Parenting Journal · Volume 2 · Issue 5 · Licensed source edition
The ENDORSE Feasibility Study: Exploring the Use of M-Health, Artificial Intelligence and Serious Games for the Management of Childhood Obesity
Originally published 2023-03-17 · Nutrients
Multidisciplinary Digital Publishing Institute (MDPI) · DOI 10.3390/nu15061451 ↗
AI / system type
Narrow AI personalization/recommendation within a multicomponent care platform; not an LLM
Direct parenting evidenceDirectly addresses parents or caregiving, including parent studies, syntheses and audits of parenting advice.
The AI connection
ENDORSE included an AI recommendation engine selecting personalized game missions and messages from tracked behavior/profile data.
Why this reading matters
A useful example of designing a shared care arrangement and checking whether automation improves the work that matters to families.
Editorial reading guide · Collaboration
Where would personalized messages help our family’s care plan, and where is direct contact with the care team more useful?
Connects child-facing games and tracking with a parent app and clinical-team communication. The AI component selected personalized missions/messages; an active comparison received clinician-written messages. Reported weight and behavior changes occurred within a package of care, and the discussion notes that the human-message group showed high adherence. This supports examining how AI and people share work, not crediting AI for the package’s changes.
Study context
50 Greek children with overweight/obesity and their mothers enrolled; 45 completed the 12-week ENDORSE program
Age / stage: Children 6–14 years; mean 10.5 years
Read with three questions
- Which ENDORSE components were used by children, mothers, and clinicians?
- How did automated messages differ from the active comparison’s clinician communication?
- Why can pooled pre/post BMI changes not isolate an AI effect or substitute for a usual-care comparison?
Keep the limits in view
The small treatment-seeking sample, changing pre-pilot/pilot platform, and COVID restrictions limit inference and transfer. The comparison was active and there was no standard-care control; AI, tracking, games, education, and clinical contact were bundled. Dietary measures were study-specific self-reports, and engagement declined for some components.
The text below is the original article’s licensed repository edition. Its wording is not rewritten. Use the Paper Agent beside the text to locate evidence; open the source for figures, tables and complete context.
Opening the verified paper and agent…
Checking the article identity, license record, and saved source text.
Open the repository recordAttribution & reuse
Follow the original.
Original authorship, publication date, journal and DOI are preserved. This issue’s TRICK placement and reading questions are editorial additions, not claims made by the original authors.
Konstantia Zarkogianni; Evi Chatzidaki; Nektaria Polychronaki; Eleftherios Kalafatis; Nicolas C. Nicolaides; Antonis Voutetakis; Vassiliki Chioti; Rosa-Anna Kitani; Kostas Mitsis; Κonstantinos Perakis; Maria Athanasiou; Danae Antonopoulou; Panagiota Pervanidou; Christina Kanaka-Gantenbein; Konstantina Nikita (2023). The ENDORSE Feasibility Study: Exploring the Use of M-Health, Artificial Intelligence and Serious Games for the Management of Childhood Obesity Nutrients. https://doi.org/10.3390/nu15061451
Permissions checked against the saved article notice; repository publication notices screened 2026-11-04. This is not a new peer-review decision. The source authors and publishers are not represented as endorsing this issue.