Predictive markers for AD in a multi-modality framework: an analysis of MCI progression in the ADNI population

Hybrid multi-modality multi-task learning for forecasting progression trajectories in subjective cognitive decline

While numerous studies strive to exploit the complementary potential of MRI and PET using learning-based methods, the effective fusion of the two modalities remains a tricky problem due to their inherently distinctive properties. In addition, current studies often face the problem of small sample sizes and missing PET data due to factors such as patient withdrawal or low image quality. To this end, we propose a hybrid multi-modality multi-task learning (HM2L) framework with cross-domain knowledge transfer for forecasting trajectories of SCD progression. Our HM2L comprises (1) missing PET imputation, (2) multi-modality feature extraction for MRI and PET feature learning with a novel softmax-triplet constraint, (3) attention-based multi-modality fusion of MRI and PET features, and (4) multi-task prediction of category labels and clinical scores such as Mini-Mental State Examination (MMSE) and Geriatric Depression Scale (GDS). To handle problems with small sample sizes, a transfer learning strategy is developed to enable knowledge transfer from a relatively large scale dataset with MRI and PET from 795 subjects to two small-scale SCD cohorts with a total of 136 subjects. Experimental results indicate HM2L surpasses several state-of-the-art methods in jointly predicting category labels and clinical scores of subjective cognitive decline. Results show that the MMSE scores of SCD subjects who develop mild cognitive impairment during the 2-year/7-year follow-up are significantly lower than those of subjects who remain stable, while there exists a complex relationship between SCD progression with GDS.

Identifying Alzheimer's Disease Progression Subphenotypes via a Graph-based Framework using Electronic Health Records

Purpose

Understanding the heterogeneity of neurodegeneration in Alzheimer's disease (AD) development, as well as identifying AD progression pathways, is vital for enhancing diagnosis, treatment, prognosis, and prevention strategies. To identify disease progression subphenotypes in patients with mild cognitive impairment (MCI) and AD using electronic health records (EHRs).

Methods

We identified patients with mild cognitive impairment (MCI) and AD from the electronic health records from the OneFlorida+ Clinical Research Consortium. We proposed an outcome-oriented graph neural network-based model to identify progression pathways from MCI to AD.

Results

Of the included 2,525 patients, 61.66% were female, and the mean age was 76. In this cohort, 64.83% were Non-Hispanic White (NHW), 16.48% were Non-Hispanic Black (NHB), and 2.53% were of other races. Additionally, there were 274 Hispanic patients, accounting for 10.85% of the total patient population. The average duration from the first MCI diagnosis to the transition to AD was 891 days. We identified four progression subphenotypes, each with distinct characteristics. The average progression times from MCI to AD varied among these subphenotypes, ranging from 805 to 1,236 days.

Conclusion

The findings suggest that AD does not follow uniform transitions of disease states but rather exhibits heterogeneous progression pathways. Our proposed framework holds the potential to identify AD progression subphenotypes, providing valuable and explainable insights for the development of the disease.

Classification of neuroimaging data in Alzheimer's disease using particle swarm optimization: A systematic review

AIM

Particle swarm optimization (PSO) is an algorithm that involves the optimization of Non-linear and Multidimensional problems to reach the best solutions with minimal parameterization. This metaheuristic model has frequently been used in the Pathological domain. This optimization model has been used in diverse forms while predicting Alzheimer's disease. It is a robust algorithm that works on linear and multi-modal data while predicting Alzheimer's disease. PSO techniques have been in action for quite some time for detecting various diseases and this paper systematically reviews the papers on various kinds of PSO techniques.

METHODS

To perform the systematic review, PRISMA guidelines were followed and a Boolean search ("particle swarm optimization" OR "PSO") AND Neuroimaging AND (Alzheimer's disease prediction OR classification OR diagnosis) were performed. The query was run in 4-reputed databases: Google Scholar, Scopus, Science Direct, and Wiley publications.

RESULTS

For the final analysis, 10 papers were incorporated for qualitative and quantitative synthesis. PSO has shown a dominant character while handling the uni-modal as well as the multi-modal data while predicting the conversion from MCI to Alzheimer's. It can be seen from the table that almost all the 10 reviewed papers had MRI-driven data. The accuracy rate was accentuated while adding other modalities or Neurocognitive measures.

CONCLUSIONS

Through this algorithm, we are providing an opportunity to other researchers to compare this algorithm with other state-of-the-art algorithms, while seeing the classification accuracy, with the aim of early prediction and progression of MCI into Alzheimer's disease.

