Fig. 2: Model performance of four GNNs on fivefold cross-validation.
From: Cell graph neural networks enable the precise prediction of patient survival in gastric cancer
a, b show the Boxplots of performance metrics of Accuracy, F1-score, and MCC on fivefold cross-validation. c, d illustrate the ROCs of GINTopK binary- and ternary models on fivefold cross-validation. In the boxplot, the center line marks the mid-point of the data; the top and bottom lines show the maximum and minimum non-outlier data; the upper and lower bounds of the box indicate the third quartile and first quartile of the data; the height of the notch indicates the 95% confidence interval of the median point; small circles represent outliers.
