Distinguish Alzheimer's Disease Patients Research Articles

Deep Learning-Based Eye-Tracking Analysis for Diagnosis of Alzheimer's Disease Using 3D Comprehensive Visual Stimuli.

Alzheimer's Disease (AD) is a neurodegenerative disorder that causes a continuous decline in cognitive functions and eventually results in death. An early AD diagnosis is important for taking active measures to slow its deterioration. Traditional diagnoses are usually based on clinical experience, which is limited by several realistic factors. In this paper, we focus on exploiting deep learning techniques to diagnose AD based on eye-tracking behaviors. Visual attention, as a typical eye-tracking behavior, is of great clinical value in detecting cognitive abnormalities in AD patients. To better analyze the differences in visual attention between AD patients and normals, we first conducted a 3D comprehensive visual task on a noninvasive eye-tracking system to collect visual attention heatmaps. Then a multilayered comparison convolutional neural network (MC-CNN) is proposed to distinguish the visual attention differences between AD patients and normals. In MC-CNN, the multilayered feature representations of heatmaps were obtained by hierarchical residual blocks to better encode eye movement behaviors, which were further integrated into a distance vector to benefit the comprehensive visual task. From evaluation, MC-CNN can distinguish AD patients from normals with 0.84 accuracy, 0.86 recall, 0.82 precision, 0.83 F1-score and 0.90 area under the curve (AUC). The above results demonstrate the effectiveness of the proposed MC-CNN in AD diagnosis based on the comprehensive 3D visual task.

Classification of Alzheimer's disease: application of a transfer learning deep Q-network method.

Early diagnosis is crucial to slowing the progression of Alzheimer's disease (AD), so it is urgent to find an effective diagnostic method for AD. This study intended to investigate whether the transfer learning approach of deep Q-network (DQN) could effectively distinguish AD patients using local metrics of resting-state functional magnetic resonance imaging (rs-fMRI) as features. This study included 1310 subjects from the Consortium for Reliability and Reproducibility (CoRR) and 50 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) GO/2. The amplitude of low-frequency fluctuation (ALFF), fractional ALFF (fALFF) and percent amplitude of fluctuation (PerAF) were extracted as features using the Power 264 atlas. Based on gender bias in AD, we searched for transferable similar parts between the CoRR feature matrix and the ADNI feature matrix, resulting in the CoRR similar feature matrix served as the source domain and the ADNI similar feature matrix served as the target domain. A DQN classifier was pre-trained in the source domain and transferred to the target domain. Finally, the transferred DQN classifier was used to classify AD and healthy controls (HC). A permutation test was performed. The DQN transfer learning achieved a classification accuracy of 86.66% (p < 0.01), recall of 83.33% and precision of 83.33%. The findings suggested that the transfer learning approach using DQN could be an effective way to distinguish AD from HC. It also revealed the potential value of local brain activity in AD clinical diagnosis.

Detecting Anosognosia from the Prodromal Stage of Alzheimer's Disease.

Though not originally developed for this purpose, the Healthy Aging Brain Care Monitor (HABC-M) seems a valuable instrument for assessing anosognosia in Alzheimer's disease (AD). Our study aimed at 1) investigating the validity of the HABC-M (31 items), and its cognitive, psychological, and functional subscales, in discriminating AD patients from controls; 2) exploring whether the HABC-M discrepancy scores between the self-reports of patients/controls in these different domains and the respective ratings provided by their caregivers/informants correlate with an online measure of self-awareness; 3) determining whether the caregiver burden level, also derived from the HABC-M, could add additional support for detecting anosognosia. The HABC-M was administered to 30 AD patients and 30 healthy controls, and to their caregivers/informants. A measure of online awareness was established from subjects' estimation of their performances in a computerized experiment. The HABC-M discrepancy scores distinguished AD patients from controls. The cognitive subscale discriminated the two groups from the prodromal AD stage, with an AUC of 0.88 [95% CI: 0.78;0.97]. Adding the caregiver burden level raised it to 0.94 [0.86;0.99]. Significant correlations between the HABC-M and online discrepancy scores were observed in the patients group, providing convergent validity of these methods. The cognitive HABC-M (six items) can detect anosognosia across the AD spectrum. The caregiver burden (four items) may corroborate the suspicion of anosognosia. The short-hybrid scale, built from these 10 items instead of the usual 31, showed the highest sensitivity for detecting anosognosia from the prodromal AD stage, which may further help with timely diagnosis.

