Current Alzheimer Research - Volume 15, Issue 2, 2018

Objective: This study presents a novel approach for early detection of cognitive impairment in the elderly. The approach incorporates the use of speech sound analysis, multivariate statistics, and data-mining techniques. We have developed a speech prosody-based cognitive impairment rating (SPCIR) that can distinguish between cognitively normal controls and elderly people with mild Alzheimer's disease (mAD) or mild cognitive impairment (MCI) using prosodic signals extracted from elderly speech while administering a questionnaire. Two hundred and seventy-three Japanese subjects (73 males and 200 females between the ages of 65 and 96) participated in this study. The authors collected speech sounds from segments of dialogue during a revised Hasegawa's dementia scale (HDS-R) examination and talking about topics related to hometown, childhood, and school. The segments correspond to speech sounds from answers to questions regarding birthdate (T1), the name of the subject's elementary school (T2), time orientation (Q2), and repetition of three-digit numbers backward (Q6). As many prosodic features as possible were extracted from each of the speech sounds, including fundamental frequency, formant, and intensity features and mel-frequency cepstral coefficients. They were refined using principal component analysis and/or feature selection. The authors calculated an SPCIR using multiple linear regression analysis. Conclusion: In addition, this study proposes a binary discrimination model of SPCIR using multivariate logistic regression and model selection with receiver operating characteristic curve analysis and reports on the sensitivity and specificity of SPCIR for diagnosis (control vs. MCI/mAD). The study also reports discriminative performances well, thereby suggesting that the proposed approach might be an effective tool for screening the elderly for mAD and MCI.

Background: Recent studies have identified the correlation between dementia and certain vocal features, such as voice and speech changes. Vocal features may act as early markers of Alzheimer's disease (AD). Despite being present in non-pathological senescence and Mild Cognitive Impairment, especially in its amnesic subtype (aMCI), these voice- and speech-related symptoms are the first signs of AD. The purpose of this study is to verify whether these signs are related to deficits in lexical access, which appear early in AD. Method: Anomic deficits in persons with MCI and AD are assessed through tests on verbal memory, denomination by confrontation, and verbal fluency. In addition, an acoustic analysis of speech is conducted in a reading task to identify the acoustic parameters associated with the groups analyzed, and their relation to the degree of anomic impairment observed in each one of them. Results and Conclusions: The results show a direct relationship between the different acoustic parameters present in AD and the verbal fluency tests results.

Background: Various types of dementia and Mild Cognitive Impairment (MCI) are manifested as irregularities in human speech and language, which have proven to be strong predictors for the disease presence and progress ion. Therefore, automatic speech analytics provided by a mobile application may be a useful tool in providing additional indicators for assessment and detection of early stage dementia and MCI. Method: 165 participants (subjects with subjective cognitive impairment (SCI), MCI patients, Alzheimer's disease (AD) and mixed dementia (MD) patients) were recorded with a mobile application while performing several short vocal cognitive tasks during a regular consultation. These tasks included verbal fluency, picture description, counting down and a free speech task. The voice recordings were processed in two steps: in the first step, vocal markers were extracted using speech signal processing techniques; in the second, the vocal markers were tested to assess their ‘power' to distinguish between SCI, MCI, AD and MD. The second step included training automatic classifiers for detecting MCI and AD, based on machine learning methods, and testing the detection accuracy. Results: The fluency and free speech tasks obtain the highest accuracy rates of classifying AD vs. MD vs. MCI vs. SCI. Using the data, we demonstrated classification accuracy as follows: SCI vs. AD = 92% accuracy; SCI vs. MD = 92% accuracy; SCI vs. MCI = 86% accuracy and MCI vs. AD = 86%. Conclusions: Our results indicate the potential value of vocal analytics and the use of a mobile application for accurate automatic differentiation between SCI, MCI and AD. This tool can provide the clinician with meaningful information for assessment and monitoring of people with MCI and AD based on a non-invasive, simple and low-cost method.

