Skip to main content

Table 4 Classification of kidney biopsy samples based on metabolites extracted from intact biopsies

From: Cancer detection and biopsy classification using concurrent histopathological and metabolomic analysis of core biopsies

  

Predicted

  

Benign

Cancer

Actual

Benign

6

0

 

Cancer

2

4

  1. The random forest confusion matrix demonstrates that benign samples can be distinguished from cancer tumor samples by using kidney biopsy samples. The prediction accuracy was 83% and provides an estimate of how accurately new observations can be predicted using the random forest model (for example, whether a sample contains cancer tumor or is benign).