Metabolic Pathway Pairwise-Based Signature as a Potential Non-Invasive Diagnostic Marker in Alzheimer's Disease Patients.

Alzheimer's disease (AD) is an incurable neurodegenerative disorder. Early screening, particularly in blood plasma, has been demonstrated as a promising approach to the diagnosis and prevention of AD. In addition, metabolic dysfunction has been demonstrated to be closely related to AD, which might be reflected in the whole blood transcriptome. Hence, we hypothesized that the establishment of a diagnostic model based on the metabolic signatures of blood is a workable strategy. To that end, we initially constructed metabolic pathway pairwise (MPP) signatures to characterize the interplay among metabolic pathways. Then, a series of bioinformatic methodologies, e.g., differential expression analysis, functional enrichment analysis, network analysis, etc., were used to investigate the molecular mechanism behind AD. Moreover, an unsupervised clustering analysis based on the MPP signature profile via the Non-Negative Matrix Factorization (NMF) algorithm was utilized to stratify AD patients. Finally, aimed at distinguishing AD patients from non-AD groups, a metabolic pathway-pairwise scoring system (MPPSS) was established using multi-machine learning methods. As a result, many metabolic pathways correlated to AD were disclosed, including oxidative phosphorylation, fatty acid biosynthesis, etc. NMF clustering analysis divided AD patients into two subgroups (S1 and S2), which exhibit distinct activities of metabolism and immunity. Typically, oxidative phosphorylation in S2 exhibits a lower activity than that in S1 and non-AD group, suggesting the patients in S2 might possess a more compromised brain metabolism. Additionally, immune infiltration analysis showed that the patients in S2 might have phenomena of immune suppression compared with S1 and the non-AD group. These findings indicated that S2 probably has a more severe progression of AD. Finally, MPPSS could achieve an AUC of 0.73 (95%CI: 0.70, 0.77) in the training dataset, 0.71 (95%CI: 0.65, 0.77) in the testing dataset, and an AUC of 0.99 (95%CI: 0.96, 1.00) in one external validation dataset. Overall, our study successfully established a novel metabolism-based scoring system for AD diagnosis using the blood transcriptome and provided new insight into the molecular mechanism of metabolic dysfunction implicated in AD.

Reliability and validity of the electronic version of the Hopkins verbal learning test-revised in middle-aged and elderly Chinese people.

The aging population is increasing, making it essential to have a standardized, convenient, and valid electronic memory test that can be accessed online for older people and caregivers. The electronic version of the Hopkins Verbal Learning Test-Revised (HVLT-R) as a test with these advantages and its reliability and validity has not yet been tested. Thus, this study examined the reliability and validity of the electronic version of the HVLT-R in middle-aged and elderly Chinese people to provide a scientific basis for its future dissemination and use. We included 1,925 healthy participants aged over 40, among whom 38 were retested after 3-6 months. In addition, 65 participants completed both the pad and paper-and-pencil versions of the HVLT-R (PAP-HVLT-R). We also recruited 42 Alzheimer's disease (AD) patients, and 45 amnestic mild cognitive impairment (aMCI) patients. All participants completed the Pad-HVLT-R, the Hong Kong Brief Cognitive Test (HKBC), the Brief Visual Memory Test-Revised (BVMT-R), and the Logical Memory Test (LM). (1) Reliability: the Cronbach's α value was 0.94, the split-half reliability was 0.96. The test-retest correlation coefficients were moderate, ranging from 0.38 to 0.65 for direct variables and 0.16 to 0.52 for derived variables; (2) Concurrent validity: the Pad-HVLT-R showed a moderate correlation with the HKBC and BVMT-R, with correlation coefficients between total recall of 0.41 and 0.54, and between long-delayed recall of 0.42 and 0.59, respectively. It also showed a high correlation with the LM, with correlation coefficients of 0.72 for total recall and 0.62 for long-delayed recall; (3) Convergent validity: the Pad-HVLT-R was moderately correlated with the PAP version, with correlation coefficients ranging from 0.29 to 0.53 for direct variables and 0.15 to 0.43 for derived variables; (4) Discriminant capacity: the Pad-HVLT-R was effective in differentiating AD patients, as demonstrated by the ROC analysis with AUC values of 0.834 and 0.934 for total recall and long-delayed recall, respectively. (1) The electronic version of HVLT-R has good reliability and validity in middle-aged and elderly Chinese people; (2) The electronic version of HVLT-R can be used as an effective tool to distinguish AD patients from healthy people.

