AI and Chatbot-Supported Interventions for Physical Activity and Obesity-Related Lifestyle Behaviors: Scoping Review With Attention to Family Involvement.

AI-enabled chatbots and related conversational systems can facilitate human-computer interaction through natural language, personalization, and automated support. In pediatric health promotion, these tools have the potential to provide scalable and flexible approaches to support physical activity (PA) and related lifestyle behavior change within family contexts. However, evidence regarding AI and chatbot-supported interventions for PA and obesity-related lifestyle behaviors among children and adolescents remains limited, and the extent to which these interventions involve parents, caregivers, or families has not been clearly characterized. This scoping review aimed to provide an up-to-date overview of how AI and chatbot-supported interventions are designed, delivered, and evaluated for PA and obesity-related lifestyle behaviors among children and adolescents, with attention to technology characteristics, family involvement, delivery platforms, outcomes, and research gaps. In accordance with PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses extension for Scoping Reviews) guideline, 7 databases (PubMed, Web of Science, APA PsycINFO, Academic Search Complete, CINAHL Ultimate, IEEE Xplore, and Scopus) were searched through February 2026. Two reviewers independently conducted title and abstract screening, followed by full-text screening in Rayyan (Qatar Computing Research Institute). Eligible studies involved children, adolescents, or families; evaluated an AI-enabled chatbot, conversational agent, or related digital system; and addressed PA, exercise, sedentary behavior, screen time, obesity, overweight, or weight management. Diet, sleep, and other lifestyle outcomes were extracted when reported within otherwise eligible studies. Data were extracted and synthesized narratively in accordance with research objectives. Of 2730 records identified, 14 studies met inclusion criteria. Most were published in 2023 or later (n=12, 85.7%) and spanned 10 countries. Mobile app delivery was most common (n=9, 64.3%). AI approaches included rule-based chatbots, hybrid personalization systems, generative AI, and single studies using recommender systems or computer vision. A total of 10 studies (71.4%) included a specific parent, caregiver, or family component. Common intervention features were personalized feedback (n=10, 71.4%), self-monitoring (n=9, 64.3%), and education (n=9, 64.3%). PA was the most common target behavior, often within broader obesity or healthy lifestyle interventions. Among 8 studies reporting direct PA or fitness outcomes, 4 showed significant improvement, 2 found no significant change, and 2 reported mixed or indirect findings. Feasibility, acceptability, usability, and engagement findings were generally favorable across studies, but cultural tailoring was reported in only one study. AI and chatbot-supported interventions for pediatric PA and obesity-related lifestyle behaviors represent a rapidly emerging but still early-stage field. Family involvement varies considerably across interventions and should be more clearly conceptualized and evaluated in future studies.