Figure 2.

Federated model training. The performance of (A) federated MLP and (B) federated LASSO models, as measured by AUROCs versus the number of training epochs. The binary cross-entropy loss of (C) federated MLP and (D) federated LASSO models versus the number of training epochs. AUROC: area under the receiver operating characteristic curve; LASSO: least absolute shrinkage and selection operator; MLP: multilayer perceptron; MSB: Mount Sinai Brooklyn; MSH: Mount Sinai Hospital; MSM: Mount Sinai Morningside; MSQ: Mount Sinai Queens; MSW: Mount Sinai West.