Table 4 Cluster representatives identified through simple logistic regression, where each cluster member was used as an independent variable (predictor) and rupture status as the dependent variable (outcome).

From: Predictive modeling and machine learning show poor performance of clinical, morphological, and hemodynamic parameters for small intracranial aneurysm rupture

Cluster representative

Parameter class

p-value

Maximum height 1

Morphological (Fig. 4a)

0.011

Maximum diameter

Morphological (Fig. 4a)

0.016

Non-sphericity index

Morphological (Fig. 4a)

0.049

Neck inflow rate

Hemodynamic (Fig. 4b)

0.016

  1. The variable with the lowest p-value in each cluster was selected as the representative, and only those with p < 0.05 were retained for further analysis. Representatives of each cluster, selected based on simple logistic regression, are shown alongside their corresponding p-values. The cluster representatives are chroma-coded, as in Fig. 4.
Back to article page