Evaluating conversion from mild cognitive impairment to Alzheimer's disease with structural MRI: a machine learning study

Alzheimer's disease is a disabling neurodegenerative disorder for which no effective treatment currently exists. To predict the diagnosis of Alzheimer's disease could be crucial for patients' outcome, but current Alzheimer's disease biomarkers are invasive, time consuming or expensive. Thus, developing MRI-based computational methods for Alzheimer's disease early diagnosis would be essential to narrow down the phenotypic measures predictive of cognitive decline. Amnestic mild cognitive impairment (aMCI) is associated with higher risk for Alzheimer's disease, and here, we aimed to identify MRI-based quantitative rules to predict aMCI to possible Alzheimer's disease conversion, applying different machine learning algorithms sequentially. At baseline, T1-weighted brain images were collected for 104 aMCI patients and processed to obtain 146 volumetric measures of cerebral grey matter regions [regions of interest (ROIs)]. One year later, patients were classified as converters (aMCI-c = 32) or non-converters, i.e. clinically and neuropsychologically stable (aMCI-s = 72) based on cognitive performance. Feature selection was performed by random forest (RF), and the identified seven ROIs volumetric data were used to implement support vector machine (SVM) and decision tree (DT) classification algorithms. Both SVM and DT reached an average accuracy of 86% in identifying aMCI-c and aMCI-s. DT found a critical threshold volume of the right entorhinal cortex (EC-r) as the first feature for differentiating aMCI-c/aMCI-s. Almost all aMCI-c had an EC-r volume <1286 mm3, while more than half of the aMCI-s patients had a volume above the identified threshold for this structure. Other key regions for the classification between aMCI-c/aMCI-s were the left lateral occipital (LOC-l), the middle temporal gyrus and the temporal pole cortices. Our study reinforces previous evidence suggesting that the morphometry of the EC-r and LOC-l best predicts aMCI to Alzheimer's disease conversion. Further investigations are needed prior to deeming our findings as a broadly applicable predictive framework. However, here, a first indication was derived for volumetric thresholds that, being easy to obtain, may assist in early identification of Alzheimer's disease in clinical practice, thus contributing to establishing MRI as a useful non-invasive prognostic instrument for dementia onset.

Frontiers and hotspots evolution in mild cognitive impairment: a bibliometric analysis of from 2013 to 2023

Background

Mild cognitive impairment is a heterogeneous syndrome. The heterogeneity of the syndrome and the absence of consensus limited the advancement of MCI. The purpose of our research is to create a visual framework of the last decade, highlight the hotspots of current research, and forecast the most fruitful avenues for future MCI research.

Methods

We collected all the MCI-related literature published between 1 January 2013, and 24 April 2023, on the "Web of Science." The visual graph was created by the CiteSpace and VOSviewer. The current research hotspots and future research directions are summarized through the analysis of keywords and co-cited literature.

Results

There are 6,075 articles were included in the final analysis. The number of publications shows an upward trend, especially after 2018. The United States and the University of California System are the most prolific countries and institutions, respectively. Petersen is the author who ranks first in terms of publication volume and influence. Journal of Alzheimer's Disease was the most productive journal. "neuroimaging," "fluid markers," and "predictors" are the focus of current research, and "machine learning," "electroencephalogram," "deep learning," and "blood biomarkers" are potential research directions in the future.

Conclusion

The cognition of MCI has been continuously evolved and renewed by multiple countries' joint efforts in the past decade. Hotspots for current research are on diagnostic biomarkers, such as fluid markers, neuroimaging, and so on. Future hotspots might be focused on the best prognostic and diagnostic models generated by machine learning and large-scale screening tools such as EEG and blood biomarkers.

Predicting changes in brain metabolism and progression from mild cognitive impairment to dementia using multitask Deep Learning models and explainable AI

BACKGROUND

The prediction of Alzheimer's disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI).

METHODS

We analyzed data from 1,617 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had undergone at least one FDG-PET scan. We identified the brain regions with the most significant hypometabolism in AD and used Deep Learning (DL) models to predict future changes in brain metabolism. The best-performing model was then adapted under a multi-task learning framework to identify pMCI individuals. Finally, this model underwent further analysis using eXplainable AI (XAI) techniques.

RESULTS

Our results confirm a strong association between hypometabolism, disease progression, and cognitive decline. Furthermore, we demonstrated that integrating data on changes in brain metabolism during training enhanced the models' ability to detect pMCI individuals (sensitivity=88.4%, specificity=86.9%). Lastly, the application of XAI techniques enabled us to delve into the brain regions with the most significant impact on model predictions, highlighting the importance of the hippocampus, cingulate cortex, and some subcortical structures.

CONCLUSION

This study introduces a novel dimension to predictive modeling in AD, emphasizing the importance of projecting variations in brain metabolism under a multi-task learning paradigm.

