A Voice App Design for Heart Failure Self-management: Proof-of-Concept Implementation Study
Bibliographic record
Abstract
BACKGROUND: Voice user interfaces are becoming more prevalent in health care and are commonly being used for patient engagement. There is a growing interest in identifying the potential this form of interface has on patient engagement with digital therapeutics (DTx) in chronic disease management. Making DTx accessible through an alternative interaction model also has the potential to better meet the needs of some patients, such as older adults and those with physical and cognitive impairments, based on existing research. OBJECTIVE: This study aimed to evaluate how participants with heart failure interacted with a voice app version of a DTx, Medly, through a proof-of-concept implementation study design. The objective was to understand whether the voice app would enable the participants to successfully interact with the DTx, with a focus on acceptability and feasibility. METHODS: A mixed methods concurrent triangulation design was used to better understand the acceptability and feasibility of the use of the Medly voice app with the study participants (N=20) over a 4-week period. Quantitative data included engagement levels, accuracy rates, and questionnaires, which were analyzed using descriptive statistics. Qualitative data included semistructured interviews and were analyzed using a qualitative descriptive approach. RESULTS: The overall average engagement level was 73% (SD 9.5%), with a 14% decline between results of weeks 1 and 4. The biggest difference was between the average engagement levels of the oldest and youngest demographics, 84% and 43%, respectively, but these results were not significant-Kruskal-Wallis test, H(2)=3.8 (P=.14). The Medly voice app had an overall accuracy rate of 97.8% and was successful in sending data to the clinic. From an acceptability perspective, the voice app was ranked in the 80th percentile, and overall, the users felt that the voice app was not a lot of work (average of 2.1 on a 7-point Likert scale). However, the overall average score for whether users would use it in the future declined by 13%. Thematic analysis revealed the following: the theme feasibility of clinical integration had 2 subthemes, namely users adapted to the voice app's conversational style and device unreliability, and the theme voice app acceptability had 3 subthemes, namely the device integrated well within household and users' lives, users blamed themselves when problems arose with the voice app, and voice app was missing specific, desirable user features. CONCLUSIONS: In conclusion, participants were largely successful in using the Medly voice app despite some of the barriers faced, proving that an app such as this could be feasible to be deployed in the clinic. Our data begin to piece together the patient profile this technology may be most suitable for, namely those who are older, have flexible schedules, are confident in using technology, and are experiencing other medical conditions.
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 | 0.014 | 0.019 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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".