BACKGROUND & AIMS: :Age-related cognitive impairment and dementia are an increasing societal burden. Epidemiological studies indicate that lifestyle factors, e.g. physical, cognitive and social activities, correlate with reduced dementia risk; moreover, positive effects on cognition of physical/cognitive training have been found in cognitively unimpaired elders. Less is known about effectiveness and action mechanisms of physical/cognitive training in elders already suffering from Mild Cognitive Impairment (MCI), a population at high risk for dementia. We assessed in 113 MCI subjects aged 65-89 years, the efficacy of combined physical-cognitive training on cognitive decline, Gray Matter (GM) volume loss and Cerebral Blood Flow (CBF) in hippocampus and parahippocampal areas, and on brain-blood-oxygenation-level-dependent (BOLD) activity elicited by a cognitive task, measured by ADAS-Cog scale, Magnetic Resonance Imaging (MRI), Arterial Spin Labeling (ASL) and fMRI, respectively, before and after 7 months of training vs. usual life. Cognitive status significantly decreased in MCI-no training and significantly increased in MCI-training subjects; training increased parahippocampal CBF, but no effect on GM volume loss was evident; BOLD activity increase, indicative of neural efficiency decline, was found only in MCI-no training subjects. These results show that a non pharmacological, multicomponent intervention improves cognitive status and indicators of brain health in MCI subjects.

背景与目标： : 与年龄相关的认知障碍和痴呆症是一个日益增加的社会负担。流行病学研究表明，生活方式因素 (例如身体，认知和社交活动) 与降低的痴呆症风险相关; 此外，在未认知障碍的老年人中发现了对身体/认知训练认知的积极影响。对于已经患有轻度认知障碍 (MCI) 的老年人 (痴呆症的高风险人群)，身体/认知训练的有效性和作用机制知之甚少。我们在113名年龄在65-89岁的MCI受试者中评估了身体-认知训练对认知下降，海马和海马旁区域的灰质 (GM) 容量损失和脑血流 (CBF) 的疗效，以及由认知任务引起的脑血氧合水平依赖性 (BOLD) 活动，分别通过ADAS-Cog量表，磁共振成像 (MRI)，动脉自旋标记 (ASL) 和fMRI测量，在7个月的训练与平时生活相比。认知状态在MCI-no训练中显著降低，在MCI-训练受试者中显著增加; 训练增加海马旁CBF，但对转基因体积损失没有明显影响; 仅在MCI-no训练受试者中发现BOLD活动增加，表明神经效率下降。这些结果表明，非药理学，多组分干预可以改善MCI受试者的认知状态和脑健康指标。

BACKGROUND & AIMS: :Mono- and polyunsaturated fatty acids (MUFA, PUFA) have been associated with a reduced risk of dementia. The association of these fatty acids with mild cognitive impairment (MCI) is not fully established. The objective of the study was to investigate the cross-sectional association of dietary fatty acids with MCI in a population-based sample. Participants aged >or= 70 years on October 1, 2004, were evaluated using the Clinical Dementia Rating Scale (participant and informant), a neurological evaluation, and neuropsychological testing. A panel of nurses, physicians, and neuropsychologists reviewed the data for each participant in order to establish a diagnosis of MCI, normal cognition, or dementia by consensus. Participants also completed a 128-item food-frequency questionnaire. Among 1,233 non-demented subjects, 163 (13.2%) had MCI. The odds ratio (OR) of MCI decreased with increasing PUFA and MUFA intake. Compared to the lowest tertile, the OR (95% confidence interval) for the upper tertiles were 0.44 (0.29-0.66; p for trend = 0.0004) for total PUFA; 0.44 (0.30-0.67; p for trend = 0.0004) for omega-6 fatty acids; 0.62 (0.42-0.91; p for trend = 0.012) for omega-3 fatty acids; and 0.56 (0.38-0.83; p for trend = 0.01) for (MUFA+PUFA):saturated fatty acid ratio after adjustment for age, sex, number of years of education, and caloric intake. In this study, higher intake of PUFA and MUFA was associated with a reduced likelihood of MCI among elderly persons in the population-based setting.

