Assessing the Usability and Effectiveness of an AI-Powered Telehealth Platform: Mixed Methods Study on the Perspectives of Patients and Providers
Bibliographic record
Abstract
BACKGROUND: Telemedicine has revolutionized health care by significantly enhancing accessibility and convenience, yet barriers remain, such as providers' challenges with technology use. With advancements in telemedicine technologies, understanding the viewpoints of patients and providers is crucial for an effective and acceptable telemedicine service. This study reports the findings on the usability and effectiveness of the HelixVM artificial intelligence powered platform, analyzing key aspetcs like asynchronous health care, access, time efficiency, productivity, data exchange, security, privacy, and quality of care from patient and provider perspectives. OBJECTIVE: This study aims 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. The survey questionnaires are a modified version of the Telehealth Usability Questionnaire. We analyzed patient data using descriptive statistics and exploratory factor analysis to identify latent demographic patterns. For provider data, we used a deductive thematic analysis approach to identify key themes from the interviews and interpreted overall sentiments of the providers as negative, neutral, or positive. We also calculated percentages of different provider responses from the survey and interviews, where applicable. RESULTS: Overall, 86.3% (88/102) of the patients reported satisfaction with HelixVM, and 89.2% (91/102) indicated that they would use the services again. A total of 91.1% (93/102) of the patients agreed that HelixVM improves access to health care and is an acceptable way to receive health care, and 98% (100/102) agreed it saves time. Chi-square tests demonstrated statistical significance for all survey questions (P<.001). The results from factor analysis show a higher propensity of middle-aged women, who had a fast-track encounter type, who self-reported a medium level of technology savviness, and who are residing in the South region of the United States rating the platform more positively. With regard to the providers, the thematic analysis identified themes of asynchronous medicine in terms of the accessibility and quality of care, time and productivity, integration within the workflow, data exchange, and artificial intelligence triage. Certain challenges regarding incomplete data in patient charts and its impact on provider time were cited. Suggestions for improvements included options to ensure the completeness of patient charts and better screening to ensure that only asynchronous, qualified patients are able to reach the provider. CONCLUSIONS: Overall, our study findings indicate a positive experience for patients and providers. The use of fast-track prescription was considered favorable compared to traditional telemedicine. Some concerns on data completeness, gaps, and accuracy exist. Suggestions are provided for improvement. This study adds to the knowledge base of existing literature and provides a detailed analysis of the real-world implementation of a telemedicine market-place platform.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.030 | 0.035 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.001 |
| Scholarly communication | 0.003 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".