Predicting Progression from Mild Cognitive Impairment to Alzheimer's Dementia Using Clinical, MRI, and Plasma Biomarkers via Probabilistic Pattern Classification

EEG Functional Connectivity Differences Predict Future Conversion to Dementia in Mild Cognitive Impairment With Lewy Body or Alzheimer Disease

BACKGROUND

Predicting which individuals may convert to dementia from mild cognitive impairment (MCI) remains difficult in clinical practice. Electroencephalography (EEG) is a widely available investigation but there is limited research exploring EEG connectivity differences in patients with MCI who convert to dementia.

METHODS

Participants with a diagnosis of MCI due to Alzheimer's disease (MCI-AD) or Lewy body disease (MCI-LB) underwent resting state EEG recording. They were followed up annually with a review of the clinical diagnosis (n = 66). Participants with a diagnosis of dementia at year 1 or year 2 follow up were classed as converters (n = 23) and those with a diagnosis of MCI at year 2 were classed as stable (n = 43). We used phase lag index (PLI) to estimate functional connectivity as well as analysing dominant frequency (DF) and relative band power. The Network-based statistic (NBS) toolbox was used to assess differences in network topology.

RESULTS

The converting group had reduced DF (U = 285.5, p = 0.005) and increased relative pre-alpha power (U = 702, p = 0.005) consistent with previous findings. PLI showed reduced average beta band synchrony in the converting group (U = 311, p = 0.014) as well as significant differences in alpha and beta network topology. Logistic regression models using regional beta PLI values revealed that right central to right lateral (Sens = 56.5%, Spec = 86.0%, -2LL = 72.48, p = 0.017) and left central to right lateral (Sens = 47.8%, Spec = 81.4%, -2LL = 71.37, p = 0.012) had the best classification accuracy and fit when adjusted for age and MMSE score.

CONCLUSION

Patients with MCI who convert to dementia have significant differences in EEG frequency, average connectivity and network topology prior to the onset of dementia. The MCI group is clinically heterogeneous and have underlying physiological differences that may be driving the progression of cognitive symptoms. EEG connectivity could be useful to predict which patients with MCI-AD and MCI-LB convert to dementia, regardless of the neurodegenerative aetiology.

Multiple Early Biomarkers to Predict Cognitive Decline in Dementia-Free Older Adults

INTRODUCTION

Baseline olfactory impairment, poor performance on cognitive test, and medial temporal lobe atrophy are considered biomarkers for predicting future cognitive decline in dementia-free older adults. However, the combined effect of these predictors has not been fully investigated.

METHODS

A group of 110 participants without dementia were continuously recruited into this study, and underwent olfactory, cognitive tests and MRI scanning at baseline and 5-year follow-up. Olfactory function was assessed using the University of Pennsylvania Smell Identification Test (UPSIT). Participants were divided into the cognitive decliners and non-decliners.

RESULTS

Among 87 participants who completed the 5-year follow-up, cognitive decline was present in 32 cases and 55 remained stable. Compared with non-decliners, cognitive decliners presented lower scores on both the UPSIT and the Montreal Cognitive Assessment (MoCA), and smaller hippocampal volume at baseline (all P < .001). The logistic regression analysis revealed that lower scores on UPSIT and MoCA, and smaller hippocampal volume were strongly associated with subsequent cognitive decline, respectively (all P < .001). For the prediction of cognitive decline, lower score on UPSIT performed the sensitivity of 63.6% and specificity of 81.2%, lower score on MoCA with the sensitivity of 74.5% and specificity of 65.6%, smaller hippocampal volume with the sensitivity of 70.9% and specificity of 78.1%, respectively. Combining three predictors resulted in the sensitivity of 83.6% and specificity of 93.7%.

CONCLUSIONS

The combination of olfactory test, cognitive test with structural MRI may enhance the predictive ability for future cognitive decline for dementia-free older adults.

Mapping Knowledge Landscapes and Emerging Trends in AI for Dementia Biomarkers: Bibliometric and Visualization Analysis

BACKGROUND

With the rise of artificial intelligence (AI) in the field of dementia biomarker research, exploring its current developmental trends and research focuses has become increasingly important. This study, using literature data mining, analyzes and assesses the key contributions and development scale of AI in dementia biomarker research.

OBJECTIVE

The aim of this study was to comprehensively evaluate the current state, hot topics, and future trends of AI in dementia biomarker research globally.

METHODS

This study thoroughly analyzed the literature in the application of AI to dementia biomarkers across various dimensions, such as publication volume, authors, institutions, journals, and countries, based on the Web of Science Core Collection. In addition, scales, trends, and potential connections between AI and biomarkers were extracted and deeply analyzed through multiple expert panels.

RESULTS

To date, the field includes 1070 publications across 362 journals, involving 74 countries and 1793 major research institutions, with a total of 6455 researchers. Notably, 69.41% (994/1432) of the researchers ceased their studies before 2019. The most prevalent algorithms used are support vector machines, random forests, and neural networks. Current research frequently focuses on biomarkers such as imaging biomarkers, cerebrospinal fluid biomarkers, genetic biomarkers, and blood biomarkers. Recent advances have highlighted significant discoveries in biomarkers related to imaging, genetics, and blood, with growth in studies on digital and ophthalmic biomarkers.

CONCLUSIONS

The field is currently in a phase of stable development, receiving widespread attention from numerous countries, institutions, and researchers worldwide. Despite this, stable clusters of collaborative research have yet to be established, and there is a pressing need to enhance interdisciplinary collaboration. Algorithm development has shown prominence, especially the application of support vector machines and neural networks in imaging studies. Looking forward, newly discovered biomarkers are expected to undergo further validation, and new types, such as digital biomarkers, will garner increased research interest and attention.

Development and validation of a patient-level model to predict dementia across a network of observational databases

BACKGROUND

A prediction model can be a useful tool to quantify the risk of a patient developing dementia in the next years and take risk-factor-targeted intervention. Numerous dementia prediction models have been developed, but few have been externally validated, likely limiting their clinical uptake. In our previous work, we had limited success in externally validating some of these existing models due to inadequate reporting. As a result, we are compelled to develop and externally validate novel models to predict dementia in the general population across a network of observational databases. We assess regularization methods to obtain parsimonious models that are of lower complexity and easier to implement.

METHODS

Logistic regression models were developed across a network of five observational databases with electronic health records (EHRs) and claims data to predict 5-year dementia risk in persons aged 55-84. The regularization methods L1 and Broken Adaptive Ridge (BAR) as well as three candidate predictor sets to optimize prediction performance were assessed. The predictor sets include a baseline set using only age and sex, a full set including all available candidate predictors, and a phenotype set which includes a limited number of clinically relevant predictors.

RESULTS

BAR can be used for variable selection, outperforming L1 when a parsimonious model is desired. Adding candidate predictors for disease diagnosis and drug exposure generally improves the performance of baseline models using only age and sex. While a model trained on German EHR data saw an increase in AUROC from 0.74 to 0.83 with additional predictors, a model trained on US EHR data showed only minimal improvement from 0.79 to 0.81 AUROC. Nevertheless, the latter model developed using BAR regularization on the clinically relevant predictor set was ultimately chosen as best performing model as it demonstrated more consistent external validation performance and improved calibration.

CONCLUSIONS

We developed and externally validated patient-level models to predict dementia. Our results show that although dementia prediction is highly driven by demographic age, adding predictors based on condition diagnoses and drug exposures further improves prediction performance. BAR regularization outperforms L1 regularization to yield the most parsimonious yet still well-performing prediction model for dementia.

Predictive models of Alzheimer's disease dementia risk in older adults with mild cognitive impairment: a systematic review and critical appraisal

BACKGROUND

Mild cognitive impairment has received widespread attention as a high-risk population for Alzheimer's disease, and many studies have developed or validated predictive models to assess it. However, the performance of the model development remains unknown.

OBJECTIVE

The objective of this review was to provide an overview of prediction models for the risk of Alzheimer's disease dementia in older adults with mild cognitive impairment.

METHOD

PubMed, EMBASE, Web of Science, and MEDLINE were systematically searched up to October 19, 2023. We included cohort studies in which risk prediction models for Alzheimer's disease dementia in older adults with mild cognitive impairment were developed or validated. The Predictive Model Risk of Bias Assessment Tool (PROBAST) was employed to assess model bias and applicability. Random-effects models combined model AUCs and calculated (approximate) 95% prediction intervals for estimations. Heterogeneity across studies was evaluated using the I2 statistic, and subgroup analyses were conducted to investigate sources of heterogeneity. Additionally, funnel plot analysis was utilized to identify publication bias.

RESULTS

The analysis included 16 studies involving 9290 participants. Frequency analysis of predictors showed that 14 appeared at least twice and more, with age, functional activities questionnaire, and Mini-mental State Examination scores of cognitive functioning being the most common predictors. From the studies, only two models were externally validated. Eleven studies ultimately used machine learning, and four used traditional modelling methods. However, we found that in many of the studies, there were problems with insufficient sample sizes, missing important methodological information, lack of model presentation, and all of the models were rated as having a high or unclear risk of bias. The average AUC of the 15 best-developed predictive models was 0.87 (95% CI: 0.83, 0.90).

