From Affect Regulation to BMI: Unveiling Childhood Obesity Patterns Through Advanced Clustering Techniques.

Area of Science:

• Pediatric Health
• Psychology
• Data Science

Background:

• Childhood obesity is a growing public health concern.
• Psychological factors are increasingly recognized as significant contributors to Body Mass Index (BMI) variations in children.

Purpose of the Study:

• To investigate the complex relationship between psychological profiles and children's BMI.
• To identify distinct patient clusters based on psychological data using advanced clustering techniques.

Main Methods:

• Application of clustering algorithms including Gaussian Mixture Models, Spectral Clustering, and Affinity Propagation.
• Analysis of psychological assessments to stratify children by risk factors related to BMI.

Main Results:

• Affinity Propagation demonstrated high efficacy in distinguishing between different psychological profiles associated with BMI.
• Identified specific clusters indicating potential targets for intervention.

Conclusions:

• Psychological assessments, when analyzed with clustering methods, can effectively inform personalized childhood obesity management strategies.
• Tailored interventions based on identified psychological clusters show promise for improving obesity outcomes in pediatric populations.