Improving Alzheimer`s Disease Diagnosis with Machine Learning Techniques

There is not a specific test to diagnose Alzheimer`s disease (AD). Its diagnosis should be based upon clinical history, neuropsychological and laboratory tests, neuroimaging and electroencephalography (EEG). Therefore, new approaches are necessary to enable earlier and more accurate diagnosis and to follow treatment results. In this study we used a Machine Learning (ML) technique, named Support Vector Machine (SVM), to search patterns in EEG epochs to differentiate AD patients from controls. As a result, we developed a quantitative EEG (qEEG) processing method for automatic differentiation of patients with AD from normal individuals, as a complement to the diagnosis of probable dementia. We studied EEGs from 19 normal subjects (14 females/5 males, mean age 71.6 years) and 16 probable mild to moderate symptoms AD patients (14 females/2 males, mean age 73.4 years. The results obtained from analysis of EEG epochs were accuracy 79.9% and sensitivity 83.2%. The analysis considering the diagnosis of each individual patient reached 87.0% accuracy and 91.7% sensitivity.

Response programming in dementia of the Alzheimer type: A kinematic analysis

Although planning is important for the functioning of patients with dementia of the Alzheimer Type (DAT), little is known about response programming in DAT. This study used a cueing paradigm coupled with quantitative kinematic analysis to document the preparation and execution of movements made by a group of 12 DAT patients and their age and sex matched controls. Participants connected a series of targets placed upon a WACOM SD420 graphics tablet, in response to the pattern of illumination of a set of light emitting diodes (LEDs). In one condition, participants could programme the upcoming movement, whilst in another they were forced to reprogramme this movement on-line (i.e. they were not provided with advance information about the location of the upcoming target). DAT patients were found to have programming deficits, taking longer to initiate movements; particularly in the absence of cues. While problems spontaneously programming a movement might cause a greater reliance upon on-line guidance, when both groups were required to guide the movement on-line, DAT patients continued to show slower and less efficient movements implying declining sensori-motor function; these differences were not simply due to strategy or medication status. (C) 1997 Elsevier Science Ltd.

Use of SVM Methods with Surface-Based Cortical and Volumetric Subcortical Measurements to Detect Alzheimer`s Disease

Here, we examine morphological changes in cortical thickness of patients with Alzheimer`s disease (AD) using image analysis algorithms for brain structure segmentation and study automatic classification of AD patients using cortical and volumetric data. Cortical thickness of AD patients (n = 14) was measured using MRI cortical surface-based analysis and compared with healthy subjects (n = 20). Data was analyzed using an automated algorithm for tissue segmentation and classification. A Support Vector Machine (SVM) was applied over the volumetric measurements of subcortical and cortical structures to separate AD patients from controls. The group analysis showed cortical thickness reduction in the superior temporal lobe, parahippocampal gyrus, and enthorhinal cortex in both hemispheres. We also found cortical thinning in the isthmus of cingulate gyrus and middle temporal gyrus at the right hemisphere, as well as a reduction of the cortical mantle in areas previously shown to be associated with AD. We also confirmed that automatic classification algorithms (SVM) could be helpful to distinguish AD patients from healthy controls. Moreover, the same areas implicated in the pathogenesis of AD were the main parameters driving the classification algorithm. While the patient sample used in this study was relatively small, we expect that using a database of regional volumes derived from MRI scans of a large number of subjects will increase the SVM power of AD patient identification.

Validation of ASHA FACS-Functional Assessment of Communication Skills for Alzheimer Disease Population

This study vas aimed to validate the American Speech-Language-Hearing Association Functional Assessment Of Communication Skills (ASHA FACS) for a Brazilian population. The scale was translated and adapted into Portuguese. Thirty-two patients with mild Alzheimer disease (AD). 25 patients with moderate AD. and 51 elderly without dementia were examined with Mini Mental State Examination, Geriatric Depression Scale. and Alzheimer Disease Assessment Scale-Cognitive subscale (ADAS-cog). The ASHA FACS was answered by their relative/caregiver. The scale`s internal consistency. its inter-examiner and intra-examiner`s reproducibility. and scale`s criterion validity were researched by correlation with ADAS-cog,. The sensitivity and specificity Were also researched. Statistical analyses indicated that the ASHA FACS has excellent internal consistency (Cronbach alpha = 0.955), test-retest reliability (interclass correlation coefficient = 0.995; P < 0.001). and inter-examiners (interclass correlation coefficient = 0.998: P < 0.001). It showed excellent criterion validity when correlated with ADAS-cog,. The ASHA FACS scale showed good sensitivity (75.0%) and specificity (82.4%) values once it is an ecologic and broad evaluation. The ASHA FACS Portuguese version is a valid and reliable instrument to verify communication alterations in AD patients and fills an important gap of efficiency indicators for speech language therapy in our country.

