Peer-Reviewed Publication
JMIR Res Protoc2024;13e51614.June 28, 2024Journal Article
Detecting Algorithmic Errors and Patient Harms for AI-Enabled Medical Devices in Randomized Controlled Trials: Protocol for a Systematic Review.
Aditya U Kale1,2,3,4, Henry David Jeffry Hogg5, Russell Pearson6, Ben Glocker7,8, Su Golder9, April Coombe10, Justin Waring11, Xiaoxuan Liu1,2,3,4, David J Moore10, Alastair K Denniston1,2,3,4
1Institute of Inflammation and Ageing, University of Birmingham, Birmingham, United Kingdom.
2University Hospitals Birmingham NHS Foundation Trust, Birmingham, United Kingdom.
3NIHR Birmingham Biomedical Research Centre, Birmingham, United Kingdom.
4NIHR Incubator for AI and Digital Health Research, Birmingham, United Kingdom.
5Population Health Science Institute, Faculty of Medical Sciences, Newcastle University, Newcastle upon Tyne, United Kingdom.
6Medicines and Healthcare Products Regulatory Agency, London, United Kingdom.
7Kheiron Medical Technologies, London, United Kingdom.
8Department of Computing, Imperial College London, London, United Kingdom.
9Department of Health Sciences, University of York, York, United Kingdom.
10Institute of Applied Health Research, University of Birmingham, Birmingham, United Kingdom.
11Health Services Management Centre, University of Birmingham, Birmingham, United Kingdom.
Abstract
BACKGROUND: Artificial intelligence (AI) medical devices have the potential to transform existing clinical workflows and ultimately improve patient outcomes. AI medical devices have shown potential for a range of clinical tasks such as diagnostics, prognostics, and therapeutic decision-making such as drug dosing. There is, however, an urgent need to ensure that these technologies remain safe for a…
Create a free account to keep reading
Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.
Want unlimited research access? See Pro plans