Deep-CDS: Deep Learning Semantic Data Lake for Clinical Decision Support

Deep-CDS：用于临床决策支持的深度学习语义数据湖

• 批准号: 10546333
• 负责人: Mansur R. Kabuka
• 金额: $ 25.35万
• 依托单位: INFOTECH SOFT, INC.
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-10 至 2023-02-28
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10546333
• 关键词: Accident and Emergency department; Acute; Address; Admission activity; Adverse event; Algorithms; Antibiotics; Artificial Intelligence; Back; Businesses; Caregivers; Caring; Cessation of life; Clinical; Clinical Practice Guideline; Computer software; Custom; Data; Data Set; Deterioration; Development; Diagnosis; Diagnostic; Early identification; Engineering; Ensure; Evaluation; Fast Healthcare Interoperability Resources; Feedback; Floor; Grant; Graph; Health; Health Personnel; Health Professional; Health Status; Hospital Mortality; Hospitals; Hour; Incidence; Inpatients; Intensive Care; Intervention; Knowledge; Laboratories; Legal patent; Length of Stay; Libraries; Life; Machine Learning; Maintenance; Metadata; Methods; Modeling; Monitor; Morphologic artifacts; National Institute of General Medical Sciences; Nurses; Patient Care; Patient Monitoring; Patient Transfer; Patient risk; Patient-Focused Outcomes; Patients; Phase; Physicians; Population; Process; Prognosis; Publishing; Quality of Care; Reporting; Resource Informatics; Risk; Risk Factors; Semantics; Sepsis; Septic Shock; Serious Adverse Event; Services; Specificity; Survival Rate; Symptoms; System; Taxonomy; Technology; Testing; Therapeutic; Time; Training; United States; Update; Visualization; base; clinical care; clinical decision support; clinical predictors; cloud based; data harmonization; data ingestion; data integration; data lake; data modeling; deep learning; deep learning model; diagnostic tool; evidence base; health data; improved; improved outcome; inpatient service; knowledge graph; knowledgebase; large datasets; learning progression; member; mortality; mortality risk; patient population; pilot test; point-of-care diagnostics; predictive modeling; prototype; response; risk stratification; septic; septic patients; tool; treatment response; trend; trend analysis; usability; user centered design; ventilation; Accident and Emergency department; Acute; Address; Admission activity; Adverse event; Algorithms; Antibiotics; Artificial Intelligence; Back; Businesses; Caregivers; Caring; Cessation of life; Clinical; Clinical Practice Guideline; Computer software; Custom; Data; Data Set; Deterioration; Development; Diagnosis; Diagnostic; Early identification; Engineering; Ensure; Evaluation; Fast Healthcare Interoperability Resources; Feedback; Floor; Grant; Graph; Health; Health Personnel; Health Professional; Health Status; Hospital Mortality; Hospitals; Hour; Incidence; Inpatients; Intensive Care; Intervention; Knowledge; Laboratories; Legal patent; Length of Stay; Libraries; Life; Machine Learning; Maintenance; Metadata; Methods; Modeling; Monitor; Morphologic artifacts; National Institute of General Medical Sciences; Nurses; Patient Care; Patient Monitoring; Patient Transfer; Patient risk; Patient-Focused Outcomes; Patients; Phase; Physicians; Population; Process; Prognosis; Publishing; Quality of Care; Reporting; Resource Informatics; Risk; Risk Factors; Semantics; Sepsis; Septic Shock; Serious Adverse Event; Services; Specificity; Survival Rate; Symptoms; System; Taxonomy; Technology; Testing; Therapeutic; Time; Training; United States; Update; Visualization; base; clinical care; clinical decision support; clinical predictors; cloud based; data harmonization; data ingestion; data integration; data lake; data modeling; deep learning; deep learning model; diagnostic tool; evidence base; health data; improved; improved outcome; inpatient service; knowledge graph; knowledgebase; large datasets; learning progression; member; mortality; mortality risk; patient population; pilot test; point-of-care diagnostics; predictive modeling; prototype; response; risk stratification; septic; septic patients; tool; treatment response; trend; trend analysis; usability; user centered design; ventilation

More than 5 million patients are admitted annually to United States ICUs with average mortality rate reported ranging from 8-19%, or about 500,000 deaths annually. Sepsis is the leading cause of in-hospital mortality, where one in three inpatient deaths are due to sepsis. Incidence of sepsis has been increasing with 1.7 million sepsis cases and 270,000 deaths per year. Early identification of deterioration has been shown to reduce the need for patient transfer to higher care units, reduce lengths of stay, and improve survival rates. Each hour of delay in ICU admission has been associated with a 1.5% increased risk of ICU death and a 1% increase in risk of hospital death. Many studies support that there is an increase in mortality rate for every hour delay in antibiotics. Pairing patient risk stratification with appropriate levels of hospital intervention is essential to reduce risk of mortality. Patients in intermediate units between the levels of monitoring found in floor units and ICUs are especially difficult to predict possibility of condition deterioration. Automated monitoring, alerts, and trend analysis are essential to identifying and proactively intervening patients under duress. Current methods of monitoring patient health have low specificity and have significant room for improvement. This project will develop Deep-CDS, a cloud-based deep learning system for context-sensitive clinical decision support in monitoring and predicting the deterioration of patient health and progression of sepsis risk factors in real-time to improve outcomes and optimize the management of care across the hospital population. To support the clinical care team, Deep-CDS provides team members with (a) a clinical care knowledgebase, (b) an early warning score for deteriorating health conditions, (c) a model for predicting septic conditions, (d) evidence-based clinical practice guidelines, and (e) visualization of patient health status trends. Deep-CDS addresses NIGMS Priorities for Small Business Development of Sepsis Diagnostics and Therapeutics, NOT-GM-20- 028: 1) Diagnostic tools for emergency department settings; 2) Predictive clinical algorithms and point-of-care diagnostics; 3) Technologies that combine various types of data for diagnosis of sepsis patients; and 4) Clinical decision support, including use of artificial intelligence and machine learning approaches, to develop tools for early recognition of sepsis, assessment of treatment responses and patient deterioration, and long-term prognosis prediction in various care settings.

每年有超过500万名患者被报告给美国ICU，并报告了平均死亡率 每年约为8-19％，约500,000人死亡。败血症是院内死亡率的主要原因， 三分之一的住院死亡是由于败血症。败血症的发病率一直在增加170万 败血症病例和每年270,000例死亡。已经证明早期鉴定劣化可以减少 需要患者转移到更高护理单位，降低住院时间并提高存活率。每个小时 ICU入院的延迟与ICU死亡风险增加1.5％，风险增加1％ 医院死亡。许多研究支持每小时延迟的死亡率增加 抗生素。将患者风险分层与适当水平的住院干预配对对于减少至关重要 死亡风险。在地板单位和ICU中发现的监测水平之间的中间单位的患者是 特别难以预测条件恶化的可能性。自动监视，警报和趋势 分析对于在胁迫下识别和主动干预患者至关重要。当前的方法 监测患者健康的特异性较低，并且有很大的改进空间。 该项目将开发深CD，这是一个基于云的深度学习系统，用于上下文敏感的临床 监测和预测患者健康状况恶化和败血症风险进展的决策支持 实时的因素改善结果并优化医院人口的护理管理。 为了支持临床护理团队，深CD为团队成员提供（a）临床护理知识库， （b）健康状况恶化的预警评分，（c）一种预测化粪池状况的模型，（d） 基于证据的临床实践指南，以及（e）患者健康状况趋势的可视化。深CD 针对败血症诊断和治疗学的小型企业开发的NIGMS优先事项，NOT-GM-20-- 028：1）急诊部门设置的诊断工具； 2）预测性临床算法和护理点 诊断； 3）结合了各种数据以诊断败血症患者的技术； 4）临床 决策支持，包括使用人工智能和机器学习方法，为早期开发工具 认识败血症，治疗反应评估和患者恶化以及长期预后 在各种护理环境中的预测。