背景与目标： : 单不饱和脂肪酸和多不饱和脂肪酸 (MUFA，PUFA) 与痴呆症风险降低有关。这些脂肪酸与轻度认知障碍 (MCI) 的关联尚未完全确定。该研究的目的是调查基于人群的样本中饮食脂肪酸与MCI的横断面关联。2004年10月1日年龄> 或 = 70岁的参与者，使用临床痴呆评定量表 (参与者和信息提供者)，神经系统评估和神经心理学测试进行评估。由护士，医师和神经心理学家组成的小组审查了每个参与者的数据，以便通过共识确定MCI，正常认知或痴呆症的诊断。参与者还完成了128项食物频率问卷。在1,233非痴呆受试者中，163 (13.2%) 患有MCI。MCI的比值比 (OR) 随着PUFA和MUFA摄入量的增加而降低。与最低三分位数相比，最高三分位数的OR (95% 置信区间) 为总PUFA的0.44 (0.29-0.66; p表示趋势 = 0.0004); Ω-6脂肪酸的0.44 (0.30-0.67; p表示趋势 = 0.0004); 0.62 (0.42-0.91; p表示趋势 = 0.012)，用于 ω-3脂肪酸; 和0.56 (0.38-0.83; p表示趋势 = 0.01)，用于 (MUFA + PUFA): 校正年龄、性别、受教育年限和热量摄入后的饱和脂肪酸比。在这项研究中，在基于人群的环境中，较高的PUFA和MUFA摄入量与老年人MCI的可能性降低有关。

BACKGROUND & AIMS: BACKGROUND:A computerized cognitive rehabilitation program can be used to treat patients with mild cognitive impairment or dementia. We developed a new computerized cognitive rehabilitation program (Bettercog) that contained various treatment programs for cognitive training for mild cognitive impairment or dementia. This study was conducted to compare the clinical efficacy of Bettercog and computer-assisted cognitive rehabilitation (COMCOG) that has had clinical efficacy previously proven in patients with mild cognitive impairment or dementia. METHODS:Randomized, single-blind comparison pilot study of 20 elderly patients with cognitive decline-eight men and 12 women-with an average age of 74.3 years. Bettercog trains not only memory and attention but also orientation, calculation, executive function, language, comprehension, and spatiotemporal abilities. To retain subjects' interest, pictures, animations, and game elements were introduced. The subjects were divided into COMCOG and Bettercog groups by random assignment and underwent 12 sessions of a computerized cognitive rehabilitation program for three weeks. In a separate space, an independent clinical psychologist conducted the Seoul Neuropsychological Screening Battery 2nd edition (SNSB-II), Korean Mini-Mental State Examination (K-MMSE), Clinical Dementia Rating (CDR), and the Korean version of the Modified Barthel Index (K-MBI) before and after treatment. RESULTS:There was no significant difference between the two groups in baseline age, sex, illiteracy, years of education, and scores on the K-MMSE, CDR, SNSB-II, and K-MBI. In the posttreatment cognitive assessment, the K-MMSE scores of patients treated with Bettercog improved from 19.2 ± 3.9 to 21.3 ± 4.0 (P = .005). In the memory domain of the SNSB-II, the percentile score improved from 15.3 ± 24.5 to 24.2 ± 30.7 (P = .026). However, there was no statistically significant difference in the final K-MMSE, CDR, and SNSB-II scores between the two treatment groups. In both groups, K-MBI scores improved statistically significantly after treatment. CONCLUSIONS:Through this preliminary study, we verified that the newly developed computerized cognitive rehabilitation program is effective in improving cognitive function. However, 12 sessions are not enough to administer a variety of cognitive rehabilitation content to patients. It is, therefore, necessary to conduct a large-scale study using a computerized cognitive rehabilitation program that has various cognitive content.