Down-regulation of the amyloid protein precursor of Alzheimer's disease by antisense oligonucleotides reduces neuronal adhesion to specific substrata

The hallmark of Alzheimer's disease is the cerebral deposition of amyloid which is derived from the amyloid precursor protein (APP). The function of APP is unknown but there is increasing evidence for the role of APP in cell-cell and/or cell-matrix interactions. Primary cultures of murine neurons were treated with antisense oligonucleotides to down-regulate APP. This paper presents evidence that APP mediates a substrate-specific interaction between neurons and extracellular matrix components collagen type I, laminin and heparan sulphate proteoglycan but not fibronectin or poly-L-lysine. It remains to be determined whether this effect is the direct result of APP-matrix interactions, or whether an intermediary pathway is involved. (C) 1997 Elsevier Science B.V.

Comparative effects of ageing and dementia of the Alzheimer type on orientation of visual attention

Age-related changes and the effects of dementia of the Alzheimer type (DAT) were investigated during a visual orienting attention task in which attention was pre-cued to one or other hemifields. Central cues were either valid, neutral, invalid or NoGo (inhibitory). The response time cost-benefit analysis showed a decreased benefit after valid cueing in the old compared with the young group with no change in the cost of invalid cueing. The older group were also slower over all cue types. These results suggest there is an age-related reduced ability to covertly orient attention in a visual hemifield before target onset. In contrast, the DAT group showed an increased response time benefit and showed a trend for a decreased cost in response time compared with controls. This was due to slowest response times after neutral cues. They also made significantly more response errors particularly following neutral cueing, and were less able to inhibit responses on NoGo trials than controls. The increased benefit and reduced cost found in the DAT group was interpreted as an impairment in dividing attention between left and right target locations.

Polymorphisms of APOE and LRP genes in Brazilian individuals with Alzheimer disease

Alzheimer disease (AD) is the most frequent cause of dementia in Western countries. Putative genetic risk factors for AD are polymorphisms in the apolipoprotein E (APOE) gene and in the low-density lipoprotein receptor-related protein (LRP) gene. Our objective was to investigate the role of the APOE coding region polymorphisms epsilon 2, epsilon 3, and epsilon 4 and APOE promoter variants A/T at position -491 and G/T at -219, as well as LRP polymorphism C/T, as risk factors for AD in Brazilian individuals. One hundred and twenty patients with probable AD, along with 120 controls were analyzed. A significant difference between patients and controls for 64 alleles was observed: frequency of this allele in AD was 0.31, and 0.10 in controls. Individuals with 2 FA alleles had a higher risk for AD than subjects with only 1 such allele; presence of 1 epsilon 2 allele proved protective. The presence of the T allele of the -219 polymorphism was also associated with an increased risk of AD, but this polymorphism is in linkage disequilibrium with APOE F polymorphisms. No significant differences between patients and controls were observed for -491 APOE or LRP polymorphisms. In this Brazilian population, both the epsilon 4 allele and T -219 polymorphism were associated with an increased risk for AD.

