metrics we compared a sequence of models, with only base covariates, base covariates + micronutrients, base covariates + micronutrients + ERS. Note that the above two metrics measure overall prediction, aggregated over all subjects. A bootstrap resampling (2000 iterations) was used to compute 95% confidence intervals of AUCs for different models [39] (the ci.auc() function in the pROC package in R [40]).