背景与目标：

BACKGROUND & AIMS: BACKGROUND:A large proportion of patients with amnestic mild cognitive impairment (MCI) progress to Alzheimer's disease (AD), but the rate of conversion is highly variable, depending on selection and inclusion criteria. In the present prospective study, amnestic MCI criteria were applied in order to enrich the study population with prodromal AD patients. METHODS:A composite CERAD word list learning z-score of -1 was applied as a cut-off for memory performance at baseline. Competing causes of memory impairment other than prodromal AD were actively excluded. A cohort of 88 amnestic MCI patients was included; 75 were available for follow-up. RESULTS:After a mean delay of 19 months, 44% were found to have converted to AD, corresponding to an annualized conversion rate of 28%. The rate of new diagnoses other than stable MCI or AD was 6%. Baseline neuropsychological variables were not instrumental to predict progression. CONCLUSION:Amnestic MCI patients, as identified by the present set of criteria, carry a high risk of median-term progression to AD.

背景与目标：

BACKGROUND & AIMS: PURPOSE:This paper examines and reviews studies on the efficacy of computer-based cognitive intervention programmes in the elderly affected by Mild Cognitive Impairment (MCI). MCI patients are at higher risk to progress to dementia. Recent effort has been made to slow the cognitive decline and delay the onset of dementia in this population. METHOD:MEDLINE sources were searched with the following subject headings: computer-based cognitive intervention, cognitive stimulation, cognitive training, aging, elderly, cognitive impairment. Selected studies were quality assessed and data extracted by two reviewers. RESULTS:Several studies reported encouraging results on cognitive interventions programmes as a means to improve cognitive abilities and emotional states and to decrease subjective memory complaints in MCI patients. CONCLUSION:Though both traditional and computer-based cognitive intervention programmes seem to be effective, the computer-based ones present more advantages: 1) they could individualize the programme tailored to the patient's neuropsychological pattern and needs. 2) they permit the user to make an immediate objective comparison with data collected earlier and thus help in setting up a systematic training plan by providing instant value-free feedback. 3) they offer a possibility of a widescale dissemination.

背景与目标：

BACKGROUND & AIMS: :Conventional Functional connectivity (FC) analysis focuses on characterizing the correlation between two brain regions, whereas the high-order FC can model the correlation between two brain region pairs. To reduce the number of brain region pairs, clustering is applied to group all the brain region pairs into a small number of clusters. Then, a high-order FC network can be constructed based on the clustering result. By varying the number of clusters, multiple high-order FC networks can be generated and the one with the best overall performance can be finally selected. However, the important information contained in other networks may be simply discarded. To address this issue, in this paper, we propose to make full use of the information contained in all high-order FC networks. First, an agglomerative hierarchical clustering technique is applied such that the clustering result in one layer always depends on the previous layer, thus making the high-order FC networks in the two consecutive layers highly correlated. As a result, the features extracted from high-order FC network in each layer can be decomposed into two parts (blocks), i.e., one is redundant while the other might be informative or complementary, with respect to its previous layer. Then, a selective feature fusion method, which combines sequential forward selection and sparse regression, is developed to select a feature set from those informative feature blocks for classification. Experimental results confirm that our novel method outperforms the best single high-order FC network in diagnosis of mild cognitive impairment (MCI) subjects.

背景与目标： : 传统的功能连通性 (FC) 分析侧重于表征两个大脑区域之间的相关性，而高阶FC可以对两个大脑区域对之间的相关性进行建模。为了减少大脑区域对的数量，应用聚类将所有大脑区域对分组为少量聚类。然后，可以根据聚类结果构造高阶FC网络。通过改变群集的数量，可以生成多个高阶FC网络，并最终选择具有最佳整体性能的网络。但是，其他网络中包含的重要信息可能会被简单地丢弃。为了解决这个问题，在本文中，我们建议充分利用所有高阶FC网络中包含的信息。首先，应用了一种聚集的层次聚类技术，使得一层中的聚类结果始终依赖于前一层，从而使两个连续层中的高阶FC网络高度相关。结果，从每一层中的高阶FC网络中提取的特征可以分解为两个部分 (块)，即，相对于其先前的层，一个是冗余的，而另一个可能是信息性的或互补的。然后，开发了一种选择性特征融合方法，该方法结合了顺序前向选择和稀疏回归，以从那些信息性特征块中选择特征集进行分类。实验结果证实，我们的新方法在诊断轻度认知障碍 (MCI) 受试者方面优于最佳的单个高阶FC网络。