The effect of hippocampal radiomic features and functional connectivity on the relationship between hippocampal volume and cognitive function in Alzheimer's disease

Hippocampal volume is associated with cognitive function in Alzheimer's disease (AD). Hippocampal radiomic features and resting-state functional connectivity (rs-FC) are promising biomarkers and correlate with AD pathology. However, few studies have been conducted on how hippocampal biomarkers affect the cognition-structure relationship. Therefore, we aimed to investigate the effects of hippocampal radiomic features and resting-state functional connectivity (rs-FC) on this relationship in AD. We enrolled 70 AD patients and 65 healthy controls (HCs). The FreeSurfer software was used to measure hippocampal volume. We selected hippocampal radiomic features to build a model to distinguish AD patients from HCs and used a seed-based approach to calculate the hippocampal rs-FC. Furthermore, we conducted mediation and moderation analyses to investigate the effect of hippocampal radiomic features and rs-FC on the relationship between hippocampal volume and cognition in AD. The results suggested that hippocampal radiomic features mediated the association between bilateral hippocampal volume and cognition in AD. Additionally, patients with AD showed weaker rs-FC between the bilateral hippocampus and right ventral posterior cingulate cortex and stronger rs-FC between the left hippocampus and left insula than HCs. The rs-FC between the hippocampus and insula moderated the relationship between hippocampal volume and cognition in AD, suggesting that this rs-FC could exacerbate or ameliorate the effects of hippocampal volume on cognition and may be essential in improving cognitive function in AD. Our findings may not only expand existing biological knowledge of the interrelationships among hippocampal biomarkers and cognition but also provide potential targets for treatment strategies for AD.

Asymmetric degeneration of the hippocampus predicts risk of Alzheimer’s disease

AbstractBackgroundAsymmetry of the hippocampus is an important finding in normal aging and Alzheimer disease (AD). However, it is largely unknown how asymmetric degeneration of the hippocampus is associated with an individual's risk of AD.MethodA deep‐learning (DL) classification model was developed to quantify degeneration of the hippocampus based on its magnetic resonance imaging (MRI) scan and binary mask. Different from most extant studies, the DL model was trained to distinguish AD patients from cognitively normal (CN) controls with their bilateral hippocampi as two separate instances for generating two classification scores (positive indicating AD‐like and negative indicating CN‐like), one for each hippocampus. An integration of the two scores of an individual’s MRI data was utilized to classify AD patients and CN controls, to predict individual mild cognitive impairment (MCI) subjects’ progression to AD dementia in a time‐to‐event analysis setting, as well as to identify subgroups of MCI subjects with distinct risk of AD dementia. Particularly, the DL classification model was trained on the ADNI 1 cohort (n=420), and then validated for distinguishing AD subjects from CN controls on the ADNI 2&amp;GO (n=469) and AIBL (n=396) cohorts and for predicting MCI subjects’ progression to AD dementia and identifying MCI subgroups on the ADNI 2&amp;GO cohort (n=439).ResultThe DL model achieved accurate classification performance with classification rates of 0.923 and 0.927 and AUC values of 0.963 and 0.961 on the ADNI‐GO&amp;2 and AIBL cohorts, respectively. The integration of the bilateral hippocampal classification scores achieved a concordance index of 0.765 for predicting individual MCI subjects’ progression to AD dementia. The MCI subgroups with bilateral AD‐like, bilateral CN‐like, and one AD‐like and one CN‐like scores were significantly different in risk of progression to AD dementia and a variety of biomarkers and cognitive scores, including Apoe4, Amyloid, tau, and ADAS‐cog score (p &lt; 0.0004).ConclusionThe present study demonstrated that the asymmetric hippocampal degeneration patterns quantified using a DL model on MRI data could achieve promising classification performance for distinguishing AD patients from CN controls and may aid the clinicians to early prediction of MCI subjects’ progression to AD dementia to facilitate personalized medicine.

