Mild Cognitive Impairment Stage Research Articles

Pixel-Level Fusion Approach with Vision Transformer for Early Detection of Alzheimer’s Disease

Alzheimer’s disease (AD) has become a serious hazard to human health in recent years, and proper screening and diagnosis of AD remain a challenge. Multimodal neuroimaging input can help identify AD in the early mild cognitive impairment (EMCI) and late mild cognitive impairment (LMCI) stages from normal cognitive development using magnetic resonance imaging (MRI) and positron emission tomography (PET). MRI provides useful information on brain structural abnormalities, while PET data provide the difference between physiological and pathological changes in brain anatomy. The precision of diagnosing AD can increase when these data are combined. However, they are heterogeneous and appropriate, and an adequate number of features are required for AD classification. This paper proposed a multimodal fusion-based approach that uses a mathematical technique called discrete wavelet transform (DWT) to analyse the data, and the optimisation of this technique is achieved through transfer learning using a pre-trained neural network called VGG16. The final fused image is reconstructed using inverse discrete wavelet transform (IDWT). The fused images are classified using a pre-trained vision transformer. The evaluation of the benchmark Alzheimer’s disease neuroimaging initiative (ADNI) dataset shows an accuracy of 81.25% for AD/EMCI and AD/LMCI in MRI test data, as well as 93.75% for AD/EMCI and AD/LMCI in PET test data. The proposed model performed better than existing studies when tested on PET data with an accuracy of 93.75%.

Structural and functional differences in the brains of patients with MCI with and without depressive symptoms and their relations with Alzheimer's disease: an MRI study.

The mild cognitive impairment (MCI) stage among elderly individuals is very complex, and the level of diagnostic accuracy is far from ideal. Some studies have tried to improve the 'MCI due to Alzheimer's disease (AD)' classification by further stratifying these patients into subgroups. Depression-related symptoms may play an important role in helping to better define the MCI stage in elderly individuals. In this work, we explored functional and structural differences in the brains of patients with nondepressed MCI (nDMCI) and patients with MCI with depressive symptoms (DMCI), and we examined how these groups relate to AD atrophy patterns and cognitive functioning. Sixty-five participants underwent MRI exams and were divided into four groups: cognitively normal, nDMCI, DMCI, and AD. We compared the regional brain volumes, cortical thickness, and white matter microstructure measures using diffusion tensor imaging among groups. Additionally, we evaluated changes in functional connectivity using fMRI data. In comparison to the nDMCI group, the DMCI patients had more pronounced atrophy in the hippocampus and amygdala. Additionally, DMCI patients had asymmetric damage in the limbic-frontal white matter connection. Furthermore, two medial posterior regions, the isthmus of cingulate gyrus and especially the lingual gyrus, had high importance in the structural and functional differentiation between the two groups. It is possible to differentiate nDMCI from DMCI patients using MRI techniques, which may contribute to a better characterization of subtypes of the MCI stage.

Lecanemab: First Approval.

Lecanemab (lecanemab-irmb; LEQEMBI™) is a humanized immunoglobulin gamma 1 (IgG1) against aggregated soluble and insoluble forms of amyloid-β peptide. It is being developed by Eisai, under a global licence from BioArctic (formerly BioArctic Neuroscience), and in collaboration with Biogen, for the treatment of Alzheimer's disease, and received its first approval for this indication on 6January 2023 in the USA under the Accelerated Approval Pathway. According to the US prescribing information, treatment should be initiated in patients with mild cognitive impairment or mild dementia stage of disease, and a confirmed presence of amyloid beta pathology (i.e. the population in which treatment was initiated in clinical trials). There are no effectiveness or safety data on initiating treatment at earlier or later stages of the disease than were studied. Lecanemab is undergoing regulatory review in the EU, Japan and China, with clinical development underway in several other countries worldwide. This article summarizes the milestones in the development of lecanemab leading to this first approval for the treatment of Alzheimer's disease.

Preliminary Validation Study of the French-Quebec Version of the Mild Behavioral Impairment Checklist.