The Alzheimer`s Association external quality control program for cerebrospinal fluid biomarkers

Background: The cerebrospinal fluid (CSF) biomarkers amyloid beta (A beta)-42, total-tau (T-tau), and phosphorylated-tau (P-tau) demonstrate good diagnostic accuracy for Alzheimer`s disease (AD). However, there are large variations in biomarker measurements between studies, and between and within laboratories. The Alzheimer`s Association has initiated a global quality control program to estimate and monitor variability of measurements, quantify batch-to-batch assay variations, and identify sources of variability. In this article, we present the results from the first two rounds of the program. Methods: The program is open for laboratories using commercially available kits for A beta, T-tau, or P-tau. CSF samples (aliquots of pooled CSF) are sent for analysis several times a year from the Clinical Neurochemistry Laboratory at the Molndal campus of the University of Gothenburg, Sweden. Each round consists of three quality control samples. Results: Forty laboratories participated. Twenty-six used INNOTEST enzyme-linked immunosorbent assay kits, 14 used Luminex xMAP with the INNO-BIA AlzBio3 kit (both measure A beta-(1-42), P-tau(181P), and T-tau), and 5 used Mesa Scale Discovery with the A beta triplex (A beta N-42, A beta N-40, and A beta N-38) or T-tau kits. The total coefficients of variation between the laboratories were 13% to 36%. Five laboratories analyzed the samples six times on different occasions. Within-laboratory precisions differed considerably between biomarkers within individual laboratories. Conclusions: Measurements of CSF AD biomarkers show large between-laboratory variability, likely caused by factors related to analytical procedures and the analytical kits. Standardization of laboratory procedures and efforts by kit vendors to increase kit performance might lower variability, and will likely increase the usefulness of CSF AD biomarkers. (C) 2011 The Alzheimer`s Association. All rights reserved.

Higher Serum sTNFR1 Level Predicts Conversion from Mild Cognitive Impairment to Alzheimer`s Disease

The activation of inflammatory cascades has been consistently demonstrated in the pathophysiology of Alzheimer`s disease (AD). Among several putative neuroinflammatory mechanisms, the tumor necrosis factor alpha (TNF-alpha) signaling system has a central role in this process. Recent evidence indicates that the abnormal production of inflammatory factors may accompany the progression from mild cognitive impairment (MCI) to dementia. We aimed to examine serum levels of TNF-alpha and its soluble receptors (sTNFR1 and sTNFR2) in patients with MCI and AD as compared to cognitively unimpaired elderly subjects. We further aimed to investigate whether abnormal levels of these cytokines predict the progression from MCI to AD upon follow-up. We utilized cross-sectional determination of serum levels of TNF-alpha, sTNFR1, and sTNFR2 (ELISA method) in a test group comprising 167 older adults (31 AD, 72 MCI, and 64 healthy controls), and longitudinal reassessment of clinical status after 18.9 +/- 10.0 months. At baseline, there were no statistically significant differences in serum TNF-alpha, sTNFR1, and sTNFR2 between patients with MCI and AD as compared to controls. Nevertheless, patients with MCI who progressed to AD had significantly higher serum sTNFR1 levels as opposed to patients who retained the diagnosis of MCI upon follow-up (p = 0.03). Cox regression analysis showed that high serum sTNFR1 levels predicted the conversion from MCI to AD (p = 0.003), whereas no significant differences were found with respect to serum levels of TNF-alpha and sTNFR2. Abnormal activation of TNF-alpha signaling system, represented by increased expression of sTNFR1, is associated with a higher risk of progression from MCI to AD.

Comparison of language impairment in late-onset depression and Alzheimer`s disease

Objectives: Depression and dementia are highly prevalent in the elderly. Language impairment is an inherent component of Alzheimer`s disease (AD), which can also be encountered in depressed patients. The aim of this study wasto compare the profiles of language abilities in late-onset depression and mild AD groups. Methods: We studied 25 patients with late-onset depression (mean age 73.6 +/- 6.6 years; schooling 9.1 +/- 5.7 years) and 30 patients with mild AD (77.6 +/- 5.4 years; 7.5 +/- 7.1 years) using the Arizona Battery for Communication Disorders of Dementia (ABCD), compared to a group of 30 controls (73.8 +/- 5.8 years; 9.1 +/- 5.4 years). Cut-off scores to discriminate between Controls x Depression and Depression x AD were determined. Results: Depressed patients` scores were similar to AD in confrontation naming, concept definition, following commands, repetition and reading comprehension (sentence). Episodic memory and mental status subtests were useful in differentiating depressed patients from AD, a result that was reproduced when using analysis of covariance to control for the effect of age in the same subtests (p = 0.01 and 0.04, respectively). Conclusion: Language impairment resembling AD was found in the aforementioned language subtests of the ABCD in elderly depressed patients; the mental status and episodic memory subtests were useful to discriminate between AD and depression. The ABCD has proven to be a suitable tool for language evaluation in this population and should aid in the differentiation of AD and pseudodementia (as that of depression).

