Skip to Main Content
Table 3.

Classifier types, inputs, and metrics for evaluation during classification

ClassifierSVMRFKNNLOG_RLDADeep learningMultipleOther
Frequency* 171 (68.4%) 20 (8.0%) 17 (6.8%) 22 (8.8%) 22 (8.8%) 20 (8.0%) 46 (18.0%) 52 (20.8%) 
  
Inputs into classifierBrain network metricsInjury/disease actorDemographicBehavior/cognitive dataMedical HxMedsGenes/blood biomarkersOther
Frequency 100% 13.5% 10.1% 5.9% 2.5% 1.7% 0% 1.6% 
  
Metric for evaluationAccuracySensitivitySpecificityAUC (AUROC)Predictive powerRegression outputsOther (e.g., F1)
Frequency 87% 70.4% 69% 40% 12% 12% 20% 
ClassifierSVMRFKNNLOG_RLDADeep learningMultipleOther
Frequency* 171 (68.4%) 20 (8.0%) 17 (6.8%) 22 (8.8%) 22 (8.8%) 20 (8.0%) 46 (18.0%) 52 (20.8%) 
  
Inputs into classifierBrain network metricsInjury/disease actorDemographicBehavior/cognitive dataMedical HxMedsGenes/blood biomarkersOther
Frequency 100% 13.5% 10.1% 5.9% 2.5% 1.7% 0% 1.6% 
  
Metric for evaluationAccuracySensitivitySpecificityAUC (AUROC)Predictive powerRegression outputsOther (e.g., F1)
Frequency 87% 70.4% 69% 40% 12% 12% 20% 

Note: SVM, support vector machine; RF, random forest; KNN, k nearest-neighbor; LOG_R, logistic regression; LDA, linear discriminant analysis. *Total >100%, including studies with more than one classification approach.

Close Modal

or Create an Account

Close Modal
Close Modal