Evaluating the Implementation of the GREAT4Diabetes WhatsApp Chatbot to Educate People With Type 2 Diabetes During the COVID-19 Pandemic: Convergent Mixed Methods Study
Bibliographic record
Abstract
BACKGROUND: In South Africa, diabetes is a leading cause of morbidity and mortality, which was exacerbated during the COVID-19 pandemic. Most education and counseling activities were stopped during the lockdown, and the GREAT4Diabetes WhatsApp Chatbot was innovated to fill this gap. OBJECTIVE: This study aimed to evaluate the implementation of the chatbot in Cape Town, South Africa, between May and October 2021. METHODS: Convergent mixed methods were used to evaluate the implementation outcomes: acceptability, adoption, appropriateness, feasibility, fidelity, cost, coverage, effects, and sustainability. Quantitative data were derived from the chatbot and analyzed using the SPSS. Qualitative data were collected from key informants and analyzed using the framework method assisted by Atlas-ti. The chatbot provided users with 16 voice messages and graphics in English, Afrikaans, or Xhosa. Messages focused on COVID-19 infection and self-management of type 2 diabetes. RESULTS: The chatbot was adopted by the Metro Health Services to assist people with diabetes who had restricted health care during the lockdown and were at a higher risk of hospitalization and death from COVID-19 infection. The chatbot was disseminated via health care workers in primary care facilities and local nonprofit organizations and via local media and television. Two technical glitches interrupted the dissemination but did not substantially affect user behavior. Minor changes were made to the chatbot to improve its utility. Many patients had access to smartphones and were able to use the chatbot via WhatsApp. Overall, 8158 people connected with the chatbot and 4577 (56.1%) proceeded to listen to the messages, with 12.56% (575/4577) of them listening to all 16 messages, mostly within 32 days. The incremental setup costs were ZAR 255,000 (US $16,876) and operational costs over 6 months were ZAR 462,473 (US $30,607). More than 90% of the users who listened to each message found them useful. Of the 533 who completed the whole program, 351 (71.1%) said they changed their self-management a lot and 87.6% (369/421) were more confident. Most users changed their lifestyles in terms of diet (315/414, 76.1%) and physical activity (222/414, 53.6%). Health care workers also saw benefits to patients and recommended that the service continues. Sustainability of the chatbot will depend on the future policy of the provincial Department of Health toward mobile health and the willingness to contract with Aviro Health. There is the potential to go to scale and include other languages and chronic conditions. CONCLUSIONS: The chatbot shows great potential to complement traditional health care approaches for people with diabetes and assist with more comprehensive patient education. Further research is needed to fully explore the patient's experience of the chatbot and evaluate its effectiveness in our context.
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 | 0.052 | 0.069 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.003 | 0.002 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.002 | 0.004 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".