Genetics of deep-learning-derived neuroimaging endophenotypes for Alzheimer's Disease

阿尔茨海默病深度学习神经影像内表型的遗传学

• 批准号: 10660742
• 负责人: Laila Rasmy Gindy Bekhet
• 金额: $ 11.7万
• 依托单位: UNIVERSITY OF TEXAS HLTH SCI CTR HOUSTON
• 依托单位国家: 美国
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10660742
• 关键词: 2019-nCoV; Acute; Admission activity; All of Us Research Program; Alzheimer' s Disease; Alzheimer' s disease related dementia; Award; Big Data; Brain; Brain imaging; COVID-19; COVID-19 complications; COVID-19 patient; COVID-19 survivors; Categories; Cerebrospinal Fluid; Classification; Clinical; Clinical Data; Cognitive; Communities; Data; Electronic Health Record; Encephalopathies; Event; Genetic; Genetic study; Headache; Health; Knowledge; Label; Long COVID; Medical Genetics; Modeling; Neural Network Simulation; Neurologic; Neurologic Symptoms; Outcome; Parents; Participant; Pathogenesis; Patients; Pattern; Phase; Phenotype; Physicians; Post-Acute Sequelae of SARS-CoV-2 Infection; Prevention; Reporting; Research; Research Personnel; Resources; Risk; Structure; Time; Training; United States; United States National Institutes of Health; Virus; Work; base; biobank; brain tissue; clinical phenotype; cohort; common symptom; coronavirus disease; cytokine; deep learning; deep learning model; endophenotype; experience; genetic association; genetic information; genome wide association study; health data; indexing; insight; neuroimaging; parent grant; post COVID-19 complications; post-COVID-19; predict clinical outcome; predictive modeling; prevent; public health relevance; recurrent neural network; supervised learning

Abstract There is still a lack of knowledge on the key genetic factors associated with post acute syndrome for COVID-19 patients, especially those related to neurological complications. In this study, we will utilize both the genetic and clinical data available through the All of Us researchers platform to study the genetic association with COVID-19 complications. In order to more accurately phenotype the patients based on their clinical trajectory mostly recorded in their electronic health records, we will utilize a pretrained deep learning model trained on more than four million patients from the N3C cohort. The pretrained model will be further fine-tuned on the All of US data, and will be used to phenotype the patients with genetic data. Further GWAS study will be performed to correlate between the deep learning based phenotype and the genetic information. Successful completion of this project will bring new insights to guide COVID-19 patients treatment to better prevent or manage further complications.

抽象的 对于与 COVID-19 急性后综合症相关的关键遗传因素仍然缺乏了解 患者，特别是那些与神经系统并发症相关的患者。在这项研究中，我们将利用遗传 以及通过 All of Us 研究人员平台提供的临床数据，以研究与 COVID-19 并发症。为了根据患者的临床轨迹更准确地对患者进行表型分析 大部分记录在他们的电子健康记录中，我们将利用经过预训练的深度学习模型 N3C 队列中超过 400 万患者。预训练模型将在 All 上进一步微调 美国数据，并将用于通过遗传数据对患者进行表型分析。进一步的 GWAS 研究将 执行以关联基于深度学习的表型和遗传信息。成功的 该项目的完成将为指导 COVID-19 患者的治疗提供新的见解，以更好地预防或 管理进一步的并发症。