BACKGROUND & AIMS: BACKGROUND:To use valid subjective reports sensible to cognitive decline is vital to identify very early signs of dementia development. Use of everyday technology (ET) has been shown to be sensitive to differentiate adults with mild cognitive impairment (MCI) from controls, but the group with subjective cognitive impairment (SCI) has not yet been examined. This study aims to investigate and compare self-perceived ability in ET use and number of ETs reported as actually used in a sample of older adults with SCI, MCI, and older adults with no known cognitive impairment, i.e. CONTROLS: METHODS:Older adults with MCI (n = 29), SCI ( n = 26), and controls (n = 30) were interviewed with the short version of the Everyday Technology Use Questionnaire (S-ETUQ) to capture self-perceived ability in ET use and number of ETs used. To generate individual measures of ability to use ET, Rasch analysis was used. The measures were then compared group-wise using ANCOVA. The numbers of ETs used were compared group-wise with ANOVA. RESULTS:Controls versus SCI and MCI differed significantly regarding ETs reported as used, but not SCI versus MCI. Similarly, in ability to use ET, controls versus SCI and MCI differed significantly but not SCI versus MCI. CONCLUSIONS:The significantly lower numbers of ETs reported as actually used and the lower ability in SCI and MCI groups compared to controls suggest that ET use is affected already in very minor cognitive decline. This indicates that self-reported ET use based on the S-ETUQ is sensitive to detect changes already in SCI.

背景与目标：

BACKGROUND & AIMS: OBJECTIVE:To analyze outcomes of patients with compressive nontoxic multinodular goiter after 131I-iodine 30 mCi treatment without previous use of recombinant human thyroid-stimulating hormone or methimazole. METHODS:We evaluated fixed-dose radioiodine therapy outcomes in patients with nontoxic multinodular goiter who did not accept thyroidectomy as a therapeutic option. Laboratory thyroid function and thyroid volume estimated by ultrasound were assessed before and one year after radioiodine therapy. RESULTS:Twenty euthyroid female patients received 30 mCi of 131I-iodine without recombinant human thyroid-stimulating hormone or methimazole pretreatment. Median thyroid volume and Tc-99m sodium pertechnetate thyroid uptake before radioiodine therapy were 68.05 cm (31.3-295.3) and 0.5% (0.1%-1.2%), respectively. One year after radioiodine therapy, thyroid volume decreased to 55.4 cm (19.8-149.9), and merely 4 patients (20%) developed hypothyroidism. Thyroid volume decreased significantly after radioiodine therapy, presenting a variation of -21.1 cm (-161.3 to -0.8) and -30.61% (-73.88 to -1.02), both with P < 0.0001. Thyroid volume variation was positively correlated with thyroid uptake in Spearman's correlation (r = 0.4730; P = 0.0352). The group satisfied with radioiodine therapy (85%, n = 17) showed a significant reduction in thyroid volume, -25.8 cm (-161.3 to -6.2) and -36.74% (-73.88 to -9.95). The dissatisfied group (15%, n = 3) showed -1.0 cm (-2.0 to -0.8) and -1.67% (-3.38 to -1.02) in thyroid volume, P = 0.0081. Patients that complained about dysphagia presented a lower percentage of thyroid volume decrease after radioiodine therapy, -21.97% (-70.12 to -1.02, P = 0.0430). CONCLUSIONS:A substantial reduction in thyroid volume associated with a low incidence of hypothyroidism and a high satisfaction rate support the use of conventional radioiodine therapy with a fixed dose of 30 mCi. This therapy is an attractive and cheaper therapeutic alternative in selected patients with nontoxic multinodular goiter.

