Is early or late biological maturation trigger obesity? A machine learning modeling research in Turkey boys and girls

Abstract

Biological maturation status can affect individual differences, sex, height, body fat, and body weight in adolescents and thus may be associated with obesity. The primary aim of this study was to examine the relationship between biological maturation and obesity. Overall, 1,328 adolescents (792 boys and 536 girls) aged 12.00 ± 0.94–12.21 ± 0.99 years, respectively (measured for body mass, body stature, sitting stature). Body weights were deter-mined with Tanita body analysis system and adolescent obesity status was calculated according to the WHO classification. Biological maturation was determined according to the somatic maturation method. Our results showed that boys mature 3.077-fold later than girls. Obesity was an increasing effect on early maturation. It was determined that being obese, overweight and healthy-weight increased the risk of early maturation 9.80, 6.99 and 1.81-fold, respectively. The equation of the model predicting maturation is: Logit (P) = 1/(1 + exp. (− (−31.386 + sex-boy * (1.124) + [chronological age = 10] * (−7.031) + [chronological age = 11] * (−4.338) + [chronological age = 12] * (−1.677) + age * (−2.075) + weight * 0.093 + height * (−0.141) + obesity * (−2.282) + overweight * (−1.944) + healthy weight * (−0.592)))). Logistic regression model predicted maturity with 80.7% [95% CI: 77.2–84.1%] accuracy. In addition, the model had a high sensitivity value (81.7% [76.2–86.6%]), which indicates that the model can successfully distinguish adolescents with early maturation. In conclusion, sex and obesity are independent predictors of maturity, and the risk of early maturation is increased, especially in the case of obesity and in girls.

A Deep Learning Neural Network to Classify Obesity Risk in Portuguese Adolescents Based on Physical Fitness Levels and Body Mass Index Percentiles: Insights for National Health Policies

“…During adolescence, rapid psychological and hormonal changes happen with the purpose to prepare all body systems for adulthood and the rest of life. However, this accelerated process makes some individuals more susceptible to becoming obese [30]. This fact is more pronounced in girls than boys, due to female hormone production being more associated to greater body fat increases [75].…”

“…In the current literature, we identified some studies using ML to predict obesity in North American [24][25][26][27][28], South Korean [29], and Turkish adolescents [30,30]. Although, none these authors considered direct physical fitness levels as potential deterministic variables for their analysis.…”

Chronic Diseases: A Comprehensive Review of Applications for Prediction of Obesity

“…In the context of obesity, ML algorithms can analyse vast datasets-from genetic predispositions to behavioural and environmental factors-enabling the development of tailored intervention strategies that are more adaptive and responsive to individual needs [9,10]. Moreover, ML can enhance the real-time monitoring and management of obesity through wearable technology and mobile applications, offering immediate feedback and support to individuals as they navigate their daily choices [11,12]. The integration of ML into obesity research and management is not without challenges [13,14].…”