Skip to main content
. 2020 Mar 20;27(5):700–708. doi: 10.1093/jamia/ocaa017

Figure 3.

Figure 3.

Results on the diabetic retinopathy test set. Each point represents the mean accuracy across 10 runs, and error bars are 95% confidence intervals for the mean accuracy. (A) Diabetic retinopathy test set accuracies vs sample size standard deviation for the various sample size splits with centrally hosted and distributed training. (B) Diabetic retinopathy test set accuracies vs sample size standard deviation for the various label distribution splits with centrally hosted and distributed training.