Skip to main content
Fig. 1 | BMC Medical Informatics and Decision Making

Fig. 1

From: Identifying the presence and severity of dementia by applying interpretable machine learning techniques on structured clinical records

Fig. 1

The decision tree predicts the dementia classes (“Dementia”/“No Dementia”) of 2505 patients for the Problem (a). The pie charts in leaves show class labels, the proportion of resulting classes and their support size. The branches demonstrate connections between features and their threshold values, leading towards class labels. In the tree, some most significant paths A, B and C predict nearly pure decisive classes for large patients. The rules of path A and path B lead to a pure “Dementia” population of 648 and 57 patients, respectively, while the rules of path C lead to a large majority of “No Dementia” population comprised by 1092 individuals. (see Additional file 1: Figure S1 in Supplementary Information for the better visibility)

Back to article page

BMC Medical Informatics and Decision Making

ISSN: 1472-6947

Contact us