DISCUSSION

Most published predictive modelling studies are deficient in rigour, resulting in a high risk of bias. Upcoming research should concentrate on enhancing methodological rigour and conducting external validation of models predicting Alzheimer's disease dementia. We also emphasize the importance of following the scientific method and transparent reporting to improve the accuracy, generalizability and reproducibility of study results.

REGISTRATION

This systematic review was registered in PROSPERO (Registration ID: CRD42023468780).

Paired plasma lipidomics and proteomics analysis in the conversion from mild cognitive impairment to Alzheimer's disease

BACKGROUND

Alzheimer's disease (AD) is a neurodegenerative condition for which there is currently no available medication that can stop its progression. Previous studies suggest that mild cognitive impairment (MCI) is a phase that precedes the disease. Therefore, a better understanding of the molecular mechanisms behind MCI conversion to AD is needed.

METHOD

Here, we propose a machine learning-based approach to detect the key metabolites and proteins involved in MCI progression to AD using data from the European Medical Information Framework for Alzheimer's Disease Multimodal Biomarker Discovery Study. Proteins and metabolites were evaluated separately in multiclass models (controls, MCI and AD) and together in MCI conversion models (MCI stable vs converter). Only features selected as relevant by 3/4 algorithms proposed were kept for downstream analysis.

RESULTS

Multiclass models of metabolites highlighted nine features further validated in an independent cohort (0.726 mean balanced accuracy). Among these features, one metabolite, oleamide, was selected by all the algorithms. Further in-vitro experiments in rodents showed that disease-associated microglia excreted oleamide in vesicles. Multiclass models of proteins stood out with nine features, validated in an independent cohort (0.720 mean balanced accuracy). However, none of the proteins was selected by all the algorithms. Besides, to distinguish between MCI stable and converters, 14 key features were selected (0.872 AUC), including tTau, alpha-synuclein (SNCA), junctophilin-3 (JPH3), properdin (CFP) and peptidase inhibitor 15 (PI15) among others.

CONCLUSIONS

This omics integration approach highlighted a set of molecules associated with MCI conversion important in neuronal and glia inflammation pathways.

Advancing the Frontier: Neuroimaging Techniques in the Early Detection and Management of Neurodegenerative Diseases

Alzheimer's and Parkinson's diseases are among the most prevalent neurodegenerative conditions affecting aging populations globally, presenting significant challenges in early diagnosis and management. This narrative review explores the pivotal role of advanced neuroimaging techniques in detecting and managing these diseases at early stages, potentially slowing their progression through timely interventions. Recent advancements in MRI, such as ultra-high-field systems and functional MRI, have enhanced the sensitivity for detecting subtle structural and functional changes. Additionally, the development of novel amyloid-beta tracers and other emerging modalities like optical imaging and transcranial ultrasonography have improved the diagnostic accuracy and capability of existing methods. This review highlights the clinical applications of these technologies in Alzheimer's and Parkinson's diseases, where they have shown improved diagnostic performance, enabling earlier intervention and better prognostic outcomes. Moreover, the integration of artificial intelligence (AI) and longitudinal research is emerging as a promising enhancement to refine early detection strategies further. However, this review also addresses the technical, ethical, and accessibility challenges in the field, advocating for the more extensive use of advanced imaging technologies to overcome these barriers. Finally, we emphasize the need for a holistic approach that incorporates both neurological and psychiatric perspectives, which is crucial for optimizing patient care and outcomes in the management of neurodegenerative diseases.

Prediction of dementia risk from multimodal repeated measures: The added value of brain MRI biomarkers

Abstract

The utility of brain magnetic resonance imaging (MRI) for predicting dementia is debated. We evaluated the added value of repeated brain MRI, including atrophy and cerebral small vessel disease markers, for dementia prediction. We conducted a landmark competing risk analysis in 1716 participants of the French population-based Three-City Study to predict the 5-year risk of dementia using repeated measures of 41 predictors till year 4 of follow-up. Brain MRI markers improved significantly the individual prediction of dementia after accounting for demographics, health measures, and repeated measures of cognition and functional dependency (area under the ROC curve [95% CI] improved from 0.80 [0.79 to 0.82] to 0.83 [0.81 to 0.84]). Nonetheless, accounting for the change over time through repeated MRIs had little impact on predictive abilities. These results highlight the importance of multimodal analysis to evaluate the added predictive abilities of repeated brain MRI for dementia and offer new insights into the predictive performances of various MRI markers.

Highlights

We evaluated whether repeated brain volumes and cSVD markers improve dementia prediction.The 5-year prediction of dementia is slightly improved when considering brain MRI markers.Measures of hippocampus volume are the main MRI predictors of dementia.Adjusted on cognition, repeated MRI has poor added value over single MRI for dementia prediction.We utilized a longitudinal analysis that considers error-and-missing-prone predictors, and competing death.

Genome-wide epistasis analysis reveals gene-gene interaction network on an intermediate endophenotype P-tau/Aβ42 ratio in ADNI cohort

Alzheimer's disease (AD) is a progressive neurodegenerative disorder and the most common cause of dementia in the elderly worldwide. The exact etiology of AD, particularly its genetic mechanisms, remains incompletely understood. Traditional genome-wide association studies (GWAS), which primarily focus on single-nucleotide polymorphisms (SNPs) with main effects, provide limited explanations for the "missing heritability" of AD, while there is growing evidence supporting the important role of epistasis. In this study, we performed a genome-wide SNP-SNP interaction detection using a linear regression model and employed multiple GPUs for parallel computing, significantly enhancing the speed of whole-genome analysis. The cerebrospinal fluid (CSF) phosphorylated tau (P-tau)/amyloid-[Formula: see text] (A[Formula: see text]) ratio was used as a quantitative trait (QT) to enhance statistical power. Age, gender, and clinical diagnosis were included as covariates to control for potential non-genetic factors influencing AD. We identified 961 pairs of statistically significant SNP-SNP interactions, explaining a high-level variance of P-tau/A[Formula: see text] level, all of which exhibited marginal main effects. Additionally, we replicated 432 previously reported AD-related genes and found 11 gene-gene interaction pairs overlapping with the protein-protein interaction (PPI) network. Our findings may contribute to partially explain the "missing heritability" of AD. The identified subnetwork may be associated with synaptic dysfunction, Wnt signaling pathway, oligodendrocytes, inflammation, hippocampus, and neuronal cells.

New horizons in the diagnosis and management of Alzheimer's Disease in older adults

Alzheimer's Disease (ad) is the most common cause of dementia, and in addition to cognitive decline, it directly contributes to physical frailty, falls, incontinence, institutionalisation and polypharmacy in older adults. Increasing availability of clinically validated biomarkers including cerebrospinal fluid and positron emission tomography to assess both amyloid and tau pathology has led to a reconceptualisation of ad as a clinical-biological diagnosis, rather than one based purely on clinical phenotype. However, co-pathology is frequent in older adults which influence the accuracy of biomarker interpretation. Importantly, some older adults with positive amyloid or tau pathological biomarkers may never experience cognitive impairment or dementia. These strides towards achieving an accurate clinical-biological diagnosis are occurring alongside recent positive phase 3 trial results reporting statistically significant effects of anti-amyloid Disease-Modifying Therapies (DMTs) on disease severity in early ad. However, the real-world clinical benefit of these DMTs is not clear and concerns remain regarding how trial results will translate to real-world clinical populations, potential adverse effects (including amyloid-related imaging abnormalities), which can be severe and healthcare systems readiness to afford and deliver potential DMTs to appropriate populations. Here, we review recent advances in both clinical-biological diagnostic classification and future treatment in older adults living with ad. Advocating for access to both more accurate clinical-biological diagnosis and potential DMTs must be done so in a holistic and gerontologically attuned fashion, with geriatricians advocating for enhanced multi-component and multi-disciplinary care for all older adults with ad. This includes those across the ad severity spectrum including older adults potentially ineligible for emerging DMTs.

A Predictive Model of the Progression to Alzheimer's Disease in Patients with Mild Cognitive Impairment Based on the MRI Enlarged Perivascular Spaces

Background

Mild cognitive impairment (MCI) is a heterogeneous condition that can precede various forms of dementia, including Alzheimer's disease (AD). Identifying MCI subjects who are at high risk of progressing to AD is of major clinical relevance. Enlarged perivascular spaces (EPVS) on MRI are linked to cognitive decline, but their predictive value for MCI to AD progression is unclear.

Objective

This study aims to assess the predictive value of EPVS for MCI to AD progression and develop a predictive model combining EPVS grading with clinical and laboratory data to estimate conversion risk.

Methods

We analyzed 358 patients with MCI from the ADNI database, consisting of 177 MCI-AD converters and 181 non-converters. The data collected included demographic information, imaging data (including perivascular spaces grade), clinical assessments, and laboratory test results. Variable selection was conducted using the Least Absolute Shrinkage and Selection Operator (LASSO) method, followed by logistic regression to develop predictive model.

