Prediction of Clinical Deterioration Using a Bayesian Belief System

使用贝叶斯信念系统预测临床恶化

• 批准号: 9768542
• 负责人: Scott B. Hu
• 金额: $ 20.55万
• 依托单位: UNIVERSITY OF CALIFORNIA LOS ANGELES
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-09-01 至 2021-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9768542
• 关键词: Accident and Emergency department; Admission activity; Algorithms; Belief System; Cardiac; Caring; Centers for Disease Control and Prevention (U.S.); Cessation of life; Clinical; Clinical Data; Clinical Informatics; Clinical assessments; Code; Computational algorithm; Computerized Medical Record; Coupled; Critical Care; Data; Data Set; Deterioration; Discipline of Nursing; Ensure; Evaluation; Event; Fatigue; Foundations; Future; Genes; Health Personnel; Heart Arrest; Hematologic Neoplasms; Hospitalization; Hospitals; Inpatients; Institution; Intensive Care Units; Intervention; Learning; Lung; Machine Learning; Medicine; Mentors; Methods; Modeling; Monitor; Morbidity - disease rate; Nature; Patient Care; Patients; Performance; Population; Predictive Value; Public Health; Reporting; Research; Risk; Science; Specificity; Stream; Subgroup; System; Techniques; Testing; Therapeutic Intervention; Time; Training; Translating; Translations; United Kingdom; United States; Validation; Work; Workload; base; biomedical informatics; burnout; career development; clinical decision support; clinical decision-making; clinical practice; clinical predictors; clinical risk; cohort; computer science; experience; improved; individual patient; insight; learning strategy; machine learning algorithm; mental state; mortality; novel; patient population; predictive modeling; prevent; response; safety net; skills

Project Summary/Abstract Approximately 5-10% of hospitalized patients suffer significant clinical deterioration after admission, resulting in either transfer to the intensive care unit (ICU) or a "code" event (i.e., cardiac or pulmonary arrest). Delayed identification of these events result in increased morbidity and mortality. Unfortunately, existing prediction models result in multiple false alarms for every true positive alarm that they generate. In addition with every passing year, new monitoring systems are introduced that generate more false alarms, resulting in alarm fatigue which has been associated with patient deaths. The objective of this mentored career development proposal is to develop and assess novel computational algorithms that can predict the clinical deterioration of hospitalized patients earlier and more accurately than clinicians or conventional early warning systems, thereby allowing for timely intervention. Building upon our experience in the hematologic malignancy subpopulation of hospitalized patients, this new effort: 1) provides a foundation upon which to combine newer machine learning (ML) methods and clinical informatics to improve the capabilities of the model for an individual patient or specific subgroup; 2) assesses the impact and value of different variables from the electronic medical record (EMR) as part of the predictive model; and 3) broadens the evaluation of this approach to additional real-world patient populations, enabling insight into the translation of the models to clinical usage. The specific aims of this project are thus: Specific Aims Aim 1 To identify and extract model variables (features) from the EMR, evaluating different feature selection methods to optimize different predictive criterion and their impact on ML algorithms. Aim 2 To develop an ML approach that handles multiple asynchronous data streams of longitudinal information from the EMR, providing predictions on clinical deterioration in real-time. Aim 3 To explore clinician and rapid response team responses to early prediction of clinical deterioration. With successful completion of this proposal, the prediction model will be integrated into the EMR system. Future direction as part of a R01 proposal will involve external validation at other institutions and assessment of clinical impact on patient care.

项目总结/摘要 大约5-10%的住院患者在入院后遭受显著的临床恶化，导致 转移到重症监护室（ICU）或“代码”事件（即，心脏或肺停止）。延迟 识别这些事件导致发病率和死亡率增加。不幸的是，现有的预测 模型对于它们生成的每个真的肯定警报导致多个假警报。此外，每 过去一年，新的监控系统被引入，产生更多的假警报，导致警报 疲劳与患者死亡有关。 这个指导职业发展建议的目标是开发和评估新的计算 这些算法可以更早、更准确地预测住院患者的临床恶化， 临床医生或传统的早期预警系统，从而允许及时干预。建立在我们的 在血液恶性肿瘤住院患者亚群的经验，这项新的努力：1）提供了一个 联合收割机结合较新的机器学习（ML）方法和临床信息学， 模型对个体患者或特定亚组的能力; 2）评估以下方面的影响和价值 来自电子病历（EMR）的不同变量作为预测模型的一部分;以及3）拓宽 对这种方法在其他真实世界患者人群中的评价， 将模型应用于临床。因此，该项目的具体目标是： 具体目标 目的1识别和提取模型变量（特征）从电子病历，评估不同的特征选择 方法来优化不同的预测标准及其对ML算法的影响。 目标2开发一种ML方法，用于处理纵向数据的多个异步数据流。 从EMR的信息，提供实时的临床恶化的预测。 目的3探讨临床医生和快速反应小组对早期预测临床恶化的反应。 随着该提案的成功完成，预测模型将被集成到EMR系统中。 作为R 01提案的一部分，未来的方向将涉及其他机构的外部验证和评估 对病人护理的临床影响。