Sepsis Physiomarkers for Appropriate Risk Knowledge of monitored patients in the ICU (SPARK-ICU)

用于对 ICU 中受监测患者进行适当风险了解的脓毒症生理标志物 (SPARK-ICU)

• 批准号: 10295735
• 负责人: Rishikesan Kamaleswaran
• 金额: $ 55.41万
• 依托单位: EMORY UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-10 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10295735
• 关键词: Acute; Admission activity; Adult; Algorithmic Software; Blood Pressure; Bolus Infusion; Cessation of life; Characteristics; Child; Clinical; Clinical Data; Complex; Computerized Medical Record; Critical Illness; Data; Data Sources; Deterioration; Development; Effectiveness of Interventions; Electrocardiogram; Electrophysiology (science); Encapsulated; Face; Fluid Balance; Fluid Therapy; Functional disorder; Funding; Futility; General Ward; Goals; Health; Heterogeneity; Hospital Mortality; Hospitals; Hour; Human; Intensive Care Units; Intervention; Knowledge; Lead; Length of Stay; Literature; Machine Learning; Manuals; Mathematics; Measures; Medicare; Medicine; Methods; Modeling; Morbidity - disease rate; Multiple Organ Failure; Organ; Outcome; Patient Monitoring; Patients; Phenotype; Physiological; Physiology; Population; Recovery; Reporting; Reproducibility; Resources; Risk; Role; Sepsis; Severities; Shock; Signal Transduction; Stream; Structure; Testing; Time; Training; Translations; Treatment Efficacy; Universities; Vulnerable Populations; Work; base; clinical decision-making; clinical phenotype; clinical practice; computer science; data streams; day length; differential expression; hemodynamics; high risk; improved; improved outcome; insight; learning algorithm; machine learning algorithm; machine learning method; mortality; mortality risk; novel; novel marker; point of care; prediction algorithm; predictive modeling; programs; secondary infection; sensor; septic patients; signal processing; structured data; targeted treatment; tool

Project Summary Critically ill patients admitted to the ICU who develop secondary infection and sepsis, can face up to a five-fold increase in the risk for death when compared to non-sepsis patients. The majority of patients who developed secondary infections are more critically ill at admission and therefore require significantly greater resources. Traditional machine learning algorithms for predicting sepsis has been largely focused and relied on the use of structured data from the electronic medical record (EMR), however the EMR was developed largely as a billing mechanism and an audit log for clinical workflow. Hence, much of the structure and availability of data are often time-delayed, prone to errors from manual entry, biases from various institutional, personal and training biases, and finally contain a significant amount of missing data. In this proposal, we seek to discover novel `physiomarkers' extracted from continuous physiological data streams, generated from non-human derived data sources, that predict the onset of sepsis in this critical population. Using such routinely collected data, along with common clinical indicators extracted from the EMR, we propose to generate robust machine learning algorithms that can be more generalized, reproducible and removed from the biases and pitfalls of manual data entry. We propose that such classes of models not only may alert clinicians to acute and critically ill patients at risk for developing sepsis in real-time, but also investigate intervention effectiveness, such as volume responsiveness and support the discovery of novel sub-types of sepsis. Secondly, much of the existing literature on predictive models for sepsis focus on hospitalized patients in the general ward, however, models that predict the onset of sepsis among patients who developed secondary infections after admission to the ICU is limited. In our previous work, we have demonstrated that markers discovered from continuous numeric data streams can inform earlier prediction of sepsis in children and adults. However, those analysis did not use high-fidelity data from the waveforms, which encapsulate rich characteristics of physiology. Therefore, by emphasizing the discovery of such novel markers and through the application of data-driven learning algorithms, we expect to develop algorithms and tools that improve our understanding of the changing physiologic dynamics of sepsis in critically ill patient. In this proposed program, we will integrate knowledge across a number of distinctive expertise that spans signal processing, mathematics, computer science and medicine to develop sophisticated tools that can analyze such data to reveal meaningful insight. In short, we will contribute significant knowledge about the role and utility of complex physiological interactions that are at present abundantly available in clinical practice but seldom used for clinical decision making.

项目概要 入住 ICU 的危重患者若出现继发感染和败血症，可能面临高达五倍的损失 与非败血症患者相比，死亡风险增加。大多数患者发展为 继发感染在入院时病情更为严重，因此需要更多的资源。 用于预测脓毒症的传统机器学习算法主要集中于并依赖于使用 来自电子病历 (EMR) 的结构化数据，但是 EMR 主要是作为计费工具开发的 临床工作流程的机制和审核日志。因此，数据的大部分结构和可用性通常是 时间延迟，容易出现手动输入错误，各种机构、个人和培训偏见带来的偏见， 最终包含大量缺失数据。在这个提案中，我们寻求发现新颖的 从连续生理数据流中提取的“生理标记”，由非人类衍生数据生成 来源，预测这一关键人群中败血症的发生。使用这些常规收集的数据，以及 从 EMR 中提取常见的临床指标，我们建议生成强大的机器学习算法 它可以更加通用、可重复，并且可以消除手动数据输入的偏差和陷阱。我们 提出此类模型不仅可以提醒临床医生注意有危险的急性和危重患者 实时发展脓毒症，还调查干预效果，例如容量反应性 并支持脓毒症新亚型的发现。其次，现有的许多关于预测的文献 脓毒症模型侧重于普通病房的住院患者，然而，预测脓毒症发作的模型 进入 ICU 后出现继发感染的患者中败血症的情况有限。在我们之前的 工作中，我们已经证明从连续数字数据流中发现的标记可以更早地提供信息 儿童和成人败血症的预测。然而，这些分析并未使用来自 波形，封装了丰富的生理学特征。因此，通过强调发现 这种新颖的标记，通过数据驱动学习算法的应用，我们期望开发 提高我们对脓毒症生理动态变化的理解的算法和工具 生病的病人。在这个拟议的计划中，我们将整合许多独特的专业知识， 跨越信号处理、数学、计算机科学和医学，开发复杂的工具 分析这些数据以揭示有意义的见解。简而言之，我们将贡献有关该角色的重要知识 复杂的生理相互作用的实用性目前在临床实践中大量可用，但 很少用于临床决策。