Results

In the univariate logistic regression analysis, both moderate (OR = 5.54, 95% CI [3.04-10.18]) and severe (OR = 25.04, 95% CI [10.07-62.23]) enlargements of the centrum semiovale perivascular space (CSO-PVS) were found to be strong predictors of disease progression. LASSO analyses yielded 12 variables, refined to six in the final model: APOE4 genotype, ADAS11 score, CSO-PVS grade, and volumes of entorhinal, fusiform, and midtemporal regions, with an AUC of 0.956 in the training and 0.912 in the validation cohort.

Conclusions

Our predictive model, emphasizing EPVS assessment, provides clinicians with a practical tool for early detection and management of AD risk in MCI patients.

Estimating Dementia Onset: AT(N) Profiles and Predictive Modeling in Mild Cognitive Impairment Patients

BACKGROUND

Mild Cognitive Impairment (MCI) usually precedes the symptomatic phase of dementia and constitutes a window of opportunities for preventive therapies.

OBJECTIVES

The objective of this study was to predict the time an MCI patient has left to reach dementia and obtain the most likely natural history in the progression of MCI towards dementia.

METHODS

This study was conducted on 633 MCI patients and 145 subjects with dementia through 4726 visits over 15 years from Alzheimer Disease Neuroimaging Initiative (ADNI) cohort. A combination of data from AT(N) profiles at baseline and longitudinal predictive modeling was applied. A data-driven approach was proposed for categorical diagnosis prediction and timeline estimation of cognitive decline progression, which combined supervised and unsupervised learning techniques.

RESULTS

A reduced vector of only neuropsychological measures was selected for training the models. At baseline, this approach had high performance in detecting subjects at high risk of converting from MCI to dementia in the coming years. Furthermore, a Disease Progression Model (DPM) was built and also verified using three metrics. As a result of the DPM focused on the studied population, it was inferred that amyloid pathology (A+) appears about 7 years before dementia, and tau pathology (T+) and neurodegeneration (N+) occur almost simultaneously, between 3 and 4 years before dementia. In addition, MCI-A+ subjects were shown to progress more rapidly to dementia compared to MCI-A- subjects.

CONCLUSION

Based on proposed natural histories and cross-sectional and longitudinal analysis of AD markers, the results indicated that only a single cerebrospinal fluid sample is necessary during the prodromal phase of AD. Prediction from MCI into dementia and its timeline can be achieved exclusively through neuropsychological measures.

[Immunological and neuroanatomic markers of the clinical dynamics of MCI and pre-MCI]

OBJECTIVE

To study the relationship of the parameters of immunity and systemic inflammation with the structural magnetic resonance imaging (MRI) parameters in patients with mild cognitive impairment (MCI) and pre-MCI undergoing neurocognitive rehabilitation to search for candidate markers of its effectiveness.

MATERIAL AND METHODS

The main group included 49 patients, aged ≥60 years, with MCI and pre-MCI with memory impairment, who underwent a course of neurorehabilitation for 5 weeks. The control group included 19 volunteers of similar age with a total MoCA score of ≥25, who did not have cognitive impairment and immuno-inflammatory disorders. The parameters of cellular and humoral immunity and markers of inflammation were studied, and structural MRI was performed.

RESULTS

The content of activated natural killer cells (NK-cells) was increased in MCI and pre-MCI (0.63±0.12% vs. 0.22±0.07% in the control group, p=2.2·10-7). The level of immunoglobulin G (IgG) <12.5 g/l in patients with MCI and pre-MCI with the Montreal Cognitive Assessment Scale (MoCA) score <22 was associated with a decrease in the volume of the right nucleus accumbens (376±35 mm3 in patients with IgG <12.5 g/l (p=0.0013) and 480±44 mm3 at IgG <12.5 g/l, 480±44 mm3 in the control group), as well as with a decrease of the thickness and volume of a number of other cortical zones. A logistic regression model including the level of immunoglobulin G, NK cells, CD8+ NK cells and right amygdala volume was constructed to predict the number of MoCA scores 6 months after the course of rehabilitation (R2=0.57; p<1·10-5; standard error of estimate: 2.93).

CONCLUSION

As a result of this work, the perspectives of assessing the immunological parameters in combination with socio-demographic data and morphometric changes of the brain as potential prognostic markers of the dynamics of cognitive impairment in patients with MCI and pre-MCI after neurorehabilitation has been shown.

Plasma Biomarkers as Predictors of Progression to Dementia in Individuals with Mild Cognitive Impairment

Background

Blood-based biomarkers (BBMs) are of growing interest in the field of Alzheimer's disease (AD) and related dementias.

Objective

This study aimed to assess the ability of plasma biomarkers to 1) predict disease progression from mild cognitive impairment (MCI) to dementia and 2) improve the predictive ability of magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) measures when combined.

Methods

We used data from the Alzheimer's Disease Neuroimaging Initiative. Machine learning models were trained using the data from participants who remained cognitively stable (CN-s) and with Dementia diagnosis at 2-year follow-up visit. The models were used to predict progression to dementia in MCI individuals. We assessed the performance of models with plasma biomarkers against those with CSF and MRI measures, and also in combination with them.

Results

Our models with plasma biomarkers classified CN-s individuals from AD with an AUC of 0.75±0.03 and could predict conversion to dementia in MCI individuals with an AUC of 0.64±0.03 (17.1% BP, base prevalence). Models with plasma biomarkers performed better when combined with CSF and MRI measures (CN versus AD: AUC of 0.89±0.02; MCI-to-AD: AUC of 0.76±0.03, 21.5% BP).

Conclusions

Our results highlight the potential of plasma biomarkers in predicting conversion to dementia in MCI individuals. While plasma biomarkers could improve the predictive ability of CSF and MRI measures when combined, they also show the potential to predict non-progression to AD when considered alone. The predictive ability of plasma biomarkers is crucially linked to reducing the costly and effortful collection of CSF and MRI measures.

Behavioral marker-based predictive modeling of functional status for older adults with subjective cognitive decline and mild cognitive impairment: Study protocol

Objective

This study describes a research protocol for a behavioral marker-based predictive model that examines the functional status of older adults with subjective cognitive decline and mild cognitive impairment.

Methods

A total of 130 older adults aged ≥65 years with subjective cognitive decline or mild cognitive impairment will be recruited from the Dementia Relief Centers or the Community Service Centers. Data on behavioral and psychosocial markers (e.g. physical activity, mobility, sleep/wake patterns, social interaction, and mild behavioral impairment) will be collected using passive wearable actigraphy, in-person questionnaires, and smartphone-based ecological momentary assessments. Two follow-up assessments will be performed at 12 and 24 months after baseline. Mixed-effect machine learning models: MErf, MEgbm, MEmod, and MEctree, and standard machine learning models without random effects [random forest, gradient boosting machine] will be employed in our analyses to predict functional status over time.

Results

The results of this study will be fundamental for developing tailored digital interventions that apply deep learning techniques to behavioral data to predict, identify, and aid in the management of functional decline in older adults with subjective cognitive decline and mild cognitive impairment. These older adults are considered the optimal target population for preventive interventions and will benefit from such tailored strategies.

Conclusions

Our study will contribute to the development of self-care interventions that utilize behavioral data and machine learning techniques to provide automated analyses of the functional decline of older adults who are at risk for dementia.

Artificial intelligence for dementia-Applied models and digital health

INTRODUCTION

The use of applied modeling in dementia risk prediction, diagnosis, and prognostics will have substantial public health benefits, particularly as "deep phenotyping" cohorts with multi-omics health data become available.

METHODS

This narrative review synthesizes understanding of applied models and digital health technologies, in terms of dementia risk prediction, diagnostic discrimination, prognosis, and progression. Machine learning approaches show evidence of improved predictive power compared to standard clinical risk scores in predicting dementia, and the potential to decompose large numbers of variables into relatively few critical predictors.

RESULTS

This review focuses on key areas of emerging promise including: emphasis on easier, more transparent data sharing and cohort access; integration of high-throughput biomarker and electronic health record data into modeling; and progressing beyond the primary prediction of dementia to secondary outcomes, for example, treatment response and physical health.

DISCUSSION

Such approaches will benefit also from improvements in remote data measurement, whether cognitive (e.g., online), or naturalistic (e.g., watch-based accelerometry).

Artificial intelligence for dementia research methods optimization

Artificial intelligence (AI) and machine learning (ML) approaches are increasingly being used in dementia research. However, several methodological challenges exist that may limit the insights we can obtain from high-dimensional data and our ability to translate these findings into improved patient outcomes. To improve reproducibility and replicability, researchers should make their well-documented code and modeling pipelines openly available. Data should also be shared where appropriate. To enhance the acceptability of models and AI-enabled systems to users, researchers should prioritize interpretable methods that provide insights into how decisions are generated. Models should be developed using multiple, diverse datasets to improve robustness, generalizability, and reduce potentially harmful bias. To improve clarity and reproducibility, researchers should adhere to reporting guidelines that are co-produced with multiple stakeholders. If these methodological challenges are overcome, AI and ML hold enormous promise for changing the landscape of dementia research and care. HIGHLIGHTS: Machine learning (ML) can improve diagnosis, prevention, and management of dementia. Inadequate reporting of ML procedures affects reproduction/replication of results. ML models built on unrepresentative datasets do not generalize to new datasets. Obligatory metrics for certain model structures and use cases have not been defined. Interpretability and trust in ML predictions are barriers to clinical translation.