Background: Even today the reliable diagnosis of the prodromal stages of Alzheimer's disease (AD) remains a great challenge. Our research focuses on the earliest detectable indicators of cognitive decline in mild cognitive impairment (MCI). Since the presence of language impairment has been reported even in the mild stage of AD, the aim of this study is to develop a sensitive neuropsychological screening method which is based on the analysis of spontaneous speech production during performing a memory task. In the future, this can form the basis of an Internet-based interactive screening software for the recognition of MCI. Methods: Participants were 38 healthy controls and 48 clinically diagnosed MCI patients. The provoked spontaneous speech by asking the patients to recall the content of 2 short black and white films (one direct, one delayed), and by answering one question. Acoustic parameters (hesitation ratio, speech tempo, length and number of silent and filled pauses, length of utterance) were extracted from the recorded speech signals, first manually (using the Praat software), and then automatically, with an automatic speech recognition (ASR) based tool. First, the extracted parameters were statistically analyzed. Then we applied machine learning algorithms to see whether the MCI and the control group can be discriminated automatically based on the acoustic features. Results: The statistical analysis showed significant differences for most of the acoustic parameters (speech tempo, articulation rate, silent pause, hesitation ratio, length of utterance, pause-per-utterance ratio). The most significant differences between the two groups were found in the speech tempo in the delayed recall task, and in the number of pauses for the question-answering task. The fully automated version of the analysis process – that is, using the ASR-based features in combination with machine learning - was able to separate the two classes with an F1-score of 78.8%. Conclusion: The temporal analysis of spontaneous speech can be exploited in implementing a new, automatic detection-based tool for screening MCI for the community.

Objective: Nowadays proper detection of cognitive impairment has become a challenge for the scientific community. Alzheimer's Disease (AD), the most common cause of dementia, has a high prevalence that is increasing at a fast pace towards epidemic level. In the not-so-distant future this fact could have a dramatic social and economic impact. In this scenario, an early and accurate diagnosis of AD could help to decrease its effects on patients, relatives and society. Over the last decades there have been useful advances not only in classic assessment techniques, but also in novel non-invasive screening methodologies. Methods: Among these methods, automatic analysis of speech -one of the first damaged skills in AD patients- is a natural and useful low cost tool for diagnosis. Results: In this paper a non-linear multi-task approach based on automatic speech analysis is presented. Three tasks with different language complexity levels are analyzed, and promising results that encourage a deeper assessment are obtained. Automatic classification was carried out by using classic Multilayer Perceptron (MLP) and Deep Learning by means of Convolutional Neural Networks (CNN) (biologically- inspired variants of MLPs) over the tasks with classic linear features, perceptual features, Castiglioni fractal dimension and Multiscale Permutation Entropy. Conclusion: Finally, the most relevant features are selected by means of the non-parametric Mann- Whitney U-test.

Background: Sensorimotor integration mechanisms can be affected by many factors, among which are those involving neuromuscular disorders. Parkinson's disease (PD) is characterized by well-known motor symptoms, among which lately have been included motor speech deficits. Measurement of the acoustic startle reflex (ASR) and its modulations (prepulse inhibition and prepulse facilitation, PPI and PPF respectively) represent a simple and quantifiable tool to assess sensorimotor function. However, it remains unknown whether measures of the PPI and PPF are associated with motor speech deficits in PD. Methods: A total of 88 subjects participated in this study, 52 diagnosed with PD and 36 control subjects. After obtaining written informed consent, participants were assessed with PPI at several interstimulus intervals, and PPF at 1000 ms using the SRH-Lab system (San Diego, CA). Percentage of change in the amplitude and latency of the ASR was analyzed between groups. Voice recordings were register of a specific text given to the subjects with a professional recorder and temporal patterns of speech were analyzed. Results: Statistical analysis conducted in this study showed differences in PPI and PPF in subjects with PD compared to controls. In addition, discriminative parameters of voice abnormalities were observed in PD subjects related to control subjects showing a reduction in phonation time, vowel pulses, breaks, breakage and voice speech periods. Conclusions: PD presents a disruption in sensorimotor filter mechanisms and speech disorders, and there is a relationship between these alterations. The correlation between the PPI and PPF with an alteration of the voice in PD subjects contributes toward understanding mechanism underlying the neurophysiological alterations in both processes. Overall, easy and non-invasive tests such as PPI, PPF together with voice analysis may be useful to identify early stages of PD.

