Trends in Clinical Validation and Usage of Food and Drug Administration (FDA)-Cleared Artificial Intelligence (AI) Algorithms for Medical Imaging

Abstract

Abstract Objective The objective of this study is to examine the current landscape of FDA-approved AI medical imaging devices and identify trends in clinical validation strategy. Materials and Methods We conducted a retrospective study that analyzed data extracted from the American College of Radiology (ACR) Data Science Institute AI Central database as of November 2021 to identify trends in FDA clearance of AI products related to medical imaging. Product and clinical validation information of each device was gathered from their respective public 510(k) summary or de novo request submission, depending on their type of authorization. Results Overall, the database included a total of 151 AI algorithms that were cleared by the FDA between 2008 and November 2021. Out of the 151 FDA summaries reviewed, 97 (64.2%) reported the use of clinical data to validate their device. Of these 151 summaries, 81 (53.6%) reported the total number of patient cases used during validation, with the average number of cases being 799 (SD: 1363) and the range of cases spanning from 15 to 9122. A total of 51 (33.8%) AI devices characterized their clinical data as multicenter, 3 (2.0%) as single-center, and the remaining 97 (64.2%) did not specify. The ground truth used for clinical validation was specified in 78 (51.6%) FDA summaries. Discussion and Conclusion A wide breadth of AI algorithms have been developed for medical imaging. Most of the devices’ FDA summaries mention their use of clinical data and patient cases for device validation, emphasizing their utility in real clinical practice.

Ähnliche Arbeiten