Skip to main content

Table 3 Values obtained for clustering metrics Silhouette Score. Calinski-Harabasz Index and Davies-Bouldin Score for the different clustering algorithms, namely, Gower’s Distance and Hierarchical Clustering, FAMD and Hierarchical Clustering, and FAMD and K-Means. For Silhouette Score and Calinski-Harabasz a higher value indicates a better performance, for Davies-Bouldin a lower value is best

From: Identifying subgroups in heart failure patients with multimorbidity by clustering and network analysis

Clustering Algorithm

k

Silhouette Score

Calinski-Harabasz

Davies-Bouldin

Gower Distance + Hierarchical Clustering

3

0.153

918.620

1.859

4

0.155

910.162

1.751

5

0.153

810.238

1.797

FAMD + Hierarchical Clustering

3

0.080

221.906

2.267

4

0.082

225.429

2.325

5

0.075

227.625

2.332

FAMD + K-Means

3

0.073

217.615

2.374

4

0.078

201.213

2.420

5

0.068

191.439

2.537