Fig. 5

Heatmaps showing the inter-rater agreement among different participants across four scenarios. (1) PTs vs. FAs without PTs-HDM (top-left); (2) PTs vs. FAs with PTs-HDM (top-right), (3) PTs-M vs. PTs-B vs. FAs without PTs-HDM (bottom-left), (4) PTs-M vs. PTs-B vs. FAs with PTs-HDM (bottom-right). Kappa values were interpreted according to Landis and Koch’s guidelines: ≤0 indicates no agreement, 0.01–0.20 slight agreement, 0.21–0.40 fair agreement, 0.41–0.60 moderate agreement, 0.61–0.80 substantial agreement, and 0.81-1.00 almost perfect agreement. Statistical significance of Kappa coefficients was tested using asymptotic standard errors under the null hypothesis (κ = 0), with p-values noted within each cell. Darker colors represent higher Kappa values, indicating better agreement. The inclusion of PTs-HDM improved inter-rater agreement across most groups, especially between more experienced participants. FAs, fibroadenomas; PTs, phyllodes tumors; -B, Benign; -M, Borderline/Malignant; PTs-HDM, phyllodes tumors hierarchical diagnosis model