Systematic review and meta-analysis of the effectiveness of chatbots on lifestyle behaviours

Abstract

Chatbots (also known as conversational agents and virtual assistants) offer the potential to deliver healthcare in an efficient, appealing and personalised manner. The purpose of this systematic review and meta-analysis was to evaluate the efficacy of chatbot interventions designed to improve physical activity, diet and sleep. Electronic databases were searched for randomised and non-randomised controlled trials, and pre-post trials that evaluated chatbot interventions targeting physical activity, diet and/or sleep, published before 1 September 2022. Outcomes were total physical activity, steps, moderate-to-vigorous physical activity (MVPA), fruit and vegetable consumption, sleep quality and sleep duration. Standardised mean differences (SMD) were calculated to compare intervention effects. Subgroup analyses were conducted to assess chatbot type, intervention type, duration, output and use of artificial intelligence. Risk of bias was assessed using the Effective Public Health Practice Project Quality Assessment tool. Nineteen trials were included. Sample sizes ranged between 25–958, and mean participant age ranged between 9–71 years. Most interventions (n = 15, 79%) targeted physical activity, and most trials had a low-quality rating (n = 14, 74%). Meta-analysis results showed significant effects (all p < 0.05) of chatbots for increasing total physical activity (SMD = 0.28 [95% CI = 0.16, 0.40]), daily steps (SMD = 0.28 [95% CI = 0.17, 0.39]), MVPA (SMD = 0.53 [95% CI = 0.24, 0.83]), fruit and vegetable consumption (SMD = 0.59 [95% CI = 0.25, 0.93]), sleep duration (SMD = 0.44 [95% CI = 0.32, 0.55]) and sleep quality (SMD = 0.50 [95% CI = 0.09, 0.90]). Subgroup analyses showed that text-based, and artificial intelligence chatbots were more efficacious than speech/voice chatbots for fruit and vegetable consumption, and multicomponent interventions were more efficacious than chatbot-only interventions for sleep duration and sleep quality (all p < 0.05). Findings from this systematic review and meta-analysis indicate that chatbot interventions are efficacious for increasing physical activity, fruit and vegetable consumption, sleep duration and sleep quality. Chatbot interventions were efficacious across a range of populations and age groups, with both short- and longer-term interventions, and chatbot only and multicomponent interventions being efficacious.

Chatbot-Delivered Online Intervention to Promote Seasonal Influenza Vaccination During the COVID-19 Pandemic

“…This trial could not provide evidence to support whether the intervention delivered by the simplified rule-based chatbot integrated with the messaging application was better than the intervention without a chatbot. The simplified rule-based chatbot might not meet the most updated definition of a chatbot . Second, the COVID-19 pandemic and COVID-19 vaccination rollout might have affected the study outcome.…”

“…A chatbot is a computerized program that acts to replicate human interaction through text, speech, and visual forms of communication . The chatbot is potentially useful to deliver SOC-tailored intervention promoting SIV.…”

Engagement, acceptability, and effectiveness of the Vira digital behavior change platform: A randomized pilot trial comparing self-care and coach-supported versions in young adults at risk for depression and obesity

“…Another study comparing experiences of human coached versus a virtual chatbot coach found that the chatbot could create a coach-like experience for participants and had the advantage of being persistent and fostering greater participant autonomy by more consistently offering choices and options during the coaching chat session [78]. Moreover, a recent systematic review and meta-analysis of the effectiveness of chatbots on lifestyle behaviors found that chatbot interventions are efficacious for many of the lifestyle behaviors targeted by Vira, such as physical activity and sleep duration [79], though larger studies with more rigorous designs, objective behavioral measures, and longer follow-up are needed. There are also limited studies examining if virtual coach solutions lead to similar improvements in clinical outcomes as human-supported digital interventions.…”

Virtual health assistants: a grand challenge in health communications and behavior change

“…Enter chatbots, which offer the potential of blending the scalability of mHealth technologies with the personalized touch of health coaching. This field, though niche, has shown considerable promise in recent years (1). With the arrival of generative AI tools such as ChatGPT in 2022, new possibilities to meet the complex and personalized requirements of health behavior modification appear vast.…”