Maintenance Notice

Due to necessary scheduled maintenance, the JMIR Publications website will be unavailable from Wednesday, July 01, 2020 at 8:00 PM to 10:00 PM EST. We apologize in advance for any inconvenience this may cause you.

Who will be affected?

Accepted for/Published in: Journal of Medical Internet Research

Date Submitted: May 24, 2022
Date Accepted: Oct 28, 2022

The final, peer-reviewed published version of this preprint can be found here:

The Feasibility and Acceptability of an mHealth Conversational Agent Designed to Support HIV Self-testing in South Africa: Cross-sectional Study

Ntinga X, Musiello F, Keter AK, Barnabas R, van Heerden A

The Feasibility and Acceptability of an mHealth Conversational Agent Designed to Support HIV Self-testing in South Africa: Cross-sectional Study

J Med Internet Res 2022;24(12):e39816

DOI: 10.2196/39816

PMID: 36508248

PMCID: 9793294

The Feasibility and Acceptability of a mHealth Conversational Agent Chatbot Designed to Support HIV Self-Testing in South Africa: A Cross-sectional Study

  • Xolani Ntinga; 
  • Franco Musiello; 
  • Alfred Kipyegon Keter; 
  • Ruanne Barnabas; 
  • Alastair van Heerden

ABSTRACT

Background:

HIV testing rates in Sub Saharan Africa remain below the targeted threshold, and primary care facilities are struggling to provide adequate services. New approaches that leverage digital technologies could improve access to HIV testing and treatment.

Objective:

HIV testing rates in Sub Saharan Africa remain below the targeted threshold, and primary care facilities are struggling to provide adequate services. New approaches that leverage digital technologies could improve access to HIV testing and treatment.

Methods:

In this study we examined the feasibility and acceptability of “Nolwazi-bot”, an isiZulu speaking conversational agent designed to support HIV self-testing in KwaZulu-Natal, South Africa. Nolwazi-Bot was designed with four different personalities that users could choose between when selecting a counsellor for their HIV self-testing (HIVST) session. We recruited a convenience sample of 120 consenting adults and invited them to undertake an HIV self-test facilitated by the Nolwazi chatbot. After testing, participants completed a structured survey to assess their experience with the chatbot-supported HIV-self testing.

Results:

Participants (N=120) ranged in age from 18 – 47 years with half being male. Over 90% had tested more than once with a human counsellor. The majority (n=45, 37.5%) chose to be counselled by the young female NolwaziBot personality. Almost one-fifth (n=21, 17.5%) of the participants that conducted an HIV self-test guided by the chatbot tested positive. The majority of participants (n=95, 79.2%) indicated that their HIV testing experience with a chatbot was much better than that with a human counsellor. Three quarters of the participants reported that they felt like they were talking to a real person stating that response tone and word choice reminded them of how they talk in daily conversations.

Conclusions:

While we wait to see the full benefits of mHealth, technological interventions including conversational agents or chatbots provide us with a good opportunity to improve HIVST, by addressing some of the barriers faced by both the facilities and the patients. The study provides insights into the potential of digital technological interventions to support health and HIV efforts, such as HIV self-testing in low- and middle-income countries, as even the participants that had previously tested with a human counsellor preferred a chatbot for the perceived benefits it offers.


 Citation

Please cite as:

Ntinga X, Musiello F, Keter AK, Barnabas R, van Heerden A

The Feasibility and Acceptability of an mHealth Conversational Agent Designed to Support HIV Self-testing in South Africa: Cross-sectional Study

J Med Internet Res 2022;24(12):e39816

DOI: 10.2196/39816

PMID: 36508248

PMCID: 9793294

Download PDF


Request queued. Please wait while the file is being generated. It may take some time.

© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.