Objective: Prosody, an important aspect of spoken language, is defined as the emphasis placed on certain syllables, changes in tempo or timing, and variance in pitch and intonation. Most studies investigating expression and comprehension of prosody have focused primarily on emotional prosody and less extensively on supralexical prosody. The distinction is indeed important, as the latter conveys information such as interrogative or assertive mode, whereas the former delivers emotional connotation, such as happiness, anger, and sadness. These functions appear to rely on distinct neuronal networks, supported by functional neuroimaging studies that show activation of the right hemisphere, specifically in the right inferior frontal area during emotional detection. Conclusion: This review summarizes the studies conducted on prosody impairment in Alzheimer's disease and other dementias, with emphasis on experiments designed to investigate the emotional vs. the supralexical aspect of speech production. We also discussed the available tools validated to test and quantify the prosodic impairment.

Background: Alzheimer's disease (AD) is currently incurable and a majority of investigational drugs have failed clinical trials. One explanation for this failure may be the invalidity of hypotheses focusing on amyloid to explain AD pathogenesis. Recently, hypotheses which are centered on synaptic and metabolic dysfunction are increasingly implicated in AD. Objective: Evaluate AD hypotheses by comparing neurotransmitter and metabolite marker concentrations in normal versus AD CSF. Methods: Meta-analysis allows for statistical comparison of pooled, existing cerebrospinal fluid (CSF) marker data extracted from multiple publications, to obtain a more reliable estimate of concentrations. This method also provides a unique opportunity to rapidly validate AD hypotheses using the resulting CSF concentration data. Hubmed, Pubmed and Google Scholar were comprehensively searched for published English articles, without date restrictions, for the keywords “AD”, “CSF”, and “human” plus markers selected for synaptic and metabolic pathways. Synaptic markers were acetylcholine, gamma-aminobutyric acid (GABA), glutamine, and glycine. Metabolic markers were glutathione, glucose, lactate, pyruvate, and 8 other amino acids. Only studies that measured markers in AD and controls (Ctl), provided means, standard errors/deviation, and subject numbers were included. Data were extracted by six authors and reviewed by two others for accuracy. Data were pooled using ratio of means (RoM of AD/Ctl) and random effects meta-analysis using Cochrane Collaboration’s Review Manager software. Results: Of the 435 identified publications, after exclusion and removal of duplicates, 35 articles were included comprising a total of 605 AD patients and 585 controls. The following markers of synaptic and metabolic pathways were significantly changed in AD/controls: acetylcholine (RoM 0.36, 95% CI 0.24-0.53, p<0.00001), GABA (0.74, 0.58-0.94, p<0.01), pyruvate (0.48, 0.24-0.94, p=0.03), glutathione (1.11, 1.01- 1.21, p=0.03), alanine (1.10, 0.98-1.23, p=0.09), and lower levels of significance for lactate (1.2, 1.00-1.47, p=0.05). Of note, CSF glucose and glutamate levels in AD were not significantly different than that of the controls. Conclusion: This study provides proof of concept for the use of meta-analysis validation of AD hypotheses, specifically via robust evidence for the cholinergic hypothesis of AD. Our data disagree with the other synaptic hypotheses of glutamate excitotoxicity and GABAergic resistance to neurodegeneration, given observed unchanged glutamate levels and decreased GABA levels. With regards to metabolic hypotheses, the data supported upregulation of anaerobic glycolysis, pentose phosphate pathway (glutathione), and anaplerosis of the tricarboxylic acid cycle using glutamate. Future applications of meta-analysis indicate the possibility of further in silico evaluation and generation of novel hypotheses in the AD field.

