Zou Kelly H, Li Jim Z, Imperato Joseph, Potkar Chandrashekhar N, Sethi Nikuj, Edwards Jon, Ray Amrit
Research, Development and Medical, Upjohn Division, Pfizer Inc, New York, NY 10017, USA.
Research, Development and Medical, Upjohn Division, Pfizer Inc, San Diego, CA 92121, USA.
J Multidiscip Healthc. 2020 Jul 22;13:671-679. doi: 10.2147/JMDH.S262776. eCollection 2020.
A vast quantity of real-world data (RWD) are available to healthcare researchers. Such data come from diverse sources such as electronic health records, insurance claims and billing activity, product and disease registries, medical devices used in the home, and applications on mobile devices. The analysis of RWD produces real-world evidence (RWE), which is clinical evidence that provides information about usage and potential benefits or risks of a drug. This review defines and explains RWD, and it also details how regulatory authorities are using RWD and RWE. The main challenges in harnessing RWD include collating and analyzing numerous disparate types or categories of available information including both structured (eg, field entries) and unstructured (eg, doctor notes, discharge summaries, social media posts) data. Although the use of artificial intelligence to capture, amalgamate, standardize, and analyze RWD is still evolving, it has the potential to support the increased use of RWE to improve global health and healthcare.
医疗保健研究人员可以获取大量的真实世界数据(RWD)。这些数据来自多种来源,如电子健康记录、保险理赔和计费活动、产品和疾病登记处、家用医疗设备以及移动设备上的应用程序。对真实世界数据的分析产生真实世界证据(RWE),这是一种临床证据,可提供有关药物使用情况以及潜在益处或风险的信息。本综述对真实世界数据进行了定义和解释,还详细介绍了监管机构如何使用真实世界数据和真实世界证据。利用真实世界数据的主要挑战包括整理和分析大量不同类型或类别的可用信息,包括结构化(如字段条目)和非结构化(如医生笔记、出院小结、社交媒体帖子)数据。尽管利用人工智能来获取、合并、标准化和分析真实世界数据仍在不断发展,但它有潜力支持更多地使用真实世界证据来改善全球健康和医疗保健。