Alzheimer disease diagnosis based on automatic spontaneous speech analysis

Alzheimer’s disease (AD) is the most prevalent form of progressive degenerative dementia and it has a high socio-economic impact in Western countries, therefore is one of the most active research areas today. Its diagnosis is sometimes made by excluding other dementias, and definitive confirmation must be done trough a post-mortem study of the brain tissue of the patient. The purpose of this paper is to contribute to im-provement of early diagnosis of AD and its degree of severity, from an automatic analysis performed by non-invasive intelligent methods. The methods selected in this case are Automatic Spontaneous Speech Analysis (ASSA) and Emotional Temperature (ET), that have the great advantage of being non invasive, low cost and without any side effects.

ICA Cleaning procedure for EEG signals analysis: application to Alzheimer's disease detection

To develop systems in order to detect Alzheimer’s disease we want to use EEG signals. Available database is raw, so the first step must be to clean signals properly. We propose a new way of ICA cleaning on a database recorded from patients with Alzheimer's disease (mildAD, early stage). Two researchers visually inspected all the signals (EEG channels), and each recording's least corrupted (artefact-clean) continuous 20 sec interval were chosen for the analysis. Each trial was then decomposed using ICA. Sources were ordered using a kurtosis measure, and the researchers cleared up to seven sources per trial corresponding to artefacts (eye movements, EMG corruption, EKG, etc), using three criteria: (i) Isolated source on the scalp (only a few electrodes contribute to the source), (ii) Abnormal wave shape (drifts, eye blinks, sharp waves, etc.), (iii) Source of abnormally high amplitude ( �100 �V). We then evaluated the outcome of this cleaning by means of the classification of patients using multilayer perceptron neural networks. Results are very satisfactory and performance is increased from 50.9% to 73.1% correctly classified data using ICA cleaning procedure.

Alzheimer Disease Diagnosis based on Automatic Spontaneous Speech Analysis

Alzheimer’s disease (AD) is the most prevalent form of progressive degenerative dementia and it has a high socio-economic impact in Western countries, therefore is one of the most active research areas today. Its diagnosis is sometimes made by excluding other dementias, and definitive confirmation must be done trough a post-mortem study of the brain tissue of the patient. The purpose of this paper is to contribute to improvement of early diagnosis of AD and its degree of severity, from an automatic analysis performed by non-invasive intelligent methods. The methods selected in this case are Automatic Spontaneous Speech Analysis (ASSA) and Emotional Temperature (ET), that have the great advantage of being non invasive, low cost and without any side effects.

A hybrid feature selection approach for the early diagnosis of Alzheimer's disease

Objective. Recently, significant advances have been made in the early diagnosis of Alzheimer’s disease from EEG. However, choosing suitable measures is a challenging task. Among other measures, frequency Relative Power and loss of complexity have been used with promising results. In the present study we investigate the early diagnosis of AD using synchrony measures and frequency Relative Power on EEG signals, examining the changes found in different frequency ranges. Approach. We first explore the use of a single feature for computing the classification rate, looking for the best frequency range. Then, we present a multiple feature classification system that outperforms all previous results using a feature selection strategy. These two approaches are tested in two different databases, one containing MCI and healthy subjects (patients age: 71.9 ± 10.2, healthy subjects age: 71.7 ± 8.3), and the other containing Mild AD and healthy subjects (patients age: 77.6 ± 10.0; healthy subjects age: 69.4± 11.5). Main Results. Using a single feature to compute classification rates we achieve a performance of 78.33% for the MCI data set and of 97.56 % for Mild AD. Results are clearly improved using the multiple feature classification, where a classification rate of 95% is found for the MCI data set using 11 features, and 100% for the Mild AD data set using 4 features. Significance. The new features selection method described in this work may be a reliable tool that could help to design a realistic system that does not require prior knowledge of a patient's status. With that aim, we explore the standardization of features for MCI and Mild AD data sets with promising results.

