Algorithm-driven digital food environments and obesity risk: a systematic review and meta-analysis
1
Faculty of medicine, south valley university, qena, egypt., Qena, Egypt
Popul. Med. 2026;8(Supplement Supplement 1):A2868
ABSTRACT
INTRODUCTION:
Algorithmic recommendation systems increasingly shape food exposure through social media video platforms and targeted advertising. These digital food environments represent a rapidly expanding yet under-recognized determinant of obesity. While individual studies suggest associations between algorithm-driven food content and unhealthy dietary behaviors no quantitative synthesis has evaluated their population-level health impact. This systematic review and meta-analysis aimed to estimate the association between exposure to algorithm-curated digital food marketing and obesity-related outcomes.
METHODS:
We systematically searched pubmed embas web of science scopus and ieee xplore from inception to april 2025. Eligible studies included observational or experimental designs assessing algorithm-based food exposure through personalized feeds recommendations or targeted advertisements. Outcomes included body mass index overweight obesity and dietary quality indicators. Two reviewers independently screened studies extracted data and assessed risk of bias using robins-i and cochrane tools. Random-effects meta-analyses pooled effect estimates comparing high versus low exposure. Subgroup analyses examined age platform type and country income level.
RESULTS:
Twenty seven studies involving 340000 participants from 18 countries met inclusion criteria. High exposure to algorithm-curated unhealthy food content was associated with increased odds of overweight or obesity with a pooled odds ratio of 1.26. Associations were stronger among adolescents than adults and in low and middle income countries. Studies evaluating personalized recommendation algorithms showed larger effect sizes than non-personalized digital marketing. Overall heterogeneity was moderate and results were robust in sensitivity analyses.
CONCLUSIONS:
Algorithm-driven digital food environments constitute a novel and quantifiable risk factor for obesity. Public health strategies should extend beyond individual behavior to include governance of artificial intelligence systems. Regulating algorithmic transparency and integrating health-protective design principles are essential for addressing emerging digital determinants of nutrition.
Algorithmic recommendation systems increasingly shape food exposure through social media video platforms and targeted advertising. These digital food environments represent a rapidly expanding yet under-recognized determinant of obesity. While individual studies suggest associations between algorithm-driven food content and unhealthy dietary behaviors no quantitative synthesis has evaluated their population-level health impact. This systematic review and meta-analysis aimed to estimate the association between exposure to algorithm-curated digital food marketing and obesity-related outcomes.
METHODS:
We systematically searched pubmed embas web of science scopus and ieee xplore from inception to april 2025. Eligible studies included observational or experimental designs assessing algorithm-based food exposure through personalized feeds recommendations or targeted advertisements. Outcomes included body mass index overweight obesity and dietary quality indicators. Two reviewers independently screened studies extracted data and assessed risk of bias using robins-i and cochrane tools. Random-effects meta-analyses pooled effect estimates comparing high versus low exposure. Subgroup analyses examined age platform type and country income level.
RESULTS:
Twenty seven studies involving 340000 participants from 18 countries met inclusion criteria. High exposure to algorithm-curated unhealthy food content was associated with increased odds of overweight or obesity with a pooled odds ratio of 1.26. Associations were stronger among adolescents than adults and in low and middle income countries. Studies evaluating personalized recommendation algorithms showed larger effect sizes than non-personalized digital marketing. Overall heterogeneity was moderate and results were robust in sensitivity analyses.
CONCLUSIONS:
Algorithm-driven digital food environments constitute a novel and quantifiable risk factor for obesity. Public health strategies should extend beyond individual behavior to include governance of artificial intelligence systems. Regulating algorithmic transparency and integrating health-protective design principles are essential for addressing emerging digital determinants of nutrition.
| eISSN: | 2654-1459 |
We process personal data collected when visiting the website. The function of obtaining information about users and their behavior is carried out by voluntarily entered information in forms and saving cookies in end devices. Data, including cookies, are used to provide services, improve the user experience and to analyze the traffic in accordance with the Privacy policy. Data are also collected and processed by Google Analytics tool (more).
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
You can change cookies settings in your browser. Restricted use of cookies in the browser configuration may affect some functionalities of the website.