Alzheimer disease dementia may be preceded by cognitive stages during which behavioral and psychological changes can occur. More precisely, behavioral symptoms may be observed during the subjective cognitive decline (SCD) or the mild cognitive impairment (MCI) stages; these symptoms can be measured using the Mild Behavioral Impairment Checklist (MBI-C). To validate the French-Quebec version of the MBI-C in individuals ages 60-85 years. The sample included 60 participants (20 MCI, 20 SCD, 20 cognitively healthy) and their informants. To assess the discriminant validity of the MBI-C, a Kruskal-Wallis analysis with a multiple comparisons test was performed on the MBI-C Total score. To determine convergent validity, Spearman correlations were calculated between the MBI-C subscales and a set of validation tools. Finally, test-retest reliability was assessed with Spearman correlations of MBI-C scores between two test sessions. All of the analyses indicated satisfactory psychometric properties for the French-Quebec version of the MBI-C. This validation study reveals that the MBI-C can be used successfully in dementia risk assessments. From now on, the use of a validated MBI-C will be possible in the French-Quebec population.

From attention-deficit hyperactivity disorder to sporadic Alzheimer's disease-Wnt/mTOR pathways hypothesis.

Alzheimer's disease (AD) is the most common neurodegenerative disorder with the majority of patients classified as sporadic AD (sAD), in which etiopathogenesis remains unresolved. Though sAD is argued to be a polygenic disorder, apolipoprotein E (APOE) ε4, was found three decades ago to pose the strongest genetic risk for sAD. Currently, the only clinically approved disease-modifying drugs for AD are aducanumab (Aduhelm) and lecanemab (Leqembi). All other AD treatment options are purely symptomatic with modest benefits. Similarly, attention-deficit hyperactivity disorder (ADHD), is one of the most common neurodevelopmental mental disorders in children and adolescents, acknowledged to persist in adulthood in over 60% of the patients. Moreover, for ADHD whose etiopathogenesis is not completely understood, a large proportion of patients respond well to treatment (first-line psychostimulants, e.g., methylphenidate/MPH), however, no disease-modifying therapy exists. Interestingly, cognitive impairments, executive, and memory deficits seem to be common in ADHD, but also in early stages of mild cognitive impairment (MCI), and dementia, including sAD. Therefore, one of many hypotheses is that ADHD and sAD might have similar origins or that they intercalate with one another, as shown recently that ADHD may be considered a risk factor for sAD. Intriguingly, several overlaps have been shown between the two disorders, e.g., inflammatory activation, oxidative stress, glucose and insulin pathways, wingless-INT/mammalian target of rapamycin (Wnt/mTOR) signaling, and altered lipid metabolism. Indeed, Wnt/mTOR activities were found to be modified by MPH in several ADHD studies. Wnt/mTOR was also found to play a role in sAD and in animal models of the disorder. Moreover, MPH treatment in the MCI phase was shown to be successful for apathy including some improvement in cognition, according to a recent meta-analysis. In several AD animal models, ADHD-like behavioral phenotypes have been observed indicating a possible interconnection between ADHD and AD. In this concept paper, we will discuss the various evidence in human and animal models supporting the hypothesis in which ADHD might increase the risk for sAD, with common involvement of the Wnt/mTOR-pathway leading to lifespan alteration at the neuronal levels.

Literature review on the interdisciplinary biomarkers of multi-target and multi-time herbal medicine therapy to modulate peripheral systems in cognitive impairment.

Alzheimer's disease (AD) is a chronic progressive neurodegenerative disease characterized by the deposition of amyloid-beta (Aβ) peptide and neurofibrillary tangles in the brain. The approved drug for AD has certain limitations such as a short period of cognitive improvement effect; moreover, the development of drug for AD therapeutic single target for Aβ clearance in brain ended in failure. Therefore, diagnosis and treatment of AD using a multi-target strategy according to the modulation of the peripheral system, which is not only limited to the brain, is needed. Traditional herbal medicines can be beneficial for AD based on a holistic theory and personalized treatment according to the time-order progression of AD. This literature review aimed to investigate the effectiveness of herbal medicine therapy based on syndrome differentiation, a unique theory of traditional diagnosis based on the holistic system, for multi-target and multi-time treatment of mild cognitive impairment or AD stage. Possible interdisciplinary biomarkers including transcriptomic and neuroimaging studies by herbal medicine therapy for AD were investigated. In addition, the mechanism by which herbal medicines affect the central nervous system in connection with the peripheral system in an animal model of cognitive impairment was reviewed. Herbal medicine may be a promising therapy for the prevention and treatment of AD through a multi-target and multi-time strategy. This review would contribute to the development of interdisciplinary biomarkers and understanding of the mechanisms of action of herbal medicine in AD.