Detecting conversion from mild cognitive impairment to Alzheimer's disease using FLAIR MRI biomarkers

Mild cognitive impairment (MCI) is the prodromal phase of Alzheimer's disease (AD) and while it presents as an imperative intervention window, it is difficult to detect which subjects convert to AD (cMCI) and which ones remain stable (sMCI). The objective of this work was to investigate fluid-attenuated inversion recovery (FLAIR) MRI biomarkers and their ability to differentiate between sMCI and cMCI subjects in cross-sectional and longitudinal data. Three types of biomarkers were investigated: volume, intensity and texture. Volume biomarkers included total brain volume, cerebrospinal fluid volume (CSF), lateral ventricular volume, white matter lesion volume, subarachnoid CSF, and grey matter (GM) and white matter (WM), all normalized to intracranial volume. The mean intensity, kurtosis, and skewness of the GM and WM made up the intensity features. Texture features quantified homogeneity and microstructural tissue changes of GM and WM regions. Composite indices were also considered, which are biomarkers that represent an aggregate sum (z-score normalization and summation) of all biomarkers. The FLAIR MRI biomarkers successfully identified high-risk subjects as significant differences (p < 0.05) were found between the means of the sMCI and cMCI groups and the rate of change over time for several individual biomarkers as well as the composite indices for both cross-sectional and longitudinal analyses. Classification accuracy and feature importance analysis showed volume biomarkers to be most predictive, however, best performance was obtained when complimenting the volume biomarkers with the intensity and texture features. Using all the biomarkers, accuracy of 86.2 % and 69.2 % was achieved for normal control-AD and sMCI-cMCI classification respectively. Survival analysis demonstrated that the majority of the biomarkers showed a noticeable impact on the AD conversion probability 4 years prior to conversion. Composite indices were the top performers for all analyses including feature importance, classification, and survival analysis. This demonstrated their ability to summarize various dimensions of disease into single-valued metrics. Significant correlation (p < 0.05) with phosphorylated-tau and amyloid-beta CSF biomarkers was found with all the FLAIR biomarkers. The proposed biomarker system is easily attained as FLAIR is routinely acquired, models are not computationally intensive and the results are explainable, thus making this pipeline easily integrated into clinical workflow.

Screening strategies and dynamic risk prediction models for Alzheimer's disease

BACKGROUND

Characterizing the progression from Mild cognitive impairment (MCI) to Alzheimer's disease (AD) is essential for early AD prevention and targeted intervention. Our goal was to construct precise screening schemes for individuals with different risk of AD and to establish prognosis models for them.

METHODS

We constructed a retrospective cohort by reviewing individuals with baseline diagnosis of MCI and at least one follow-up visits between November 2005 and May 2021. They were stratified into high-risk and low-risk groups with longitudinal cognitive trajectory. Then, we established a screening framework and obtained optimal screening strategies for two risk groups. Cox and random survival forest (RSF) models were developed for dynamic prognosis prediction.

RESULTS

In terms of screening strategies, the combination of Clinical Dementia Rating Sum of Boxes (CDRSB) and hippocampus volume was recommended for the high-risk MCI group, while the combination of Alzheimer's Disease Assessment Scale Cognitive 13 items (ADAS13) and FAQ was recommended for low-risk MCI group. The concordance index (C-index) of the Cox model for the high-risk group was 0.844 (95% CI: 0.815-0.873) and adjustments for demographic information and APOE ε4. The RSF model incorporating longitudinal ADAS13, FAQ, and demographic information and APOE ε4 performed for the low-risk group.

CONCLUSION

This precise screening scheme will optimize allocation of medical resources and reduce the economic burden on individuals with low risk of MCI. Moreover, dynamic prognosis models may be helpful for early identification of individuals at risk and clinical decisions, which will promote the secondary prevention of AD.

AD-BERT: Using pre-trained language model to predict the progression from mild cognitive impairment to Alzheimer's disease

OBJECTIVE

We develop a deep learning framework based on the pre-trained Bidirectional Encoder Representations from Transformers (BERT) model using unstructured clinical notes from electronic health records (EHRs) to predict the risk of disease progression from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD).

METHODS

We identified 3657 patients diagnosed with MCI together with their progress notes from Northwestern Medicine Enterprise Data Warehouse (NMEDW) between 2000 and 2020. The progress notes no later than the first MCI diagnosis were used for the prediction. We first preprocessed the notes by deidentification, cleaning and splitting into sections, and then pre-trained a BERT model for AD (named AD-BERT) based on the publicly available Bio+Clinical BERT on the preprocessed notes. All sections of a patient were embedded into a vector representation by AD-BERT and then combined by global MaxPooling and a fully connected network to compute the probability of MCI-to-AD progression. For validation, we conducted a similar set of experiments on 2563 MCI patients identified at Weill Cornell Medicine (WCM) during the same timeframe.

RESULTS

Compared with the 7 baseline models, the AD-BERT model achieved the best performance on both datasets, with Area Under receiver operating characteristic Curve (AUC) of 0.849 and F1 score of 0.440 on NMEDW dataset, and AUC of 0.883 and F1 score of 0.680 on WCM dataset.

CONCLUSION

The use of EHRs for AD-related research is promising, and AD-BERT shows superior predictive performance in modeling MCI-to-AD progression prediction. Our study demonstrates the utility of pre-trained language models and clinical notes in predicting MCI-to-AD progression, which could have important implications for improving early detection and intervention for AD.

Does adding MRI and CSF-based biomarkers improve cognitive status classification based on cognitive performance questionnaires?

BACKGROUND

Cognitive status classification (e.g. dementia, cognitive impairment without dementia, and normal) based on cognitive performance questionnaires has been widely used in population-based studies, providing insight into the population dynamics of dementia. However, researchers have raised concerns about the accuracy of cognitive assessments. MRI and CSF biomarkers may provide improved classification, but the potential improvement in classification in population-based studies is relatively unknown.

METHODS

Data come from the Alzheimer's Disease Neuroimaging Initiative (ADNI). We examined whether the addition of MRI and CSF biomarkers improved cognitive status classification based on cognitive status questionnaires (MMSE). We estimated several multinomial logistic regression models with different combinations of MMSE and CSF/MRI biomarkers. Based on these models, we also predicted prevalence of each cognitive status category using a model with MMSE only and a model with MMSE + MRI + CSF measures and compared them to diagnosed prevalence.

RESULTS

Our analysis showed a slight improvement in variance explained (pseudo-R2) between the model with MMSE only and the model including MMSE and MRI/CSF biomarkers; the pseudo-R2 increased from .401 to .445. Additionally, in evaluating differences in predicted prevalence for each cognitive status, we found a small improvement in the predicted prevalence of cognitively normal individuals between the MMSE only model and the model with MMSE and CSF/MRI biomarkers (3.1% improvement). We found no improvement in the correct prediction of dementia prevalence.

CONCLUSION

MRI and CSF biomarkers, while important for understanding dementia pathology in clinical research, were not found to substantially improve cognitive status classification based on cognitive status performance, which may limit adoption in population-based surveys due to costs, training, and invasiveness associated with their collection.

Artificial Intelligence for Dementia Research Methods Optimization

INTRODUCTION

Machine learning (ML) has been extremely successful in identifying key features from high-dimensional datasets and executing complicated tasks with human expert levels of accuracy or greater.

METHODS

We summarize and critically evaluate current applications of ML in dementia research and highlight directions for future research.

RESULTS

We present an overview of ML algorithms most frequently used in dementia research and highlight future opportunities for the use of ML in clinical practice, experimental medicine, and clinical trials. We discuss issues of reproducibility, replicability and interpretability and how these impact the clinical applicability of dementia research. Finally, we give examples of how state-of-the-art methods, such as transfer learning, multi-task learning, and reinforcement learning, may be applied to overcome these issues and aid the translation of research to clinical practice in the future.

DISCUSSION

ML-based models hold great promise to advance our understanding of the underlying causes and pathological mechanisms of dementia.

Sex-Specific Heterogeneity of Mild Cognitive Impairment Identified Based on Multi-Modal Data Analysis

BACKGROUND

Mild cognitive impairment (MCI), a prodromal phase of Alzheimer's disease (AD), is heterogeneous with different rates and risks of progression to AD. There are significant gender disparities in the susceptibility, prognosis, and outcomes in patients with MCI, with female being disproportionately negatively impacted.

OBJECTIVE

The aim of this study was to identify sex-specific heterogeneity of MCI using multi-modality data and examine the differences in the respective MCI subtypes with different prognostic outcomes or different risks for MCI to AD conversion.

METHODS

A total of 325 MCI subjects (146 women, 179 men) and 30 relevant features were considered. Mixed-data clustering was applied to women and men separately to discover gender-specific MCI subtypes. Gender differences were compared in the respective subtypes of MCI by examining their MCI to AD disease prognosis, descriptive statistics, and conversion rates.

RESULTS

We identified three MCI subtypes: poor-, good-, and best-prognosis for women and for men, separately. The subtype-wise comparison (for example, poor-prognosis subtype in women versus poor-prognosis subtype in men) showed significantly different means for brain volumetric, cognitive test-related, also for the proportion of comorbidities. Also, there were substantial gender differences in the proportions of participants who reverted to normal function, remained stable, or converted to AD.