Autoencoder to Identify Sex-Specific Sub-phenotypes in Alzheimer's Disease Progression Using Longitudinal Electronic Health Records

Alzheimer's Disease (AD) is a complex neurodegenerative disorder significantly influenced by sex differences, with approximately two-thirds of AD patients being women. Characterizing the sex-specific AD progression and identifying its progression trajectory is a crucial step to developing effective risk stratification and prevention strategies. In this study, we developed an autoencoder to uncover sex-specific sub-phenotypes in AD progression leveraging longitudinal electronic health record (EHR) data from OneFlorida+ Clinical Research Consortium. Specifically, we first constructed temporal patient representation using longitudinal EHRs from a sex-stratified AD cohort. We used a long short-term memory (LSTM)-based autoencoder to extract and generate latent representation embeddings from sequential clinical records of patients. We then applied hierarchical agglomerative clustering to the learned representations, grouping patients based on their progression sub-phenotypes. The experimental results show we successfully identified five primary sex-based AD sub-phenotypes with corresponding progression pathways with high confidence. These sex-specific sub-phenotypes not only illustrated distinct AD progression patterns but also revealed differences in clinical characteristics and comorbidities between females and males in AD development. These findings could provide valuable insights for advancing personalized AD intervention and treatment strategies.

Predicting the Conversion from Mild Cognitive Impairment to Alzheimer's Disease Using Graph Frequency Bands and Functional Connectivity-Based Features

Accurate prediction of the progression from mild cognitive impairment (MCI) to Alzheimer's disease (AD) is crucial for disease management. Machine learning techniques have demonstrated success in classifying AD and MCI cases, particularly with the use of resting-state functional magnetic resonance imaging (rs-fMRI) data.This study utilized three years of rs-fMRI data from the ADNI, involving 142 patients with stable MCI (sMCI) and 136 with progressive MCI (pMCI). Graph signal processing was applied to filter rs-fMRI data into low, middle, and high frequency bands. Connectivity-based features were derived from both filtered and unfiltered data, resulting in a comprehensive set of 100 features, including global graph metrics, minimum spanning tree (MST) metrics, triadic interaction metrics, hub tendency metrics, and the number of links. Feature selection was enhanced using particle swarm optimization (PSO) and simulated annealing (SA). A support vector machine (SVM) with a radial basis function (RBF) kernel and a 10-fold cross-validation setup were employed for classification. The proposed approach demonstrated superior performance, achieving optimal accuracy with minimal feature utilization. When PSO selected five features, SVM exhibited accuracy, specificity, and sensitivity rates of 77%, 70%, and 83%, respectively. The identified features were as follows: (Mean of clustering coefficient, Mean of strength)/Radius/(Mean Eccentricity, and Modularity) from low/middle/high frequency bands of graph. The study highlights the efficacy of the proposed framework in identifying individuals at risk of AD development using a parsimonious feature set. This approach holds promise for advancing the precision of MCI to AD progression prediction, aiding in early diagnosis and intervention strategies.

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.

A multimodal machine learning model for predicting dementia conversion in Alzheimer's disease

Alzheimer's disease (AD) accounts for 60-70% of the population with dementia. Mild cognitive impairment (MCI) is a diagnostic entity defined as an intermediate stage between subjective cognitive decline and dementia, and about 10-15% of people annually convert to AD. We aimed to investigate the most robust model and modality combination by combining multi-modality image features based on demographic characteristics in six machine learning models. A total of 196 subjects were enrolled from four hospitals and the Alzheimer's Disease Neuroimaging Initiative dataset. During the four-year follow-up period, 47 (24%) patients progressed from MCI to AD. Volumes of the regions of interest, white matter hyperintensity, and regional Standardized Uptake Value Ratio (SUVR) were analyzed using T1, T2-weighted-Fluid-Attenuated Inversion Recovery (T2-FLAIR) MRIs, and amyloid PET (αPET), along with automatically provided hippocampal occupancy scores (HOC) and Fazekas scales. As a result of testing the robustness of the model, the GBM model was the most stable, and in modality combination, model performance was further improved in the absence of T2-FLAIR image features. Our study predicts the probability of AD conversion in MCI patients, which is expected to be useful information for clinician's early diagnosis and treatment plan design.

Intelligent prediction of Alzheimer's disease via improved multifeature squeeze-and-excitation-dilated residual network