Early Detection of Alzheimer's Disease Beta-amyloid Pathology -Applicability of Positron Emission Tomography with the Amyloid Radioligand 11C-PIB

Early Detection of Alzheimer's Disease Beta-amyloid Pathology -Applicability of Positron Emission Tomography with the Amyloid Radioligand ¹¹C-PIB Accumulation of beta amyloid (Abeta) in the brain is characteristic for Alzheimer’s disease (AD). Carbon-11 labeled 2-(4’-methylaminophenyl)-6-hydroxybenzothiazole (¹¹C-PIB) is a novel positron emission tomography (PET) amyloid imaging agent that appears to be applicable for in vivo Abeta plaque detection and quantitation. The biodistribution and radiation dosimetry of ¹¹C-PIB were investigated in 16 healthy subjects. The reproducibility of a simplified ¹¹C-PIB quantitation method was evaluated with a test-retest study on 6 AD patients and 4 healthy control subjects. Brain ¹¹C-PIB uptake and its possible association with brain atrophy rates were studied over a two-year follow-up in 14 AD patients and 13 healthy controls. Nine monozygotic and 8 dizygotic twin pairs discordant for cognitive impairment and 9 unrelated controls were examined to determine whether brain Abeta accumulation could be detected with ¹¹C-PIB PET in cognitively intact persons who are at increased genetic risk for AD. The highest absorbed radiation dose was received by the gallbladder wall (41.5 mjuGy/MBq). About 20 % of the injected radioactivity was excreted into urine, and the effective whole-body radiation dose was 4.7 mjuSv/MBq. Such a dose allows repeated scans of individual subjects. The reproducibility of the simplified ¹¹C-PIB quantitation was good or excellent both at the regional level (VAR 0.9-5.5 %) and at the voxel level (VAR 4.2-6.4 %). ¹¹C-PIB uptake did not increase during 24 months’ follow-up of subjects with mild or moderate AD, even though brain atrophy and cognitive decline progressed. Baseline neocortical ¹¹C-PIB uptake predicted subsequent volumetric brain changes in healthy control subjects (r = 0.725, p = 0.005). Cognitively intact monozygotic co-twins – but not dizygotic co-twins – of memory-impaired subjects exhibited increased ¹¹C-PIB uptake (117-121 % of control mean) in their temporal and parietal cortices and the posterior cingulate (p<0.05), when compared with unrelated controls. This increased uptake may be representative of an early AD process, and genetic factors seem to play an important role in the development of AD-like Abeta plaque pathology. ¹¹C-PIB PET may be a useful method for patient selection and follow-up for early-phase intervention trials of novel therapeutic agents. AD might be detectable in high-risk individuals in its presymptomatic stage with ¹¹C-PIB PET, which would have important consequences both for future diagnostics and for research on disease-modifying treatments.

Verbal learning in mild cognitive impairment and alzheimer's disease : behavioural and neural approaches

