Psychosis Risk Evaluation, Data Integration and Computational Technologies (PREDICT): Data Processing, Analysis, and Coordination Center

精神病风险评估、数据集成和计算技术 (PREDICT)：数据处理、分析和协调中心

• 批准号: 10457174
• 负责人: Rene S. Kahn
• 金额: $ 77.74万
• 依托单位: BRIGHAM AND WOMEN'S HOSPITAL
• 依托单位国家: 美国
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-09-09 至 2025-05-31
• 项目状态: 未结题
• 来源: https://reporter.nih.gov/project-details/10457174
• 关键词: Address; Affect; Algorithms; Anxiety Disorders; Attenuated; Behavior; Big Data; Biological Markers; Clinical; Clinical Trials; Collection; Common Data Element; Computer software; Computers; Custom; Data; Data Aggregation; Data Analyses; Data Set; Development; Disease; Early Intervention; Early identification; Enrollment; Ensure; Evaluation; FAIR principles; Funding; Future; Goals; Grant; Heterogeneity; Human Resources; Impaired cognition; Individual; Informatics; Infrastructure; Intervention; Lead; Machine Learning; Medicine; Mental disorders; Methods; Modification; Monitor; Moods; Motivation; National Institute of Mental Health; Outcome; Parents; Pharmacotherapy; Population; Population Heterogeneity; Privatization; Procedures; Process; Protocols documentation; Psychoses; Quality Control; Recovery; Research; Research Personnel; Risk; Safety; Sampling; Schizophrenia; Scientist; Secure; Site; Software Tools; Standardization; Substance Use Disorder; Symptoms; System; Technology; Testing; Thinking; Time; Training; Transact; Travel; Validation; Visualization; Visualization software; Work; adverse outcome; analytical tool; attenuated psychosis syndrome; barrier to care; base; bioinformatics infrastructure; candidate marker; clinical heterogeneity; clinical risk; clinically relevant; cloud based; computer science; computerized data processing; dashboard; data archive; data de-identification; data dictionary; data harmonization; data infrastructure; data integration; data tools; demographics; design; disability; drug development; effective intervention; effective therapy; experience; functional decline; functional disability; high risk; improved; individualized medicine; innovation; multidisciplinary; multimodal data; multimodality; multiple data types; novel marker; outcome prediction; predictive marker; predictive modeling; prevent; prospective; psychotic symptoms; quality assurance; recruit; research study; resilience; response; risk prediction model; risk stratification; software development; targeted treatment; therapy development; tool; web based interface; web site

The “clinical high risk” (CHR) for psychosis syndrome is an antecedent period characterized by attenuated psychotic symptoms marked by subtle deviations from normal development in thinking, motivation, affect, behavior, and a decline in functioning. Early intervention in this population is critical to prevent psychosis onset as well as other adverse outcomes. However, the presentation of symptoms and subsequent course is highly variable, and there is a paucity of biomarkers to guide treatment development. To improve clinically relevant predictive models, several issues need to be addressed: 1) to focus on outcomes beyond psychosis; 2) to take into account heterogeneity in samples and outcomes; and 3) to integrate data sets with a broad array of variables using innovative algorithms. To address these challenges, the Accelerated Medicines Partnership Schizophrenia (AMP SCZ) study will collect diverse multi-modal data via two research networks (PRESCIENT and ProNET – 42 acquisition sites) in conjunction with the Psychosis Risk Evaluation Data Integration and Computational Technologies: Data Processing, Analysis, and Coordination Center (PREDICT-DPACC). The ultimate goal is to identify new CHR biomarkers, and CHR subtypes that will enhance future clinical trials and lead to effective new treatments. The PREDICT-DPACC is tasked with, 1) providing collaborative management, direction, data processing and coordination for the two research networks; and 2) developing and applying advanced algorithms to identify biomarkers that predict outcomes, in addition to stratifying CHR into subtypes based on outcome trajectories. The PREDICT-DPACC team will include multiple data types and will address the needs of the CHR research networks and the overall AMP SCZ goals. Data will be rapidly obtained, processed, and uploaded to the NIMH Data Archive (NDA). Planned analysis methods will be powerful and robust, leveraging the expertise and experience of computer scientist developers, and experienced clinical researchers. This supplement will allow the PREDICT-DPACC team to address unexpected personnel effort needs to meet the goals set forth in the original grant submission, including, but not limited to, 1) two networks with separate and independent data capture systems that need separate development of software tools to aggregate data, which involves twice the effort to install, test, and deploy tools on their infrastructure for each network; 2) coordination with both networks to ensure that the forms and data dictionaries match across networks and with the NIMH National Data Archive; 3) the study dashboard needs to be customized further to meet the visualization needs of both networks; 4) the inclusion of additional healthy controls, and co-enrollment requirements also deviate from what was expected and complicates the proposed analytic approaches; 5) there is also participation in additional unexpected organizational activities such as team workgroups, which will continue and are needed to harmonize ideas, methods, and approaches to meet AMP SCZ goals. The supplement will fill in gaps that could not have been anticipated at the start of this study and will allow us to meet the scientific goals which have not changed.

精神病综合征的“临床高风险”（CHR）是一个前期，其特征是衰减 在思维，动机，情感中，与正常发展相比，精神病符号的标志是 行为和功能下降。对该人群的早期干预对于预防精神病至关重要 以及其他不利结果。但是，症状的表现和随后的过程高度高 可变，并且生物标志物缺乏指导治疗发展。改善临床相关 预测模型，需要解决几个问题：1）专注于精神病以外的结果； 2） 考虑到样品和结果的异质性； 3）将数据集与大量变量集成 使用创新算法。为了应对这些挑战，加速的药物伙伴关系精神分裂症 （AMP SCZ）研究将通过两个研究网络（Prescient和Pronet - 42采集站点）结合精神病风险评估数据整合和计算 技术：数据处理，分析和协调中心（预测DPACC）。最终目标是 识别新的CHR生物标志物和CHR亚型，可增强未来的临床试验并导致有效的新试验 治疗。预测DPACC的任务是1）提供协作管理，指导，数据 两个研究网络的处理和协调； 2）开发和应用高级算法 除了根据结果将CHR分层为亚型外，还可以识别预测结果的生物标志物 轨迹。预测DPACC团队将包括多种数据类型，并将满足CHR的需求 研究网络和整体AMP SCZ目标。数据将迅速获得，处理和上传到 NIMH数据存档（NDA）。计划分析方法将是强大而强大的，利用专业知识 以及计算机科学家开发人员以及经验丰富的临床研究人员的经验。这种补充会 允许预测DPACC团队解决意外的人员努力，以实现在 原始赠款提交，包括但不限于1）两个具有独立和独立数据的网络 捕获需要单独开发软件工具来汇总数据的系统，这涉及两倍 努力在每个网络的基础架构上安装，测试和部署工具； 2）与两个网络的协调 确保表格和数据词典跨网络以及NIMH国家数据存档匹配； 3）需要进一步定制研究仪表板，以满足两个网络的可视化需求； 4） 包括其他健康对照，共同注册的要求也偏离了预期 并使提出的分析方法复杂化； 5）也有其他意外 组织活动（例如团队工作组）将继续并需要和协调思想， 方法和实现AMP SCZ目标的方法。补充将填补不可能的空白 在本研究开始时进行了预期，将使我们能够实现没有改变的科学目标。