Fig. 3: Predicting mortality of COVID-19 test positive patients from UC CORDS data (dataset X1–X2). | Nature Communications

Fig. 3: Predicting mortality of COVID-19 test positive patients from UC CORDS data (dataset X1–X2).

From: Distributed cross-learning for equitable federated models - privacy-preserving prediction on data from five California hospitals

Fig. 3

a Evaluation setup on dataset X1 and X2. b–c Main results for horizontal modeling on dataset X1 and X2. All box plots are derived from 30 trials, with median as center line, upper and lower quartiles as box limits, 1.5x interquartile range as whiskers, and outliers as points.

Back to article page