Clinical and Economic Assessment in Early-Stage Dementia by Severity and Amyloid-β Status: A 5-Year Retrospective Claims Study of GERAS-US Patients.

The high burden of dementia and Alzheimer's disease (AD) increases substantially as disease progresses. Characterizing early patterns of health care utilization among patients who develop cognitive impairment may deepen our understanding of early disease trajectory and potentially facilitate timely diagnosis and management. Describe clinical characteristics, healthcare utilization, and costs in early-stage dementia by disease severity and amyloid-β status before enrollment in an observational study (GERAS-US). Consented patients' GERAS-US data were linked to available five-years of Medicare claims history before GERAS-US enrollment. Clinical characteristics, comorbidity, and pre-/post-diagnosis healthcare use and costs were assessed. Continuous and categorical variables were compared between severity and amyloid-status cohorts using t-test and Chi-square statistics; linear regression models were used to compare cost and utilization measures after adjusting for differences in patients' observation time. Relative likelihood of observed diagnoses, comorbidity, and prescription drug use among cohorts were presented as OR and 90% confidence interval (CI). Of 174 patients clinically diagnosed with early dementia (mild cognitive impairment (MCI): 101; mild dementia (MILD): 73), 55% were amyloid-positive. Memory loss was more likely in MILD versus MCI (OR:1.85, 90% CI 1.10-3.09) and in amyloid-positive versus amyloid-negative cohorts (OR:1.98, 90% CI 1.19-3.29). Mean annual healthcare costs after cognitive impairment/dementia diagnosis were significantly higher for MILD versus MCI ($1191 versus $712, p = 0.067) and amyloid-negative versus amyloid-positive ($1281 versus $701, p = 0.034). Diabetes was more prevalent in MILD and amyloid-negative cohorts. Comorbidity and economic burden increased in earliest stages of MCI and MILD and were higher in patients who were amyloid-negative.

Hybridized Deep Learning Approach for Detecting Alzheimer's Disease.

Alzheimer's disease (AD) is mainly a neurodegenerative sickness. The primary characteristics are neuronal atrophy, amyloid deposition, and cognitive, behavioral, and psychiatric disorders. Numerous machine learning (ML) algorithms have been investigated and applied to AD identification over the past decades, emphasizing the subtle prodromal stage of mild cognitive impairment (MCI) to assess critical features that distinguish the disease's early manifestation and instruction for early detection and treatment. Identifying early MCI (EMCI) remains challenging due to the difficulty in distinguishing patients with cognitive normality from those with MCI. As a result, most classification algorithms for these two groups perform poorly. This paper proposes a hybrid Deep Learning Approach for the early detection of Alzheimer's disease. A method for early AD detection using multimodal imaging and Convolutional Neural Network with the Long Short-term memory algorithm combines magnetic resonance imaging (MRI), positron emission tomography (PET), and standard neuropsychological test scores. The proposed methodology updates the learning weights, and Adam's optimization is used to increase accuracy. The system has an unparalleled accuracy of 98.5% in classifying cognitively normal controls from EMCI. These results imply that deep neural networks may be trained to automatically discover imaging biomarkers indicative of AD and use them to identify the illness accurately.

Validation of the cross-cultural dementia screening test in Alzheimer's disease and Parkinson's disease.

The Cross-Cultural Dementia (CCD) is a new screening tool to evaluate cognitive impairment based on a cross-cultural perspective to reduce the bias of education, and language and cultural differences. We aimed to evaluate the diagnostic properties of the CCD in Spaniards for the assessment of patients with Alzheimer's disease in mild cognitive impairment (AD-MCI) and mild dementia stages (AD-D) and patients with mild cognitive impairment associated with Parkinson's disease (PD-MCI). Sixty participants with AD (50% MCI) and thirty with PD-MCI were enrolled. Each clinical group was compared against a healthy control group (HC) with the same number of participants and no significant differences in age, education, and sex. A comprehensive neuropsychological test battery and CCD were completed. Intergroup comparisons, ROC curves, and cut-off scores were calculated for the study of diagnostic properties. Intergroup differences were found in accordance with the cognitive profile of each clinical condition. Memory measures (Objects test) were especially relevant for the classification between AD and HC. Memory and executive function scores (Sun-Moon and Dots tests) were useful in the case of PD-MCI and HC. Furthermore, CCD described differences in executive functions and speed scores comparing AD-MCI and PD-MCI. Correlations between standardized neuropsychological tests and CCD measures supported the convergent validity of the test. CCD showed good discrimination properties and cut-off scores for dementia and extended its application to a sample of prodromal stages of AD and PD with mild cognitive impairment.