CONCLUSION

Analyzing sex-specific heterogeneity of MCI offers the opportunity to advance the understanding of the pathophysiology of both MCI and AD, allows stratification of risk in clinical trials of interventions, and suggests gender-based early intervention with targeted treatment for patients at risk of developing AD.

A Deep Longitudinal Model for Mild Cognitive Impairment to Alzheimer’s Disease Conversion Prediction in Low-Income Countries

Alzheimer’s disease (AD) is a progressive and fatal disease, due to the nonavailability of any permanent cure. Some treatments are under experimentation that can slow down and possibly pause the progression of the disease only if the disease is diagnosed earlier. The onset of AD can only be detected at the mild cognitive impairment (MCI) stage in which slight memory loss is observed but daily routine functions are intact. A small fraction of the patient progresses from MCI to AD. In this research, we have designed a cascaded deep neural network model to identify those MCI subjects who will progress to AD in the following year. The analysis and experimentation have been performed using twenty longitudinal neuropsychological measures (NMs) provided by Alzheimer’s Disease Neuroimaging Initiative (ADNI). After normalization and ranking of longitudinal data, the deep neural network regression model is trained and tuned to forecast the next in-sequence biomarker value using two previous follow-up readings for each marker. Then, the three time-domain window samples are fed into another deep neural network classifier model for the classification of MCI progressor (MCIp) and MCI stables (MCIs). Our model presented regression forecasting MAE of 0.13 and classification accuracy of 86.9% with AUC of 92.1% (Sensitivity: 67.7%, specificity: 92.3%) over 5-fold cross-validation. We conclude that time-domain measures of NM alone can deliver comparable MCI to AD conversion prediction performance without leveraging more expensive and invasive counterparts such as MR imaging, PET scans, and CSF measures. Middle and low-income countries will benefit from such cheap and effective solutions greatly.

Mitochondria - Nucleus communication in neurodegenerative disease. Who talks first, who talks louder?

Mitochondria - nuclear coadaptation has been central to eukaryotic evolution. The dynamic dialogue between the two compartments within the context of multiorganellar interactions is critical for maintaining cellular homeostasis and directing the balance survival-death in case of cellular stress. The conceptualisation of mitochondria - nucleus communication has so far been focused on the communication from the mitochondria under stress to the nucleus and the consequent signalling responses, as well as from the nucleus to mitochondria in the context of DNA damage and repair. During ageing processes this dialogue may be better viewed as an integrated bidirectional 'talk' with feedback loops that expand beyond these two organelles depending on physiological cues. Here we explore the current views on mitochondria - nucleus dialogue and its role in maintaining cellular health with a focus on brain cells and neurodegenerative disease. Thus, we detail the transcriptional responses initiated by mitochondrial dysfunction in order to protect itself and the general cellular homeostasis. Additionally, we are reviewing the knowledge of the stress pathways initiated by DNA damage which affect mitochondria homeostasis and we add the information provided by the study of combined mitochondrial and genotoxic damage. Finally, we reflect on how each organelle may take the lead in this dialogue in an ageing context where both compartments undergo accumulation of stress and damage and where, perhaps, even the communications' mechanisms may suffer interruptions.

Predicting future cognitive decline from non-brain and multimodal brain imaging data in healthy and pathological aging

Previous literature has focused on predicting a diagnostic label from structural brain imaging. Since subtle changes in the brain precede a cognitive decline in healthy and pathological aging, our study predicts future decline as a continuous trajectory instead. Here, we tested whether baseline multimodal neuroimaging data improve the prediction of future cognitive decline in healthy and pathological aging. Nonbrain data (demographics, clinical, and neuropsychological scores), structural MRI, and functional connectivity data from OASIS-3 (N = 662; age = 46-96 years) were entered into cross-validated multitarget random forest models to predict future cognitive decline (measured by CDR and MMSE), on average 5.8 years into the future. The analysis was preregistered, and all analysis code is publicly available. Combining non-brain with structural data improved the continuous prediction of future cognitive decline (best test-set performance: R2 = 0.42). Cognitive performance, daily functioning, and subcortical volume drove the performance of our model. Including functional connectivity did not improve predictive accuracy. In the future, the prognosis of age-related cognitive decline may enable earlier and more effective individualized cognitive, pharmacological, and behavioral interventions.

Categorical predictive and disease progression modeling in the early stage of Alzheimer's disease

BACKGROUND

A preclinical stage of Alzheimer's disease (AD) precedes the symptomatic phases of mild cognitive impairment (MCI) and dementia, which constitutes a window of opportunities for preventive therapies or delaying dementia onset.

NEW METHOD

We propose to use categorical predictive models based on survival analysis with longitudinal data which are capable of determining subsets of markers to classify cognitively unimpaired (CU) subjects who progress into MCI/dementia or not. Subsequently, the proposed combination of markers was used to construct disease progression models (DPMs), which reveal long-term pathological trajectories from short-term clinical data. The proposed methodology was applied to a population recruited by the ADNI.

RESULTS

A very small subset of standard MRI-based data, CSF markers and cognitive measures was used to predict CU-to-MCI/dementia progression. The longitudinal data of these selected markers were used to construct DPMs using the algorithms of growth models by alternating conditional expectation (GRACE) and the latent time joint mixed effects model (LTJMM). The results show that the natural history of the proposed cognitive decline classifies the subjects well according to the clinical groups and shows a moderate correlation between the conversion times and their estimates by the algorithms.

COMPARISON WITH EXISTING METHODS

Unlike the training of the DPM algorithms without preselection of the markers, here, it is proposed to construct and evaluate the DPMs using the subsets of markers defined by the categorical predictive models.

CONCLUSIONS

The estimates of the natural history of the proposed cognitive decline from GRACE were more robust than those using LTJMM. The transition from normal to cognitive decline is mostly associated with an increase in temporal atrophy, worsening of clinical scores and pTAU/Aβ. Furthermore, pTAU/Aβ, Everyday Cognition score and the normalized volume of the entorhinal cortex show alterations of more than 20% fifteen years before the onset of cognitive decline.

Late combination shows that MEG adds to MRI in classifying MCI versus controls

Early detection of Alzheimer's disease (AD) is essential for developing effective treatments. Neuroimaging techniques like Magnetic Resonance Imaging (MRI) have the potential to detect brain changes before symptoms emerge. Structural MRI can detect atrophy related to AD, but it is possible that functional changes are observed even earlier. We therefore examined the potential of Magnetoencephalography (MEG) to detect differences in functional brain activity in people with Mild Cognitive Impairment (MCI) - a state at risk of early AD. We introduce a framework for multimodal combination to ask whether MEG data from a resting-state provides complementary information beyond structural MRI data in the classification of MCI versus controls. More specifically, we used multi-kernel learning of support vector machines to classify 163 MCI cases versus 144 healthy elderly controls from the BioFIND dataset. When using the covariance of planar gradiometer data in the low Gamma range (30-48 Hz), we found that adding a MEG kernel improved classification accuracy above kernels that captured several potential confounds (e.g., age, education, time-of-day, head motion). However, accuracy using MEG alone (68%) was worse than MRI alone (71%). When simply concatenating (normalized) features from MEG and MRI into one kernel (Early combination), there was no advantage of combining MEG with MRI versus MRI alone. When combining kernels of modality-specific features (Intermediate combination), there was an improvement in multimodal classification to 74%. The biggest multimodal improvement however occurred when we combined kernels from the predictions of modality-specific classifiers (Late combination), which achieved 77% accuracy (a reliable improvement in terms of permutation testing). We also explored other MEG features, such as the variance versus covariance of magnetometer versus planar gradiometer data within each of 6 frequency bands (delta, theta, alpha, beta, low gamma, or high gamma), and found that they generally provided complementary information for classification above MRI. We conclude that MEG can improve on the MRI-based classification of MCI.

Development of a machine learning model to predict mild cognitive impairment using natural language processing in the absence of screening

BACKGROUND

Patients and their loved ones often report symptoms or complaints of cognitive decline that clinicians note in free clinical text, but no structured screening or diagnostic data are recorded. These symptoms/complaints may be signals that predict who will go on to be diagnosed with mild cognitive impairment (MCI) and ultimately develop Alzheimer's Disease or related dementias. Our objective was to develop a natural language processing system and prediction model for identification of MCI from clinical text in the absence of screening or other structured diagnostic information.

METHODS

There were two populations of patients: 1794 participants in the Adult Changes in Thought (ACT) study and 2391 patients in the general population of Kaiser Permanente Washington. All individuals had standardized cognitive assessment scores. We excluded patients with a diagnosis of Alzheimer's Disease, Dementia or use of donepezil. We manually annotated 10,391 clinic notes to train the NLP model. Standard Python code was used to extract phrases from notes and map each phrase to a cognitive functioning concept. Concepts derived from the NLP system were used to predict future MCI. The prediction model was trained on the ACT cohort and 60% of the general population cohort with 40% withheld for validation. We used a least absolute shrinkage and selection operator logistic regression approach (LASSO) to fit a prediction model with MCI as the prediction target. Using the predicted case status from the LASSO model and known MCI from standardized scores, we constructed receiver operating curves to measure model performance.