Colorimetric and surface-enhanced Raman scattering dual-mode magnetic immunosensor for ultrasensitive detection of blood phosphorylated tau in Alzheimer's disease

Phosphorylation of tau at Ser 396, 404 (p-tau396,404) is the earliest phosphorylation event and a promising biomarker for the early diagnosis of Alzheimer's disease (AD). However, the detection of blood p-tau is challenging because of its low abundance, easy degradation, and complex formation with various blood proteins or cells, often leading to the underestimation of p-tau levels in conventional plasma-based assays. Herein, we developed a colorimetric and surface-enhanced Raman scattering (SERS) dual-mode magnetic immunosensor for highly sensitive, specific, and robust detection of p-tau396,404 in whole blood samples. The detection assay was based on an immunoreaction between p-tau396,404 proteins, wherein antibody-modified superparamagnetic iron oxide nanoparticles act as recognition elements to capture p-tau396,404 in blood, and then horseradish peroxidase- and Raman tags label the corresponding paired antibody as a reporter to provide high signal-to-noise ratios for the immunosensor. This dual-mode immunosensor achieved identified as low as 1.5 pg/mL of p-tau396,404 in the blood in SERS mode and 24 pg/mL in colorimetric mode by the naked eye. More importantly, this immunosensor rapidly and accurately distinguished AD patients from healthy individuals based on blood p-tau396,404 levels, and also had the potential to distinguish AD patients of different severities. Therefore, the dual-mode immunosensor is promising for rapid clinical diagnosis of AD, especially in large-scale AD screening.

Blood extracellular vesicles carrying synaptic function- and brain-related proteins as potential biomarkers for Alzheimer's disease.

Objective and accessible markers for Alzheimer's disease (AD) and other dementias are critically needed. We identified NMDAR2A, a protein related to synaptic function, as a novel marker of central nervous system (CNS)-derived plasma extracellular vesicles (EVs) and developed a flow cytometry-based technology for detecting such plasma EVs readily. The assay was initially tested in our local cross-sectional study to distinguish AD patients from healthy controls (HCs) or from Parkinson's disease (PD) patients, followed by a validation study using an independent cohort collected from multiple medical centers (the Alzheimer's Disease Neuroimaging Initiative). Cerebrospinal fluid AD molecular signature was used to confirm diagnoses of all AD participants. Likely CNS-derived EVs in plasma were significantly reduced in AD compared to HCs in both cohorts. Integrative models including CNS-derived EV markers and AD markers present on EVs reached area under the curve of 0.915 in discovery cohort and 0.810 in validation cohort. This study demonstrated that robust and rapid analysis of individual neuron-derived synaptic function-related EVs in peripheral blood may serve as a helpful marker of synaptic dysfunction in AD and dementia.

LncRNA HOTAIR in exercise-induced neuro-protective function in Alzheimer's disease.

Exercise is effective in Alzheimer's disease (AD), which is characterized by neuro-degenerative progress with increasing morbidity. The present study aimed to explore whether HOTAIR participated in the regulation of exercise in AD. Arelative expression of serum HOTAIR was detected using quantitative real-time polymerase chain reaction (PCR). The diagnostic significance of HOTAIR on distinguishing AD patients was evaluated by receiver operating characteristic (ROC) curve. Correlations between HOTAIR expression and Mini-Mental State Examination (MMSE) score or Alzheimer's Disease Assessment Scale-Cognitive (ADAS-Cog) score were analyzed with Pearson's test. Logistic regression analysis was applied to investigate factors as independent indicators for HOTAIR expression. In AD patients, the expression of HOTAIR was increased, and it could function as adiagnostic marker in AD patients. The expression of HOTAIR was associated with MMSE score and ADAS-Cog score in AD patients before exercise. Exercise ameliorated the cognitive impairment and reduced the relative serum expression of HOTAIR. Exercise was proved to be an independent indicator of HOTAIR expression. HOTAIR was apossible biomarker for indicating AD patients, and it was correlated with MMSE scores and ADAS-Cog results. Exercise might moderate AD progress via controlling HOTAIR.

