Monah Suranna R, Wagner Matthias W, Biswas Asthik, Khalvati Farzad, Erdman Lauren E, Amirabadi Afsaneh, Vidarsson Logi, McCradden Melissa D, Ertl-Wagner Birgit B
Department of Diagnostic Imaging, The Hospital for Sick Children, 555 University Ave., Toronto, ON, M5G 1X8, Canada.
Great Ormond Street Hospital, London, UK.
Pediatr Radiol. 2022 Oct;52(11):2111-2119. doi: 10.1007/s00247-022-05427-2. Epub 2022 Jul 6.
The integration of human and machine intelligence promises to profoundly change the practice of medicine. The rapidly increasing adoption of artificial intelligence (AI) solutions highlights its potential to streamline physician work and optimize clinical decision-making, also in the field of pediatric radiology. Large imaging databases are necessary for training, validating and testing these algorithms. To better promote data accessibility in multi-institutional AI-enabled radiologic research, these databases centralize the large volumes of data required to effect accurate models and outcome predictions. However, such undertakings must consider the sensitivity of patient information and therefore utilize requisite data governance measures to safeguard data privacy and security, to recognize and mitigate the effects of bias and to promote ethical use. In this article we define data stewardship and data governance, review their key considerations and applicability to radiologic research in the pediatric context, and consider the associated best practices along with the ramifications of poorly executed data governance. We summarize several adaptable data governance frameworks and describe strategies for their implementation in the form of distributed and centralized approaches to data management.
人类智能与机器智能的融合有望深刻改变医学实践。人工智能（AI）解决方案的迅速普及凸显了其在简化医生工作以及优化临床决策方面的潜力，在儿科放射学领域亦是如此。大型影像数据库对于训练、验证和测试这些算法至关重要。为了在多机构的人工智能放射学研究中更好地促进数据可及性，这些数据库集中了实现准确模型和结果预测所需的大量数据。然而，此类工作必须考虑患者信息的敏感性，因此要采用必要的数据治理措施来保护数据隐私和安全，识别并减轻偏差的影响，以及促进道德使用。在本文中，我们定义了数据管理和数据治理，回顾了它们的关键考量因素及其在儿科背景下对放射学研究的适用性，并考虑了相关的最佳实践以及数据治理执行不力的后果。我们总结了几个可适配的数据治理框架，并以分布式和集中式数据管理方法的形式描述了其实施策略。
