Distinguishing age-related cognitive decline from dementias: A study based on machine learning algorithms

• Published in: Journal of clinical neuroscience Vol. 42; pp. 186 - 192
• Main Authors: Er, Füsun, Iscen, Pınar, Sahin, Sevki, Çinar, Nilgun, Karsidag, Sibel, Goularas, Dionysis
• Format: Journal Article
• Language: English
• Published: Scotland Elsevier Ltd 01.08.2017
• Subjects: Age-related cognitive decline; Aged; Aged, 80 and over; Alzheimer Disease - diagnosis; Cognitive Dysfunction - diagnosis; Dementia, machine learning; Dementia, Vascular - diagnosis; Diagnosis, Computer-Assisted - methods; Diagnosis, Differential; Female; Humans; Machine Learning; Male; Mild cognitive impairment; Neurology; Dementia, machine learning; AD; Mild cognitive impairment; NCTB; NINDS-AIREN; BNT; M5P; NINCDS-ADRDA; SVM; ARCD; WMS-R; VD; CDR; MLP; MCI; NIMH; Age-related cognitive decline; ANOVA; WAIS-R; AROC; IPA; Ö-VMPT; NCT; vascular dementia; Wechsler memory scale-revised; National Institute of Neurological Disorders and Stroke and Association Internationale pour la Recherche et l’Enseignement en Neurosciences; analysis of variance; Boston naming test; multilayer perceptron; age-related cognitive decline; Alzheimer's Disease and Related Disorders Association; neurocognitive test battery; Alzheimer’s disease; clinical dementia rating scale; Öktem verbal memory processes test; area under the receiver-operating curve; neurocognitive test; support vector machine; International Psychogeriatric Association Working Party; M5-model trees; Wechsler adult intelligence scale-revised; mild cognitive impairment; National Institute of Mental Health
• ISSN: 0967-5868; 1532-2653; 1532-2653
• DOI: 10.1016/j.jocn.2017.03.021

•Computer-aided diagnosis for age-related cognitive decline based on cognitive tests.•Some of the tests are Öktem Verbal Memory, semantic fluency and Boston naming tests.•Completely separable from Alzheimer’s disease with a success rate of 100%.•Highly separable from mild cognitive impairment and vascular dementia. This study aims to examine the distinguishability of age-related cognitive decline (ARCD) from dementias based on some neurocognitive tests using machine learning. 106 subjects were divided into four groups: ARCD (n=30), probable Alzheimer’s disease (AD) (n=20), vascular dementia (VD) (n=21) and amnestic mild cognitive impairment (MCI) (n=35). The following tests were applied to all subjects: The Wechsler memory scale-revised, a clock-drawing, the dual similarities, interpretation of proverbs, word fluency, the Stroop, the Boston naming (BNT), the Benton face recognition, a copying-drawings and Öktem verbal memory processes (Ö-VMPT) tests. A multilayer perceptron, a support vector machine and a classification via regression with M5-model trees were employed for classification. The pairwise classification results show that ARCD is completely separable from AD with a success rate of 100% and highly separable from MCI and VD with success rates of 95.4% and 86.30%, respectively. The neurocognitive tests with the higher merit values were Ö-VMPT recognition (ARCD vs. AD), Ö-VMPT total learning (ARCD vs. MCI) and semantic fluency, proverbs, Stroop interference and naming BNT (ARCD vs. VD). The findings show that machine learning can be successfully utilized for distinguishing ARCD from dementias based on neurocognitive tests.