Figure 5 | Scientific Reports

Figure 5

From: Consensus Clustering of temporal profiles for the identification of metabolic markers of pre-diabetes in childhood (EarlyBird 73)

Figure 5

Evaluation of the overlap in composition of clusters of temporal trajectories of clinical variable HOMA IR obtained with different methods, using n = 2 as number of clusters. Circle color and size encode the Adjusted Rand Index for each comparison. Top row: females, (a) early (5–10 years) and (b) late time points (11–16 years). Bottom row: males (c) early and (d) late time points. The results are obtained by averaging 100 comparison between all possible pairs of clustering schemes. The following abbreviations have been used: Mfuzz and kmInMfuzz respectively for the fuzzy logic and the k-means implementations in the R package Mfuzz; nbclust1 and nbclust3 respectively for the clustering schemes described in the text and implemented in the R package NbClust; SSClust for the Smoothing Spline Clustering method (SSC) implemented in the R package SSCLUST; tscluCORThc and tscluCORTpam respectively for the clustering schemes described in the text and implemented in the R package TSclust.

Back to article page