PREcision Care In Cardiac ArrEst - ICECAP (PRECICECAP)

项目总结： 心脏骤停的精确护理-ICECAP(PRECICECAP)父母R01研究旨在发现 心脏骤停后预测治疗反应和长期疗效的新生物标志物 恢复。心脏骤停是一个重大的公共卫生问题，也是发病率和死亡率的首要原因。 全国范围内。提高存活率和功能恢复至关重要。我们假设 通过创新的、多参数数据驱动的方法，我们将能够识别不同的 临床相关的患者亚组。我们的主要分析计划使我们能够实现我们的目标，但 不容易被其他人概括或使用。NIH资助的项目数量不断增加 收集和分析相似的数据集，并开发自己的定制解决方案。这种特别的方法是 成本高、效率低，并威胁到严密性和可重复性。本附录的目的是 PRECICECAP将完成一个公开可用的软件平台，允许端到端的管理 复杂的神经危重护理数据，为人工智能/机器学习(AI/ML)做好准备 来自原始波形数据的分析数据集。在我们以前工作的基础上，我们将解决 通过以下方式实现这一目标所需的剩余差距：1)制定标准流程以确保数据 质量、细分和抽样；2)功能工程；以及3)对我们的 输油管道。这项工作符合并支持NIH实现生物医学研究数据现代化的目标 通过开发一种软件产品来处理这种类型的复杂数据的AI/ML，从而实现了对生态系统的支持。它 还将允许共享最后确定的分析数据集，供其他人使用。通过继续我们久经考验的 临床医生研究人员、数据科学家和行业之间的协作，我们将采用NIH支持的 来自PRECICECAP研究的数据，并使其广泛可用和易于使用。该项目 提供了一个重要的软件工具，可供其他进行类似研究的人使用， NIH的使命是使复杂的数据公平(可查找、可访问、可互操作和可重复使用)。 这一结果将促进科学家之间使用类似数据进行公开、广泛的合作。

Project Summary: The PREcision Care In Cardiac ArrEst - ICECAP (PRECICECAP) parent R01 study aims to discover novel biomarker signatures after cardiac arrest that predict treatment responsiveness and long-term recovery. Cardiac arrest is a major public health problem and top cause of morbidity and mortality nationally. Improving survival and functional recovery is of critical importance. We hypothesize that through innovative, multi-parametric data driven approaches we will be able to identify distinct clinically relevant subgroups of patients. Our primary analytical plan allows us to achieve our aims but is not readily generalizable or usable by others. An ever-growing number of NIH-funded projects amass and analyze similar datasets and develop their own custom solutions. This ad hoc approach is costly, inefficient, and threatens both rigor and reproducibility. The objective of this supplement to PRECICECAP is to complete a publicly available software platform that allows end-to-end curation of complex neurocritical care data to create artificial intelligence/machine learning (AI/ML) ready analytical datasets from raw waveform data. Building on our previous work, we will address the remaining gaps needed to achieve this goal by: 1) developing standard processes to ensure data quality, segmentation, and sampling; 2) feature engineering; and, 3) external validation of our entire pipeline. This work aligns with and supports NIH goals for modernizing the biomedical research data ecosystem by developing a software product that can handle AI/ML on this type of complex data. It will also allow the sharing of a finalized analytical data set for use by others. By continuing our proven collaboration between clinician investigators, data scientists and industry, we will take NIH-supported data from the PRECICECAP study and make it broadly available and easily usable. The project delivers an important software tool that can be used by others conducting similar research, advancing the NIH’s mission to make complex data FAIR (Findable, Accessible, Interoperable, and Reusable). The result will facilitate an open, wide collaboration between scientists, using similar data.