Fig. 5From: Explanation and prediction of clinical data with imbalanced class distribution based on pattern discovery and disentanglementPattern Discovery Result of Thoracic Dataset using cPDD a In both First and the Second Disentangled Space, two AV Clusters corresponding to Risk = T and RISK=F were discovered b Detailed Patterns discovered from the above two AV Clusters. Note that no AV of attributes PRE17, PRE19 and PRE32 are associated with any significant patterns. They were dismissed autonomously without undergoing feature engineeringBack to article page