Alterations in Glycerolipid and Fatty Acid Metabolic Pathways in Alzheimer's Disease Identified by Urinary Metabolic Profiling: A Pilot Study.

An easily accessible and non-invasive biomarker for the early detection of Alzheimer's disease (AD) is needed. Evidence suggests that metabolic dysfunction underlies the pathophysiology of AD. While urine is a non-invasively collectable biofluid and a good source for metabolomics analysis, it is not yet widely used for this purpose. This small-scale pilot study aimed to examine whether the metabolic profile of urine from AD patients reflects the metabolic dysfunction reported to underlie AD pathology, and to identify metabolites that could distinguish AD patients from cognitively healthy controls. Spot urine of 18 AD patients (AD group) and 18 age- and sex-matched, cognitively normal controls (control group) were analyzed by mass spectrometry (MS). Capillary electrophoresis time-of-flight MS and liquid chromatography–Fourier transform MS were used to cover a larger range of molecules with ionic as well as lipid characteristics. A total of 304 ionic molecules and 81 lipid compounds of 12 lipid classes were identified. Of these, 26 molecules showed significantly different relative concentrations between the AD and control groups (Wilcoxon's rank-sum test). Moreover, orthogonal partial least-squares discriminant analysis revealed significant discrimination between the two groups. Pathway searches using the KEGG database, and pathway enrichment and topology analysis using Metaboanalyst software, suggested alterations in molecules relevant to pathways of glycerolipid and glycerophospholipid metabolism, thermogenesis, and caffeine metabolism in AD patients. Further studies of urinary metabolites will contribute to the early detection of AD and understanding of its pathogenesis.

Clinical application of serological Alzheimer's disease diagnosis using a highly sensitive biosensor with hydrogel-enhanced dielectrophoretic force

Analysis of a ratio between amyloid beta 1–40 and 1–42 (Aβ1-40 and Aβ1-42) presented in plasm enables a highly accurate diagnosis of Alzheimer's disease (AD). However, the analysis of plasma Aβs is not routinely conducted because of the lack of Aβ detection techniques sensitive enough to specifically detect Aβ from thousands of biomaterials present in the plasma. We developed a hydrogel-patterned spiral microelectrode sensor combined with a hopping dielectrophoretic (DEP) force, combining the negative DEP and positive DEP forces, for Aβ detection. The hydrogel effectively increased the number of immobilized fragmented antibodies in the reaction region of the sensor and enabled size-exclusive passive filtration of non-specific plasma proteins from that region. The hopping DEP force further concentrated the Aβs and removed the non-specific plasma proteins. Consequently, our sensor achieved a limit of detection (LOD) of approximately ∼ 0.15 pg/mL for both Aβ1-40 and Aβ1-42 in the standard plasma. Finally, comparing the ratio between Aβ1-40 and Aβ1-42 signals, we distinguished AD patients from cognitively normal subjects with 95.83% accuracy and 92.31% precision (n = 24, p < 0.0001, One-way ANOVA).

Comparison of the decreases in regional cerebral blood flow in the posterior cingulate cortex, precuneus, and parietal lobe between suspected non-Alzheimer's disease pathophysiology and Alzheimer's disease.

Suspected non-Alzheimer's disease pathophysiology (SNAP) shows Alzheimer's disease (AD)-like neurodegeneration; however, amyloid β, which is a biological marker in AD, remains within normal levels. Since the effectiveness of anti-dementia drugs for AD on SNAP is unknown, it is important to distinguish between patients with SNAP and AD. We aimed to compare decreases in regional cerebral blood flow (rCBF) of the posterior cingulate cortex (PCC), precuneus, and parietal lobe critical to AD between SNAP and AD groups using the easy Z-score imaging system in single-photon emission computed tomography (eZIS-SPECT). We retrospectively analysed eZIS-SPECT data of 13 SNAP and 24 AD patients. The three indicators (severity, extent, and ratio) that distinguished AD patients from healthy controls in previous studies were automatically calculated and were compared between the SNAP and AD groups. Receiver operating characteristic curve analysis and the area under the curve (AUC) were used to evaluate the diagnostic performance of the three indicators of eZIS in discriminating between the two groups. The mean values of severity, extent, and ratio were significantly lower in the SNAP group than in the AD group (P=0.024, P=0.044, and P=0.045, respectively). The AUC values for severity, extent, and ratio were 0.668, 0.683, and 0.692, respectively. The present study suggests that SNAP shows milder reduction of rCBF in the PCC, precuneus, and parietal lobe as compared to AD. However, it may be difficult to distinguish between SNAP and AD with the degrees of decrease in rCBF in these regions.