背景与目标：

BACKGROUND & AIMS: :Although both human epidemiologic and animal model studies have suggested that caffeine/coffee protects against Alzheimer's disease, direct human evidence for this premise has been lacking. In the present case-control study, two separate cohorts consisting of 124 total individuals (65-88 years old) were cognitively assessed and a blood sample taken for caffeine/biomarker analysis. Subjects were then monitored for cognitive status over the ensuing 2-4 year period to determine the extent to which initial plasma caffeine/biomarkers levels would be predictive of changes in cognitive status. Plasma caffeine levels at study onset were substantially lower (-51%) in mild cognitive impairment (MCI) subjects who later progressed to dementia (MCI→DEM) compared to levels in stable MCI subjects (MCI→MCI). Moreover, none of the MCI→DEM subjects had initial blood caffeine levels that were above a critical level of 1200 ng/ml, while half of stable MCI→MCI subjects had blood caffeine levels higher than that critical level. Thus, plasma caffeine levels greater than 1200 ng/ml (≈6 μM) in MCI subjects were associated with no conversion to dementia during the ensuing 2-4 year follow-up period. Among the 11 cytokines measured in plasma, three of them (GCSF, IL-10, and IL-6) were decreased in MCI→DEM subjects, but not in stable MCI→MCI subjects with high plasma caffeine levels. Coffee would appear to be the major or perhaps only source of caffeine for such stable MCI patients. This case-control study provides the first direct evidence that caffeine/coffee intake is associated with a reduced risk of dementia or delayed onset, particularly for those who already have MCI.

背景与目标： : 尽管人类流行病学和动物模型研究都表明咖啡因/咖啡可以预防阿尔茨海默氏病，但缺乏直接的人类证据。在本病例对照研究中，认知评估了由124个总个体 (65-88岁) 组成的两个独立队列，并采集了血液样本进行咖啡因/生物标志物分析。然后在随后的2-4年中监测受试者的认知状态，以确定初始血浆咖啡因/生物标志物水平对认知状态变化的预测程度。与稳定的MCI受试者 (MCI → MCI) 的水平相比，后来发展为痴呆 (MCI → dem) 的轻度认知障碍 (MCI) 受试者在研究开始时的血浆咖啡因水平明显较低 (-51%)。此外，没有一个mci → dem受试者的初始血液咖啡因水平高于1200 ng/ml的临界水平，而一半稳定的mci → mci受试者的血液咖啡因水平高于该临界水平。因此，在随后的2-4年随访期间，MCI受试者的血浆咖啡因水平大于1200 ng/ml (≈ 6μm) 与未转化为痴呆相关。在血浆中测量的11种细胞因子中，mci → dem受试者中的三种 (GCSF，IL-10和IL-6) 降低，但在血浆咖啡因水平较高的稳定mci → mci受试者中却没有降低。对于这种稳定的MCI患者，咖啡似乎是咖啡因的主要或唯一来源。这项病例对照研究提供了第一个直接证据，表明咖啡因/咖啡的摄入与痴呆症或延迟发作的风险降低有关，特别是对于那些已经患有MCI的人。

BACKGROUND & AIMS: INTRODUCTION:Shared-housing arrangements (SHAs) are small, home-like care environments in Germany. Residents are predominantly people with dementia. The risk for all-cause hospitalisation is consistently higher for people with dementia compared with people without dementia and there is currently no evidence-based intervention to reduce the risk of hospitalisation. Thus, the DemWG study investigates whether a complex intervention is effective in reducing hospitalisation (primary outcome), behavioural and psychological symptoms of dementia and falls and for stabilising cognitive functioning and quality of life in people with dementia and mild cognitive impairment (MCI) in German SHAs. METHODS AND ANALYSIS:Based on the UK Medical Research Council framework 'Developing and evaluating complex interventions', a prospective, mixed-methods, multicentre, cluster-randomised controlled trial combining primary and secondary data analyses as well as quantitative and qualitative research methods is being conducted. The intervention consists of three parts: (A) education of nursing staff in SHAs; (B) awareness raising and continuing medical education (CME) of general practitioners; (C) multicomponent non-pharmacological group intervention MAKS-mk+ ('m'=motor training; 'k'=cognitive training; '+'=fall prevention) for people with dementia and MCI. Randomisation is stratified by the German federal states and type of setting (rural vs urban). Neither the trained professionals nor the participants are blinded. Data are collected at baseline and after 6, 12 and 18 months with standardised instruments. Quantitative data will be analysed by multivariate analyses according to the general linear model, qualitative data using qualitative content analysis. Recruitment is still ongoing until 31 December 2020. ETHICS AND DISSEMINATION:All procedures were approved by the Ethics Committee of the University of Bremen (Ref. 2019-18-06-3). Informed consent will be obtained before enrolment of participants. Due to findings of previous randomised controlled trials, serious adverse events are not expected. Results will be disseminated in peer-reviewed journal publications and conference presentations. TRIAL REGISTRATION NUMBER:ISRCTN89825211.

