FDA approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: An updated landscape

Abstract

As artificial intelligence (AI) has been highly advancing in the last decade, machine learning (ML) based medical devices are increasingly used in healthcare. In this article, we did an extensive search on the FDA database and performed an analysis of FDA-approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices. We have presented all the listed AI/ML-Enabled Medical Devices according to the date of approval, medical specialty, implementation modality of Medical Devices, anatomical site of use, and brief summary of each tool. Furthermore, we presented the approval pathways based on FDA currently updated criteria and risk level. according to the date of approval, medical specialty, implementation modality of Medical Devices, anatomical site of use, and brief summary of each tool. Furthermore, we presented the approval pathways based on FDA currently updated criteria and risk level.

Using Machine Learning to Predict Antimicrobial Resistance―A Literature Review

“…In order for ML models to be adopted into daily routine, they must be externally validated on different datasets and have end-point outcomes evaluated in real-world studies or randomized controlled trials (RCTs) [ 67 ]. Essentially, this confirms that ML-based tools and methods for medical use do not exist in a vacuum and must be designed with a clear view of the targeted audience (the medical practitioner or the trained patient), respecting the well-established procedures that, to date, shape the way other medical discoveries eventually find their way to the market through regulation (for example, FDA has initiated the process of admitting ML-based solutions in a variety of settings, but AMR prediction is not yet one of them [ 68 ]).…”

Artificial Intelligence for Antimicrobial Resistance Prediction: Challenges and Opportunities towards Practical Implementation

“…Therefore, the applications of artificial intelligence (AI) techniques, especially machine-learning (ML) and deep-learning (DL) techniques, are being used across different fields [ 9 , 10 , 11 ]. The application of AI is also increasing in the medical sector [ 12 , 13 , 14 ]. The metaverse is being developed for intelligent healthcare [ 13 ].…”

“…The metaverse is being developed for intelligent healthcare [ 13 ]. The authors in [ 12 ] listed Food and Drug Administration (FDA)-approved AI/ML-enabled devices across different medical fields. Significant increase in the approval of such AI-enabled devices is observed from 2018 onwards which constitutes about 85% of all approved devices.…”

“…Significant increase in the approval of such AI-enabled devices is observed from 2018 onwards which constitutes about 85% of all approved devices. [ 12 ]. In total, around 531 AI/ML-enabled devices have been approved, and the majority of the approved devices are related to radiology.…”

“…In total, around 531 AI/ML-enabled devices have been approved, and the majority of the approved devices are related to radiology. Among the others listed, five AI/ML-enabled approved devices are related to microbiology and four are related to pathology [ 12 ].…”