RESULTS

Chart abstraction identified 42 MCI concepts. Prediction model performance in the validation data set was modest with an area under the curve of 0.67. Setting the cutoff for correct classification at 0.60, the classifier yielded sensitivity of 1.7%, specificity of 99.7%, PPV of 70% and NPV of 70.5% in the validation cohort.

DISCUSSION AND CONCLUSION

Although the sensitivity of the machine learning model was poor, negative predictive value was high, an important characteristic of models used for population-based screening. While an AUC of 0.67 is generally considered moderate performance, it is also comparable to several tests that are widely used in clinical practice.

Signature of Alzheimer’s Disease in Intestinal Microbiome: Results From the AlzBiom Study

Background

Changes in intestinal microbiome composition have been described in animal models of Alzheimer’s disease (AD) and AD patients. Here we investigated how well taxonomic and functional intestinal microbiome data and their combination with clinical data can be used to discriminate between amyloid-positive AD patients and cognitively healthy elderly controls.

Methods

In the present study we investigated intestinal microbiome in 75 amyloid-positive AD patients and 100 cognitively healthy controls participating in the AlzBiom study. We randomly split the data into a training and a validation set. Intestinal microbiome was measured using shotgun metagenomics. Receiver operating characteristic (ROC) curve analysis was performed to examine the discriminatory ability of intestinal microbiome among diagnostic groups.

Results

The best model for discrimination of amyloid-positive AD patients from healthy controls with taxonomic data was obtained analyzing 18 genera features, and yielded an area under the receiver operating characteristic curve (AUROC) of 0.76 in the training set and 0.61 in the validation set. The best models with functional data were obtained analyzing 17 GO (Gene Ontology) features with an AUROC of 0.81 in the training set and 0.75 in the validation set and 26 KO [Kyoto Encyclopedia of Genes and Genomes (KEGG) ortholog] features with an AUROC of 0.83 and 0.77, respectively. Using ensemble learning for these three models including a clinical model with the 4 parameters age, gender, BMI and ApoE yielded an AUROC of 0.92 in the training set and 0.80 in the validation set.

Discussion

In conclusion, we identified a specific Alzheimer signature in intestinal microbiome that can be used to discriminate amyloid-positive AD patients from healthy controls. The diagnostic accuracy increases from taxonomic to functional data and is even better when combining taxonomic, functional and clinical models. Intestinal microbiome represents an innovative diagnostic supplement and a promising area for developing novel interventions against AD.

Prediction Models for Conversion From Mild Cognitive Impairment to Alzheimer’s Disease: A Systematic Review and Meta-Analysis

Background and Purpose

Alzheimer’s disease (AD) is a devastating neurodegenerative disorder with no cure, and available treatments are only able to postpone the progression of the disease. Mild cognitive impairment (MCI) is considered to be a transitional stage preceding AD. Therefore, prediction models for conversion from MCI to AD are desperately required. These will allow early treatment of patients with MCI before they develop AD. This study performed a systematic review and meta-analysis to summarize the reported risk prediction models and identify the most prevalent factors for conversion from MCI to AD.

Methods

We systematically reviewed the studies from the databases of PubMed, CINAHL Plus, Web of Science, Embase, and Cochrane Library, which were searched through September 2021. Two reviewers independently identified eligible articles and extracted the data. We used the Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies (CHARMS) checklist for the risk of bias assessment.

Results

In total, 18 articles describing the prediction models for conversion from MCI to AD were identified. The dementia conversion rate of elderly patients with MCI ranged from 14.49 to 87%. Models in 12 studies were developed using the data from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). C-index/area under the receiver operating characteristic curve (AUC) of development models were 0.67–0.98, and the validation models were 0.62–0.96. MRI, apolipoprotein E genotype 4 (APOE4), older age, Mini-Mental State Examination (MMSE) score, and Alzheimer’s Disease Assessment Scale cognitive (ADAS-cog) score were the most common and strongest predictors included in the models.

Conclusion

In this systematic review, many prediction models have been developed and have good predictive performance, but the lack of external validation of models limited the extensive application in the general population. In clinical practice, it is recommended that medical professionals adopt a comprehensive forecasting method rather than a single predictive factor to screen patients with a high risk of MCI. Future research should pay attention to the improvement, calibration, and validation of existing models while considering new variables, new methods, and differences in risk profiles across populations.

Improving the diagnostic accuracy for major depressive disorder using machine learning algorithms integrating clinical and near-infrared spectroscopy data

BACKGROUND

Given that major depressive disorder (MDD) is both biologically and clinically heterogeneous, a diagnostic system integrating neurobiological markers and clinical characteristics would allow for better diagnostic accuracy and, consequently, treatment efficacy.

OBJECTIVE

Our study aimed to evaluate the discriminative and predictive ability of unimodal, bimodal, and multimodal approaches in a total of seven machine learning (ML) models-clinical, demographic, functional near-infrared spectroscopy (fNIRS), combinations of two unimodal models, as well as a combination of all three-for MDD.

METHODS

We recruited 65 adults with MDD and 68 matched healthy controls, who provided both sociodemographic and clinical information, and completed the HAM-D questionnaire. They were also subject to fNIRS measurement when participating in the verbal fluency task. Using the nested cross validation procedure, the classification performance of each ML model was evaluated based on the area under the receiver operating characteristic curve (ROC), balanced accuracy, sensitivity, and specificity.

RESULTS

The multimodal ML model was able to distinguish between depressed patients and healthy controls with the highest balanced accuracy of 87.98 ± 8.84% (AUC = 0.92; 95% CI (0.84-0.99) when compared with the uni- and bi-modal models.

CONCLUSIONS

Our multimodal ML model demonstrated the highest diagnostic accuracy for MDD. This reinforces the biological and clinical heterogeneity of MDD and highlights the potential of this model to improve MDD diagnosis rates. Furthermore, this model is cost-effective and clinically applicable enough to be established as a robust diagnostic system for MDD based on patients' biosignatures.

Corpus Callosum Atrophy in Detection of Mild and Moderate Alzheimer's Disease Using Brain Magnetic Resonance Image Processing and Machine Learning Techniques

Background:

The total number of people with dementia is projected to reach 82 million in 2030 and 152 in 2050. Early and accurate identification of the underlying causes of dementia, such as Alzheimer’s disease (AD) is of utmost importance. A large body of research has shown that imaging techniques are most promising technologies to improve subclinical and early diagnosis of dementia. Morphological changes, especially atrophy in various structures like cingulate gyri, caudate nucleus, hippocampus, frontotemporal lobe, etc., have been established as markers for AD. Being the largest white matter structure with a high demand of blood supply from several main arterial systems, anatomical alterations of the corpus callosum (CC) may serve as potential indication neurodegenerative disease.

Objective:

To detect mild and moderate AD using brain magnetic resonance image (MRI) processing and machine learning techniques.

Methods:

We have performed automatic detection and segmentation of the CC and calculated its morphological features to feed into a multivariate pattern analysis using support vector machine (SVM) learning techniques.

Results:

Our results using large patients’ cohort show CC atrophy-based features are capable of distinguishing healthy and mild/moderate AD patients. Our classifiers obtain more than 90%sensitivity and specificity in differentiating demented patients from healthy cohorts and importantly, achieved more than 90%sensitivity and > 80%specificity in detecting mild AD patients.

Conclusion:

Results from this analysis are encouraging and advocate development of an image analysis software package to detect dementia from brain MRI using morphological alterations of the CC.

Classification of Initial Stages of Alzheimer’s Disease through Pet Neuroimaging Modality and Deep Learning: Quantifying the Impact of Image Filtering Approaches

Alzheimer’s disease (AD) is a leading health concern affecting the elderly population worldwide. It is defined by amyloid plaques, neurofibrillary tangles, and neuronal loss. Neuroimaging modalities such as positron emission tomography (PET) and magnetic resonance imaging are routinely used in clinical settings to monitor the alterations in the brain during the course of progression of AD. Deep learning techniques such as convolutional neural networks (CNNs) have found numerous applications in healthcare and other technologies. Together with neuroimaging modalities, they can be deployed in clinical settings to learn effective representations of data for different tasks such as classification, segmentation, detection, etc. Image filtering methods are instrumental in making images viable for image processing operations and have found numerous applications in image-processing-related tasks. In this work, we deployed 3D-CNNs to learn effective representations of PET modality data to quantify the impact of different image filtering approaches. We used box filtering, median filtering, Gaussian filtering, and modified Gaussian filtering approaches to preprocess the images and use them for classification using 3D-CNN architecture. Our findings suggest that these approaches are nearly equivalent and have no distinct advantage over one another. For the multiclass classification task between normal control (NC), mild cognitive impairment (MCI), and AD classes, the 3D-CNN architecture trained using Gaussian-filtered data performed the best. For binary classification between NC and MCI classes, the 3D-CNN architecture trained using median-filtered data performed the best, while, for binary classification between AD and MCI classes, the 3D-CNN architecture trained using modified Gaussian-filtered data performed the best. Finally, for binary classification between AD and NC classes, the 3D-CNN architecture trained using box-filtered data performed the best.