CD34+ progenitor cells as diagnostic and therapeutic targets in Alzheimer's disease.

CD34+ progenitor cells as diagnostic and therapeutic targets in Alzheimer's disease.

Deep Learning-Based Ensembling Technique to Classify Alzheimer's Disease Stages Using Functional MRI.

The major issue faced by elderly people in society is the loss of memory, difficulty learning new things, and poor judgment. This is due to damage to brain tissues, which may lead to cognitive impairment and eventually Alzheimer's. Therefore, the detection of such mild cognitive impairment (MCI) becomes important. Usually, this is detected when it is converted into Alzheimer's disease (AD). AD is irreversible and cannot be cured whereas mild cognitive impairment (MCI) can be cured. The goal of this research is to diagnose Alzheimer's patients for timely treatment. For this purpose, functional MRI images from the publicly available dataset are used. Various deep-learning models have been used by the scientific community for the automatic detection of Alzheimer's subjects. These include the binary classification of scans of patients into MCI and AD stages, and limited work is carried out for multiclass classification of Alzheimer's disease up to six different stages. This study is divided into two steps. In the first step, a binary classification of the subject's scan is performed using Custom CNN. The second step involves the use of different deep learning models along with Custom CNN for multiclass classification of a subject's scan into one of the six stages of Alzheimer's disease. The models are evaluated based on different evaluation metrics, and the overall result of the models is improved using the max-voting ensembling technique. The experimental results show that an overall average accuracy of 98.8% is achieved for Alzheimer's stages classification.

Can basic magnetic resonance imaging along with neuropsychological assessment be used as a cost-effective means for the detection of early dementia in the Indian sub-continent?

ABSTRACT Introduction: The mild cognitive impairment (MCI) stage occurs sporadically between healthy aging and the onset of Alzheimer’s disease (AD). MCI shows significant defacement in magnetic resonance imaging (MRI) of the brain along with neuropsychological and behavioral parameters. Aim: Assessment of neuropsychological, behavioral, and structural MRI changes in MCI and their relation with each other. Methodology: Seventy-eight participants in the MCI group and healthy controls (HC) were assessed using Addenbrooke’s Cognitive Examination (ACE), Mini-Mental Status Examination (MMSE), Clinical Dementia Rating Scale (CDR); and behavioral assessment by using Behavioral Pathology In AD (BEHAVE-AD). MRI brain volumetric analysis was performed using the software MYRIAN. Statistical analysis was performed using the Mann–Whitney U test, unpaired t-test (P = <0.05), and Spearman’s rank correlation. Results: MCI group showed significant impairments in ACE, MMSE, and CDR and significantly higher behavioral symptoms on BEHAVE-AD. Episodic memory had a significant positive correlation with normalized right hippocampal volume and total intracranial volume (TICV). Remote memory had a significant negative correlation with normalized left hippocampal volumes. Global CDR score had a moderately negative correlation with normalized right and left hippocampal volumes. Affective disturbances were negatively correlated with TICV. Conclusions: Comparable analysis of correctly scaled neuropsychological assessments may provide unbiased proxies for MRI-based measures of dementia risk.

Computational Models for Biomarker Discovery.

Alzheimer's disease (AD) is a prevalent and debilitating neurodegenerative disorder characterized by progressive cognitive decline. Early diagnosis and accurate prediction of disease progression are critical for developing effective therapeutic interventions. In recent years, computational models have emerged as powerful tools for biomarker discovery and disease prediction in Alzheimer's and other neurodegenerative diseases. This paper explores the use of computational models, particularly machine learning techniques, in analyzing large volumes of data and identifying patterns related to disease progression. The significance of early diagnosis, the challenges in classifying patients at the mild cognitive impairment (MCI) stage, and the potential of computational models to improve diagnostic accuracy are examined. Furthermore, the importance of incorporating diverse biomarkers, including genetic, molecular, and neuroimaging indicators, to enhance the predictive capabilities of these models is highlighted. The paper also presents case studies on the application of computational models in simulating disease progression, analyzing neurodegenerative cascades, and predicting the future development of Alzheimer's. Overall, computational models for biomarker discovery offer promising opportunities to advance our understanding of Alzheimer's disease, facilitate early diagnosis, and guide the development of targeted therapeutic strategies.

