CTSA Administrative Supplement for Informatics Core: A novel AI/ML system to predict respiratory failure and ARDS in Covid-19 patients

CTSA 信息学核心行政补充：一种预测 Covid-19 患者呼吸衰竭和 ARDS 的新型 AI/ML 系统

• 批准号: 10158737
• 负责人: MARLA J KELLER
• 金额: $ 100.34万
• 依托单位: ALBERT EINSTEIN COLLEGE OF MEDICINE
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-07-09 至 2021-02-28
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10158737
• 关键词: 2019-nCoV; Acute; Acute respiratory failure; Address; Administrative Supplement; Adult Respiratory Distress Syndrome; Arrhythmia; Artificial Intelligence; Award; Awareness; COVID-19; COVID-19 pandemic; Cessation of life; Clinical; Clinical Data; Clinical Decision Support Systems; Clinical Research; Collaborations; Communities; Competence; Complex; Coronavirus; Data; Data Science; Data Scientist; Detection; Deterioration; Development; Diagnosis; Engineering; Expert Systems; Fatal Outcome; Functional disorder; Funding; Future; Generations; Goals; Health; Health system; Healthcare; Heart Injuries; Hospitals; Hypoxemia; Infection; Informatics; Injury to Kidney; Inpatients; Institutes; Intervention; Lead; Life; Link; Literature; Lung Compliance; Mechanical ventilation; Medical center; Methods; Modeling; Morbidity - disease rate; New York City; Organ; Parents; Patients; Pneumonia; Population; Preventive; Process; Public Health; Publishing; Research; Research Personnel; Research Support; Resources; Respiratory Failure; Risk Assessment; Seasons; Severities; Software Engineering; Source; Standardization; System; Thromboembolism; Time; Training; Translating; Translational Research; United States National Institutes of Health; Upper Respiratory Infections; base; care delivery; care providers; clinical decision-making; cohort; complex data; coronavirus disease; data modeling; deep learning; design; evidence base; experience; flu; health data; infection rate; innovation; machine learning algorithm; mortality; multidisciplinary; novel; pandemic disease; preemptive intervention; prevent; prognostic; programs; response; software systems; tool

PROJECT SUMMARY The Einstein-Montefiore Institute for Clinical and Translational Research (ICTR) proposes an Administrative Supplement pursuant to NOT-TR-20-011, CTSA Program Applications to Address 2019 Novel Coronavirus (Covid-19). Specifically, this application addresses the urgent need for research on the coronavirus pandemic with a project focusing on informatics and data science to preemptively identify patients with the life- threatening complications of SARS-CoV-2, using CTSA-supported core resources. Characterized by severe hypoxemia, tachypnea, and decreased lung compliance, the diagnosis of acute respiratory failure (ARF) is a bad prognostic sign, and in a subset, leads to development of acute respiratory distress syndrome (ARDS). The rates of Covid-19 infection and death in the Bronx have been higher than any other borough of NYC. As the major regional health system, our experience with Covid-19 provides guideposts that may prevent future victims of this pandemic. The bleak picture for ARDS in the 4,452 patients admitted showed that 78% of our intubated Covid-19 patients developed ARDS, with 42% mortality. The overall goal of this proposal is to leverage our novel informatics and analytics platforms enabled by the Einstein-Montefiore CTSA (NIH/NCATS 1ULTR002556), and extensive Artificial Intelligence and Deep Learning resources to implement a novel, situational awareness and clinical decision support system for ARF and ARDS (SA-ARDS). We will re-train our existing deep learning models with data collected from Covid-19 patients and contextualize its implementation with data from the Covid-19 response during the pandemic in NYC. The SA-ARDS data platform will provide longitudinally integrated clinical data for research and multi-institutional and national collaborations, with the following specific aims: Aim 1: To integrate, re-train, and validate our novel, near real-time, Electronic Risk Assessment System (ERAS 1.0) optimized for early recognition of ARF, ARDS, and inpatient mortality; Aim 2: To develop an evidence based, real-time, and context appropriate Situational Awareness clinical decision support system targeting ARF and ARDS response (SA-ARDS); and Aim 3: Through our partner CTSA organizations, to standardize and disseminate ERAS 1.0 and the SA-ARDS to other health systems, including the NYC consortium of CTSA hubs and the PCORI INSIGHT network. We will use the clinical data underlying the SA-ARDS to support research in local, regional, and national collaborations. All the methods and tools developed will be shared with the CTSA community via NCATS' National Center for Data to Health (CD2H).

项目概要 爱因斯坦-蒙蒂菲奥里临床和转化研究所 (ICTR) 提出了一项行政管理 根据 NOT-TR-20-011、CTSA 计划申请的补充，以应对 2019 年新型冠状病毒 （新冠肺炎）。具体来说，该应用程序解决了冠状病毒大流行研究的迫切需求 一个专注于信息学和数据科学的项目，旨在抢先识别患有生命危险的患者 使用 CTSA 支持的核心资源，应对 SARS-CoV-2 的威胁性并发症。其特点是严重 低氧血症、呼吸急促和肺顺应性下降，急性呼吸衰竭（ARF）的诊断是 不良的预后征兆，并且在一部分中，会导致急性呼吸窘迫综合征（ARDS）的发展。 布朗克斯区的 Covid-19 感染率和死亡率高于纽约市任何其他行政区。作为 对于主要的区域卫生系统，我们在 Covid-19 方面的经验提供了指导方针，可以预防未来的 这次流行病的受害者。 4,452 名收治的 ARDS 患者的惨淡情况表明，我们 78% 的患者 插管的 Covid-19 患者出现 ARDS，死亡率为 42%。该提案的总体目标是 利用由 Einstein-Montefiore CTSA (NIH/NCATS) 支持的新型信息学和分析平台 1ULTR002556），以及广泛的人工智能和深度学习资源来实施新颖的、 ARF 和 ARDS 的态势感知和临床决策支持系统 (SA-ARDS)。我们将重新训练我们的 现有的深度学习模型，包含从 Covid-19 患者收集的数据，并将其实施情境化 纽约市大流行期间 Covid-19 应对措施的数据。 SA-ARDS数据平台将提供 纵向整合临床数据用于研究以及多机构和国家合作， 以下具体目标： 目标 1：集成、重新训练和验证我们新颖的、近实时的电子风险 评估系统（ERAS 1.0）优化用于早期识别 ARF、ARDS 和住院患者死亡率；目标 2： 制定基于证据的、实时的、适合情境的情境意识临床决策 针对 ARF 和 ARDS 反应的支持系统 (SA-ARDS)；目标 3：通过我们的合作伙伴 CTSA 组织，以标准化 ERAS 1.0 和 SA-ARDS 并将其传播到其他卫生系统，包括 纽约市 CTSA 中心联盟和 PCORI INSIGHT 网络。我们将使用基础临床数据 SA-ARDS 支持地方、区域和国家合作的研究。所有方法和工具 开发的数据将通过 NCATS 国家健康数据中心 (CD2H) 与 CTSA 社区共享。