Predicting Body Mass Index in Early Childhood Using Data from the First 1,000 Days

Few existing efforts to predict childhood obesity have included risk factors across the prenatal and early infancy periods, despite evidence that the first 1,000 days is critical for obesity prevention. In this study, we employed machine learning techniques to understand the influence of factors in the first 1,000 days on children’s early growth patterns. We used LASSO regression to identify 12 features in addition to sex and history weight, height, and BMI that were relevant to childhood obesity. We then developed prediction models based on support vector regression with 5-fold cross validation, estimating BMI for three time periods: 30-36, 36-42, and 42-48 months. Our 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.