AICORE-kids: Artificial Intelligence COVID-19 Risk AssEssment for kids

AICORE-kids：针对儿童的人工智能 COVID-19 风险评估

• 批准号: 10272787
• 负责人: CARL E ALLEN
• 金额: $ 81.75万
• 依托单位: BAYLOR COLLEGE OF MEDICINE
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-01-01 至 2022-04-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10272787
• 关键词: 2019-nCoV; Admission activity; Adopted; Adoption; Algorithms; Ambulatory Care; Artificial Intelligence; Award; Biological Assay; Blood; COVID-19; COVID-19 diagnostic; COVID-19 patient; COVID-19 severity; Caregivers; Characteristics; Child; Childhood; Clinical; Communities; Country; Data; Data Analyses; Data Collection; Data Coordinating Center; Development; Diagnostic Procedure; Differentiation Antigens; Disease; Emergency Situation; Ensure; FDA Emergency Use Authorization; Family; Future; Image; Immune; Individual; Infection; Inherited; Laboratories; Literature; Machine Learning; Methods; Monitor; Mucocutaneous Lymph Node Syndrome; Multisystem Inflammatory Syndrome in Children; Participant; Pathway interactions; Patients; Pediatric Hospitals; Phase; PhenX Toolkit; Physiologic Monitoring; Policies; Preparation; Process; Progressive Disease; Psychological Transfer; Publishing; RADx Radical; Readiness; Records; Risk; Risk Assessment; Schools; Serology; Severities; Severity of illness; Speed; Spottings; Stratification; System; Testing; Texas; Time Series Analysis; TimeLine; Training; Translations; Validation; Work; assay development; base; biomedical referral center; biosignature; case-based; chemokine; cytokine; data integration; data standards; design; epigenomics; genetic variant; hemodynamics; heterogenous data; improved; inflammatory marker; interoperability; learning progression; learning strategy; machine learning algorithm; next generation; novel; patient population; pediatric patients; prognostic; programs; radiomics; repository; response; social health determinants; transcriptomics; treatment planning

This work is directed at characterizing pediatric COVID-19 and stratifying incoming patients by projected (future) disease severity. Such stratification has several implications: immediately improving treatment planning, and as disease mechanistic pathways are uncovered, directing treatment. Predicting future severity will inform the risks of outpatient treatment; to the patients themselves, their family, other caregivers/cohabitants, and to schools and employers. As varying levels of “reopening” are adopted across the country (and the world), such prognostication will inform policy on the handling of pediatric carriers in the community. Based on our preliminary analysis we assert that a combination of novel assays including quantitative serology inflammatory markers (cytokine/chemokine profiles, immune profiles), transcriptomics, epigenomics, longitudinal physiological monitoring, time series analysis, imaging, radiomics and clinical observation including social determinants of health, contains adequate information even at early stages of infection to stratify the disease and predict disease severity. We propose an artificial intelligence/machine learning approach to integrate this rich and heterogeneous dataset, characterize the spectrum of disease and identify biosignatures that predict severity in progressive disease. To facilitate translation of the approaches developed in this work to a wide user community, we incorporate a Translational Development function, to oversee the design-control process and ensure readiness of our methods for regulatory review. Incorporated into our timelines are appropriate regulatory milestones intended to conform with the Emergency Use Authorization (EUA) programs in effect for SARS- CoV-2 diagnostics.

这项工作旨在描述儿科新冠肺炎的特征，并根据预测对新入院患者进行分层 (未来)疾病严重程度。这种分层有几个影响：立即改善治疗计划，以及 因为疾病的机制途径被发现，指导治疗。预测未来的严重程度将告知 门诊治疗；患者本身、他们的家人、其他照顾者/同居者，以及学校和 雇主。随着全国(乃至全世界)采取不同程度的“重新开放”，这样的预测将 告知社区处理儿科携带者的政策。根据我们的初步分析，我们断言 包括定量血清学炎症标志物(细胞因子/趋化因子图谱， 免疫图谱)、转录组学、表观基因组学、纵向生理监测、时间序列分析、成像 放射组学和临床观察，包括健康的社会决定因素，即使在早期也包含足够的信息 将疾病分为不同的感染阶段，并预测疾病的严重程度。我们提出了一种人工智能/机器 整合这个丰富且不同种类的数据集、描述疾病谱并识别的学习方法 预测进展性疾病严重程度的生物特征。为了便于翻译本文件中开发的方法 与广泛的用户社区合作，我们整合了翻译开发功能，以监督设计控制 处理并确保我们的方法准备就绪，以进行监管审查。纳入我们的时间表是适当的 旨在符合SARS紧急使用授权(EUA)计划的监管里程碑- CoV-2诊断。