[Skip to Navigation]
August 1997

Classification and Staging of Dementia of the Alzheimer Type: A Comparison Between Neural Networks and Linear Discriminant Analysis

Author Affiliations

From the Department of Psychology (Ms French and Dr Dobbs) and the Biological Computation Project, Department of Psychology (Dr Dawson), University of Alberta, Edmonton.

Arch Neurol. 1997;54(8):1001-1009. doi:10.1001/archneur.1997.00550200057011

Objective:  To examine the utility of artificial neural networks (ANNs) for differentiating patients with Alzheimer disease from healthy control subjects and for staging the degree of dementia.

Design:  Comparison of the classification abilities of ANNs with the statistical technique of linear discriminant analysis (LDA) using the results of 11 neuropsychological tests as predictors.

Participants:  Ninety-two patients with a diagnosis of probable Alzheimer disease (referred from a geriatric clinic) and 43 elderly control subjects (independently solicited). The patients met National Institute of Neurological and Communicative Disorders and Stroke—Alzheimer's Disease and Related Disorders Association criteria for probable dementia, with clinical ratings of dementia severity derived from the Cambridge Examination for Mental Disorders of the Elderly (CAMDEX).

Main Outcome Measures:  Classifications between and within groups were determined by using LDA and ANNs, and more detailed comparisons of the 2 methods were performed by using X2 analyses and unweighted and weighted κ statistics.

Results:  Linear discriminant analysis correctly identified 71.9% of cases. Artificial neural networks, trained to classify the subjects using the same data, correctly classified 91.1% of the cases. Subsidiary analyses showed that although both techniques effectively discriminated between the control subjects and patients with dementia, the ANNs were more powerful in discriminating severity levels within the dementia population. The analyses for goodness of fit revealed that the ANN classification produced a better fit to the actual data. A comparison of the weighted proportion of agreement between the criterion and predictor variables also showed that the ANNs clearly outperformed LDA in classification accuracy for the full data set and patients-only data set.

Conclusion:  The results demonstrate the utility of ANNs for group classification of patients with Alzheimer disease and elderly controls and for staging dementia severity using neuropsychological data.

Add or change institution