Related Experiment Video
Updated: Jul 28, 2025

Assessment of Child Anthropometry in a Large Epidemiologic Study
Published on: February 2, 2017
Predicting body mass index in early childhood using data from the first 1000 days
Erika R Cheng1, Ahmet Yahya Cengiz2, Zina Ben Miled3,4
1Division of Children's Health Services Research, Department of Pediatrics, Indiana University School of Medicine, 410 W. 10th Street, Indianapolis, IN, 46220, USA. echeng@iu.edu.
Insights
Machine learning models accurately predict childhood obesity by analyzing risk factors from the first 1000 days. These models can aid early life obesity prevention strategies.
Area of Science:
- Pediatrics
- Public Health
- Machine Learning
Background:
- The first 1000 days of life are critical for obesity prevention.
- Existing childhood obesity prediction models often lack prenatal and early infancy risk factors.
Purpose of the Study:
- To utilize machine learning to identify early life risk factors for childhood obesity.
- To develop accurate predictive models for body mass index (BMI) in early childhood.
Main Methods:
- LASSO regression identified 13 relevant features beyond standard measurements.
- Support vector regression with fivefold cross-validation was used to build BMI prediction models.
- Models were trained on 80% of patient data and validated on the remaining 20%.
Main Results:
- The models achieved high accuracy in predicting children's BMI at 30-36, 36-42, and 42-48 months.
- Mean average errors ranged from 0.96 to 1.00, with low standard deviations.
- Identified key risk factors from the first 1000 days influencing childhood BMI.
Conclusions:
- Machine learning models can effectively predict childhood BMI using early life data.
- These predictive tools can support clinical and public health initiatives for early obesity prevention.
Abstract:
Few existing efforts to predict childhood obesity have included risk factors across the prenatal and early infancy periods, despite evidence that the first 1000 days is critical for obesity prevention. In this study, we employed machine learning techniques to understand the influence of factors in the first 1000 days on body mass index (BMI) values during childhood. We used LASSO regression to identify 13 features in addition to historical weight, height, and BMI that were relevant to childhood obesity. We then developed prediction models based on support vector regression with fivefold cross validation, estimating BMI for three time periods: 30-36 (N = 4204), 36-42 (N = 4130), and 42-48 (N = 2880) months. Our models were developed using 80% of the patients from each period. When tested on the remaining 20% of the patients, the models predicted children's BMI with high accuracy (mean average error [standard deviation] = 0.96[0.02] at 30-36 months, 0.98 [0.03] at 36-42 months, and 1.00 [0.02] at 42-48 months) and can be used to support clinical and public health efforts focused on obesity prevention in early life.
Related Concept Videos
Obesity
z Scores and Area Under the Curve
Regression Toward the Mean
Environmental Influences on Intelligence

