Research and Implementation Lessons Learned From a Youth-Targeted Digital Health Randomized Controlled Trial (the ARMADILLO Study)

Background: Evidence is lacking on the efficacy of sexual and reproductive health (SRH) communication interventions for youth (aged 15-24 years), especially from low- and middle-income countries. Therefore, the World Health Organization initiated the Adolescent/Youth Reproductive Mobile Access and Delivery Initiative for Love and Life Outcomes (ARMADILLO) program, a free, menu-based, on-demand text message (SMS, short message service) platform providing validated SRH content developed in collaboration with young people. A randomized controlled trial (RCT) assessing the effect of the ARMADILLO intervention on SRH-related outcomes was implemented in Kwale County, Kenya. Objective: This paper describes the implementation challenges related to the RCT, observed during enrollment and the intervention period, and their implications for digital health researchers and program implementers. Methods: This was an open, three-armed RCT. Following completion of a baseline survey, participants were randomized into the ARMADILLO intervention (arm 1), a once-a-week contact SMS text message (arm 2), or usual care (arm 3, no intervention). The intervention period lasted seven weeks, after which participants completed an endline survey. Results: Two study team decisions had significant implications for the success of the trial's enrollment and intervention implementation: a hands-off participant recruitment process and a design flaw in an initial language selection menu. As a result, three weeks after recruitment began, 660 participants had been randomized; however, 107 (53%) participants in arm 1 and 136 (62%) in arm 2 were "stuck" at the language menu. The research team called 231 of these nonengaging participants and successfully reached 136 to learn reasons for nonengagement. Thirty-two phone numbers were found to be either not linked to our participants (a wrong number) or not in their primary possession (a shared phone). Among eligible participants, 30 participants indicated that they had assumed the introductory message was a scam or spam. Twenty-seven participants were confused by some aspect of the system. Eleven were apathetic about engaging. Twenty-four nonengagers experienced some sort of technical issue. All participants eventually started their seven-week study period. Conclusions: The ARMADILLO study's implementation challenges provide several lessons related to both researching and implementing client-side digital health interventions, including (1) have meticulous phone data collection protocols to reduce wrong numbers, (2) train participants on the digital intervention in efficacy assessments, and (3) recognize that client-side digital health interventions have analog discontinuation challenges. Implementation lessons were (1) determine whether an intervention requires phone ownership or phone access, (2) digital health campaigns need to establish a credible presence in a busy digital space, and (3) interest in a service can be sporadic or fleeting.