JoVE - Journal of Visualized Experiments
JoVE Visualize
Contact Us

The effect of chatbot-based exercise interventions on physical activity, exercise habits, and sedentary behavior: A systematic review and meta-analysis of randomized controlled trials

  • 0Faculty of Medicine, Macau University of Science and Technology, Macau SAR, China.
Digital Health +

|

July 14, 2025

|

July 14, 2025

View abstract on PubMed

Summary

This summary is machine-generated.

Chatbot-based exercise interventions show promise for increasing physical activity (PA) but have limited impact on exercise habits (EH) or sedentary behavior (SB). Further research is needed to confirm these findings and explore chatbot applications.

Area Of Science

  • Digital Health Interventions
  • Exercise Science
  • Behavioral Medicine

Background

  • Chatbots offer personalized, autonomous digital health interventions, overcoming space and time limitations.
  • They have the potential to enhance user engagement and adherence in health programs.
  • This review focuses on chatbot-based exercise interventions (EIs) within randomized controlled trials (RCTs).

Purpose Of The Study

  • To quantitatively evaluate the effectiveness of chatbot-based EIs in RCTs.
  • To assess the impact on physical activity (PA), exercise habits (EH), and sedentary behavior (SB).
  • To identify potential modifying factors through subgroup analyses (SAs).

Main Methods

  • A systematic literature search was conducted across Embase, Web of Science, PubMed, and Cochrane databases (Jan 2010 - Oct 2024).
  • Included studies were analyzed for characteristics of participants, interventions, and chatbots.
  • A meta-analysis synthesized the impact of chatbot-based EIs on PA, EH, and SB, with SAs performed.

Main Results

  • Twelve studies (2013-2024) involving 2446 participants were analyzed.
  • Chatbot-based EIs significantly enhanced PA (SMD = 0.20, p = 0.02) but did not significantly impact overall EH or SB.
  • Subgroup analyses indicated a small, significant short-term increase in EH (SMD = 0.29, p = 0.006).

Conclusions

  • Chatbot-based EIs demonstrate potential for improving physical activity, especially moderate to vigorous PA.
  • Further RCTs with diverse designs, larger samples, and objective measures are needed.
  • Future research should explore chatbot adaptation to different contexts and integration with advanced technologies like ChatGPT.

Keywords: