Skip to main content

Table 3 Additional models for confusion matrices/discrepancies

From: In-silico performance, validation, and modeling of the Nanostring Banff Human Organ transplant gene panel using archival data from human kidney transplants

A. Average discrepancies between Diagnoses All PC   
Model Target Data % Discrepancies   
Multinomial logistic regression Diagnoses ALL PC 37.3  
Boot strap forest Diagnoses ALL PC 24.1  
Partial least squares Diagnoses ALL PC 37.3  
B. Average discrepancies between Clusters All PC   
Model Target Data % Discrepancies   
Multinomial logistic regression Clusters ALL PC 10.0  
Boot strap forest Clusters ALL PC 12.2  
Partial least squares Clusters ALL PC 15.1  
C. Average discrepancies CPPC, UPC, & PBPC   
Model Target Data % Discrepancies   
Multinomial logistic regression Diagnoses CPPC 36.9  
Boot strap forest Diagnoses CPPC 25.6  
Partial least squares Diagnoses CPPC 27.2  
Multinomial logistic regression Diagnoses UPC 24.4  
Boot strap forest Diagnoses UPC 24.9  
Partial least squares Diagnoses UPC 27.0  
Multinomial logistic regression Diagnoses PBPC 35.2  
Boot strap forest Diagnoses PBPC 27.5  
Partial least squares Diagnoses PBPC 29.2  
D. Average per sample discrepancies between Diagnoses All PC   
Model Target Data % Discrepancies   
Multinomial logistic regression vs Boot strap forest Diagnoses ALL PC 33.1  
Multinomial logistic regression vs Partial least squares Diagnoses ALL PC 32.7  
Boot strap forest vs Partial least squares Diagnoses ALL PC 33.1  
E. Average per sample discrepancies between Clusters All PC   
Model Target Data % Discrepancies   
Multinomial logistic regression vs Boot strap forest Clusters ALL PC 12.4  
Multinomial logistic regression vs Partial least squares Clusters ALL PC 13.5  
Boot strap forest vs Partial least squares Clusters ALL PC 14.4  
F. Additional models for diagnoses all PC, CPPC, PBPC, & UPC*
Model Target Data Mean accuracy Average precision/recall Percent errors
Extreme Gradient Boosting Diagnoses ALL PC 0.74 0.79 36.5
Linear Discriminant Analysis Diagnoses CPPC 0.75 0.78 32.6
Extra Tree Classifier Diagnoses PBPC 0.75 0.76 35.3
Linear discriminant analysis Diagnoses UPC 0.76 0.70 33.9
G. Additional models for clusters all PC, CPPC, PBPC, & UPC*
Model Target Data Mean accuracy Average precision/recall Percent errors
Multinomial logistic regression Clusters ALL PC 0.93 0.95 6.9
Extra tree classifier Clusters CPPC 0.90 0.93 6.9
Extreme gradient boosting Clusters PBPC 0.92 0.94 6.2
Multinomial logistic regression Clusters UPC 0.92 0.94 6.9
  1. *Best model chosen; N = 12