Adult height prediction using the growth curve comparison method

Area of Science:

• Pediatrics
• Anthropometry
• Biostatistics

Background:

• Accurate child and adolescent height prediction is crucial for development assessment.
• Current methods like radiological assessments are invasive, while percentile-based predictions lack accuracy, especially during puberty.
• There is a need for precise, non-invasive height prediction tools for sports, physical education, and endocrinology.

Purpose of the Study:

• To develop and validate a novel, non-invasive method for predicting adult height in children and adolescents.
• To compare the performance of the new method against existing prediction techniques.
• To provide a tool for monitoring somatic and motor development.

Main Methods:

• Developed the Growth Curve Comparison (GCC) method for height prediction.
• Utilized a large cohort of over 16,000 Slovenian schoolchildren, with yearly data from ages 8 to 18.
• Compared GCC against percentile, linear regressor, decision tree regressor, and extreme gradient boosting models.

Main Results:

• The GCC method demonstrated superior prediction accuracy compared to all other tested methods across the entire age range for both boys and girls.
• The developed method was integrated into a publicly accessible web application.
• GCC showed potential for broader application in predicting other developmental outcomes.

Conclusions:

• The Growth Curve Comparison (GCC) method offers a significant advancement in non-invasive height prediction for children and adolescents.
• GCC provides a more accurate and accessible tool for professionals in pediatrics, sports science, and physical education.
• This method can enhance the assessment and monitoring of child and adolescent development.