Previously submitted to: JMIR Public Health and Surveillance (no longer under consideration since Oct 03, 2023)
Date Submitted: Jul 24, 2022
Warning: This is an author submission that is not peer-reviewed or edited.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.
Application of reinforcement learning in public health: a scoping review of literature
ABSTRACT
Background:
Making public health decisions is arduous due to the multifaceted complexity of data. The advancement of the reinforcement learning (RL) model provides a robust and explainable artificial intelligence framework for making decisions under uncertainty.
Objective:
This review paper summarizes the extensive research on the reinforcement model in public health applications.
Methods:
This review was done in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analysis Extension for Scoping Reviews (PRISMA-ScR) Statement. From January 2011 to December 2021, electronic databases PUBMED and Google Scholar were routinely searched. Keywords such as exercise, critical care, drugs, diseases, COVID-19, and pandemic were extracted from the articles. Full text, Validation Study, Clinical Study, Observational Study, and case report based on reinforcement learning and public health were included and the articles that did not have a full text available in English were removed.
Results:
In the 27 articles reviewed, we observed the application of RL in Public Health in Intervention modeling, Mitigation Policies, Personalised Treatment, and in general complex decision making. Five of the studies that were reviewed dealt with COVID-19, six with critical care and conditions such as Type 2 Diabetes Mellitus, Lung Nodule, Neurocritical, and Neurosurgical Care; five with developing applications for Personalised Healthcare Recommendations, nine with Public Health and measures that can be taken using reinforcement learning, four with emphasizing the future aspects of reinforcement learning and three were review papers.
Conclusions:
The reinforcement learning algorithm, which consists of both off-policy and on-policy algorithms, has been used to make complicated Public Health decisions in Personalised Treatment, COVID-19, Type 2 Diabetes Mellitus, Lung Nodule, Neurocritical, and Neurosurgical Care. As a result, while RL holds great potential for enhancing the effectiveness and efficiency of data-driven decision-making in public health, it is important to acknowledge that this potential impact will necessitate both computational and theoretical advancements as well as a change in how stakeholders view decision-making in intricate healthcare systems.
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.