Increased platelet GSK3B activity in patients with mild cognitive impairment and Alzheimer`s disease

The disruption of glycogen synthase kinase 3-beta (GSK3B) homeostasis has implications in the pathophysiology of neuropsychiatric disorders, namely Alzheimer`s disease (AD). GSK3B activity is increased within the AD brain, favoring the hyperphosphorylation of microtubule-associated protein Tau and the formation of neurofibrillary tangles. Such abnormality has also been detected in leukocytes of patients with cognitive disorders. The aim of the present study was to determine the expression of total and phosphorylated GSK3B at protein level in platelets of older adults with varying degrees of cognitive impairment, and to compare GSK3B activity in patients with AD, mild cognitive impairment (MCI) and healthy controls. Sixty-nine older adults were included (24 patients with mild to moderate AD, 22 patients with amnestic MCI and 23 elderly controls). The expression of platelet GSK3B (total- and Ser-9 phosphorylated GSK3B) was determined by Western blot. GSK3B activity was indirectly assessed by means of the proportion between phospho-GSK3B to total GSK3B (GSK3B ratio), the former representing the inactive form of the enzyme. Ser-9 phosphorylated GSK3B was significantly reduced in patients with MCI and AD as compared to controls (p = 0.04). Platelet GSK3B ratio was significantly decreased in patients with MCI and AD (p = 0.04), and positively correlated with scores on memory tests (r = 0.298, p = 0.01). In conclusion, we corroborate previous evidence of increased GSK activity in peripheral tissues of patients with MCI and AD, and further propose that platelet GSK may be an alternative peripheral biomarker of this abnormality, provided samples are adequately handled in order to preclude platelet activation. (C) 2010 Elsevier Ltd. All rights reserved.

Can the CAMCOG be a good cognitive test for patients with Alzheimer`s disease with low levels of education?

Background: The Cambridge Cognitive Examination (CAMCOG) is a useful test in screening for Alzheimer`s disease (AD). However, the interpretation of CAMCOG cut-off scores is problematic and reference values are needed for different educational strata. Given the importance of earlier diagnoses of mild dementia, new cut-off values are required which take into account patients with low levels of education. This study aims to evaluate whether the CAMCOG can be used as an accurate screening test among AD patients and normal controls with different educational levels. Methods: Cross-sectional assessment was undertaken of 113 AD and 208 elderly controls with heterogeneous educational levels (group 1: 1-4 years; group 2: 5-8 years; and group 3: >= 9 years) from a geriatric clinic. submitted to a thorough diagnostic evaluation for AD including the Cambridge Examination for Mental Disorders of the Elderly (CAMDEX). Controls had no cognitive or mood complaints. Sensitivity (SE) and specificity (SP) for the CAMCOG in each educational group was assessed with receiver-operator-characteristic (ROC) curves. Results: CAMCOG mean values were lower when education was reduced in both diagnostic groups (controls - group 1: 87; group 2: 91; group 3: 96; AD - group 1: 63; group 2: 62; group 3: 77). Cutoff scores for the three education groups were 79, 80 and 90, respectively. SE and SP varied among the groups (group 1: 88.1% and 83.5%; group 2: 84.6% and 96%; group 3: 70.8% and 90%). Conclusion: The CAMCOG can be used as a cognitive test for patients with low educational level with good accuracy. Patients with higher education showed lower scores than previously reported.