The main focus of the present thesis was at verbal episodic memory processes that are particularly vulnerable to preclinical and clinical Alzheimer’s disease (AD). Here these processes were studied by a word learning paradigm, cutting across the domains of memory and language learning studies. Moreover, the differentiation between normal aging, mild cognitive impairment (MCI) and AD was studied by the cognitive screening test CERAD. In study I, the aim was to examine how patients with amnestic MCI differ from healthy controls in the different CERAD subtests. Also, the sensitivity and specificity of the CERAD screening test to MCI and AD was examined, as previous studies on the sensitivity and specificity of the CERAD have not included MCI patients. The results indicated that MCI is characterized by an encoding deficit, as shown by the overall worse performance on the CERAD Wordlist learning test compared with controls. As a screening test, CERAD was not very sensitive to MCI. In study II, verbal learning and forgetting in amnestic MCI, AD and healthy elderly controls was investigated with an experimental word learning paradigm, where names of 40 unfamiliar objects (mainly archaic tools) were trained with or without semantic support. The object names were trained during a 4-day long period and a follow-up was conducted one week, 4 weeks and 8 weeks after the training period. Manipulation of semantic support was included in the paradigm because it was hypothesized that semantic support might have some beneficial effects in the present learning task especially for the MCI group, as semantic memory is quite well preserved in MCI in contrast to episodic memory. We found that word learning was significantly impaired in MCI and AD patients, whereas forgetting patterns were similar across groups. Semantic support showed a beneficial effect on object name retrieval in the MCI group 8 weeks after training, indicating that the MCI patients’ preserved semantic memory abilities compensated for their impaired episodic memory. The MCI group performed equally well as the controls in the tasks tapping incidental learning and recognition memory, whereas the AD group showed impairment. Both the MCI and the AD group benefited less from phonological cueing than the controls. Our findings indicate that acquisition is compromised in both MCI and AD, whereas long13 term retention is not affected to the same extent. Incidental learning and recognition memory seem to be well preserved in MCI. In studies III and IV, the neural correlates of naming newly learned objects were examined in healthy elderly subjects and in amnestic MCI patients by means of positron emission tomography (PET) right after the training period. The naming of newly learned objects by healthy elderly subjects recruited a left-lateralized network, including frontotemporal regions and the cerebellum, which was more extensive than the one related to the naming of familiar objects (study III). Semantic support showed no effects on the PET results for the healthy subjects. The observed activation increases may reflect lexicalsemantic and lexical-phonological retrieval, as well as more general associative memory mechanisms. In study IV, compared to the controls, the MCI patients showed increased anterior cingulate activation when naming newly learned objects that had been learned without semantic support. This suggests a recruitment of additional executive and attentional resources in the MCI group.

New [18F]Tracers for Alzheimer's Disease Imaging. Labeling Synthesis And Biological Testing

Alzheimer’s disease (AD) is the most common form of dementia. Characteristic changes in an AD brain are the formation of β-amyloid protein (Aβ) plaques and neurofibrillary tangles, though other alterations in the brain have also been connected to AD. No cure is available for AD and it is one of the leading causes of death among the elderly in developed countries. Liposomes are biocompatible and biodegradable spherical phospholipid bilayer vesicles that can enclose various compounds. Several functional groups can be attached on the surface of liposomes in order to achieve long-circulating target-specific liposomes. Liposomes can be utilized as drug carriers and vehicles for imaging agents. Positron emission tomography (PET) is a non-invasive imaging method to study biological processes in living organisms. In this study using nucleophilic 18F-labeling synthesis, various synthesis approaches and leaving groups for novel PET imaging tracers have been developed to target AD pathology in the brain. The tracers were the thioflavin derivative [18F]flutemetamol, curcumin derivative [18F]treg-curcumin, and functionalized [18F]nanoliposomes, which all target Aβ in the AD brain. These tracers were evaluated using transgenic AD mouse models. In addition, 18F-labeling synthesis was developed for a tracer targeting the S1P3 receptor. The chosen 18F-fluorination strategy had an effect on the radiochemical yield and specific activity of the tracers. [18F]Treg-curcumin and functionalized [18F]nanoliposomes had low uptake in AD mouse brain, whereas [18F]flutemetamol exhibited the appropriate properties for preclinical Aβ-imaging. All of these tracers can be utilized in studies of the pathology and treatment of AD and related diseases.

A retrospective study of cholinesterase inhibitors for Alzheimer's disease : the effect of cerebrovascular disease on patient outcomes and the impact of biases on the results.

