Skip to main content

Table 6 Model performance with different predetermined number of clusters in the training and testing sets, respectively

From: Detecting cardiovascular diseases using unsupervised machine learning clustering based on electronic medical records

Predetermined No. of clusters

Model performance

Training set

Testing set

k = 2

0.8560

0.8598

k = 4

0.8634

0.8659

k = 8

0.8506

0.8525

Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us