Conversational agent for healthy lifestyle behaviour change: an online feasibility study (Preprint)

BACKGROUND The rising incidence of chronic diseases is a growing concern, especially in Singapore with amongst the highest prevalence of diabetes in developed countries. Interventions promoting healthy lifestyle changes have been proven effective in reducing the progression of prediabetes to diabetes, but their in-person delivery may not be feasible at a large scale. Novel technologies such as conversational agents are a potential alternative for delivery of behavioural interventions towards healthy lifestyle change for the public. OBJECTIVE To assess the feasibility and acceptability of using a conversational agent promoting healthy lifestyle changes in the general population in Singapore. METHODS We performed an online, single-arm feasibility study. Participants were recruited via Facebook over four weeks. The Facebook Messenger conversational agent was used to deliver the intervention. The conversations focused on diet, exercise, sleep and stress and aimed to promote healthy lifestyle changes and improve participants’ knowledge of diabetes. Messages were sent to participants four times a week (once for each of the four topics of focus) for four weeks. We assessed feasibility of recruitment, defined as at least 75% of our target sample of 200 participants in four weeks, as well as retention, defined as 33% of the recruited sample completing the study. We also assessed participants’ satisfaction with and usability of the conversational agent. We also performed baseline and follow-up assessments of quality of life (QoL), diabetes knowledge and risk perception, diet, exercise, sleep and stress. RESULTS We recruited 37.5% (75/200) of the target sample size in one month. Of the eligible participants, 60 provided digital informed consent and completed baseline assessments whilst 56 followed the study through till completion. Retention was high, at 93% (56/60), along with engagement, denoted by 50% of participants communicating with the conversational agent at each interaction. Acceptability, usability, and satisfaction were generally high. Preliminary efficacy of the intervention showed no definitive improvements in health-related behaviour. CONCLUSIONS The delivery of a conversational agent for healthy lifestyle behaviour change via Facebook manager was feasible and acceptable. We were unable to recruit our planned sample solely using free options in Facebook. However, participant retention and conversational agent engagement rates were high. Our findings provide important insights to inform the design of a future randomised controlled trial.