MétaCan
Menu
← Back to cohort
Record W4414211392 · doi:10.2196/71793

Shesha, a WhatsApp Chatbot for Linking Household Contacts to Tuberculosis Treatment or Preventive Therapy in South Africa: Design and Development

2025· article· en· W4414211392 on OpenAlexvenueno aff
Don Mudzengi, Thobani Ntshiqa, Yohhei Hamada, Felex Ndebele, Thapelo Mpanza, Bridget Kyobutungi, C. Williams, Meghan Kennealy, Molebogeng X. Rangaka, Kavindhran Velen, Salome Charalambous

Bibliographic record

VenueJMIR Formative Research · 2025
Typearticle
Languageen
FieldHealth Professions
TopicMobile Health and mHealth Applications
Canadian institutionsnot available
FundersEuropean and Developing Countries Clinical Trials Partnership
KeywordsChatbotmHealthDocumentationPsychological interventionTuberculosiseHealthPublic healthTelemedicine

Abstract

fetched live from OpenAlex

Background: Literature on the development of mobile health (mHealth) tools for public health interventions is scarce. This scarcity creates a knowledge gap, and new tools may repeat the mistakes of past implementations. Objective: In this paper, we describe the development of Shesha, a WhatsApp-based chatbot designed to facilitate linkage to care for household contacts of people being treated for tuberculosis (TB). Shesha facilitates linkage by providing TB test results, TB preventive treatment (TPT) information, nudges, reminders, and personalized support. We developed Shesha to address the human resource capacity challenges posed by South Africa's new universal TB testing and TPT policies. Methods: We applied a design thinking framework with 7 phases: empathize, discover, define, prototype, build and launch, improve, and evaluate. The process started with gathering insights from TB contact tracing studies and consulting with global and local experts to address the challenges of universal TB testing and TPT. Based on these findings, we defined the core functionalities of Shesha and incorporated them in the Health Belief Model to encourage health-seeking behavior. In collaboration with the developers, we developed the WhatsApp-based chatbot. We selected WhatsApp for its wide accessibility and user-friendliness. Results: We successfully developed and launched the Shesha in September 2023, with implementation expected to continue until March 2025. Early user acceptance revealed that users generally valued the information provided on the tool regarding TB and TPT; however, they required ongoing engagement to link to care. Ongoing evaluations, guided by the Reach Effectiveness Adoption Implementation Maintenance (RE-AIM) framework, will assess the tool's impact on reducing community health worker workloads and improving linkage to care. Conclusions: Documenting the development of mHealth technologies is crucial for guiding future projects and improving health interventions. In our study, frameworks like design thinking and the Health Belief Model aligned Shesha with user needs and programmatic goals. Comprehensive documentation may help assess the chatbot's performance and guide future improvements, supporting scalability and efficiency in mHealth interventions across public health settings.

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)0.006
metaresearch head score (Gemma)0.012
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: none
Teacher disagreement score0.006
Threshold uncertainty score0.034

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0060.012
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0010.000
Science and technology studies0.0010.001
Scholarly communication0.0010.002
Open science0.0010.002
Research integrity0.0010.001
Insufficient payload (model declined to judge)0.0050.001

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.

Opus teacher head0.270
GPT teacher head0.510
Teacher spread0.240 · 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 designBench or experimental
Domainnot available
GenreMethods

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

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same venueJMIR Formative Research→Same topicMobile Health and mHealth Applications→French-language works237,207→