Introduction: La démence peut être causée par la maladie d’Alzheimer (MA), la maladie cérébrovasculaire (MCEREV), ou une combinaison des deux. Lorsque la maladie cérébrovasculaire est associée à la démence, les chances de survie sont considérées réduites. Il reste à démontrer si le traitement avec des inhibiteurs de la cholinestérase (ChEIs), qui améliore les symptômes cognitifs et la fonction globale chez les patients atteints de la MA, agit aussi sur les formes vasculaires de démence. Objectifs: La présente étude a été conçue pour déterminer si la coexistence d’une MCEREV était associée avec les chances de survie ou la durée de la période jusqu’au placement en hebergement chez les patients atteints de la MA et traités avec des ChEIs. Des études montrant de moins bons résultats chez les patients souffrant de MCEREV que chez ceux n’en souffrant pas pourrait militer contre l’utilisation des ChEIs chez les patients atteints à la fois de la MA et la MCEREV. L'objectif d'une seconde analyse était d'évaluer pour la première fois chez les patients atteints de la MA l'impact potentiel du biais de « temps-immortel » (et de suivi) sur ces résultats (mort ou placement en hebergement). Méthodes: Une étude de cohorte rétrospective a été conduite en utilisant les bases de données de la Régie de l’Assurance Maladie du Québec (RAMQ) pour examiner la durée de la période jusqu’au placement en hebergement ou jusqu’au v décès des patients atteints de la MA, âgés de 66 ans et plus, avec ou sans MCEREV, et traités avec des ChEIs entre le 1er Juillet 2000 et le 30 Juin 2003. Puisque les ChEIs sont uniquement indiquées pour la MA au Canada, chaque prescription de ChEIs a été considérée comme un diagnostic de la MA. La MCEREV concomitante a été identifié sur la base d'un diagnostic à vie d’un accident vasculaire cérébral (AVC) ou d’une endartériectomie, ou d’un diagnostic d'un accident ischémique transitoire au cours des six mois précédant la date d’entrée. Des analyses séparées ont été conduites pour les patients utilisant les ChEIs de façon persistante et pour ceux ayant interrompu la thérapie. Sept modèles de régression à risque proportionnel de Cox qui ont varié par rapport à la définition de la date d’entrée (début du suivi) et à la durée du suivi ont été utilisés pour évaluer l'impact du biais de temps-immortel. Résultats: 4,428 patients ont répondu aux critères d’inclusion pour la MA avec MCEREV; le groupe de patients souffrant seulement de la MA comptait 13,512 individus. Pour le critère d’évaluation composite considérant la durée de la période jusqu’au placement en hebergement ou jusqu’au décès, les taux de survie à 1,000 jours étaient plus faibles parmi les patients atteints de la MA avec MCEREV que parmi ceux atteints seulement de la MA (p<0.01), mais les différences absolues étaient très faibles (84% vs. 86% pour l’utilisation continue de ChEIs ; 77% vs. 78% pour la thérapie avec ChEIs interrompue). Pour les critères d’évaluation secondaires, la période jusqu’au décès était plus courte chez les patients avec la MCEREV que sans la MCEREV, mais la période jusqu’au vi placement en hebergement n’était pas différente entre les deux groupes. Dans l'analyse primaire (non-biaisée), aucune association a été trouvée entre le type de ChEI et la mort ou le placement en maison d'hébergement. Cependant, après l'introduction du biais de temps-immortel, on a observé un fort effet différentiel. Limitations: Les résultats peuvent avoir été affectés par le biais de sélection (classification impropre), par les différences entre les groupes en termes de consommation de tabac et d’indice de masse corporelle (ces informations n’étaient pas disponibles dans les bases de données de la RAMQ) et de durée de la thérapie avec les ChEIs. Conclusions: Les associations entre la coexistence d’une MCEREV et la durée de la période jusqu’au placement en hebergement ou au décès apparaissent peu pertinentes cliniquement parmi les patients atteints de la MA traités avec des ChEIs. L’absence de différence entre les patients atteints de la MA souffrant ou non de la MCEREV suggère que la coexistence d’une MCEREV ne devrait pas être une raison de refuser aux patients atteints de la MA l’accès au traitement avec des ChEIs. Le calcul des « personne-temps » non exposés dans l'analyse élimine les estimations biaisées de l'efficacité des médicaments.

