Informatics Approach to Identification and Deep Phenotyping of PASC Cases

PASC 病例识别和深度表型分析的信息学方法

• 批准号: 10696087
• 负责人: Xiaoming Li
• 金额: $ 18.04万
• 依托单位: UNIVERSITY OF SOUTH CAROLINA AT COLUMBIA
• 依托单位国家: 美国
• 财政年份: 2022
• 资助国家: 美国
• 起止时间: 2022-09-06 至 2024-08-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10696087
• 关键词: Acute; Address; Algorithms; Back; Biological Markers; COVID-19; COVID-19 patient; Cardiovascular system; Caring; Chest Pain; China; Clinic; Clinical; Clinical Data; Clinical Trials Design; Collection; Community Health; Data; Data Reporting; Data Science; Data Sources; Disease; Dyspnea; Electronic Health Record; Epidemiology; Europe; Event; Fatigue; Foundations; Funding; Graph; Guidelines; Health; Health Services; Health Status; Health system; Heterogeneity; Immune; Individual; Informatics; Intervention; Kidney; Link; Longevity; Longitudinal cohort; Longitudinal cohort study; Lung; Machine Learning; Manuals; Mediating; Methodology; Mining; Modeling; Morphology; National Institute of Allergy and Infectious Disease; Natural Language Processing; Neurologic; Observational Study; Organ; Outcome; Palpitations; Patients; Persons; Phase; Phenotype; Physiological; Post-Acute Sequelae of SARS-CoV-2 Infection; Public Health; Reaction Time; Records; Recovery; Reporting; Research; Research Priority; Risk Factors; SARS-CoV-2 infection; Semantics; Social Behavior; South Carolina; Structure; Supervision; Symptoms; System; Testing; Therapeutic; Time; United States National Institutes of Health; acute infection; biomedical informatics; biomedical ontology; burden of illness; clinical care; cohort; data repository; evidence base; experience; health record; improved; individual response; machine learning method; machine learning model; multimodal data; outcome prediction; persistent symptom; phenotyping algorithm; post-COVID-19; preventive intervention; programs; research clinical testing; risk prediction; supervised learning; symptom cluster; trait; treatment response; unstructured data

PROJECT SUMMARY/ABSTRACT Increasingly there have been reports of persistent symptoms and multi-organ multi-system manifestations (e.g., pulmonary, cardiovascular, renal, and neurological) among individuals who were recovered from the acute phase of COVID-19, denoted as Post-Acute Sequela of SARS-CoV-2 infection (PASC). Given that 76.7 million people are known to have been infected in the US as of February of 2022, millions of people will potentially experience PASC. This projected disease burden will have a profound public health impact with respect to patients' clinical outcomes and US health systems during post-COVID-19 care. Timely identification of individuals with PASC from existing COVID-19 cohorts and newly identified COVID-19 patients is urgently needed for PASC clinics and longitudinal cohort studies on PASC. Building on biomedical informatics methodologies, we propose a high- throughput and semi-supervised Deep Phenotyping approach to identifying individuals with PASC and characterizing their phenotypes. Our approach is based on a Graph representational model constructed based on the South Carolina COVID-19 Cohort (S3C), funded by the National Institute of Allergy and Infectious Diseases (NIAID) (R01A127203-4S1). S3C (n=~1,400, 000 COVID-19 patients by the February of 2022) is a multi-modal data repository consisting of EHR, health systems data, community-based health services data, and claims data, with complete temporal trajectory of every datum at individual-level. Building on top of the Graph model, we will detect phenotypes of candidate PASC patients by using unsupervised clustering algorithms. We will then identify and validate clinically plausible PASC cases and corresponding phenotypes by incorporating clinical evaluation and supervised algorithms. This study will result in a high-throughput algorithm application for identifying and characterizing PASC cases from COVID-19 EHR cohorts. The resulted EHR and machine learning models are interpretable, generalizable, and will form a foundation for testing and implementing in state-wide and national post-COVID clinics/programs.

项目摘要/摘要 越来越多地报道了持续的症状和多器官多系统表现（例如， 从急性期回收的个体中的肺，心血管，肾脏和神经系统 Covid-19的of-19，被称为SARS-COV-2感染（PASC）的急性后续集。考虑到7670万人 已知截至2022年2月在美国被感染，数百万的人可能会经历 PASC。这种预计的疾病负担将对患者的临床产生深远的公共卫生影响 结局和美国卫生系统在19日后护理期间。及时确定PASC的人 PASC诊所和 PASC的纵向队列研究。在生物医学信息学方法论的基础上，我们提出了一个高级 吞噬和半监督的深层表型方法，以识别患有PASC和的个体 表征他们的表型。我们的方法基于基于图表的图表模型 在南卡罗来纳州共同-19同伙（S3C）上，由美国国家过敏和感染研究所资助 疾病（NIAID）（R01A127203-4S1）。 S3C（n = 〜1,400，000 covid-192222222222222年2月） 多模式数据存储库包括EHR，卫生系统数据，基于社区的卫生服务数据以及 索赔数据，具有个人级别的每个基准的完全时间轨迹。在图表上建立 模型，我们将使用无监督的聚类算法检测候选PASC患者的表型。我们 然后，将通过合并来识别和验证临床上合理的PASC病例和相应的表型 临床评估和监督算法。这项研究将导致高通量算法应用 用于识别和表征来自COVID-19-EHR队列的PASC病例。由此产生的EHR和机器 学习模型是可解释的，可推广的，将构成测试和实施的基础 全州和国家后诊所/计划。