Table 2 The AUC results of tenfold cross-validation of the training set obtained through 100 iterations of data shuffling.

From: A multimodal machine learning model for predicting dementia conversion in Alzheimer’s disease

Modality combination

Machine learning models

DT

RF

SVM

LR

GBM

XGB

Mean ± SD

Mean ± SD

Mean ± SD

Mean ± SD

Mean ± SD

Mean ± SD

demo

0.772 ± 0.032

0.811 ± 0.029

0.792 ± 0.027

0.771 ± 0.023

0.796 ± 0.031

0.798 ± 0.027

A

0.827 ± 0.026

0.921 ± 0.015

0.952 ± 0.018

0.936 ± 0.017

0.918 ± 0.017

0.921 ± 0.014

N

0.822 ± 0.030

0.966 ± 0.008

0.991 ± 0.005

0.893 ± 0.026

0.967 ± 0.009

0.959 ± 0.010

V

0.682 ± 0.039

0.739 ± 0.032

0.688 ± 0.073

0.716 ± 0.040

0.720 ± 0.041

0.728 ± 0.040

demo + A

0.852 ± 0.025

0.938 ± 0.012

0.965 ± 0.012

0.944 ± 0.016

0.941 ± 0.013

0.944 ± 0.011

demo + N

0.837 ± 0.031

0.970 ± 0.008

0.991 ± 0.005

0.898 ± 0.025

0.968 ± 0.010

0.959 ± 0.011

demo + V

0.775 ± 0.035

0.853 ± 0.023

0.835 ± 0.030

0.811 ± 0.026

0.835 ± 0.030

0.842 ± 0.028

demo + AN

0.869 ± 0.027

0.967 ± 0.008

0.989 ± 0.005

0.957 ± 0.016

0.978 ± 0.009

0.977 ± 0.008

demo + NV

0.836 ± 0.030

0.969 ± 0.008

0.991 ± 0.005

0.906 ± 0.025

0.968 ± 0.009

0.960 ± 0.010

demo + AV

0.849 ± 0.027

0.941 ± 0.012

0.961 ± 0.014

0.945 ± 0.014

0.942 ± 0.012

0.946 ± 0.011

demo + ANV

0.871 ± 0.027

0.968 ± 0.008

0.989 ± 0.005

0.959 ± 0.014

0.978 ± 0.008

0.976 ± 0.007

  1. AUC; Area Under ROC Curve, SD; Standard Deviation, DT; Decision Trees, RF; Random Forests, SVM; Support Vector Machines, LR; Linear Regression Classifiers, GBM; Gradient Boosting Models, XGB; Extreme Gradient Boosting, demo; demographic characteristics, A; amyloid PET image features, N; T1-weigted image features, V; T2-FLAIR image features.
Back to article page