Background: The global, nearly universal penetration of mobile phones has offered novel opportunities for delivering health services and communicating health-related information to individuals. A low-cost system that facilitates autonomous communication with individuals via mobile phones holds potential for expanding the reach of health messaging and service delivery in settings with human resource and infrastructure limitations. Objective: We sought to design a flexible, low-code system using open-source software that could be adapted to different contexts and technical environments and accommodate a wide range of automation needs. We report on key details of the mobile phone-based appointment reminder and incentive system (mParis), document its use, review implementation challenges and adaptations to address these challenges in the context of a quasi-randomized trial of mobile phone-based reminders and incentives as means of increasing the timeliness of routine childhood vaccinations in Tanzania, and outline other use cases that highlight the versatility of the system. Methods: The mParis instance described in this manuscript, which is hosted in Tanzania, sent automated, individualized vaccination reminders to the mobile phones of mothers of young children. Process workflows, based on the national childhood vaccination schedule of Tanzania, were programmed into mParis. Reminders for vaccinations due at ages 6, 10, and 14 weeks were sent 7 days and 1 day prior to and 14 days after each vaccination due date. A subset of messages included financial incentive offers to mothers for the timely vaccination of their children. We report on implementation outcomes, challenges, and adaptations to address these challenges. Results: Between August and December 2017, 412 pregnant women were enrolled into the trial. After mothers reported the birth of their children, individualized vaccination reminder messages were sent for vaccination due dates between January and July 2018. From March 2018, messages contained financial incentive offers. Of 1,397 messages sent, 1,122 SMS (80.3%) were recorded as delivered, 249 (18.8%) as expired and resent, 23 (1.6%) as failed, and 3 (0.2%) as sent but lacking delivery confirmation. 633 messages (45.3%) contained tiered incentive offers. Of 173 women who received at least one message, 67 (38.7%) were sent reminders only; 106 women (61.3%) were sent at least one incentivized message. Numerous challenges were encountered during the system’s implementation, despite its deliberate design to accommodate basic problems such as intermittent internet access and power failures. Continuous adaptation to increase the resilience of the system, complemented by limited backstops, resulted in a successful deployment. Conclusions: mParis’ open-source nature, auditability, and ability to autonomously execute algorithms in a low-resource setting with frequent infrastructure challenges suggest favorable prospects to automate health communication in a wide range of settings. mParis’ use in multiple other health-related research studies demonstrates its versatility and ability to accommodate challenges that may be encountered in diverse other contexts. Clinical Trial: ClinicalTrials.gov: NCT03252288

Background: Alcohol use is prevalent in many societies and has major adverse impacts on health, but the availability of effective interventions limits treatment options for those who want assistance in changing their patterns of alcohol use. Objective: This study evaluated the new Daybreak program, which is accessible via mobile app and desktop and was developed by Hello Sunday Morning to support high-risk drinking individuals looking to change their relationship with alcohol. In particular, we compared the effect of adding online coaching via real-time chat messages (intervention group) to an otherwise self-guided program (control group). Methods: We designed the intervention as a randomized control trial, but as some people (n=48; 11.9%) in the control group were able to use the online coaching, the main analysis comprised all participants. We collected online surveys at one-month and three-months follow-up. The primary outcome was change in alcohol risk (measured with the alcohol use disorders identification test–consumption [AUDIT–C] score), but other outcomes included the number of standard drinks per week, alcohol-related days out of role, psychological distress (Kessler-10), and quality of life (EUROHIS-QOL). Markers of engagement with the program included posts to the site and comments on the posts of others. The primary analysis used Weighted Generalized Estimating Equations. Results: We recruited 398 people to the intervention group (50.2%) and 395 people to the control group (49.8%). Most were female (71%) and the mean age was 40.1 years. Most participants were classified as probably dependent (550, 69%) on the AUDIT–10, with 243 (31%) classified with hazardous or harmful consumption. We followed up with 334 (42.1%) participants at one month and 293 (36.9%) at three months. By three months there were significant improvements in AUDIT–C scores (down from mean 9.1 [SD 1.9] to 5.8 [SD 3.1]), alcohol consumed per week (down from mean 37.1 [SD 28.3] to mean 17.5 [SD 18.9]), days out of role (down from mean 1.6 [SD 3.6] to 0.5 [SD 1.6]), quality of life (up from 3.2 [SD 0.7] to 3.6 [SD 0.7]) and reduced distress (down from 24.8 [SD 7.0] to 19.0 [SD 6.6]). Accessing online coaching was not associated with improved outcomes, but engagement with the program (eg, posts and comments on the posts of others) were significantly associated with improvements (eg, in AUDIT–C, alcohol use and EUROHIS-QOL). Reduced alcohol use was found for both probably dependent (estimated marginal mean of 40.8 to 20.1 drinks) and hazardous or harmful alcohol users (estimated marginal mean of 22.9 to 11.9 drinks). Conclusions: Clinically significant reductions in alcohol use were found, as well as reduced alcohol risk (AUDIT–C) and days out of role. Importantly, improved alcohol-related outcomes were found for both hazardous or harmful and probably dependent drinkers. Since October 2016, Daybreak has reached more than 50,000 participants. Therefore, there is the potential for the program to have an impact on alcohol-related problems at a population health level, importantly including an effect on probably dependent drinkers. Trial Registration: Australian New Zealand Clinical Trials Registry: ACTRN12618000010291; https://www.anzctr.org.au/Trial/Registration/TrialReview.aspx?id=373110 International Registered Report Identifier (IRRID): RR2-10.2196/9982