Fig. 3

Calibration curves for the predictive models. The Y-axis is the true fraction of newborns who are low birth weight (LBW) and the X-axis is the model-predicted probability of being LBW. The worst performing model was k-nearest neighbors; the near-horizontal line for this curve indicates the model will predict a consistent LBW percentage of around 15% regardless of the true incidence of LBW. The best performing model was the linear support vector machine, which predicts nearly perfectly for the lowest incidence rates and begins to diverge around 40% incidence