Fig. 1: The testing of multiple machine learning models against specific ethnicities in the data set.
From: Ethnic disparity in diagnosing asymptomatic bacterial vaginosis using machine learning
Data was collected using 10 runs of 5-fold cross-validation. a Precision-recall curves for each model. b, d The balanced accuracy (b) and average precision (d) with 95% confidence interval of each model as an average of the 50 runs. Bold means the highest performance among methods (columns), and underline means the highest performance among ethnicities (rows). c, e Boxplots showing the median, upper quartile and lower quartile of the balanced accuracy (c) and average precision (e). Outliers are excluded. Values for boxplots are available in Supplementary Tables 1 and 2.
