Truace
Subscribe
70/100

Moderate evidence

Cite
More
Export CSVExport JSONEmailLinkedInX

Review of 12 trials finds exercise chatbots modestly raise physical activity

Study title: 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

Evidence type
Systematic review or meta-analysis
Sample
n = 2,446
Sources
1 sourcePeer-reviewed
Published
2 min read
Truvace record
TRV-2026-2741cite or check it

Study title: 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

A systematic review and meta-analysis pooled 12 randomized controlled trials run between 2013 and 2024, covering 2,446 participants and 240 parent-child dyads aged 8 to 71. Chatbot-based exercise interventions raised physical activity compared with control groups, with a standardized mean difference of 0.20 (95% CI 0.04–0.37).

Read the study abstract

Objectives Chatbots, transcending the limitations of space and time while reducing user resistance, offer a personalized and autonomous approach potentially enhancing digital health interventions. This systematic review aims to quantitatively evaluate the effectiveness of chatbot-based exercise interventions (EIs) in randomized controlled trials (RCTs), emphasizing physical activity (PA), exercise habits (EH), and sedentary behavior (SB). Methods A comprehensive search was carried out across Embase, Web of Scien…

The gain

A meta-analysis of 12 randomized trials with 2,446 participants found chatbot-based exercise interventions raised physical activity more than control groups did (SMD 0.20, 95% CI 0.04–0.37).

In brief

The effect is small. Chatbots did not significantly change exercise habits overall (SMD 0.29, 95% CI −0.48 to 1.06) or reduce sedentary behavior (SMD 0.32, 95% CI −0.54 to 1.19). A subgroup analysis did find a small short-term increase in exercise habits (SMD 0.29, 95% CI 0.08–0.50).

The authors say chatbots look most promising for moderate to vigorous physical activity. They call for larger trials, low-resource settings, accelerometer-measured sedentary time, longer follow-up, and tests of newer tools such as ChatGPT.

Main points

  1. The review searched Embase, Web of Science, PubMed and Cochrane for studies published from January 2010 to October 2024.
  2. Twelve randomized trials from 2013 to 2024 were included, with 2,446 participants and 240 parent-child dyads.
  3. Participants ranged in age from 8 to 71 years.
  4. Physical activity rose significantly versus controls (SMD 0.20, 95% CI 0.04–0.37, p = 0.02), with moderate heterogeneity (I² = 51%).
  5. Overall exercise habits did not change significantly (SMD 0.29, 95% CI −0.48 to 1.06, p = 0.46).
  6. Sedentary behavior did not fall significantly (SMD 0.32, 95% CI −0.54 to 1.19, p = 0.46).
  7. A subgroup analysis found a small, significant short-term increase in exercise habits (SMD 0.29, 95% CI 0.08–0.50, p = 0.006).

What the review found when it combined the studies

These are the review’s own pooled results, copied from its abstract. Truvace did not recalculate them.

  • Sedentary time with chatbot-based exercise interventions compared with control groups

    SMD 0.32 (95% CI −0.54 to 1.19)

    12 studies · 2,446 people · search to October 2024

    The review’s own words
    The analysis indicated that chatbot-based interventions were not associated with a significant reduction in sedentary time relative to control groups (SMD = 0.32, 95% CI = −0.54–1.19, p = 0.46; I² = 0%, p = 0.91).

  • Exercise habits with chatbot-based exercise interventions compared with control groups

    SMD 0.29 (95% CI −0.48 to 1.06)

    12 studies · 2,446 people · search to October 2024

    The review’s own words
    The difference observed was not statistically significant (SMD = 0.29, 95% CI = −0.48–1.06, p = 0.46; I² = 54%, p = 0.11).

  • Moderate to vigorous physical activity with chatbot-based exercise interventions compared with controls

    SMD 0.26 (95% CI 0.05 to 0.46)

    search to October 2024

    The review’s own words
    A pronounced effect was noted in the subgroup engaging in MVPA, where the intervention group demonstrated a significant increase compared to controls (SMD = 0.26, 95% CI = 0.05–0.46, p < 0.05 ).

  • Short-term physical activity (8 weeks or less) with chatbot-based exercise interventions compared with controls

    SMD 0.29 (95% CI 0.08 to 0.50)

    search to October 2024

    The review’s own words
    In the analysis stratified by duration, the chat-based EI was linked with a modest increase in PA in the short term (SMD = 0.29, 95% CI = 0.08–0.50, p < 0.05 ), which had statistical significance ( p < 0.05; see Figure 4 ).

  • Physical activity with chatbot-based exercise interventions compared with control groups

    SMD 0.20 (95% CI 0.04 to 0.37)

    12 studies · 2,446 people · search to October 2024

    The review’s own words
    The chatbot-based EI significantly improved PA compared to the control group, as indicated by a standardized mean difference (SMD = 0.20, 95% CI = 0.04–0.37, p < 0.05 ; I² = 51%, p = 0.04; Figure 3 ).

Code checks every number above against the review’s text before it is shown. The short labels are an AI model’s reading of that text, so the review’s own sentence sits under each one. A pooled figure is only as strong as the studies behind it. How Truvace uses pooled results

The full story

The authors searched four databases for randomized controlled trials of chatbot-based exercise interventions published from January 2010 to October 2024. They analyzed the characteristics of the studies and the chatbots, then pooled results for physical activity, exercise habits and sedentary behavior. The review was registered in PROSPERO (CRD42024609852).

Twelve studies met the criteria. Pooled results showed a significant gain in physical activity over control groups, with moderate heterogeneity across trials. Exercise habits and sedentary behavior showed no significant overall effect, and the confidence intervals for both were wide.

Subgroup analyses were run to look for modifying effects and found a short-term rise in exercise habits. The authors conclude chatbots appear promising for physical activity, especially moderate to vigorous activity, and recommend trials with more diverse chatbot designs, larger samples, low-resource settings and longer follow-up.

Sources

1 on file
  1. DIGITAL HEALTHdoi:10.1177/20552076251353731
    Peer-reviewed2025-05-01

Talk it over

Four questions to start onWho gets this benefit, and who was left out of the study or story?

Start with a question

Review of 12 trials finds exercise chatbots modestly raise physical activityhttps://truvace.com/item/the-effect-of-chatbot-based-exercise-interventions-on-physical-activity-exercise

  1. Who gets this benefit, and who was left out of the study or story?

    The gain A meta-analysis of 12 randomized trials with 2,446 participants found chatbot-based exercise interventions raised physical activity more than control groups did (SMD 0.20, 95% CI 0.04–0.37).

    Answer in the thread

  2. How do we know? What can this kind of evidence show, and what can’t it?

    The evidence This rests on a systematic review or meta-analysis with a sample of 2,446, from DIGITAL HEALTH.

    Answer in the thread

  3. What does it leave open? What else would you want to know before acting on it?

    The record’s own caveat The authors say more trials are needed with larger samples, low-resource settings, objective measures of sedentary behavior such as accelerometers, and longer follow-up before the findings can be corroborated.

    Answer in the thread

  4. Have you seen AI used this way where you study, work or live? Did it go the same way?

    Answer in the thread

The questions are the same on every record. The details under them are taken from this record as written.

What readers say

More from Health