Enhanced Metadata Design, Architecture, and Learning (MeDAL) for Development of Generalizable Deep Learning-based Predictive Analytics from Electronic Health Records

增强元数据设计、架构和学习 (MeDAL)，用于根据电子健康记录开发基于深度学习的通用预测分析

• 批准号: 10420954
• 负责人: SHAMIM NEMATI
• 金额: $ 33.58万
• 依托单位: UNIVERSITY OF CALIFORNIA, SAN DIEGO
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-05-01 至 2026-01-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10420954
• 关键词: Accident and Emergency department; Acute Renal Failure with Renal Papillary Necrosis; Acute Respiratory Distress Syndrome; Adult; Adverse event; Algorithms; Architecture; Area Under Curve; Artificial Intelligence; Biological Assay; Biometry; Blood Vessels; Caring; Case Study; Cessation of life; Clinical; Collaborations; Computer software; Computers; Critical Illness; Data; Data Set; Development; Devices; Effectiveness; Electronic Health Record; Ensure; Environment; Evaluation; Event; Fast Healthcare Interoperability Resources; Frequencies; Funding; General Hospitals; Goals; Health; Healthcare Systems; Heterogeneity; Hospital Costs; Hospital Mortality; Hospitalization; Hospitals; Hour; Hypotension; Incidence; Infection; Inflammation; Injury to Kidney; Inpatients; Institution; Intensive Care Units; Learning; Life; Liver; Lung; Measurement; Measures; Medical; Metadata; Methodology; Methods; Modeling; Morbidity - disease rate; Outcome; Patients; Pattern; Performance; Pharmaceutical Preparations; Pilot Projects; Population; Predictive Analytics; Prevention; Process; Reader; Reproducibility; Research; Research Personnel; Respiratory Failure; Risk; Risk Estimate; Savings; Sepsis; Septic Shock; Site; System; Testing; Time; Training; Uncertainty; Variant; Work; acute care; authority; base; cloud based; deep learning; demographics; design; improved; interest; laboratory equipment; mortality; multi-task learning; novel; organ injury; patient population; patient response; personalized care; portability; prediction algorithm; predictive modeling; prevent; prospective; research and development; response; septic patients; theories; tool; treatment optimization; treatment response; trustworthiness; ward

Project Summary / Abstract Sepsis, Septic Shock, Acute Kidney Injury (AKI), acute respiratory distress syndrome (ARDS) and respiratory failure are among the top causes of hospital mortality, morbidity, and an increase in duration and cost of hospitalization. Successful prevention and management of these conditions rely on the ability of clinicians to estimate the risk, and ideally, to anticipate and prevent these events. Acute care settings and in particular intensive care units (ICUs) provide an environment where an immense amount of data is acquired, and it is expected that with the advent of wearables and biometric patches even more data will be available in such settings. But at present, very little of these data are used effectively to prognosticate, and the existing predictive analytics risk scores suffer from lack of generalizability across institutions and performance degradation within the same institution over time. The PIs on this proposal recently demonstrated that a Deep Learning-based algorithm can reliably predict new sepsis cases in the emergency departments, general hospital wards, and ICUs by as much as 4-6 hours in advance and an area under the curve (ROC) of 0.85-0.90. Furthermore, through a 2-year pilot study funded via Biomedical Advanced Research and Development Authority (BARDA), we recently joined forces in a multicenter academic consortium to retrospectively validate this algorithm at each site. Our collaboration has resulted in a multi-center longitudinal EHR dataset of critically ill patients and has generated several important questions and findings related to design of portable and generalizable predictive analytics algorithms that are robust to problems arising from gaps, errors, and biases in electronic health records (EHRs) due to workflow-related factors (e.g. staffing-level), and heterogeneity of patient populations and measurement devices. We propose to significantly expand our prior work by designing new deep learning architectures that are robust to data missingness and biases introduced through the variability in process of care, 2) development of new learning methodologies to improve generalizability of the proposed models under data/population drifts (aka distributional changes), 3) enhanced metadata design to assist in quantifying `conditions for use' of such algorithms via algorithmic controls, and 4) HL7 and FHIR-based prospective implementation and testing of these methodologies to provide real-world clinical evidence for the effectiveness of the proposed approaches. Ultimately, these novel methodologies and tools will enhance our ability to use EHR and other types of continuously measured longitudinal data to predict adverse events, assess patients' response to therapy, and optimize and personalize care at the beside.

项目总结/摘要 脓毒症、脓毒性休克、急性肾损伤（阿基）、急性呼吸窘迫综合征（ARDS）和 呼吸衰竭是医院死亡率、发病率和持续时间增加的主要原因之一 和住院费用。成功预防和管理这些疾病依赖于 临床医生估计风险，理想情况下，预测和预防这些事件。急症护理环境 特别是重症监护病房（ICU）提供了一个环境， 被收购，预计随着可穿戴设备和生物识别补丁的出现， 将在这样的环境中使用。但目前，这些数据很少被有效地用于 现有的预测分析风险评分缺乏跨平台的普遍性， 随着时间的推移，同一机构内的绩效下降。 关于这一提议的PI最近证明，基于深度学习的算法可以可靠地 预测急诊科、综合医院病房和ICU的新脓毒症病例 提前4-6小时，曲线下面积（ROC）为0.85-0.90。此外，通过两年 一项由生物医学高级研究与发展局（巴尔达）资助的试点研究，我们最近 联合多中心学术联盟的力量，在每个站点回顾性验证该算法。 我们的合作产生了一个多中心的重症患者纵向EHR数据集， 产生了几个重要的问题和相关的便携式和可推广的设计结果 预测分析算法，对由差距、错误和偏见引起的问题具有鲁棒性， 电子健康记录（EHR），由于工作流程相关因素（如人员水平）和异质性 患者群体和测量设备。 我们建议通过设计新的深度学习架构来显着扩展我们之前的工作， 对通过护理过程中的可变性引入的数据缺失和偏倚具有鲁棒性，2） 开发新的学习方法，以提高拟议模型的普遍性， 数据/总体漂移（又称分布变化），3）加强元数据设计，以协助量化 通过算法控制“使用”这种算法的条件，以及4）HL 7和FHIR的前瞻性 这些方法的实施和测试，以提供真实世界的临床证据， 建议的方法的有效性。最终，这些新的方法和工具将提高 我们能够使用EHR和其他类型的连续测量的纵向数据来预测不利的 事件，评估患者对治疗的反应，并在旁边优化和个性化护理。