Relation entre la structure et la fonction des artères cérébrales dans l’athérosclérose : impact des traitements cardioprotecteurs

Thèse réalisée en cotutelle avec Dre Christine Des Rosiers

Tyrosine-based rivastigmine-loaded organogels in the treatmant of Alzheimer's disease

Faculté de Pharmacie

A study of the polycomb group complexes in the maintenance of heterochromatic genome stability and Alzheimer's disease.

La démence d'Alzheimer est une maladie neurodégénérative caractérisée par une perte progressive et irreversible des fonctions cognitives et des compétences intellectuelles. La maladie d’Alzheimer se présente sous deux formes: la forme familiale ou précoce (EOAD) qui représente 5% des cas et elle est liée à des mutations génétiques affectant le métabolisme des peptides amyloïde; et la forme tardive ou sporadique (LOAD) qui représente 95% des cas mais son étiologie est encore mal définie. Cependant, le vieillissement reste le principal facteur de risque pour développer LOAD. Les changements épigénétiques impliquant des modifications des histones jouent un rôle crucial dans les maladies neurodégénératives et le vieillissement lié à l'âge. Des données récentes ont décrit LOAD comme un désordre de l'épigénome et ont associé ce trouble à l'instabilité génomique. Les protéines Polycomb sont des modificateurs épigénétiques qui induisent le remodelage de la chromatine et la répression des gènes à l'hétérochromatine facultative. Nous rapportons que les souris hétérozygotes pour une protéine Polycomb développent avec l'âge un trouble neurologique ressemblant à LOAD caractérisé par l’altération des fonctions cognitives, la phosphorylation de la protéine tau, l'accumulation des peptides amyloïde, et le dysfonctionnement synaptique. Ce phénotype pathologique est précédé par la décondensation de l’hétérochromatine neuronale et l'activation de la réponse aux dommages à l'ADN. Parallèlement, une réduction d’expression de polycomb, malformations de l'hétérochromatine neuronale, et l'accumulation de dommages à l'ADN étaient également présents dans les cerveaux de patients LOAD. Remarquablement, les dommages de l'ADN ne sont pas distribués de façon aléatoire sur le génome mais sont enrichis au niveau des séquences répétitives. Les conclusions présentées dans cette thèse ont identifié des modifications épigénétiques spécifiques qui conduisent à une instabilité génomique aberrante menant à la formation de LOAD. Ces résultats vont aider au développement de nouveaux traitements qui peuvent potentiellement ralentir la neurodégénérescence.

An LDA and probability-based classifier for the diagnosis of Alzheimer's Disease from structural MRI

In this paper a custom classification algorithm based on linear discriminant analysis and probability-based weights is implemented and applied to the hippocampus measurements of structural magnetic resonance images from healthy subjects and Alzheimer’s Disease sufferers; and then attempts to diagnose them as accurately as possible. The classifier works by classifying each measurement of a hippocampal volume as healthy controlsized or Alzheimer’s Disease-sized, these new features are then weighted and used to classify the subject as a healthy control or suffering from Alzheimer’s Disease. The preliminary results obtained reach an accuracy of 85.8% and this is a similar accuracy to state-of-the-art methods such as a Naive Bayes classifier and a Support Vector Machine. An advantage of the method proposed in this paper over the aforementioned state of the art classifiers is the descriptive ability of the classifications it produces. The descriptive model can be of great help to aid a doctor in the diagnosis of Alzheimer’s Disease, or even further the understand of how Alzheimer’s Disease affects the hippocampus.