Background: Alzheimer's disease (AD) is a neurodegenerative disorder characterized by extracellular amyloid plaque and neurofibrillary tangles in the brain. Studies have shown that neurons are able to re-enter the cell cycle, but not enough to enable full replication. This leads to cell death and consequent neurodegeneration. Objective: This study aimed to characterize the expression of the MAPT gene and CDK5 (the gene involved in cell cycle regulation) in brain samples from patients with AD and controls. Method: The real-time-PCR technique was used to characterize 150 samples from three areas of the brain (entorhinal cortex, auditory cortex, and hippocampus) of 26 AD patients and 24 healthy elderly subjects. Results: When the brain samples were analyzed collectively, a decrease in CDK5 and MAPT gene expression was found in AD patients. When each groups' samples were separated by area of the brain and compared, significant differences were found in CDK5 expression in the hippocampus and the entorhinal cortex. In both cases, mRNA was lower in the AD group (p=0.0001); however, the same analysis using the MAPT gene revealed no significant statistical differences. No statistical differences were found when gene expression was compared between the different regions of the brain within each group. Conclusion: These results may contribute to a better understanding of the involvement of CDK5 and MAPT genes in AD in that they consider different areas of the brain that are affected differently based on disease progression. The main challenge is to establish an effective therapy for this debilitating disease in the future.

Background: Psychosis is a common phenomenon in Alzheimer's disease (AD). The APOE ε4 allele is the strongest genetic risk factor for the development of AD, but its association with psychosis remains unclear. Objective: We investigated the associations between psychosis, subdivided into delusions and hallucinations, as well as APOE ε4 allele on cognitive and functional outcomes. Secondarily, we investigated the associations between APOE ε4, Lewy bodies, and psychosis. Methods: Data from the National Alzheimer's Coordinating Center (NACC) were used. Nine hundred patients with a confirmed diagnosis of AD based on the NIA-AA Reagan were included in the analysis. Global cognition was assessed using the Mini-Mental State Exam (MMSE) and functional status was assessed using the Functional Activities Questionnaire (FAQ). Psychosis status was determined using the Neuropsychiatric Inventory Questionnaire (NPI-Q). Factorial design was used to assess the effects of psychosis and APOE ε4, as well as their interaction. Results: Psychosis and the presence of APOE ε4 were both associated with lower MMSE scores, while only psychosis was associated with higher FAQ scores. Furthermore, patients with hallucinations had lower MMSE and higher FAQ scores than patients with only delusions. There was a significant interaction effect between psychosis and APOE ε4 on MMSE scores, with APOE ε4 negatively affecting patients with hallucinations-only psychosis. APOE ε4 was positively associated with the presence of Lewy body pathology, and both were found to be more prevalent in psychotic patients, with a stronger association with hallucinations. Conclusion: Psychosis in AD was associated with greater cognitive and functional impairments. Patients with hallucinations-with or without delusions-conferred even greater deficits compared to patients with only delusions. The APOE ε4 allele was associated with worse cognition, especially for patients with hallucination-only psychosis. APOE ε4 may mediate cognitive impairment in the hallucinations phenotype through the development of Lewy bodies. Our findings support that subtypes of psychosis should be evaluated separately.

Background: The findings from previous studies exploring the association between BMI and cognitive function in the elderly are conflicting. The purpose of the present study is twofold; to verify the association between BMI and cognitive functions and examine whether this association is impacted by height, when adjusted for possible covariates. Methods: The data for this study, consisted of 2287 older adults aged 60 years and above, drawn from a nationally representative population-based survey entitled “Determinants of Wellness among Older Malaysians: A Health Promotion Perspective” conducted in 2009. Results: The mean age of the respondents was 68.7 (SD=6.6) years. The average score of cognitive function, measured by MMSE was 24.5 (SD=5.6). About 40% of the respondents were classified as overweight. Results of the multiple linear regression analysis revealed a significant association between BMI and cognitive function (Beta=.10, p<.001). The Factorial ANCOVA revealed significant interaction effect between BMI and height on cognitive function (F= 10.8, p<.001), after adjusting for possible covariates. Conclusion: The findings from the current study indicating the positive association between BMI and cognitive function depends on height, therefore it is suggested that short people might be targeted for dementia prevention.