Classification and staging of dementia of the Alzheimer type: a comparison between neural networks and linear discriminant analysis.

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 chi2 analyses and unweighted and weighted kappa 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.

[1]  Alfred W. Kaszniak,et al.  Communication and Cognition in Normal Aging and Dementia , 1987 .

[2]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[3]  R D Hill,et al.  Very mild senile dementia of the Alzheimer type. II. Psychometric test performance. , 1989, Archives of neurology.

[4]  J. C. Wells,et al.  Discriminant validity of a reduced set of Mini‐Mental State Examination items for dementia and Alzheimer's disease , 1992, Acta psychiatrica Scandinavica.

[5]  Geoffrey E. Hinton,et al.  The appeal of parallel distributed processing , 1986 .

[6]  B. G. Rule,et al.  Adult age differences in working memory. , 1989, Psychology and aging.

[7]  H Morgenstern,et al.  Development of dementing illnesses in an 80‐year‐old volunteer cohort , 1989, Annals of neurology.

[8]  H. Chui,et al.  Clinical subtypes of dementia of the Alzheimer type , 1985, Neurology.

[9]  Murray A. Raskind,et al.  Alzheimer's Disease and Other Dementing Disorders , 1992 .

[10]  R. Mayeux,et al.  Heterogeneity in dementia of the Alzheimer type , 1985, Neurology.

[11]  N Butters,et al.  Detection of abnormal memory decline in mild cases of Alzheimer's disease using CERAD neuropsychological measures. , 1991, Archives of neurology.

[12]  P. Smolensky.  On the proper treatment of connectionism , 1988, Behavioral and Brain Sciences.

[13]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[14]  M. Storandt,et al.  Psychometric discrimination of moderate senile dementia of the Alzheimer type. , 1992, Archives of neurology.

[15]  Geoffrey E. Hinton,et al.  Distributed Representations , 1986, The Philosophy of Artificial Intelligence.

[16]  W. Hauser,et al.  Seizures and myoclonus in patients with Alzheimer's disease , 1986, Neurology.

[17]  Istvan S. N. Berkeley.  Density Plots of Hidden Value Unit Activations Reveal Interpretable Bands , 1995, Connect. Sci..

[18]  D. Knopman,et al.  A verbal memory test with high predictive accuracy for dementia of the Alzheimer type. , 1989, Archives of neurology.

[19]  M. Folstein,et al.  Clinical diagnosis of Alzheimer's disease , 1984, Neurology.

[20]  Michael R. W. Dawson,et al.  Modifying the Generalized Delta Rule to Train Networks of Non-monotonic Processors for Pattern Classification , 1992 .

[21]  David A. Medler,et al.  Training redundant artificial neural networks: Imposing biology on technology , 1994, Psychological research.

[22]  N Butters,et al.  Detection and staging of dementia in Alzheimer's disease. Use of the neuropsychological measures developed for the Consortium to Establish a Registry for Alzheimer's Disease. , 1992, Archives of neurology.

[23]  B. Milner.  Some cognitive effects of frontal-lobe lesions in man. , 1982, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[24]  R. Mohs,et al.  Consortium to establish a registry for Alzheimer's disease (CERAD) clinical and neuropsychological assessment of Alzheimer's disease. , 2002, Psychopharmacology bulletin.

[25]  R. Leiguarda,et al.  Sensitivity and specificity of the Mini-Mental State Exam in the diagnosis of dementia. , 1993, Behavioural neurology.

[26]  H. Crystal,et al.  Predicting development of dementia in the elderly with the Selective Reminding Test. , 1990, Journal of clinical and experimental neuropsychology.

[27]  C. Gottfries.  Clinical classification of dementias. , 1995, Archives of gerontology and geriatrics.

[28]  B. Everitt,et al.  Large sample standard errors of kappa and weighted kappa. , 1969 .

[29]  M. Roth.  CAMDEX : the Cambridge examination for mental disorders of the elderly , 1999 .

[30]  D. Benson,et al.  Dementia: A Clinical Approach , 1983 .

[31]  S. Corkin,et al.  Cognitive test performance in detecting, staging, and tracking Alzheimer's disease. , 1995, Archives of neurology.

[32]  C. P. Hughes,et al.  Psychometric differentiation of mild senile dementia of the Alzheimer type. , 1984, Archives of neurology.

[33]  A. Damasio,et al.  Neuropsychologic detection of abnormal mental decline in older persons. , 1985, JAMA.

[34]  Jacob Cohen.  A Coefficient of Agreement for Nominal Scales , 1960 .

[35]  B Horwitz,et al.  Longitudinal study of the early neuropsychological and cerebral metabolic changes in dementia of the Alzheimer type. , 1988, Journal of clinical and experimental neuropsychology.

[36]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[37]  W. Freeman.  Second Commentary: On the proper treatment of connectionism by Paul Smolensky (1988) - Neuromachismo Rekindled , 1989 .

[38]  Jacob Cohen,et al.  Weighted kappa: Nominal scale agreement provision for scaled disagreement or partial credit. , 1968 .

[39]  J C Morris,et al.  Progressive aphasia , 1990, Neurology.

[40]  L. Labree,et al.  Evidence of subtypes of Alzheimer's disease and implications for etiology. , 1993, Archives of general psychiatry.