Forecasting the Prevalence of Alzheimer's Disease at Mild Cognitive Impairment and Mild Dementia Stages in France in 2022.

Given the evolution of early diagnosis guidelines and future disease-modifying therapies, estimating the prevalence of Alzheimer's disease (AD) at early stages is key. To estimate the number of people living with mild cognitive impairment (MCI) due to AD and mild AD dementia in France in 2022 that could be eligible to future AD therapies. A step-by-step approach was defined based on disease stages definition and clinical practice. In line with AD guidelines, amyloid-positive profile is considered in our estimates to enhance the diagnosis accuracy of early stages of AD. Age-stratified prevalence from French cohort and international pooled analyses were identified to feed the different steps. To consider uncertainty around mean prevalence values, low and high scenarii based on the lower and upper bounds of the 95% confidence interval were conducted. We estimated that 2.5 (low scenario: 1.7 - high scenario: 3.6) million people suffer from mild cognitive impairment in France in 2022 among whom 1.65 (low: 1.5 - high: 1.8) million people meet the criteria for mild cognitive impairment due to AD i.e., with amyloid positive profile. The expected number of clinical AD dementia is estimated at 925,886 people. Among those, 379,278 people suffer from mild AD dementia based on clinical diagnosis, including 311,043 (low: 289,174 - high: 328,332) cases with amyloid positive profile. MCI due to AD, and mild dementia stages are potentially of high prevalence. Population-based studies are needed to confirm those estimates.

EVERYDAY FUNCTION PROFILES IN PRODROMAL STAGES OF MOTORIC COGNITIVE RISK SYNDROME: A PROSPECTIVE COHORT STUDY

Abstract Assessment of everyday function is crucial to diagnosing pre-dementia and dementia syndromes in older individuals. Prodromal stages of mild cognitive impairment (MCI) are associated with mild limitations in complex activities of daily living. It is unknown whether such limitations exist in the prodromal period before criteria is met for motoric cognitive risk syndrome (MCR), a pre-dementia syndrome defined by subjective cognitive complaints and slow gait speed. We compared complex everyday functional profiles at baseline in 46 community-dwelling older individuals (aged 65+) with normal cognitive performance at baseline who went on to develop incident MCR (‘pre-MCR’) with 265 older individuals who remained cognitively normal over follow-up. Patients diagnosed with MCI and global cognitive function scores more than 1.5 standard deviations below the mean at baseline were excluded. The mean number of limitations on complex everyday function at baseline was 3.52±3.1 in the pre-MCR cases and 1.78±2.2 in the 265 normal controls (OR 1.28; 95% CI 1.14–1.43). After adjusting for demographic factors, comorbidities, and follow-up time, the overall number of limitations remained significantly higher in the pre-MCR participants compared to the normal participants (OR 1.18; 95% CI 1.02–1.37). Of the limitations, difficulty completing hobbies and handling finances were associated with pre-MCR after adjustments. Limitations on complex everyday functions in individuals occur before they meet criteria for incident MCR on longitudinal follow-up. Such limitations over time will help clinicians identify individuals at-risk for dementia early in clinical practice.

Development of a Gastrointestinal-Myoelectrical-Activity-Based Nomogram Model for Predicting the Risk of Mild Cognitive Impairment.

Mild cognitive impairment (MCI) is the prodromal stage and an important risk factor of Alzheimer's disease (AD). Interventions at the MCI stage are significant in reducing the occurrence of AD. However, there are still many obstacles to the screening of MCI, resulting in a large number of patients going undetected. Given the strong correlation between gastrointestinal function and neuropsychiatric disorders, the aim of this study is to develop a risk prediction model for MCI based on gastrointestinal myoelectrical activity. The Mini-Mental State Examination and electrogastroenterography were applied to 886 participants in western China. All participants were randomly assigned to the training and validation sets in a ratio of 7:3. In the training set, risk variables were screened using LASSO regression and logistic regression, and risk prediction models were built based on nomogram and decision curve analysis, then validation was performed. Eight predictors were selected in the training set, including four electrogastroenterography parameters (rhythm disturbance, dominant frequency and dominant power ratio of gastric channel after meal, and time difference of intestinal channel after meal). The area under the ROC curve for the prediction model was 0.74 in the training set and 0.75 in the validation set, both of which exhibited great prediction ability. Furthermore, decision curve analysis displayed that the net benefit was more desirable when the risk thresholds ranged from 15% to 35%, indicating that the nomogram was clinically usable. The model based on gastrointestinal myoelectrical activity has great significance in predicting the risk of MCI and is expected to be an alternative to scales assessment.