A Genetic Algorithm for the selection of structural MRI features for classification of Mild Cognitive Impairment and Alzheimer's Disease

This work investigates the problem of feature selection in neuroimaging features from structural MRI brain images for the classification of subjects as healthy controls, suffering from Mild Cognitive Impairment or Alzheimer’s Disease. A Genetic Algorithm wrapper method for feature selection is adopted in conjunction with a Support Vector Machine classifier. In very large feature sets, feature selection is found to be redundant as the accuracy is often worsened when compared to an Support Vector Machine with no feature selection. However, when just the hippocampal subfields are used, feature selection shows a significant improvement of the classification accuracy. Three-class Support Vector Machines and two-class Support Vector Machines combined with weighted voting are also compared with the former and found more useful. The highest accuracy achieved at classifying the test data was 65.5% using a genetic algorithm for feature selection with a three-class Support Vector Machine classifier.

Peripheral Oxidative Stress Biomarkers in Mild Cognitive Impairment and Alzheimer`s Disease

Oxidative stress has been associated with normal aging and Alzheimer`s disease (AD). However, little is known about oxidative stress in mild cognitive impairment (MCI) patients who present a high risk for developing AD. The aim of this study was to investigate plasma production of the lipid peroxidation marker, malonaldehyde (MDA) and to determine, in erythrocytes, the enzymatic antioxidant activity of catalase, glutathione peroxidase (GPx), glutathione reductase (GR), and glutathione S-transferase (GST) in 33 individuals with MCI, 29 with mild probable AD and 26 healthy aged subjects. GR/GPx activity ratio was calculated to better assess antioxidant defenses. The relationship between oxidative stress and cognitive performance was also evaluated by the Mini Mental State Examination (MMSE). AD patients showed higher MDA levels than both MCI and healthy elderly subjects. MCI subjects also exhibited higher MDA levels compared to controls. Catalase and GPx activity were similar in MCI and healthy individuals but higher in AD. GR activity was lower in MCI and AD patients than in healthy aged subjects. Additionally, GR/GPx ratio was higher in healthy aged subjects, intermediate in MCI and lower in AD patients. No differences in GST activity were detected among the groups. MMSE was negatively associated with MDA levels (r = -0.31, p = 0.028) and positively correlated with GR/GPx ratio in AD patients (r = 0.68, p < 0.001). MDA levels were also negatively correlated to GR/GPx ratio (r = -0.31, p = 0.029) in the AD group. These results suggest that high lipid peroxidation and decreased antioxidant defenses may be present early in cognitive disorders.

False-positive results of a rapid K39-based strip test and Chagas disease

Background: The definitive diagnosis of visceral. leishmaniasis (VL) requires invasive procedures with demonstration of amastigotes in tissue or promastigotes in culture. Unfortunately, these approaches require laboratory materials not available in poor countries where the disease is endemic. The correct diagnosis of VL is important, and made more difficult by the fact that several common tropical diseases such as malaria, disseminated tuberculosis, and enteric fever share the same clinical presentation. Serological tests have been developed to replace parasitological diagnosis in the field. A commercially available K39-based strip test for VL has been developed for this purpose. The endemic area of leishmaniasis in Brazil overlaps the endemic area of Chagas disease, a disease that can cause false-positive serological test results. The aim of this study was to evaluate the incidence of false-positive exams using a rapid test for VL in patients with Chagas disease. Methods: A rapid test based on the recombinant K39 antigen of Leishmania was used in: (1) 30 patients with confirmed Chagas disease, (2) 30 patients with a serological diagnosis of Chagas disease by ELISA, indirect immunofluorescence, indirect hemagglutination, and chemiluminescence, (3) 30 healthy patients from a non-endemic area as the control group, (4) 30 patients with confirmed VL, and (5) 20 patients with proved cutaneous leishmaniasis. Results: The sensitivity and specificity of the rapid strip test were 100% when compared with healthy volunteers and those with confirmed Chagas disease. One false-positive result occurred in the group with Chagas disease diagnosed by serological tests (specificity of 96%). Conclusion: The rapid test based on recombinant K39 is a useful diagnostic assay, and a false-positive result rarely occurs in patients with a serological diagnosis of Chagas disease. (C) 2008 International Society for Infectious Diseases. Published by Elsevier Ltd. All rights reserved.