Prediction of Alzheimer's Disease Progression Based on Magnetic Resonance Imaging

The neuroimaging method of multimodal magnetic resonance imaging (MRI) can identify the changes in brain structure and function caused by Alzheimer's disease (AD) at different stages, and it is a practical method to study the mechanism of AD progression. This paper reviews the studies of methods and biomarkers for predicting AD progression based on multimodal MRI. First, different approaches for predicting AD progression are analyzed and summarized, including machine learning, deep learning, regression, and other MRI analysis methods. Then, the effective biomarkers of AD progression under structural magnetic resonance imaging, diffusion tensor imaging, functional magnetic resonance imaging, and arterial spin labeling modes of MRI are summarized. It is believed that the brain changes shown on MRI may be related to the cognitive decline in different prodrome stages of AD, which is conducive to the further realization of early intervention and prevention of AD. Finally, the deficiencies of the existing studies are analyzed in terms of data set size, data heterogeneity, processing methods, and research depth. More importantly, future research directions are proposed, including enriching data sets, simplifying biomarkers, utilizing multimodal magnetic resonance, etc. In the future, the study of AD progression by multimodal MRI will still be a challenge but also a significant research hotspot.

DNA Methylation in Genetic and Sporadic Forms of Neurodegeneration: Lessons from Alzheimer's, Related Tauopathies and Genetic Tauopathies

Genetic and sporadic forms of tauopathies, the most prevalent of which is Alzheimer's Disease, are a scourge of the aging society, and in the case of genetic forms, can also affect children and young adults. All tauopathies share ectopic expression, mislocalization, or aggregation of the microtubule associated protein TAU, encoded by the MAPT gene. As TAU is a neuronal protein widely expressed in the CNS, the overwhelming majority of tauopathies are neurological disorders. They are characterized by cognitive dysfunction often leading to dementia, and are frequently accompanied by movement abnormalities such as parkinsonism. Tauopathies can lead to severe neurological deficits and premature death. For some tauopathies there is a clear genetic cause and/or an epigenetic contribution. However, for several others the disease etiology is unclear, with few tauopathies being environmentally triggered. Here, we review current knowledge of tauopathies listing known genetic and important sporadic forms of these disease. Further, we discuss how DNA methylation as a major epigenetic mechanism emerges to be involved in the disease pathophysiology of Alzheimer's, and related genetic and non-genetic tauopathies. Finally, we debate the application of epigenetic signatures in peripheral blood samples as diagnostic tools and usages of epigenetic therapy strategies for these diseases.

A Role for Prior Knowledge in Statistical Classification of the Transition from Mild Cognitive Impairment to Alzheimer's Disease

BACKGROUND

The transition from mild cognitive impairment (MCI) to dementia is of great interest to clinical research on Alzheimer's disease and related dementias. This phenomenon also serves as a valuable data source for quantitative methodological researchers developing new approaches for classification. However, the growth of machine learning (ML) approaches for classification may falsely lead many clinical researchers to underestimate the value of logistic regression (LR), which often demonstrates classification accuracy equivalent or superior to other ML methods. Further, when faced with many potential features that could be used for classifying the transition, clinical researchers are often unaware of the relative value of different approaches for variable selection.

OBJECTIVE

The present study sought to compare different methods for statistical classification and for automated and theoretically guided feature selection techniques in the context of predicting conversion from MCI to dementia.

METHODS

We used data from the Alzheimer's Disease Neuroimaging Initiative (ADNI) to evaluate different influences of automated feature preselection on LR and support vector machine (SVM) classification methods, in classifying conversion from MCI to dementia.

RESULTS

The present findings demonstrate how similar performance can be achieved using user-guided, clinically informed pre-selection versus algorithmic feature selection techniques.

CONCLUSION

These results show that although SVM and other ML techniques are capable of relatively accurate classification, similar or higher accuracy can often be achieved by LR, mitigating SVM's necessity or value for many clinical researchers.

Effect of Advanced Glycation End Products on Cognition in Older Adults with Type 2 Diabetes: Results from a Pilot Clinical Trial

BACKGROUND

Dietary advanced glycation end-products (AGEs) are linked to cognitive decline. However, clinical trials have not tested the effect of AGEs on cognition in older adults.

OBJECTIVE

The aim of the current pilot trial was to examine the feasibility of an intervention to reduce dietary AGEs on cognition and on cerebral blood flow (CBF).

METHODS

The design is a pilot randomized controlled trial of dietary AGEs reduction in older adults with type 2 diabetes. Seventy-five participants were randomized to two arms. The control arm received standard of care (SOC) guidelines for good glycemic control; the intervention arm, in addition to SOC guidelines, were instructed to reduce their dietary AGEs intake. Global cognition and CBF were assessed at baseline and after 6 months of intervention.

RESULTS

At baseline, we found a reverse association between AGEs and cognitive functioning, possibly reflecting the long-term toxicity of AGEs on the brain. There was a significant improvement in global cognition at 6 months in both the intervention and SOC groups which was more prominent in participants with mild cognitive impairment. We also found that at baseline, higher AGEs were associated with increased CBF in the left inferior parietal cortex; however, 6 months of the AGEs lowering intervention did not affect CBF levels, despite lowering AGEs exposure in blood.

CONCLUSION

The current pilot trial focused on the feasibility and methodology of intervening through diet to reduce AGEs in older adults with type 2 diabetes. Our results suggest that participants with mild cognitive impairment may benefit from an intensive dietary intervention.

Combination of Plasma Neurofilament Light Chain and Mini-Mental State Examination Score Predicts Progression from Mild Cognitive Impairment to Alzheimer's Disease within 5 Years

BACKGROUND

Individuals with mild cognitive impairment (MCI) are at high risk of progression to Alzheimer's disease (AD) dementia, but some remain stable. There is a need to identify those at higher risk of progression to improve patient management and outcomes.

OBJECTIVE

To evaluate the trajectory of plasma neurofilament light chain (pNFL) prior to progression from MCI to AD dementia, the performance of pNFL, in combination with the Mini-Mental State Examination (MMSE), as a predictor of progression from MCI to AD dementia and to inform clinicians on the use of pNFL as a predictive biomarker.

METHODS

Participants (n = 440) with MCI and longitudinal follow-up (mean = 4.2 years) from the AD Neuroimaging Initiative dataset were included. pNFL as a marker for neurodegeneration and the MMSE as a cognitive measure were investigated as simple/practical predictors of progression. The risk of progressing from MCI to AD dementia associated with pNFL and MMSE scores was assessed using Cox and logistic regression models.

RESULTS

The current risk of progression to AD dementia was 37%higher in individuals with high pNFL (> 56 ng/L) compared to those with average pNFL (≤40 ng/L). A combination of baseline pNFL and MMSE could differentiate those who progressed within 5 years (AUC = 0.75) from stable individuals. Including change in MMSE over 6-12 months further improved the model (AUC = 0.84).

CONCLUSION

Our findings reveal that combining pNFL with a simple dementia screener (MMSE) can reliably predict whether a person with MCI is likely to progress to AD dementia within 5 years.

Harnessing forgetfulness: can episodic-memory tests predict early Alzheimer's disease?

A rapid increase in the number of patients with Alzheimer's disease (AD) is expected over the next decades. Accordingly, there is a critical need for early-stage AD detection methods that can enable effective treatment strategies. In this study, we consider the ability of episodic-memory measures to predict mild cognitive impairment (MCI) to AD conversion and thus, detect early-stage AD. For our analysis, we studied 307 participants with MCI across four years using data from the Alzheimer's Disease Neuroimaging Initiative (ADNI). Using a binary logistic regression, we compared episodic-memory tests to each other and to prominent neuroimaging methods in MCI converter (MCI participants who developed AD) and MCI non-converter groups (MCI participants who did not develop AD). We also combined variables to test the accuracy of mixed-predictor models. Our results indicated that the best predictors of MCI to AD conversion were the following: a combined episodic-memory and neuroimaging model in year one (59.8%), the Rey Auditory Verbal Learning Test in year two (71.7%), a mixed episodic-memory predictor model in year three (77.7%) and the Logical Memory Test in year four (77.2%) of ADNI. Overall, we found that individual episodic-memory measure and mixed models performed similarly when predicting MCI to AD conversion. Comparatively, individual neuroimaging measures predicted MCI conversion worse than chance. Accordingly, our results indicate that episodic-memory tests could be instrumental in detecting early-stage AD and enabling effective treatment.

Serum Extracellular Vesicle-Derived miR-124-3p as a Diagnostic and Predictive Marker for Early-Stage Acute Ischemic Stroke

Background: A delay in the diagnosis of acute ischemic stroke (AIS) reduces the eligibility and outcome of patients for thrombolytic therapy. Therefore, early diagnosis and treatment of AIS are crucial. The present study evaluated the sensitivity and accuracy of serum extracellular vesicle (EV)-derived miR-124-3p in the diagnosis and prediction of AIS.

