ABCD Course on Reproducible Data Analyses

项目摘要/摘要 ABCD-ReproNim课程(1R25-DA051675)是一种合作伙伴关系，旨在提供研究教育 对ABCD研究的数据进行可重复分析的培训。该课程整合了ReproNim的课程： 可复制神经成像计算中心，这是NIBIB资助的P41生物医学技术 资源中心(BTRC)，其愿景是帮助神经成像研究人员获得更多可重复性的数据 分析工作流程和结果。ReproNim方法依赖于现成的 易于访问、用户友好的计算工具和服务，可轻松集成到当前研究中 实践，以及广泛的关于可再现性的教育推广到整个神经成像社区， 包括基础科学和临床学科的开发人员和应用研究人员。海流 项目提出了一项行政补充建议，以提供专门的研究培训，如何从 青少年大脑认知发展(ABCD)研究博览会(即可找到、可访问、可互操作和 可重用性)和AI/ML(即人工智能和机器学习)准备就绪。ML/AI应用程序增加 在发现生物标志物、预测干预结果和整合信息方面的相关性 数据集。然而，进行有效的生物医学ML研究所需的知识跨越了以下知识 数据、科学问题、计算技术以及ML/AI平台和工具。ABCD-ReproNim AI/ML课程将扩展当前的培训，使学员了解以下工具、概念和注意事项 ABCD数据的多模式ML/AI处理。学生将首先接受为期5周的在线课程培训 这包括讲座、阅读资料和有关以下主题的数据练习：(1)公平与公平 ML/AI应用，(2)ML核心概念，(3)，神经成像ML，(4)可解释/可解释ML，和(5) 深度学习入门。涉及的能力和技能将包括培训和出版ML 模型，组织和评估ML应用程序的数据，以及高效地重用现有模型。说教 授课后将进行为期5天的远程项目周，学生将在其中应用所学技能和工作 接近完成AI/ML数据分析项目。成功将产生训练有素的研究人员，他们能够 应用可重现的AI/ML实践来测试AI/ML模型对横截面和纵向的泛化能力 跨ABCD数据集的预测。

PROJECT SUMMARY/ABSTRACT The ABCD-ReproNim Course (1R25-DA051675) is a collaborative partnership to provide research educational training in reproducible analyses of data from the ABCD Study. The course integrates curriculum from ReproNim: A Center for Reproducible Neuroimaging Computation, which is a NIBIB-funded P41 Biomedical Technology Resource Center (BTRC) whose vision is to help neuroimaging researchers achieve more reproducible data analysis workflows and outcomes. The ReproNim approach relies on both technical development of readily accessible, user-friendly computational tools and services that can be readily integrated into current research practices, as well as a broad educational outreach about reproducibility to the neuroimaging community at large, including developers as well as applied researchers across basic sciences and clinical disciplines. The current project proposes an administrative supplement to provide dedicated research training on making data from the Adolescent Brain Cognitive Development (ABCD) Study FAIR (i.e., Findable, Accessible, Interoperable, and Reusable) and AI/ML (i.e., Artificial Intelligence and Machine Learning) ready. ML/AI applications have increased relevance in the discovery of biomarkers, predicting intervention outcomes, and integrating information across datasets. However, the knowledge required to perform effective biomedical ML research spans knowledge about data, scientific questions, computing technologies alongside ML/AI platforms and tools. The ABCD-ReproNim AI/ML Course will extend the current training to make trainees aware of the tools, concepts, and caveats for multimodal ML/AI processing of ABCD data. Students will first receive training across a 5-week online course that includes lectures, readings, and ABCD data exercises on topics that include: (1) FAIR for and FAIRness in ML/AI Applications, (2) Core Concepts in ML, (3), Neuroimaging ML, (4) Interpretable/Explainable ML, and (5) Introduction to Deep Learning. Competencies and skills addressed will include training and publishing ML models, organizing and evaluating data for ML applications, and reusing existing models efficiently. Didactic instruction will be followed by a 5-day remote Project Week, where students will apply the skills learned and work towards completion of AI/ML data analysis projects. Success will result in well-trained researchers who are able to apply reproducible AI/ML practices to test generalizability of AI/ML models for cross-sectional and longitudinal prediction across the ABCD dataset.