I n t r o d u c t i o n: Co-occurrence of physical and cognitive dysfunctions contribute to functional decline and a gradual loss of independence.

O b j e c t i v e s: The purpose of this study was to evaluate the association between global cognitive impairment and physical mobility in older adults with and without mild cognitive impairment (MCI).

Ma t e r i a l a n d Me t h o d s: A total of 800 older adults were recruited (653 with normal cognitive functioning and 147 participants with MCI). Motor performance was measured with the Timed Up and Go test (TUG) and the 6 Minute Walk Test (6MWT). Cognitive functions were evaluated using Mini- Mental State Examination (MMSE) and Addenbrooke’s Cognitive Examination (ACE-III).

R e s u l t s: ACE-III scores were associated with the TUG test performance in older adults (with and without MCI), but not with 6MWT results. The overall score in ACE-III and its subscales, i.e. a) memory and fluency in the MCI group and in the total group, and b) fluency in the control group, were associated with TUG aft er adjusting for age, sex, body mass index, medication use, depressive symptoms, hypertension, coronary artery disease and diabetes. In the case of the 6MWT test results, only the ACE-III fluency subscale scores and not the overall ACE-III score were associated with them.

C o n c l u s i o n s: Global cognitive function, verbal fluency and memory were independently associated with the TUG. ACE-III, being a more extensive testing tool than MMSE, made it possible to show the relationship between global cognition and motor skills.

Abstract—The prevalence of dementia is expected to increment in the next decades as the elderly population grows and ages. Hence, Alzheimer’s Disease (AD), as the most frequent dementia, will be more problematic from a socioeconomic point of view. Different diagnostic criteria have been proposed by clinicians for the early diagnosis of AD. After discarding the longitudinal and prognosis articles, a selection of articles from the last decade and based on Artificial Neural Networks (ANNs) was collated from the PubMed database, and complemented with researches extracted from others. The latest trends on this field were discovered in these selected articles, which were later discussed. Only articles based whether on shallow ANNs, Deep Learning (DL) or a mix of both were included. The total number of cross-sectional articles that complied with our selection criteria was 154. Convolutional Neural Networks (CNNs) combined with neuroimaging has been the most popular approach, yielding very good performance results. Approaches based on nonneuroimaging techniques, such as gait, genetics, speech and neuropsychological tests, were less common but have their own advantages. Multimodality solutions may become even more prevalent in the near future. Similarly, novel diagnostic criteria will appear and the popularity of currently not-so-common ones will expand. A new proposal emerged from these trends, which is based on ontogenetic ANNs.