MRI norm percentile in age‐related atrophy starts from MCI stage

AbstractBackgroundAge related atrophy occurs in Alzheimer’s disease and related dementia (ADRD). Although atrophy was reported in early stage as mild cognitive impairment (MCI), the knowledge about earlier changes is limited. To fill this knowledge, we explored the age‐related atrophy in our pilot MRI database when participants at different stages of ADRD.MethodMRI data are analyzed using NeuroQuant. We studied MRI data in cognitively healthy (CH, n=74) individuals when their cerebrospinal fluid (CSF) amyloid/tau ratios were normal (CH‐NATs, n=18) or pathological (CH‐PATs, n=41), in participants with impaired or MCI (n=9), and Alzheimer’s disease (AD, n=6), and other dementia (OD, n=6). We explored age, gender‐corrected norm percentiles for atrophy analysis in age‐related structures – (including hippocampal occupancy score (HOC, percent of hippocampi volume relative to inferior lateral ventricle volume), hippocampi, entorhinal cortex, and inferior lateral ventricles) and whole brain, cerebral white matter. We compared the data between CH, MCI, AD, and OD, compared between CH‐NATs and CH‐PATs, and compared between CH with cerebrospinal fluid (CSF) amyloid pathology (ChA+, n=15) and CH without CSF pathology (ChA‐T‐N‐, n=13) based on CSF Aβ42, phosphor‐tau (p‐tau), and total tau (t‐tau). Bonferroni correction was used for Multiple comparisons.ResultAnalysis of MRIs collected at HMRI show neuro‐quantitative data in CH participants compared to MCI, AD, or OD, and MCI to AD and OD. Compared to CH, MCI have decreased HOC and larger superior lateral ventricle (Table 1, Figure 1), AD have decreased HOC, hippocampi, whole brain, and cerebral white matter, and larger lateral ventricles, OD have similar changes except hippocampi (no change). No significant changes observed between MCI and AD or OD. No significant changes were observed between CH‐NATs and CH‐PATs, or between ChA+ and ChA‐T‐N‐.ConclusionDespite sample size limitation, these results suggest: 1) norm percentile is sensitive to age‐related atrophy at impaired stages, consistent with known changes; Whole brain volume decreases in AD and OD, only AD observed decreased hippocampal atrophy; 2) No apparent age‐related changes were observed in CH stage. Overall, MRI age‐ and gender‐corrected norm percentile for age‐related atrophy analysis is informative in individuals as early as MCI stage.

Cerebrospinal Fluid Lactate Levels along the Alzheimer’s Disease Continuum and Associations with Blood‐Brain Barrier Integrity, Age, Cognition and Biomarkers

AbstractBackgroundCerebrospinal fluid (CSF) lactate levels have been suggested to be associated with disease severity and progression in several neurological diseases as an indicator of impaired energy metabolism, neuronal death or microglial activation. A small number of studies have examined CSF lactate levels in dementia due to Alzheimer’s disease (AD) and found higher values in AD patients compared to healthy controls (HC). However, these studies were mostly small in size, the inclusion criteria were not always well defined, and the diagnostic value and pathophysiological significance of CSF lactate in AD remains unclear.MethodsWe examined CSF lactate levels and potentially associated factors in a large (n=312), biologically and clinically well‐defined sample of patients with AD at the stage of mild cognitive impairment (MCI‐AD) and dementia (ADD), HC, and patients with frontotemporal lobar degeneration (FTLD).ResultsContrary to previous studies, patients with ADD and HC did not differ in CSF lactate levels. However, we found higher values for patients with MCI‐AD compared to those with ADD and to HC in univariate analysis, as well as for MCI‐AD compared to ADD when controlling for age and blood‐brain barrier integrity. CSF lactate levels were associated with age and blood‐brain barrier integrity but not with clinical severity or CSF biomarkers of AD.ConclusionCSF lactate does not indicate biological or clinical disease severity in AD, nor does it differentiate between patients with AD and healthy controls or patients with FTLD. However, higher CSF lactate levels were found in earlier stages of AD, which might be interpreted in the context of inflammatory processes.

