Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Feb 6, 2020
Date Accepted: Oct 30, 2020
Warning: This is an author submission that is not peer-reviewed or edited.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.
AI in Self-Diagnosis: Background and Testing of Four Apps in Ophthalmology in 2018 and 2020
ABSTRACT
Background:
Consumer-oriented mobile self-diagnosis apps have been developed using undisclosed algorithms, presumably based on machine learning (ML) and other artificial intelligence (AI) technologies.
Objective:
The objective of this work is to present in an interdisciplinary manner the background of human and algorithm-based diagnosis and the underlying techniques, to analyze their potentials to improve public health, to present a qualitative literature review on the current state of research on relevant AI/healthcare related issues and to test four popular apps on three simple ophthalmologic diagnoses.
Methods:
The potential impact on public health is illustrated used simple stochastic considerations. A short literature overview shows current research on relevant issues in this topic. Four presently available apps using AI technologies (Ada, Babylon, and Your.MD on Android, Buoy Health as a web app) are compared and tested on three diagnoses of different grades of urgency from the ophthalmology branch; test results from 2018 and 2020 are compared for all apps.
Results:
Diagnosis apps can potentially help improve public health in general. There are still gaps in the current research and regulation of AI-assisted healthcare. The tested apps differ prominently in their diagnostic accuracy, time efficiency and the results between 2018 and 2020. There is no observable trend to improvement of the results in this timespan.
Conclusions:
While regulations have already been proposed in the US and the EU, the demand for profound research and evaluation of the sector is growing. Amongst others, disclosure of the algorithms and standardized evaluation should be in public interest due to their potential influence on public health. For the branch of Ophthalmology, the results offered by the apps are inconsistent.
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.