The ENDORSE Feasibility Study: Exploring the Use of M-Health, Artificial Intelligence and Serious Games for the Management of Childhood Obesity.
Konstantia ZarkogianniEvi ChatzidakiNektaria PolychronakiEleftherios KalafatisNicolas C NicolaidesAntonis VoutetakisVassiliki ChiotiRosa-Anna KitaniKostas MitsisΚonstantinos PerakisMaria AthanasiouDanae AntonopoulouPanagiota PervanidouChristina Kanaka-GantenbeinKonstantina NikitaPublished in: Nutrients (2023)
Childhood obesity constitutes a major risk factor for future adverse health conditions. Multicomponent parent-child interventions are considered effective in controlling weight. Τhe ENDORSE platform utilizes m-health technologies, Artificial Intelligence (AI), and serious games (SG) toward the creation of an innovative software ecosystem connecting healthcare professionals, children, and their parents in order to deliver coordinated services to combat childhood obesity. It consists of activity trackers, a mobile SG for children, and mobile apps for parents and healthcare professionals. The heterogeneous dataset gathered through the interaction of the end-users with the platform composes the unique user profile. Part of it feeds an AI-based model that enables personalized messages. A feasibility pilot trial was conducted involving 50 overweight and obese children (mean age 10.5 years, 52% girls, 58% pubertal, median baseline BMI z-score 2.85) in a 3-month intervention. Adherence was measured by means of frequency of usage based on the data records. Overall, a clinically and statistically significant BMI z-score reduction was achieved (mean BMI z-score reduction -0.21 ± 0.26, p -value < 0.001). A statistically significant correlation was revealed between the level of activity tracker usage and the improvement of BMI z-score (-0.355, p = 0.017), highlighting the potential of the ENDORSE platform.
Keyphrases
- artificial intelligence
- big data
- body mass index
- machine learning
- healthcare
- mental health
- deep learning
- public health
- weight gain
- human health
- young adults
- high throughput
- health information
- physical activity
- randomized controlled trial
- climate change
- primary care
- type diabetes
- electronic health record
- risk assessment
- health promotion
- skeletal muscle
- data analysis
- glycemic control
- weight loss
- adverse drug
- metabolic syndrome