Methods: An miRNA expression profile was downloaded from Gene Expression Omnibus (GEO) database and analyzed by R software. EVs were harvested from the serum of AIS patients using a total exosome isolation kit and characterized by Western blotting, a transmission electron microscope, and the nanoparticle tracking analysis. BV2 microglia were pre-stimulated with lipopolysaccharide (LPS), followed by miR-124-3p treatment for 24 h and subsequent analysis of viability, apoptosis, and migration (scratch assay), and Western blotting. The relative expression of the selected genes was assessed by qRT-PCR. The phosphorylation of Erk1/2, PI3K/Akt, and p38MAPK in BV2 microglia cells was evaluated by Western blotting, while the luciferase reporter gene assay detected the correlation between key genes involved in the pro-inflammatory signaling pathways and miR-124-3p.

Results:hsa-miR-124-3p was downregulated in AIS serum compared to the non-AIS serum (p < 0.05), and the gene expression of has-miR-124-3p in EVs was negatively correlated with serum pro-inflammatory cytokines and the NIHSS (p < 0.05). In addition, miR-124-3p promoted the viability and inhibited the apoptosis of LPS-induced BV2 microglia. Furthermore, miR-124-3p reduced the phosphorylation of Erk1/2, PI3K/Akt, and p38MAPK, and promoted the migration in LPS-induced BV2 microglia (p < 0.05).

Conclusion: Serum EV-derived miR-124-3p serves as a diagnostic and predictive marker for early-stage AIS.

Comparison of the predictive accuracy of multiple definitions of cognitive impairment for incident dementia: a 20-year follow-up of the Whitehall II cohort study

BACKGROUND

Studies generally use cognitive assessment done at one timepoint to define cognitive impairment in order to examine conversion to dementia. Our objective was to examine the predictive accuracy and conversion rate of seven alternate definitions of cognitive impairment for dementia.

METHODS

In this prospective study, we included participants from the Whitehall II cohort study who were assessed for cognitive impairment in 2007-09 and were followed up for clinically diagnosed dementia. Algorithms based on poor cognitive performance (defined using age-specific and sex-specific thresholds, and subsequently thresholds by education or occupation levels) and objective cognitive decline (using data from cognitive assessments in 1997-99, 2002-04, and 2007-09) were used to generate seven alternate definitions of cognitive impairment. We compared predictive accuracy using Royston's R 2, the Akaike information criterion (AIC), sensitivity, specificity, and Harrell's C-statistic.

FINDINGS

5687 participants, with a mean age of 65·7 years (SD 5·9) in 2007-09, were included and followed up for a median of 10·5 years (IQR 10·1-10·9). Over follow-up, 270 (4·7%) participants were clinically diagnosed with dementia. Cognitive impairment defined using both cognitive performance and decline had higher hazard ratios (from 5·08 [95% CI 3·82-6·76] to 5·48 [4·13-7·26]) for dementia than did definitions based on cognitive performance alone (from 3·25 [2·52-4·17] to 3·39 [2·64-4·36]) and cognitive decline alone (3·01 [2·37-3·82]). However, all definitions had poor predictive performance (C-statistic ranged from 0·591 [0·565-0·616] to 0·631 [0·601-0·660]), primarily due to low sensitivity (21·6-48·4%). A predictive model containing age, sex, and education without measures of cognitive impairment had better predictive performance (C-statistic 0·783 [0·758-0·809], sensitivity 74·2%, specificity 72·2%) than all seven definitions of cognitive impairment (all p<0·0001).

INTERPRETATION

These findings suggest that cognitive impairment in early old age might not be useful for dementia prediction, even when it is defined using longitudinal data on cognitive decline and thresholds of poor cognitive performance additionally defined by education or occupation.

FUNDING

National Institutes of Health, UK Medical Research Council.

Predicting Conversion from MCI to AD Combining Multi-Modality Data and Based on Molecular Subtype

Alzheimer’s disease (AD) is a neurodegenerative brain disease in the elderly. Identifying patients with mild cognitive impairment (MCI) who are more likely to progress to AD is a key step in AD prevention. Recent studies have shown that AD is a heterogeneous disease. In this study, we propose a subtyping-based prediction strategy to predict the conversion from MCI to AD in three years according to MCI patient subtypes. Structural magnetic resonance imaging (sMRI) data and multi-omics data, including genotype data and gene expression profiling derived from peripheral blood samples, from 125 MCI patients were used in the Alzheimer’s Disease Neuroimaging Initiative (ADNI)-1 dataset and from 98 MCI patients in the ADNI-GO/2 dataset. A variational Bayes approximation model based on the multiple kernel learning method was constructed to predict whether an MCI patient will progress to AD within three years. In internal fivefold cross-validation within ADNI-1, we achieved an overall AUC of 0.83 (79.20% accuracy, 81.25% sensitivity, 77.92% specificity) compared to the model without subtyping, which achieved an AUC of 0.78 (76.00% accuracy, 77.08% sensitivity, 75.32% specificity). In external validation using ADNI-1 as a training set and ADNI-GO/2 as an independent test set, we attained an AUC of 0.78 (74.49% accuracy, 74.19% sensitivity, 74.63% specificity). Identifying MCI patient subtypes with omics data would improve the accuracy of predicting the conversion from MCI to AD. In addition to evaluating statistics, obtaining the significant sMRI, single nucleotide polymorphism (SNP) and mRNA expression data from peripheral blood of MCI patients is noninvasive and cost-effective for predicting conversion from MCI to AD.

A Deep Neural Network-Based Method for Prediction of Dementia Using Big Data

The rise in dementia among the aging Korean population will quickly create a financial burden on society, but timely recognition of early warning for dementia and proper responses to the occurrence of dementia can enhance medical treatment. Health behavior and medical service usage data are relatively more accessible than clinical data, and a prescreening tool with easily accessible data could be a good solution for dementia-related problems. In this paper, we apply a deep neural network (DNN) to prediction of dementia using health behavior and medical service usage data, using data from 7031 subjects aged over 65 collected from the Korea National Health and Nutrition Examination Survey (KNHANES) in 2001 and 2005. In the proposed model, principal component analysis (PCA) featuring and min/max scaling are used to preprocess and extract relevant background features. We compared our proposed methodology, a DNN/scaled PCA, with five well-known machine learning algorithms. The proposed methodology shows 85.5% of the area under the curve (AUC), a better result than that using other algorithms. The proposed early prescreening method for possible dementia can be used by both patients and doctors.

Increased Plasma Level of 24S-Hydroxycholesterol and Polymorphism of CYP46A1 SNP (rs754203) Are Associated With Mild Cognitive Impairment in Patients With Type 2 Diabetes

Background

Abnormal cholesterol metabolism is common in type 2 diabetes mellitus (T2DM) and causes dementia. Cholesterol 24S-hydroxylase (CYP46A1) converts cholesterol into 24S-hydroxycholesterol (24-OHC) and maintains cholesterol homeostasis in the brain.

Objective

This study aimed to investigate the roles of 24-OHC and the CYP46A1 (rs754203) polymorphism in patients with T2DM and mild cognitive impairment (MCI).

Methods

A total of 193 Chinese patients with T2DM were recruited into two groups according to the Montreal Cognitive Assessment (MoCA). Demographic and clinical data were collected, and neuropsychological tests were conducted. Enzyme-linked immunosorbent assay (ELISA) and Seqnome method were used to detect the concentration of plasma 24-OHC and the CYP46A1 rs754203 genotype, respectively.

Results

Compared with 118 healthy cognition participants, patients with MCI (n = 75) displayed a higher plasma level of 24-OHC and total cholesterol concentration (all p = 0.031), while no correlation was found between them. In the overall diabetes population, the plasma level of 24-OHC was negatively correlated with MoCA (r = −0.150, p = 0.039), and it was further proved to be an independent risk factor of diabetic MCI (OR = 1.848, p = 0.001). Additionally, patients with MCI and the CC genotype of CYP46A1 rs754203 showed the highest plasma level of 24-OHC even though the difference was not statistically significant, and they obtained low scores in both the verbal fluency test and Stroop color and word test A (p = 0.008 and p = 0.029, respectively).

Conclusion

In patients with T2DM, high plasma level of 24-OHC and the CC genotype carrier of CYP46A1 rs754203 may portend a high risk of developing early cognitive impairment, including attention and executive deficits.

Predicting the Prognosis of MCI Patients Using Longitudinal MRI Data

The aim of this study is to develop a computer-aided diagnosis system with a deep-learning approach for distinguishing "Mild Cognitive Impairment (MCI) due to Alzheimer's Disease (AD)" patients among a list of MCI patients. In this system we are using the power of longitudinal data extracted from magnetic resonance (MR). For this work, a total of 294 MCI patients were selected from the ADNI database. Among them, 125 patients developed AD during their follow-up and the rest remained stable. The proposed computer-aided diagnosis system (CAD) attempts to identify brain regions that are significant for the prediction of developing AD. The longitudinal data were constructed using a 3D Jacobian-based method aiming to track the brain differences between two consecutive follow-ups. The proposed CAD system distinguishes MCI patients who developed AD from those who remained stable with an accuracy of 87.2 percent. Moreover, it does not depend on data acquired by invasive methods or cognitive tests. This work demonstrates that the use of data in different time periods contains information that is beneficial for prognosis prediction purposes that outperform similar methods and are slightly inferior only to those systems that use invasive methods or neuropsychological tests.