@Article{info:doi/10.2196/52048,
author="Nkabane-Nkholongo, Elizabeth
and Mpata-Mokgatle, Mathildah
and Jack, Brian W
and Julce, Clevanne
and Bickmore, Timothy",
title="Usability and Acceptability of a Conversational Agent Health Education App (Nthabi) for Young Women in Lesotho: Quantitative Study",
journal="JMIR Hum Factors",
year="2024",
month="Mar",
day="12",
volume="11",
pages="e52048",
keywords="preconception care; conversational agent technology; women's health education; mHealth adaptation; health information technology; health education in Africa; education; women's health; women; woman; health information; young women; survey; usability; acceptability; application; applications; app; health promotion",
abstract="Background: Young women in Lesotho face myriad sexual and reproductive health problems. There is little time to provide health education to women in low-resource settings with critical shortages of human resources for health. Objective: This study aims to determine the acceptability and usability of a conversational agent system, the Nthabi health promotion app, which was culturally adapted for use in Lesotho. Methods: We conducted a descriptive quantitative study, using a 22-item Likert scale survey to assess the perceptions of the usability and acceptability of 172 young women aged 18-28 years in rural districts of Lesotho, who used the system on either smartphones or tablets for up to 6 weeks. Descriptive statistics were used to calculate the averages and frequencies of the variables. $\chi$2 tests were used to determine any associations among variables. Results: A total of 138 participants were enrolled and completed the survey. The mean age was 22 years, most were unmarried, 56 (40.6{\%}) participants had completed high school, 39 (28.3{\%}) participants were unemployed, and 88 (63.8{\%}) participants were students. Respondents believed the app was helpful, with 134 (97.1{\%}) participants strongly agreeing or agreeing that the app was ``effective in helping them make decisions'' and ``could quickly improve health education and counselling.'' In addition, 136 (98.5{\%}) participants strongly agreed or agreed that the app was ``simple to use,'' 130 (94.2 {\%}) participants reported that Nthabi could ``easily repeat words that were not well understood,'' and 128 (92.7{\%}) participants reported that the app ``could quickly load the information on the screen.'' Respondents were generally satisfied with the app, with 132 (95.6{\%}) participants strongly agreeing or agreeing that the health education content delivered by the app was ``well organised and delivered in a timely way,'' while 133 (96.4{\%}) participants ``enjoyed using the interface.'' They were satisfied with the cultural adaptation, with 133 (96.4{\%}) participants strongly agreeing or agreeing that the app was ``culturally appropriate and that it could be easily shared with a family or community members.'' They also reported that Nthabi was worthwhile, with 127 (92{\%}) participants reporting that they strongly agreed or agreed that they were ``satisfied with the application and intended to continue using it,'' while 135 (97.8{\%}) participants would ``encourage others to use it.'' Participants aged 18-24 years (vs those aged 25-28 years) agreed that the ``Nthabi app was simple to use'' (106/106, 100{\%} vs 30/32, 98.8{\%}; P=.01), and agreed that ``the educational content was well organised and delivered in a timely way'' (104/106, 98.1{\%} vs 28/32, 87.5{\%}; P=.01). Conclusions: These results support further study of conversational agent systems as alternatives to traditional face-to-face provision of health education services in Lesotho, where there are critical shortages of human resources for health. Trial Registration: ClinicalTrials.gov NCT04354168; https://www.clinicaltrials.gov/study/NCT04354168 ",
issn="2292-9495",
doi="10.2196/52048",
url="https://humanfactors.jmir.org/2024/1/e52048",
url="https://doi.org/10.2196/52048",
url="http://www.ncbi.nlm.nih.gov/pubmed/38470460"
}