The Wilmer Institute Mentored Clinician Scientist Scholar Program-Supplement

威尔默研究所指导临床医生科学家学者计划-补充

• 批准号: 10405937
• 负责人: Harry Alan Quigley
• 金额: $ 8.64万
• 依托单位: JOHNS HOPKINS UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2003
• 资助国家: 美国
• 起止时间: 2003-05-01 至 2022-06-30
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10405937
• 关键词: Address; Artificial Intelligence; Charge; Data; Data Set; Ear; Educational Curriculum; Ensure; Eye; FAIR principles; Fostering; Guidelines; Image; Institutes; Institution; Learning; Machine Learning; Massachusetts; Medicine; Mentors; Modeling; NCI Scholars Program; Ophthalmology; Performance; Reproducibility; Research; Scientist; Series; Standardization; Training; Universities; Validation; data curation; deep learning; improved; intelligent algorithm; lectures

PROJECT SUMMARY/ ABSTRACT Artificial intelligence (AI), in the form of machine learning (ML) and deep learning (DL), has revolutionized the field of medicine, especially in subspecialties with access to a large number of images, such as ophthalmology. While promising, the application of ML/AI in ophthalmology is limited by the lack of clear guidelines on how to extract ophthalmic data, convert these data into a form that is usable for ML/AI model training and ensure these data are adhering to the principles of FAIR (Findability, Accessibility, Interoperability, and Reuse). Our proposal aims to address these limitations by delineating the best practices for data curation via an online lecture series that will be available free of charge to the public, once the curriculum is assessed and validated by another academic institution (Harvard/Massachusetts Eye and Ear Infirmary). If successful, the proposal will be impactful, as it will: 1. Accelerate reproducible research in ML/AI by enabling the creation of standardized ML/AI-ready and FAIR datasets. 2. Disseminate the best practices in data curation beyond Johns Hopkins University (JHU), as the online lectures will be made free of charge to the public. 3. Foster the creation of standardized multi-institutional datasets that will improve both performance and generalizability of ML/AI algorithms in ophthalmology, by enabling federated learning approaches and external validation of models.

项目总结/摘要 人工智能（AI），以机器学习（ML）和深度学习（DL）的形式， 已经彻底改变了医学领域，特别是在亚专业领域， 大量的图像，如眼科。尽管前景看好， 眼科学中的ML/AI由于缺乏关于如何提取的明确指南而受到限制 眼科数据，将这些数据转换为可用于ML/AI模型训练的形式 并确保这些数据符合公平原则（可查找性，可访问性， 互操作性和重用）。我们的提案旨在通过以下方式解决这些限制 通过在线讲座系列描述数据策展的最佳实践， 免费向公众提供，一旦课程被评估和验证， 另一个学术机构（哈佛/马萨诸塞州眼耳医院）。 如果成功，该提案将产生影响，因为它将： 1.加速ML/AI中的可重复研究， 标准化ML/AI就绪和FAIR数据集。 2.在约翰霍普金斯大学之外传播数据策展的最佳实践 (JHU)，因为网上讲座将免费向公众提供。 3.促进创建标准化的多机构数据集， ML/AI算法在眼科学中的性能和可推广性， 支持联合学习方法和模型的外部验证。