The impact of machine learning on physical activity–related health outcomes: A systematic review and meta‐analysis
Open Access
- 12 May 2025
- journal article
- review article
- Published by Wiley in International Nursing Review
- Vol. 72 (2) , e70019
Abstract
Aim: To analyze randomized controlled trials evaluating the effectiveness of machine learning (ML)–based interventions in promoting physical activity.Background: Evidence on the effectiveness of ML‐based interventions to increase physical activity from randomized controlled trials is limited. Synthesizing existing evidence is crucial for nurses to integrate such advancements into their care and implement health‐promoting interventions.Methods: Randomized controlled trials from 2013 to 2024 have been accessed by PubMed, EBSCO, Cochrane, and Turkish national databases. The study was conducted and reported in accordance with the PRISMA statement. The methodological quality was assessed using the Cochrane Risk of Bias 1 (RoB 1) tool. Ten studies with a total sample size of 2269 individuals were included.Results: Analysis of studies showed that ML‐based lifestyle interventions are effective in detecting physical activity levels, increasing daily step count and moderate to vigorous physical activity, predicting adherence to physical activity levels goals, and tailoring recommendations and feedback. Meta‐analysis revealed that ML interventions significantly increased daily step count (Hedge's g = 0.402, 95% CI: 0.231–0.573, p<0.000).Discussion: The studies involving ML‐based physical activity promotion initiatives led by nurses were limited. The inclusion of studies published only in English and Turkish may have excluded potentially valuable data.Conclusion: ML can effectively support public health initiatives by enabling self‐monitoring, personalized recommendations, adaptive interventions, and predicting future physical activity behavior.Implications for Nursing Practice and Policy: Nurses can leverage ML algorithms to provide timely, tailored, and cost‐effective care to promote physical activity. To integrate ML into public health initiatives, and develop programs aligned with care models, it is essential to create opportunities and policies that support collaboration between nurses and software developers with nurses leading the process.Keywords
This publication has 44 references indexed in Scilit:
- Physical Activity Change in an RCT: Comparison of Measurement MethodsAmerican Journal of Health Behavior, 2019
- User Models for Personalized Physical Activity Interventions: Scoping ReviewJMIR mHealth and uHealth, 2019
- The impact of patient, intervention, comparison, outcome (PICO) as a search strategy tool on literature search quality: a systematic reviewJournal of the Medical Library Association, 2018
- Worldwide trends in insufficient physical activity from 2001 to 2016: a pooled analysis of 358 population-based surveys with 1·9 million participantsThe Lancet Global Health, 2018
- Evaluating Machine Learning–Based Automated Personalized Daily Step Goals Delivered Through a Mobile Phone App: Randomized Controlled TrialJMIR mHealth and uHealth, 2018
- The role of smartphones in encouraging physical activity in adultsInternational Journal of General Medicine, 2017
- Efficacy of interventions that use apps to improve diet, physical activity and sedentary behaviour: a systematic reviewInternational Journal of Behavioral Nutrition and Physical Activity, 2016
- Obesity: definition, comorbidities, causes, and burden.2016
- Bias in meta-analysis detected by a simple, graphical testBMJ, 1997
- Operating Characteristics of a Rank Correlation Test for Publication Bias1994