OBJECTIVES

: This study aims to build a predictive model for Alzheimer using artificial neural network and compare its performance to logistic regression model.

METHODS

: A public database was used in this study. All the participants who were eligible were randomly assigned into 2 groups: training sample and testing sample. Two models were built using training sample: artificial neural network and logistic regression. We used these two models to predict the risk of Alzheimer in the testing sample. Receiver operating characteristic (ROC) were calculated and compared for these two models for their discrimination capability and a curve using predicted probability versus observed probability were plotted to demonstrate the calibration measure for these two models.

RESULTS

: A total of 127 (40%) records out of 317 were from Alzheimer patients in the data.

According to the logistic regression, patient age, mini mental state examination (MMSE), normalize whole brain volume (nWBV) and gender were important predictors for Alzheimer.

According to this neural network, the top 5 most important predictors were mini mental state examination (MMSE), socioeconomic status (SES), atlas scaling factor (ASF), education and gender.

For training sample, the ROC was 0.94 for the Logistic regression and 0.97 for the artificial neural network. In testing sample, the ROC was 0.94 for the Logistic regression and 0.88 for the artificial neural network. Artificial neural network had worse performance than Logistic regression.

CONCLUSIONS

: In this study, we identified several important predictors for Alzheimer e.g., mini mental state examination, normalize whole brain volume, atlas scaling factor. When compared to artificial neural network model, artificial neural network had a similar discriminating capability with logistic regression.