背景与目标：

BACKGROUND & AIMS: :This study aimed to validate the TICS and modified TICS (TICSm) in Korean elderly population and to compare MCI and dementia screening ability between TICS and TICSm. TICS and TICSm were administered to 70 cognitively normal (CN), 75 MCI, and 85 dementia subjects, with mini-mental state examination (MMSE) and other cognitive and functional measures. TICS and TICSm scores were highly correlated with other global cognitive and functional scores. The CN vs. dementia discrimination ability of both instruments was as excellent as that of MMSE (sensitivity/specificity at optimal cutoff: 87.1/90.1 for TICS; 88.2/90.0 for TICSm). Although their CN vs. MCI discrimination performances were comparable to that of MMSE, they were far from perfect (sensitivity/specificity: 69.3/68.6 for TICS; 73.3/67.1 for TICSm). There was no significant difference in dementia or MCI screening accuracy between TICS and TICSm. Both of them also showed high test-retest reliability. Our findings indicate that TICS and TICSm are reliable and as valid as MMSE in regard of screening cognitively impaired elderly. In terms of the comparison between TICSm and TICS, however, TICSm has little advantage over TICS for screening dementia and even MCI, in spite of longer administration time and more efforts required.

背景与目标： : 本研究旨在验证韩国老年人群的TICS和改良TICS (TICSm)，并比较TICS和TICSm之间的MCI和痴呆症筛查能力。对70名认知正常 (CN)，75名MCI和85名痴呆症受试者进行了TICS和TICSm，并进行了迷你精神状态检查 (MMSE) 和其他认知和功能测量。TICS和TICSm评分与其他全球认知和功能评分高度相关。两种仪器的CN与痴呆鉴别能力与MMSE一样出色 (最佳临界点的敏感性/特异性: TICS的87.1/90.1; TICSm的88.2/90.0)。尽管它们的CN与MCI区分性能与MMSE相当，但它们远非完美 (敏感性/特异性: TICS的69.3/68.6; TICSm的73.3/67.1)。TICS和TICSm在痴呆或MCI筛查准确性方面没有显着差异。两者也都显示出很高的重测可靠性。我们的发现表明，在筛查认知受损的老年人方面，TICS和TICSm是可靠的，并且与MMSE一样有效。然而，就TICSm和TICS之间的比较而言，TICSm在筛查痴呆症甚至MCI方面比TICS没有什么优势，尽管给药时间更长，需要更多的努力。

BACKGROUND & AIMS: :Data support the evidence that neuropsychological rehabilitation is effective in Alzheimer disease (AD), to strengthen the pharmacological treatment to delay the progression of dementia. At moment, a few studies have examined the efficacy of non-pharmacological treatment in MCI. This is a controlled study that assesses the effectiveness of neuropsychological rehabilitation on cognitive and behavioral symptoms and functional status in a group of community-dwelling subjects with MCI and MD. Our results demonstrate that a systematic rehabilitation, that provides a computerized cognitive program training, produces an improvement in cognitive and affective status of patients with MCI and MD, while a rehabilitation program not providing a punctual stimulation of cognitive functions, does not have significant effects.

