Predicting Attrition in a Text-Based Nutrition Education Program: Survival Analysis of Text2BHealthy (Preprint)

Abstract

BACKGROUND Text-based programs have been shown to effectively address a wide variety of health issues. Although little research examines short message service (SMS) text messaging program characteristics that predict participant retention and attrition, features of SMS text message programs, such as program duration and intensity, message content, and the participants’ context, may have an impact. The impact of stop messages—messages with instructions for how to drop out of an SMS text message program—may be particularly important to investigate. OBJECTIVE The aim of this study was to describe attrition from Text2BHealthy, a text-based nutrition and physical activity promotion program for parents of low-income elementary school children, and to determine the impact of message content and number of stop messages received on attrition. METHODS Using data from 972 parents enrolled in Text2BHealthy, we created Kaplan-Meier curves to estimate differences in program duration for different SMS text message types, including nutrition, physical activity, stop, and other messages. Covariates, including rurality and number of stop messages received, were included. RESULTS Retention rates by school ranged from 74% (60/81) to 95.0% (132/139), with an average retention rate of 85.7% (833/972) across all schools. Program duration ranged from 7 to 282 days, with a median program duration of 233 days and an average program duration of 211.7 days. Among those who dropped out, program duration ranged from 7 to 247 days, with a median program duration of 102.5 days. Receiving a stop message increased the probability of attrition compared with receiving messages about nutrition, physical activity, or other topics (hazard ratio=51.5, 95% CI 32.46-81.7; P<.001). Furthermore, each additional stop message received increased the probability of attrition (hazard ratio=10.36, 95% CI 6.14-17.46; P<.001). The degree of rurality also had a significant effect on the probability of attrition, with metropolitan county participants more likely to drop out of the program than rural county participants. The interaction between SMS text message type and total number of stop messages received had a significant effect on attrition, with the effect of the number of stop messages received dependent on the SMS text message type. CONCLUSIONS This study demonstrates the potential of SMS text message programs to retain participants over time. Furthermore, this study suggests that the probability of attrition increases substantially when participants receive messages with instructions for dropping out of the program. Program planners should carefully consider the impact of stop messages and other program content and characteristics on program retention. Additional research is needed to identify participant, programmatic, and contextual predictors of program duration and to explicate the relationship between program duration and program efficacy.