Predicting conversion from mild cognitive impairment to Alzheimer's disease using neuropsychological tests and multivariate methods

• Published in: Journal of clinical and experimental neuropsychology Vol. 33; no. 2; pp. 187 - 199
• Main Authors: Chapman, Robert M., Mapstone, Mark, McCrary, John W., Gardner, Margaret N., Porsteinsson, Anton, Sandoval, Tiffany C., Guillily, Maria D., DeGrush, Elizabeth, Reilly, Lindsey A.
• Format: Journal Article
• Language: English
• Published: Hove Taylor & Francis Group 01.02.2011; Psychology Press
• Subjects: Adult and adolescent clinical studies; Aged; Alzheimer Disease - psychology; Alzheimer's disease; Biological and medical sciences; Cognition Disorders - psychology; Degenerative and inherited degenerative diseases of the nervous system. Leukodystrophies. Prion diseases; Depression - diagnosis; Depression - psychology; Diagnostic and Statistical Manual of Mental Disorders; Discriminant analysis; Disease Progression; Educational Status; Female; Geriatrics; Humans; Male; Medical sciences; Memory - physiology; Mild cognitive impairment; Multivariate; Multivariate Analysis; Neurology; Neuropsychological Tests; Organic mental disorders. Neuropsychology; Posterior probability; Predict; Predictive Value of Tests; Principal Component Analysis; Prognosis; Psychology. Psychoanalysis. Psychiatry; Psychopathology. Psychiatry; Reading; Reproducibility of Results; Space Perception - physiology; Stroop Test; Trail Making Test; Verbal Behavior; Word Association Tests; Human; Predict; Nervous system diseases; Discriminant analysis; Cognitive disorder; Alzheimer disease; Neuropsychological test; Probability; Psychometrics; Cerebral disorder; Posterior probability; Neuropsychological tests; Central nervous system disease; Degenerative disease; mild cognitive impairment; Predictive factor; Elderly; Alzheimer's disease; Multivariate; Principal component analysis
• ISSN: 1380-3395; 1744-411X; 1744-411X
• DOI: 10.1080/13803395.2010.499356

Behavioral markers measured through neuropsychological testing in mild cognitive impairment (MCI) were analyzed and combined in multivariate ways to predict conversion to Alzheimer's disease (AD) in a longitudinal study of 43 MCI patients. The test measures taken at a baseline evaluation were first reduced to underlying components (principal component analysis, PCA), and then the component scores were used in discriminant analysis to classify MCI individuals as likely to convert or not. When empirically weighted and combined, episodic memory, speeded executive functioning, recognition memory (false and true positives), visuospatial memory processing speed, and visuospatial episodic memory were together strong predictors of conversion to AD. These multivariate combinations of the test measures achieved through the PCA were good, statistically significant predictors of MCI conversion to AD (84% accuracy, 86% sensitivity, and 83% specificity). Importantly, the posterior probabilities of group membership that accompanied the binary prediction for each participant indicated the confidence of the prediction. Most of the participants (81%) were in the highly confident probability bins (.70-1.00), where the obtained prediction accuracy was more than 90%. The strength and reliability of this multivariate prediction method were tested by cross-validation and randomized resampling.