Fig. 7
From: miR-129-5p as a biomarker for pathology and cognitive decline in Alzheimer’s disease
The ROC curves and mean AUC of machine learning approach using penalized logistic regression. Sensitivity is on the y-axis and 1-specificity is on the x-axis. 10-fold cross validation was used to investigate and compare the classification performance of five different classification models for differentiating AD from NCI. The gray zone around the mean ROC curve represents ± 1 standard deviation. Five different classification models are shown per following training features. A Training features include age, sex, and apolipoprotein E (APOE) ε4 carrier status. B Training features include five AD-associated hub miRNAs. C Training features include age, sex, APOE ε4 carrier status, and five AD-associated hub miRNAs. D Training features include all 309 miRNAs. E Training features include age, sex, APOE ε4 carrier status, and all 309 miRNAs. AD Alzheimer’s dementia, AUC area under the curve, miRNAs microRNAs, NCI no cognitive impairment, ROC receiver operating characteristic