Screening for Alzheimer`s Disease Among Illiterate Elderly: Accuracy Analysis for Multiple Instruments

One of the challenges in screening for dementia in developing countries is related to performance differences due to educational and cultural factors. This study evaluated the accuracy of single screening tests as well as combined protocols including the Mini-Mental State Examination (MMSE), Verbal Fluency animal category (VF), Clock Drawing test (CDT), and Pfeffer Functional Activities Questionnaire (PFAQ) to discriminate illiterate elderly with and without Alzheimer`s disease (AD) in a clinical sample. Cross-sectional study with 66 illiterate outpatients diagnosed with mild and moderate AD and 40 illiterate normal controls. Diagnosis of AD was based on NINCDS-ADRDA. All patients were submitted to a diagnostic protocol including a clinical interview based on the CAMDEX sections. ROC curves area analyses were carried out to compare sensitivity and specificity for the cognitive tests to differentiate the two groups (each test separately and in two by two combinations). Scores for all cognitive (MMSE, CDT, VF) and functional assessments (PFAQ) were significantly different between the two groups (p < 0.001). The best screening instruments for this sample of illiterate elderly were the MMSE and the PFAQ. The cut-off scores for the MMSE, VF, CDT, and PFAQ were 17.5, 7.5, 2.5, and 11.5, respectively. The most sensitive combination came from the MMSE and PFAQ (94.1%), and the best specificity was observed with the combination of the MMSE and CDT (89%). Illiterate patients can be successfully screened for AD using well-known screening instruments, especially in combined protocols.

The Cholinergic System in Mild Cognitive Impairment and Alzheimer`s Disease: An In Vivo MRI and DTI study

Few studies have investigated in vivo changes of the cholinergic basal forebrain in Alzheimer`s disease (AD) and amnestic mild cognitive impairment (MCI), an at risk stage of AD. Even less is known about alterations of cortical projecting fiber tracts associated with basal forebrain atrophy. In this study, we determined regional atrophy within the basal forebrain in 21 patients with AD and 16 subjects with MCI compared to 20 healthy elderly subjects using deformation-based morphometry of MRI scans. We assessed effects of basal forebrain atrophy on fiber tracts derived from high-resolution diffusion tensor imaging (DTI) using tract-based spatial statistics. We localized significant effects relative to a map of cholinergic nuclei in MRI standard space as determined from a postmortem brain. Patients with AD and MCI subjects showed reduced volumes in basal forebrain areas corresponding to anterior medial and lateral, intermediate and posterior nuclei of the Nucleus basalis of Meynert (NbM) as well as in the diagonal band of Broca nuclei (P < 0.01). Effects in MCI subjects were spatially more restricted than in AD, but occurred at similar locations. The volume of the right antero-lateral NbM nucleus was correlated with intracortical projecting fiber tract integrity such as the corpus callosum, cingulate, and the superior longitudinal, inferior longitudinal, inferior fronto-occipital, and uncinate fasciculus (P < 0.05, corrected for multiple comparisons). Our findings suggest that a multimodal MRI-DTI approach is supportive to determine atrophy of cholinergic nuclei and its effect on intracortical projecting fiber tracts in AD. Hum Brain Mapp 32: 1349-1362, 2011. (C) 2010 Wiley-Liss, Inc.

Functional Disability in Alzheimer Disease A Validation Study of the Brazilian Version of the Disability Assessment for Dementia (DAD-Br)

Background: The assessment of activities of daily living (ADL) is important both for the diagnosis and staging of dementia. The objective of this study was to verify the applicability and validity of the Brazilian version of the Disability Assessment for Dementia (DAD-Br). Methods: The DAD was applied to caregivers of 89 patients with probable Alzheimer disease (AD) and to 40 elderly individuals without cognitive impairment (controls). We assessed the construct validity of the scale and its diagnostic accuracy (sensitivity, specificity, and predictive value). In addition, intergroup and intragroup analyses were conducted to characterize patient performance on basic and instrumental ADL and to determine underlying deficits (initiation, planning, or effective execution). Results: AD patients and controls had mean ages of 76.4 +/- 6.9 years and 74.5 +/- 7.3 years (P = 0.08), respectively. Mean Mini-Mental State Examination scores were 17.4 +/- 5.0 and 26.1 +/- 5.1 (P < 0.001) and scores on the DAD were 68.4 +/- 19.0 and 99.8 +/- 0.9 (P < 0.001), for patients and controls, respectively. The DAD scale showed good internal consistency (Cronbach alpha = 0.77) and correlation with the Mini-Mental State Examination (r = 0.44; P < 0.001). The AD group did better on basic ADL than on instrumental ADL (P < 0.001). As expected, controls did not exhibit significant deficits on the items evaluated. Conclusion: The Brazilian version of the DAD is an adequate and reliable tool for assessing functional ability in AD patients.