背景与目标： : 数据支持神经心理康复对阿尔茨海默病 (AD) 有效的证据，以加强药物治疗以延缓痴呆症的进展。目前，一些研究已经检查了MCI中非药物治疗的功效。这是一项对照研究，旨在评估一组患有MCI和MD的社区居民中神经心理康复对认知和行为症状以及功能状态的有效性。我们的结果表明，提供计算机化认知程序训练的系统康复可以改善MCI和MD患者的认知和情感状态，而康复程序不提供准时的认知功能刺激，则没有显着效果。

BACKGROUND & AIMS: BACKGROUND:The timed up and go (TUG) is a test used to assess mobility in older adults and patients with neurological conditions. This study aims to compare brain gray matter (GM) correlates and structural covariance networks associated with the TUG time in cognitively healthy individuals (CHI) and in patients with mild cognitive impairment (MCI). METHODS:The TUG time was measured in 326 non-demented older community-dwellers (age 71.3 ± 4.5; 42% female) - 156 CHI and 170 MCI. GM covariance networks were computed using voxel-based morphometry with the main neural correlates of TUG for each group as seed regions. RESULTS:Increased TUG time (i.e., poor performance) was associated with distinct brain volume reductions between CHI and MCI. The covariance analysis showed cortical regions involving the default mode network in CHI and bilateral cerebellar regions in MCI. CONCLUSIONS:GM networks associated with the TUG vary between CHI and MCI, suggesting distinct brain control for locomotion between CHI and MCI patients.

背景与目标：

BACKGROUND & AIMS: OBJECTIVES:To use a Machine Learning (ML) approach to compare Neuropsychiatric Symptoms (NPS) in participants of a longitudinal study who developed dementia and those who did not. DESIGN:Mann-Whitney U and ML analysis. Nine ML algorithms were evaluated using a 10-fold stratified validation procedure. Performance metrics (accuracy, recall, F-1 score, and Cohen's kappa) were computed for each algorithm, and graphic metrics (ROC and precision-recall curves) and features analysis were computed for the best-performing algorithm. SETTING:Primary care health centers. PARTICIPANTS:128 participants: 78 cognitively unimpaired and 50 with MCI. MEASUREMENTS:Diagnosis at baseline, months from the baseline assessment until the 3rd follow-up or development of dementia, gender, age, Charlson Comorbidity Index, Neuropsychiatric Inventory-Questionnaire (NPI-Q) individual items, NPI-Q total severity, and total stress score and Geriatric Depression Scale-15 items (GDS-15) total score. RESULTS:30 participants developed dementia, while 98 did not. Most of the participants who developed dementia were diagnosed at baseline with amnestic multidomain MCI. The Random Forest Plot model provided the metrics that best predicted conversion to dementia (e.g. accuracy=.88, F1=.67, and Cohen's kappa=.63). The algorithm indicated the importance of the metrics, in the following (decreasing) order: months from first assessment, age, the diagnostic group at baseline, total NPI-Q severity score, total NPI-Q stress score, and GDS-15 total score. CONCLUSIONS:ML is a valuable technique for detecting the risk of conversion to dementia in MCI patients. Some NPS proxies, including NPI-Q total severity score, NPI-Q total stress score, and GDS-15 total score, were deemed as the most important variables for predicting conversion, adding further support to the hypothesis that some NPS are associated with a higher risk of dementia in MCI.

背景与目标：

BACKGROUND & AIMS: OBJECTIVE:Although visual memory has been shown to be impaired in amnestic mild cognitive impairment (aMCI), the differences between MCI subtypes are not well defined. The current study attempted to investigate visual memory profiles in different MCI subtypes. METHODS:One hundred and seventy volunteers aged older than 50 years performed several visual memory tests included in the CANTAB battery. Participants were classified into four groups: (1) multiple domain aMCI (mda-MCI) (32 subjects); (2) single domain aMCI (sda-MCI)(57 subjects); (3) multiple domain non amnestic MCI (mdna-MCI) (32 subjects); and (4) controls (54 healthy individuals without cognitive impairment). Parametric and non parametric analyses were performed to compare the groups and to obtain their corresponding memory profiles. RESULTS:The mda-MCI group exhibited impairments in both dimensions of episodic memory (recognition and recollection/recall), and also in learning and working memory, whereas the sda-MCI only showed impairment in recollection-delayed recall and learning. The mdna-MCI group displayed impairment in working memory but good preservation of learning and episodic memory. CONCLUSION:The CANTAB visual memory profiles may contribute to better cognitive characterization of patients with different MCI subtypes, allowing comparison across several processes involved in visual memory such as attention, recognition, recollection and working memory.

背景与目标：