Early sepsis detection with model-based patient monitoring

通过基于模型的患者监测进行早期脓毒症检测

基本信息

批准号：
7611260
负责人：
Robert Matthew Pipke
金额：
$ 9.5万
依托单位：
VENTURE GAIN, LLC
依托单位国家：
美国
项目类别：
财政年份：
2009
资助国家：
美国
起止时间：
2009-04-01 至 2009-09-30
项目状态：
已结题

来源：
https://reporter.nih.gov/project-details/7611260
关键词：
Accounting Acute Advocate Algorithms Antibiotics Bacteremia Beds Behavior Catheters Cessation of life Chicago Clinical Research Complex Complication Computer software Coupled Critical Care Data Data Set Detection Diagnosis Disease Progression Early Diagnosis Economic Burden Electronics Exhibits Fertilization Floor Goals Health Healthcare Healthcare Systems Hospitalization Hospitals Hour Human Illinois Infection Intensive Care Units Length of Stay Manuals Measures Medical Metric Mission Modeling Monitor Morbidity - disease rate Nature Nosocomial Infections Nuclear Power Plants Outcome Patient Care Patient Monitoring Patients Pattern Performance Phase Policies Prevention Recovery Research Infrastructure Resistance Retrospective Studies Risk Sepsis Sepsis Syndrome Septic Shock Signal Transduction Solutions Staging System Technology Telemetry Testing Time Validation Work analytical tool antimicrobial base computer network cost detector economic cost improved killings medical complication mortality new technology novel prospective public health relevance sensor software development tool vigilance

项目摘要

DESCRIPTION (provided by applicant): Sepsis accounts for 215,000 deaths in the US each year. The average cost of treating a case of sepsis is $22,100, with annual total costs of $16.7 billion nationally. Early detection of sepsis in the critical care setting is essential to improve outcomes, reduce length of stay and contain economic costs. The project focuses on analysis of continuous patient telemetry, e.g., bedside monitor data, using advanced anomaly detection algorithms to provide early sepsis detection in the critical care setting. The algorithms will be used to generate a model of normal patient behavior from selected cases of complication-free patient cases. The model provides a dynamic baseline for comparison with real-time monitored data, with the aim of revealing subtle indications of incipient sepsis when it occurs. The goal of the project is to provide software monitoring of hospital data for earliest possible sepsis detection. It is envisioned this continuous telemetry analysis platform can be expanded to detect a variety of important health conditions in monitored patients at critical early stages. PUBLIC HEALTH RELEVANCE: Sepsis kills 215,000 people in the US each year and costs $16.7 billion annually. Early detection of sepsis in the critical care setting is essential for successful treatment. The project will develop software to automatically detect sepsis early in hospitalized patients.

描述（申请人提供）：败血症每年在美国占21.5万人死亡。治疗败血症病例的平均成本为22,100美元，全国总成本为167亿美元。在重症监护环境中对败血症的早期检测对于改善预后，减少住院时间并包含经济成本至关重要。该项目着重于使用高级异常检测算法的连续患者遥测（例如床旁监视器数据）分析，以在重症监护设置中提供早期败血症检测。该算法将用于从某些无并发症患者病例中的正常患者行为产生正常患者行为模型。该模型提供了与实时监控数据进行比较的动态基线，目的是揭示出发时脓毒症的微妙迹象。该项目的目的是为最早可能的败血症检测提供对医院数据的软件监控。可以预见，可以扩展这个连续的遥测分析平台，以检测受监视的患者在关键早期阶段的各种重要健康状况。公共卫生相关性：每年败血症杀死21.5万人，每年占167亿美元。重症监护环境中败血症的早期检测对于成功治疗至关重要。该项目将开发用于住院患者早期自动检测败血症的软件。