What are the most important prognosticators of Alzheimer's disease progression? – Answers from machine learning

AbstractBackgroundNumerous variables that influence the risk of decline in Alzheimer’s disease (AD) have been identified. Previous studies have only examined a relatively small number of these variables. To our knowledge, no study has compared all variables in a large dataset to determine which are the most important.We hypothesised that the most important variables are neuropsychological assessment (NPA) scores and neuroimaging findings; moreover, the prognostic value of all variables will vary with disease stage: normal control (NC), mild cognitive impairment (MCI) or dementia. Secondly, we hypothesised that non‐NPA variables, such as imaging, cerebrospinal fluid (CSF) and genetics, will add prognostic value to that provided by NPA variables alone.MethodWe analysed all relevant variables in the Alzheimer’s Disease Neuroimaging Initiative database – the largest open‐access dataset of subjects with or at risk of AD. With machine learning, we identified those variables which are the strongest predictors of the annual rate of change in up to the first 10 years of Alzheimer’s Disease Assessment Scale – Cognitive Subscale, 13‐item version (ADAS‐Cog13) and Clinical Dementia Rating, Sum of Boxes (CDR‐SB) scores. We repeated this analysis for each disease stage subgroup. Secondly, we compared models that only used NPA‐related variables (NPA‐only) with those that used up to 2 non‐NPA modalities (NPA‐plus) and contrasted the findings between the same subgroups.ResultAcross all subjects, the strongest predictors of the rate of change of both ADAS‐Cog13 and CDR‐SB scores are CSF total tau and amyloid levels, fluorodeoxyglucose (FDG) positron emission tomography (PET) findings, and certain NPA measures. At the NC and MCI stages, CSF and imaging variables are strong predictors, but only NPA variables remained useful at the dementia stage. Secondly, NPA‐plus models consistently outperformed NPA‐only models. The non‐NPA modalities which added the most predictive power varied based on a subject’s disease stage in a manner similar to the previous findings.ConclusionWe identified a multi‐modal set of variables that have the strongest impact on predicting decline during different stages of AD. Our findings are clinically relevant as they recommend the investigations that are of most prognostic yield for clinicians to undertake at each stage of AD progression.

Towards Fair ML-based Language Assessment Methods for Detecting Alzheimer's Disease.

Alzheimer's disease (AD) tends to affect the parietal lobe, which is responsible for language functions in the patient's brain. Thus, one significant impairment associated with AD is language impairment which is the cause that patients with AD have deficits at the word level (vocabulary size in speech can be an early sign of cognitive impairment [1]), sentence-level, and discourse-level of their languages. Thus, language disorders can be considered as markers to diagnose AD in a patient at its earliest stage [2]. The recent progress in the machine learning (ML) domain has revolutionized the early detection of AD in particular developing and deploying ML-based language assessment (MLLA) methods for detecting AD at its mild cognitive impairment stage [3]. The ML community needs to develop fair MLLA methods for detecting individuals with AD. To develop a fair MLLA first we should consider how we can formulate the fairness for developing a MLLA method and how potential bias in language data can be identified and quantified, how text preprocessing, data augmentation and word embedding techniques can be applied without adding biases to MLLA, how can we identify protected and unprotected linguistic features? and finally how can we protect underserved groups in the deployment process of MLLA methods? We suggest a fair ML pipeline includes 1) preprocessing (i.e., eliminating sources of bias in data collection and data sharing, text augmentation and text preprocessing, defining unknown sensitive features including linguistic diversity, which are highly correlated with sensitive attributes such as races and genders. Note that sensitive attributes can be used to alleviate the bias). 2) In-processing (i.e., adjusting machine learning process, e.g., using a regularization approach). 3) Post-processing (i.e., adjusting trained model). The development of fair MLLA methods is crucial to ensure all groups are treated fairly and there are no results that unfairly harm any subgroups of our population. Using our suggested pipeline, we can foster the confidence of clinical services to use MLLA methods and motivate patients to accept the results.