Accepted for/Published in: JMIR Research Protocols
Date Submitted: Sep 14, 2023
Open Peer Review Period: Sep 14, 2023 - Nov 9, 2023
Date Accepted: Feb 13, 2024
(closed for review but you can still tweet)
Warning: This is an author submission that is not peer-reviewed or edited. Preprints - unless they show as "accepted" - should not be relied on to guide clinical practice or health-related behavior and should not be reported in news media as established information.
Study protocol: Diabetic eye screening using machine learning enabled automated retinal imaging analysis software, a target product profile for England (DART)
ABSTRACT
Background:
Diabetic eye screening (DES) is a promising use case for machine learning technologies which may improve clinical, economic, and service outcomes. All these outcomes could however be negatively impacted by the implementation of machine learning technologies if these are not developed, evaluated and implemented appropriately. Target product profiles (TPPs) summarise the clinical, economic and technical characteristics necessary for successful product implementation, aiming to produce technologies that are of utility and value to patients and end-users.
Objective:
Produce a TPP for a machine learning-enabled automated retinal imaging analysis software (ML-ARIAS) for use in DES in England, to guide product development, evaluation and deployment.
Methods:
This work will consist of three phases. Phase 1 will establish what characteristics should be addressed in an ML-ARIAS TPP. A list of candidate characteristics for inclusion in the TPP will be generated from the following sources: an overview of systematic reviews of diagnostic test TPPs; a systematic review of digital health/AI TPPs; and the National Institute for Health and Care Excellence’s Evidence Standards Framework for Digital Health Technologies. This list of candidate characteristics (e.g. ‘Target Population’) will be mapped against the technology and use case and those not relevant excluded following review by a multistakeholder group. Specifications for these characteristics (e.g. people with diabetes >12 years old) will be drafted following a series of semi-structured interviews with stakeholders in Phase 2. Phase 3 will consist of a multi-stakeholder Delphi consensus study consisting of two online rounds and an in-person consensus meeting to finalise the TPP.
Results:
Phase 1 is currently underway and expected to be completed by November 2023, Phase 2 February 2024 and Phase 3 July 2024 with publication of the final TPP.
Conclusions:
The development of a TPP for an ML-ARIAS for use in UK DES with multi-stakeholder involvement will help developers produce tools that serve the needs of patients, healthcare systems and their staff. The TPP development process will also provide methods and a template for others to produce similar documents for AI diagnostic tests in other disease areas. Clinical Trial: Submitted to JMIR Preprints
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.