Skip to main content
. 2024 Dec 23;7(1):vdae230. doi: 10.1093/noajnl/vdae230

Figure 3.

Figure 3.

Comparison of (A) weighted and (B) macro averaged accuracy, F1-score, and specificity between GPT and SVM models, across different datasets (D1, D2, and D3) and normalization methods (Naive, N4, N4/Zscore, and N4/WS). The error bar represents the SD calculated through bootstrapping. Abbreviation: SVM, support vector machine.