Long Longitudinal Tract Lesion Contributes to the Progression of Alzheimer's Disease

Background: The degenerative pattern of white matter (WM) microstructures during Alzheimer's disease (AD) and its relationship with cognitive function have not yet been clarified. The present research aimed to explore the alterations of the WM microstructure and its impact on amnestic mild cognitive (aMCI) and AD patients. Mechanical learning methods were used to explore the validity of WM microstructure lesions on the classification in AD spectrum disease.Methods: Neuropsychological data and diffusion tensor imaging (DTI) images were collected from 28 AD subjects, 31 aMCI subjects, and 27 normal controls (NC). Tract-based spatial statistics (TBSS) were used to extract diffusion parameters in WM tracts. We performed ANOVA analysis to compare diffusion parameters and clinical features among the three groups. Partial correlation analysis was used to explore the relationship between diffusion metrics and cognitive functions controlling for age, gender, and years of education. Additionally, we performed the support vector machine (SVM) classification to determine the discriminative ability of DTI metrics in the differentiation of aMCI and AD patients from controls.Results: As compared to controls or aMCI patients, AD patients displayed widespread WM lesions, including in the inferior longitudinal fasciculus, inferior fronto-occipital fasciculi, and superior longitudinal fasciculus. Significant correlations between fractional anisotropy (FA), mean diffusivity (MD), and radial diffusion (RD) of the long longitudinal tract and memory deficits were found in aMCI and AD groups, respectively. Furthermore, through SVM classification, we found DTI indicators generated by FA and MD parameters can effectively distinguish AD patients from the control group with accuracy rates of up to 89 and 85%, respectively.Conclusion: The WM microstructure is extensively disrupted in AD patients, and the WM integrity of the long longitudinal tract is closely related to memory, which would hold potential value for monitoring the progression of AD. The method of classification based on SVM and WM damage features may be objectively helpful to the classification of AD diseases.

White Matter Differences in Networks in Elders with Mild Cognitive Impairment and Alzheimer's Disease.

Background: Alzheimer's disease (AD) is associated with impairment of large-scale brain networks, disruption in structural connections, and functional disconnection between distant brain regions. Although decreased functional connectivity has been thoroughly investigated and reported by existing functional neuroimaging literature, this study investigated network-based differences due to the structural changes in white matter pathways in AD patients. We hypothesize that diffusion metrics of disrupted tracts that go through cognitive networks related with intrinsic awareness, motor movement, and executive control can be utilized as biomarkers to distinguish prodromal stage from AD stage. Methods: Diffusion MRI data of a total 154 subjects, including patients with clinical AD (n = 47) and patients with mild cognitive impairment (MCI) (n = 107) was used. To study structural changes associated with white matter fiber pathways voxel-averaged diffusion metrics and fiber density metrics were calculated. Results: Study revealed that AD patients exhibit disruptions in intrahemispheric tracts and projection fiber tracts as suggested by diffusion indices. Our whole brain analysis revealed that network differences within default mode network (DMN), sensory motor network, and frontoparietal networks are associated with disruption in inferior fronto-occipital fasciculus (IFOF), corticospinal tract, and superior longitudinal fasciculus. Global function revealed by Mini Mental State Examination correlate with those fiber pathways that form reciprocal connections within networks associated with motor movement and executive control. Conclusion: Diffusion metrics appear to be more sensitive than fiber density metrics in differentiating the structural changes in the white matter. Decreased fractional anisotropy along with increased mean diffusivity and radial diffusivity in forceps minor, corticospinal tract, and IFOF as an imaging biomarker would be ideal to distinguish AD patients from MCI patients. Difference of DMN, sensory motor network, and frontal parietal network in our study reveals that AD patients may suffer from poor motor movement and degraded executive control.

