MétaCan
Menu
← Back to cohort
Record W4414931747 · doi:10.2196/78923

Determining the Feasibility and Usability of a Co-Designed Culturally Appropriate Conversational Agent (DESI-Heart) to Support Self-Care in People With Cardiovascular Diseases: Protocol for a Single-Arm Pilot Trial

2025· article· en· W4414931747 on OpenAlexvenueno aff
Ann Tresa Sebastian, Paul Jansons, Ee Ling Ng, Ralph Maddison

Bibliographic record

VenueJMIR Research Protocols · 2025
Typearticle
Languageen
FieldPsychology
TopicDigital Mental Health Interventions
Canadian institutionsnot available
Fundersnot available
KeywordsUsabilityProtocol (science)Pilot trialPilot testCulturally appropriate

Abstract

fetched live from OpenAlex

BACKGROUND: Cardiovascular diseases (CVDs) are a leading cause of death and disability worldwide. For people living with CVD, clinical guidelines recommend ongoing self-care such as symptom monitoring, medication adherence, and lifestyle modifications. However, many people struggle to engage in this due to the complexity of disease management, limited understanding, and a lack of cultural support. Conversational agents (CAs) offer a solution by providing artificial intelligence-driven, voice-based support that enables human-like communication. While many CAs and digital interventions are good for people with CVDs, they are for mainstream populations and overlook culturally and linguistically diverse communities. OBJECTIVE: This study outlines the protocol for pilot testing the feasibility and usability of Diaspora Engaged Self-Care Intervention and Heart (DESI-Heart) program, to support self-care management among Indian diaspora populations with CVDs in Australia over an 8-week intervention period. The formative development of DESI-Heart is also described. METHODS: We integrated the Double Diamond Model and the ecological validity model to develop our DESI-Heart program. First, we co-designed the program with end users, who identified 4 key goals for engagement with self-care through culturally and linguistically appropriate approaches. Based on these priorities and ideas, we developed specific goals, including (1) medication reminders, (2) daily exercise guidance, (3) diet buddy, and (4) guided meditation. Participants will access the DESI-Heart program through a web-based CA, available on smartphones, laptops, or PCs. Based on their preferred timing, individuals will receive links to access specific components of the program corresponding to each goal. These links will be sent to participants via SMS or email, depending on their preference. A single-arm prepost pilot trial (N=28) will be conducted to evaluate the feasibility and usability of the DESI-Heart program among Indian adults living in Australia with CVDs. The primary outcome will assess feasibility indicators, including recruitment, engagement, and usability, while secondary outcomes will examine changes in self-care behaviors and quality of life. RESULTS: The DESI-Heart program received ethics approval in July 2024. Recruitment for the pilot trial is scheduled to begin in June 2025 and conclude by September 2025, with participant follow-up expected to be completed by the end of December 2025. All 28 participants have been recruited, and data analysis will be conducted once follow-up is finalized. CONCLUSIONS: We have co-designed and developed the DESI-Heart program, a culturally and linguistically appropriate self-care intervention aimed at supporting Indian adults with CVD living in Australia. The next step is to conduct a pilot study to assess the feasibility and usability of DESI-Heart, which will inform the design of a larger evaluation trial. DESI-Heart has the potential to complement existing health services by helping individuals with CVD manage their condition within the community, while acknowledging their cultural backgrounds and language preferences. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): PRR1-10.2196/78923.

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 imitation

Not 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.

metaresearch head score (Codex)0.039
metaresearch head score (Gemma)0.039
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Non-randomized trial · Consensus signal: none
GenreCandidate signal: Protocol · Consensus signal: Protocol
Teacher disagreement score0.039
Threshold uncertainty score0.207

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0390.039
Meta-epidemiology (narrow)0.0030.002
Meta-epidemiology (broad)0.0040.004
Bibliometrics0.0020.001
Science and technology studies0.0030.003
Scholarly communication0.0030.003
Open science0.0030.002
Research integrity0.0040.007
Insufficient payload (model declined to judge)0.0300.006

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.

Opus teacher head0.253
GPT teacher head0.549
Teacher spread0.296 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designNon-randomized trial
Domainnot available
GenreProtocol

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".

Quick stats

Citations1
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Research Protocols→Same topicDigital Mental Health Interventions→French-language works237,207→