Accepted for/Published in: JMIR Formative Research
Date Submitted: May 31, 2024
Date Accepted: Oct 15, 2024
Date Submitted to PubMed: Oct 17, 2024
Warning: This is an author submission that is not peer-reviewed or edited.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.
Usability and effectiveness of a telehealth artificial-intelligence powered platform: perspectives from patients and providers in a mixed-methods study
ABSTRACT
Background:
Telemedicine has revolutionized healthcare by significantly enhancing accessibility. However, the acceptability and uptake of tele-medicine is prone to various hindering factors. Studies have shown that both patients and healthcare providers appreciate the aspect of convenience. However, healthcare providers’ limited understanding of or inability to leverage the technology involved can be a barrier. With advancements in telemedicine technologies, understanding the viewpoints of patients and providers is crucial for an effective and acceptable telemedicine service. This study reports findings from a usability study of HelixVM™, a telemedicine platform that uses an Artificial Intelligence (AI)-powered triage for healthcare delivery. We discuss aspects of asynchronous medicine, healthcare accessibility, saving time, productivity, data exchange, security, privacy, AI-powered triage and quality of care.
Objective:
To assess the usability and effectiveness of the HelixVM marketplace platform.
Methods:
We recruited 102 patients and 12 providers in a mixed-methods study design involving surveys, and in-depth structured interviews with a subset of the providers only. The survey questionnaires are a modified version of the telehealth utility questionnaire. We analyzed the patient’s data using descriptive statistics and factor analysis to identify latent demographic patterns. For the providers data, we used a deductive thematic analysis approach to identify key themes from the interviews and interpreted overall sentiments of the providers for negative, neutral or positive. We also calculated percentages of different responses for the providers from the surveys and interviews, where applicable.
Results:
Patients: Overall, 86% of patients are satisfied with HelixVM and 89% will use the services again. More than 90% of patients agreed that HelixVM improves access to healthcare, saves time and that the platform is an acceptable way to receive healthcare. Chi-square tests demonstrate statistical significance for all the survey questions (P-value <.001). Results from factor analysis show a higher propensity of female gender in middle age groups whose encounter type is fast-track, self-report medium level of tech-savviness and residing in the South regions of US rate the platform more positively. Providers: Thematic analysis identified themes of asynchronous medicine in terms of accessibility and quality of care, time and productivity, integration within the workflow, data exchange and AI-triage. Certain challenges of incomplete data in patient chart and its impact on provider time are cited. Suggestions for improvements include options to ensure completeness of patient questionnaires and better screening to ensure that only asynchronous 'qualified’ patients get through to the provider.
Conclusions:
Overall, our study findings indicate a positive experience for patients and providers. The use of fast-track prescription is favorable as compared to traditional telemedicine. Some concerns on data completeness, gaps and accuracy exist. Suggestions are provided for improvement. This study adds to the knowledgebase of existing literature and provides for a detailed analysis into the real-world implementation of a telemedicine market-place platform.
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.