Plasma Amyloid Concentration in Alzheimer's Disease: Performance of a High-Throughput Amyloid Assay in Distinguishing Alzheimer's Disease Cases from Controls.

Background:Collection of cerebrospinal fluid (CSF) for measurement of amyloid-β (Aβ) species is a gold standard in Alzheimer’s disease (AD) diagnosis, but has risks. Thus, establishing a low-risk blood Aβ test with high AD sensitivity and specificity is of outmost interest.Objective:We evaluated the ability of a commercially available plasma Aβ assay to distinguish AD patients from biomarker-healthy controls.Method:In a case-control design, we examined plasma samples from 44 AD patients (A + N+) and 49 controls (A–N–) from a memory clinic. AD was diagnosed using a combination of neuropsychological examination, CSF biomarker analysis and brain imaging. Total Aβ40 and total Aβ42 in plasma were measured through enzyme-linked immunosorbent assay (ELISA) technology using ABtest40 and ABtest42 test kits (Araclon Biotech Ltd.). Receiver operating characteristic (ROC) analyses with outcome AD were performed, and sensitivity and specificity were calculated.Results:Plasma Aβ42/40 was weakly positively correlated with CSF Aβ42/40 (Spearman’s rho 0.22; p = 0.037). Plasma Aβ42/40 alone was not able to statistically significantly distinguish between AD patients and controls (AUC 0.58; 95% CI 0.46, 0.70). At a cut-point of 0.076 maximizing sensitivity and specificity, plasma Aβ42/40 had a sensitivity of 61.2% and a specificity of 63.6%.Conclusion:In this sample, the high-throughput blood Aβ assay was not able to distinguish well between AD patients and controls. Whether or not the assay may be useful in large-scale epidemiological settings remains to be seen.

Independent and reproducible hippocampal radiomic biomarkers for multisite Alzheimer’s disease: diagnosis, longitudinal progress and biological basis

Hippocampal morphological change is one of the main hallmarks of Alzheimer's disease (AD). However, whether hippocampal radiomic features are robust as predictors of progression from mild cognitive impairment (MCI) to AD dementia and whether these features provide any neurobiological foundation remains unclear. The primary aim of this study was to verify whether hippocampal radiomic features can serve as robust magnetic resonance imaging (MRI) markers for AD. Multivariate classifier-based support vector machine (SVM) analysis provided individual-level predictions for distinguishing AD patients (n = 261) from normal controls (NCs; n = 231) with an accuracy of 88.21% and intersite cross-validation. Further analyses of a large, independent the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset (n = 1228) reinforced these findings. In MCI groups, a systemic analysis demonstrated that the identified features were significantly associated with clinical features (e.g., apolipoprotein E (APOE) genotype, polygenic risk scores, cerebrospinal fluid (CSF) Aβ, CSF Tau), and longitudinal changes in cognition ability; more importantly, the radiomic features had a consistently altered pattern with changes in the MMSE scores over 5 years of follow-up. These comprehensive results suggest that hippocampal radiomic features can serve as robust biomarkers for clinical application in AD/MCI, and further provide evidence for predicting whether an MCI subject would convert to AD based on the radiomics of the hippocampus. The results of this study are expected to have a substantial impact on the early diagnosis of AD/MCI.

Detecting Alzheimer's Disease from Continuous Speech Using Language Models.

