An Artificial Intelligence–Based, Personalized Smartphone App to Improve Childhood Immunization Coverage and Timelines Among Children in Pakistan: Protocol for a Randomized Controlled Trial (Preprint)

Abstract

BACKGROUND The immunization uptake rates in Pakistan are much lower than desired. Major reasons include lack of awareness, parental forgetfulness regarding schedules, and misinformation regarding vaccines. In light of current pandemic and distancing measures, the Childhood Routine Immunization (CRI) coverage is adversely affected as caregivers avoid tertiary care hospitals or primary health centers. Innovative and cost-effective measures need to be taken to understand and address the causes of low immunization rates. However, only a few smartphone-based interventions have been carried out in LMICs to improve CRI. OBJECTIVE The primary objectives of this study are to evaluate whether a personalized mobile application can improve on-time visits at 10 and 14 weeks of age for CRI as compared with standard care. Secondly, whether Artificial intelligence (AI) model can be incorporated into the application. Secondary objectives are to learn the perception and attitudes of caregivers regarding childhood vaccination and understand the factors that might influence mobile phone-based application for vaccination improvement. METHODS A mixed-methods randomized controlled trial with an intervention and control arm. The study will be conducted at the AKUH vaccination center. Caregivers of the newborns (NB) or infants visiting for 6-week vaccination will be recruited. The intervention arm will be subjected to a smartphone application with text, voice, video, and pictorial messages regarding CRI. This application will be developed based on the findings of the pretrial qualitative component of the study, in addition to ‘no show’ study findings[1], exploring Caregivers Perceptions about CRI and Mobile Phone-based application in improving the CRI Coverage. RESULTS Pretrial qualitative IDIs were conducted in February 2020. The enrollment of the study participants for the randomized control trial is in process. Study exit interviews will be conducted at 14-week immunization visit if the caregivers visit the immunization facility or over the phone at 18 weeks of child’s age. CONCLUSIONS This study will generate useful insights into the feasibility, acceptability, and usability of an AI based smartphone application for improving CRI in Pakistan and LMICs. CLINICALTRIAL ClinicalTrials.gov NCT04449107; https://clinicaltrials.gov/ct2/show/NCT04449107 INTERNATIONAL REGISTERED REPORT DERR1-10.2196/22996