Deep Learning and Streaming Analytics for Prediction of Adverse Events in the ICU

用于预测 ICU 不良事件的深度学习和流分析

基本信息

批准号：
9983413
负责人：
SHAMIM NEMATI
金额：
$ 19.02万
依托单位：
UNIVERSITY OF CALIFORNIA, SAN DIEGO
依托单位国家：
美国
项目类别：
财政年份：
2019
资助国家：
美国
起止时间：
2019-08-03 至 2021-07-31
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/9983413
关键词：
Address Adverse event Affect Algorithms American Antibiotics Antihypertensive Agents Beds Benchmarking Big Data Blood Pressure Caring Clinic Clinical Clinical Data Collection Communication Computerized Medical Record Computers Critical Care Critical Illness Data Data Analyses Data Set Databases Decision Trees Deterioration Differential Equation Disease Progression Early Diagnosis Ensure Environment Goals Heart Rate Hospital Mortality Hospitalization Hospitals Hour Inflammation Inflammation Mediators Inflammatory Response Intensive Care Units Intervention Intravenous Laboratories Link Liquid substance Literature Machine Learning Measurement Medical Medicare Medicine Methods Microbiology Modeling Modernization Monitor Morphologic artifacts Nature Organ Pathologic Patient Monitoring Patients Pattern Pattern Recognition Performance Pharmaceutical Preparations Physiological Reporting Reproducibility Research Research Personnel Resolution Resuscitation Risk Risk Assessment Risk stratification SCAP2 gene Sampling Sepsis Series Serum Severity of illness Stream System Techniques Technology Telemedicine Testing Therapeutic Intervention Time United States Validation Visit Work base beneficiary cohort cost data acquisition deep learning experience feeding high dimensionality improved machine learning algorithm mathematical model mortality risk multi-scale modeling multimodality novel outcome forecast parallel computer patient safety physiologic model portability prognostic public health relevance respiratory safety practice sensor septic patients simulation standard of care time use

项目摘要

DESCRIPTION (provided by applicant) Critical care medicine in the United States costs over 80 billion dollars annually. Over the past decade the rate of intensive care unit (ICU) use has been increasing, with a recent study reporting almost one in three Medicare beneficiaries experiencing an ICU visit during the last month of their lives. Every year, sepsis, a medical condition characterized by whole-body inflammation, strikes between 800,000 and 3.1 million Americans, killing approximately one in four patients affected. There is currently no definite treatment for sepsis in spite of many clinicl trials. However, early detection of sepsis and timely initiation of interventions are widely considered as important determinants of patient survival. However, basic care tasks (such as microbiological sampling and antibiotic delivery within 1 h, fluid resuscitation, and risk stratification using serum lactate or alternative), which are known to benefit most patients, are not performed in a timely manner. Previous literature suggests that high-resolution vital signs (such as heart rate, blood pressure, respiratory rate, etc.), and other sequential measurements within the electronic medical records (EMRs), can be dynamically integrated using Machine Learning techniques to help with early detection of sepsis. With the ubiquity of inexpensive high- capacity storage and high-bandwidth streaming technology it is now possible to monitor patients' vital signs continuously (for instance, the research application developed by the Emory hospital ICU uses IBM's streaming analytics platform to transmit over 100,000 real-time data points per 100 beds, per second). Despite this continuous feed of data, commonly used acuity scores, such as APACHE and SAPS, are based on snapshot values of these vital signs (typically the worst values during a 24 hours period). This limitation is partially due to unavailability of computationally efficient and robust algorithms capable of finding predictive features in multivariate, nonlinear and nonstationary sequential data, which may reveal inter- organ communication and disintegration of causal couplings with critical illnesses such as sepsis. We have recently developed a novel Machine Learning algorithm to discover automatically a collection of predictive multivariate dynamical patterns in a database of patient time-series, which can be used to classify patients or to monitor progression of disease in a given patient. The primary goal of this proposal is to apply our method to assess the predictive power of high- resolution multivariate time-series of vital signs and sequentially recorded EMR data in the ICU for early detection of sepsis and risk stratification of septic patient. To accomplish this, we aim to benchmark our technique on a large ICU cohort (the MIMIC II database with over 60,000 patients), as well as simulated data from a multiscale mathematical model of influence of inflammatory mediators on dynamical patterns of vital signs. Next, the technique will be externally validated on two separate ICU sepsis cohorts (the Emory Sepsis dataset and the Mayo Clinic Metric dataset). Finally, we will provide a real-time implementation of the proposed algorithm in an streaming environment (such as the IBM streaming analytics), in order to address the Big Data challenge of harnessing real-time, streaming sensor data from bedside monitors within the ICU, while enabling advanced pattern recognition and real-time forecasting. Ultimately we believe these methods can change the current standard of care through faster recognition and initiation of basic care, as well as guiding interventional strategis based on severity of illness and mechanisms underlying physiological deterioration.

描述（由申请人提供）美国的重症监护医学每年耗资超过800亿美元。在过去的十年中，重症监护室（ICU）的使用率一直在增加，最近的一项研究报告了三分之一的Medicare受益人在其生命的最后一个月中经历了ICU访问。每年，败血症是一种以全身感染为特征的医疗状况，罢工在80万至310万美国人中，杀死了大约四分之一的患者。尽管有许多临床试验，但目前尚无针对败血症的定义治疗方法。但是，早期检测败血症和及时开始干预措施被普遍认为是患者生存的重要决定剂。但是，基本的护理任务（例如1小时内的微生物采样和抗生素递送，流体复苏以及使用血清乳酸或替代性的风险分层），已知会使大多数患者受益的风险分层，并未及时进行。以前的文献表明，可以使用机器学习技术动态整合了高分辨率的生命体征（例如心率，血压，呼吸率等）以及电子病历（EMR）内的其他顺序测量，以帮助早期检测到脓毒症。凭借廉价的高容量存储和高带宽流媒体技术的普遍性，现在可以连续监测患者的生命体征（例如，由Emory Hospital ICU开发的研究应用程序使用IBM的流媒体分析平台来传输超过100,000多个每100床的实时数据点的超过100,000个实时数据点）。尽管存在这种连续的数据，但通常使用的敏锐度得分（例如Apache和SAPS）基于这些生命体征的快照值（通常是24小时内最差的值）。这种局限性部分是由于能够在多元，非线性和非组织顺序数据中找到预测特征的计算有效且可靠的算法的不可用，这可能会揭示与症状疾病（如脓毒症）的催化偶联的催化偶联的催化偶联。我们最近开发了一种新型的机器学习算法，以自动发现患者时间序列数据库中的预测性多元动态模式集合，该模式可用于对患者进行分类或监测给定患者的疾病进展。该提案的主要目的是应用我们的方法来评估生命体征的高分辨率多元时间序列的预测能力，并在ICU中依次记录了EMR数据，以早期检测败血症和败血症患者的风险分层。为此，我们旨在基准在大型ICU队列（具有60,000多名患者的模拟II数据库）上进行基准测试，以及来自炎症介体对生命体征动态模式的影响的多尺度数学模型的模拟数据。接下来，该技术将在两个独立的ICU败血症同类群（Emory Sepsis数据集和Mayo诊所度量数据集）上进行外部验证。最后，我们将在流媒体环境（例如IBM流分析）中提供所提出的算法的实时实现，以解决ICU内的床旁监视器的大量数据挑战，在ICU内的床头显示器数据进行流式传感器数据，同时启用先进的图案识别和实时预测。最终，我们认为这些方法可以通过更快的认可和基本护理的倡议来改变当前的护理标准，以及基于疾病严重性和身体定义的机制的指导介入策略。