Recently, many studies have been carried out to detect Alzheimer's disease (AD) from continuous speech by linguistic analysis and modeling. However, few of them utilize language models (LMs) to extract linguistic features and to investigate the lexical-level differences between AD and healthy speech. Our goals include obtaining state-of-art performance of automatic AD detection, emphasizing N-gram LMs as powerful tools for distinguishing AD patients' narratives from those of healthy controls, and discovering the differences of lexical usages between AD patients and healthy people. We utilize a subset of the DementiaBank corpus, including 242 control samples from 99 control participants and 256 AD samples from 169 "PossibleAD" or "ProbableAD" participants. Baseline models are built through area under curve-based feature selection and using five machine learning algorithms for comparison. Perplexity features are extracted using LMs to build enhanced detection models. Finally, the differences of lexical usages between AD patients and healthy people are investigated by a proportion test based on unigram probabilities. Our baseline model obtains a detection accuracy of 80.7%. This accuracy increases to 85.4% after integrating the perplexity features derived from LMs. Further investigations show that AD patients tend to use more general, less informative, and less accurate words to describe characters and actions than healthy controls. The perplexity features extracted by LMs can benefit the automatic AD detection from continuous speech. There exist lexical-level differences between AD and healthy speech that can be captured by statistical N-gram LMs.

A metabolomic approach to identifying biomarkers in blood of Alzheimer's disease

ObjectiveThis study aims to identify metabolites with altered levels of expression in patients with early and progressive stages of Alzheimer's disease (AD).MethodsAll participants of the study underwent genetic screening and were diagnosed using both neuropsychological assessment and amyloid imaging before metabolome analysis. According to these assessments, the patients were classified as normal (n = 15), with mild cognitive impairment (n = 10), and with AD (n = 15).ResultsUsing a targeted metabolomic approach, we found that plasma levels of C3, C5, and C5‐DC acylcarnitines, arginine, phenylalanine, creatinine, symmetric dimethylarginine (SDMA) and phosphatidylcholine ae C38:2 were significantly altered in patients with early and progressive stages of AD. We created a predictive model based on the decision tree that included three main parameters: age, arginine and C5 plasma concentrations. The model distinguished AD patients from other participants with 60% sensitivity and 86.7% specificity. For healthy controls, the sensitivity was 85.7% and specificity was 61.5%. Multivariate ROC analysis to develop a decision tree showed that our model reached moderate diagnostic power in differentiating between older adults who are cognitively normal (AUC = 0.77) and those with AD (AUC = 0.72).InterpretationThe plasma levels of arginine and valeryl carnitine, together with subject age, are promising as biomarkers for the diagnosis of AD in older adults.

Diagnostic manifestations of total hemispheric glucose metabolism ratio in neuronal network diaschisis: diagnostic implications in Alzheimer's disease and mild cognitive impairment.

We tested the hypothesis that lateralized hemispheric glucose metabolism may have diagnostic implications in Alzheimer's disease (AD) and mild cognitive impairment (MCI). We performed FDG-PET/CT in 23 patients (mean age 63.7 years, range 50-78, 17 females) diagnosed with AD (n = 15) or MCI (n = 8) during a six-month period in 2014. Ten neurologically healthy individuals (HIs) (mean age 62.5 years, range 43-75, 5 females) served as controls. A neuroimaging expert provided visual assessment of diaschisis. The total hemispheric glucose metabolism ratio (THGr) was calculated, and with area-under the curve of receiver operating characteristics (AUC-ROC) we generated a "Network Diaschisis Test (NDT)". The qualitative detection of cerebral (Ce) and cerebellar (Cb) diaschisis was 7/15 (47%), 0/8 (0%), and 0/10 (0%) in AD, MCI, and HI groups, respectively. Median cerebral THGr was 0.68 (range 0.43-0.99), 0.86 (range 0.64-0.98), and 0.95 (range 0.65-1.00) for AD, MCI, and HI groups, respectively (p =0.04). Median cerebellar THGr was, respectively, 0.70 (range 0.18-0.98), 0.70 (range 0.48-0.81), and 0.84 (range 0.75-0.96) (p = 0.0138). A positive NDT yielded a positive predictive value of 100% for the presence of AD or MCI and a 86% negative predictive value for healthy brain. Moreover, the diagnostic manifestation of THGr between MCI and AD led to a positive predictive value of 100% for AD, but a negative predictive value of 42.9% for MCI. Patients with AD or MCI had more pronounced diaschisis, lateralized hemispheric glucose metabolism and lower THGr compared to healthy controls. The NDT distinguished AD and MCI patients from HIs, and AD from MCI patients with a high positive predictive value and moderate and low negative predictive values. THGr can be a straightforward source of investigating neuronal network diaschisis in AD and MCI and in other cerebral diseases, across institutions.