monitoring Parsimony).We will simultaneously iteratively design and test a graphical user interface (GUI) and clinical decision support system (CDSS) driven by these parsimoniously derived predictive smart alerts and functional hemodynamic monitoring treatment approaches in two human simulation environments (PITT & UC Irvine).We envision a basic monitoring surveillance that identifies patients most likely to develop CRI to apply focused clinician attention and targeted treatments to deliver highly personalized medical care.

项目摘要/摘要：如果一个人能够准确地预测谁、何时和为什么患者会发生 心脏呼吸不稳定(CRI)，则可以给予有效的预防性治疗以改善预后和 更好地利用护理资源。然而，CRI通常是不被认识的，直到它被很好地建立起来，患者 治疗较难治，或进展为器官损伤。我们已经证明，综合监测 从连续非侵入性获取的监控参数获得的系统警报，并与护理相结合 算法改善了降压单元(SDU)患者的预后。我们还表明，高级人力资源变异性 分析(样本熵)在2分钟内识别出有CRI风险的SDU患者，如果监测5分钟 区分可能发生CRI或在接下来的48小时内保持稳定的患者。我们也 将机器学习(ML)建模应用于我们临床相关的失血性休克猪模型 描述对低血容量、出血和复苏的反应，预测哪些动物将或将 低血容量时不崩溃，比传统监测提前5分钟发现隐匿性出血。 我们现在建议将我们的工作应用于易受侵入性监控的ICU患者。我们将发展 通过ML数据驱动分类技术的多变量模型，如回归、傅立叶和 主成分分析、人工神经网络、随机森林分类等，以及更新颖 预测ICU CRI的方法(我们团队开发的时间规则学习；贝叶斯聚合) 病人。我们将首先使用我们现有的带注释的高保真波形模拟II临床数据集(4200 患者)为不同的CRI驱动程序开发预测模型和差异签名。我们还将使用我们的 高密度数据收集和处理平台(Bernoulli)，预期在三个月内从ICU收集数据 院校：大学。匹兹堡(匹兹堡)大学加州大学欧文分校和加州大学圣地亚哥分校(初始算法 在PIT进行开发，并在UC系统中进行验证)。我们将确定数量和类型 创建稳健算法所需的独立衡量标准、采样频率和交付时间：1)预测 迫在眉睫的CRI，2)选择最有效的治疗，3)监测治疗反应，以及4)确定何时 治疗已经恢复了生理稳定，可以停止。我们还将确定最小的数字 与各类参数耦合的CRI提前期最长，实现上述四个指标的效果最好 灵敏度和特异度(我们称之为监控简约的概念)。我们将同时迭代地设计 并测试由这些驱动的图形用户界面(GUI)和临床决策支持系统(CDSS 简单易行的预测性智能警报和功能性血流动力学监测治疗方法 在两个人体模拟环境(PITT和UC Irvine)中。我们设想了一个基本的监视监视 确定最有可能发生CRI的患者，以便将重点临床医生的注意力和针对性治疗应用于 提供高度个性化的医疗服务。