This study aimed to address the issue of larger prediction errors existing in intelligent predictive tasks related to Alzheimer's disease (AD). A cohort of 487 enrolled participants was categorized into three groups: normal control (138 individuals), mild cognitive impairment (238 patients), and AD (111 patients) in this study. An improved multifeature squeeze-and-excitation-dilated residual network (MFSE-DRN) was proposed for two important AD predictions: clinical scores and conversion probability. The model was characterized as three modules: squeeze-and-excitation-dilated residual block (SE-DRB), multifusion pooling (MF-Pool), and multimodal feature fusion. To assess its performance, the proposed model was compared with two other novel models: ranking convolutional neural network (RCNN) and 3D vision geometrical group network (3D-VGGNet). Our method showed the best performance in the two AD predicted tasks. For the clinical scores prediction, the root-mean-square errors (RMSEs) and mean absolute errors (MAEs) of mini-mental state examination (MMSE) and AD assessment scale-cognitive 11-item (ADAS-11) were 1.97, 1.46 and 4.20, 3.19 within 6 months; 2.48, 1.69 and 4.81, 3.44 within 12 months; 2.67, 1.86 and 5.81, 3.83 within 24 months; 3.02, 2.03 and 5.09, 3.43 within 36 months, respectively. At the AD conversion probability prediction, the prediction accuracies within 12, 24, and 36 months reached to 88.0, 85.5, and 88.4%, respectively. The AD predication would play a great role in clinical applications.

Novel Biomarkers for Alzheimer's Disease: Plasma Neurofilament Light and Cerebrospinal Fluid

Neurodegenerative disorders such as Alzheimer's disease (AD) represent an increasingly significant public health concern. As clinical diagnosis faces challenges, biomarkers are becoming increasingly important in research, trials, and patient assessments. While biomarkers like amyloid-β peptide, tau proteins, CSF levels (Aβ, tau, and p-tau), and neuroimaging techniques are commonly used in AD diagnosis, they are often limited and invasive in monitoring and diagnosis. For this reason, blood-based biomarkers are the optimal choice for detecting neurodegeneration in brain diseases due to their noninvasiveness, affordability, reliability, and consistency. This literature review focuses on plasma neurofilament light (NfL) and CSF NfL as blood-based biomarkers used in recent AD diagnosis. The findings revealed that the core CSF biomarkers of neurodegeneration (T-tau, P-tau, and Aβ42), CSF NFL, and plasma T-tau were strongly associated with Alzheimer's disease, and the core biomarkers were strongly associated with mild cognitive impairment due to Alzheimer's disease. Elevated levels of plasma and cerebrospinal fluid NfL were linked to decreased [18F]FDG uptake in corresponding brain areas. In participants with Aβ positivity (Aβ+), NfL correlated with reduced metabolism in regions susceptible to Alzheimer's disease. In addition, CSF NfL levels correlate with brain atrophy and predict cognitive changes, while plasma total tau does not. Plasma P-tau, especially in combination with Aβ42/Aβ40, is promising for symptomatic AD stages. Though not AD-exclusive, blood NfL holds promise for neurodegeneration detection and assessing treatment efficacy. Given the consistent levels of T-tau, P-tau, Aβ42, and NFL in CSF, their incorporation into both clinical practice and research is highly recommended.

Predicting mild cognitive impairment in older adults: A machine learning analysis of the Alzheimer's Disease Neuroimaging Initiative

AIM

Mild cognitive impairment (MCI) in older adults is potentially devastating, but an accurate prediction model is still lacking. We hypothesized that neuropsychological tests and MRI-related markers could predict the onset of MCI early.

METHODS

We analyzed data from 306 older adults who were cognitive normal (CN) attending the Alzheimer's Disease Neuroimaging Initiative sequentially (474 pairs of visits) within 3 years. There were 231 pairs of MCI conversion (CN to MCI), and 242 pairs of CN maintenance (CN to CN). Variables on demographic, neuropsychological tests, genetic, and MRI-related markers were collected. Machine learning was used to construct MCI prediction models, comparing the area under the receiver operating characteristic curve (AUC) as the primary metric of performance. Important predictors were ranked for the optimal model.

RESULTS

The baseline age of the study sample was 74.8 years old. The best-performing model (gradient boosting decision tree) with 13 variables predicted MCI with an AUC of 0.819, and the rank of variable importance showed that intracranial volume, hippocampal volume, and score from task 4 (word recognition) of the Alzheimer's Disease Assessment Scale were important predictors of MCI.

CONCLUSIONS

With the help of machine learning, fewer neuropsychological tests and MRI-related markers are required to accurately predict MCI within 3 years, thereby facilitating targeted intervention. Geriatr Gerontol Int 2024; 24: 96-101.

Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer's Disease Using Electronic Health Records

Alzheimer's disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. In this study, we proposed an outcome-oriented model to identify progression pathways from mild cognitive impairment (MCI) to AD using electronic health records (EHRs) from the OneFlorida+ Clinical Research Consortium. To achieve this, we employed the long short-term memory (LSTM) network to extract relevant information from the sequential records of each patient. The hierarchical agglomerative clustering was then applied to the learned representation to group patients based on their progression subtypes. Our approach identified multiple progression pathways, each of which represented distinct patterns of disease progression from MCI to AD. These pathways can serve as a valuable resource for researchers to understand the factors influencing AD progression and to develop personalized interventions to delay or prevent the onset of the disease.

Machine Learning Approach for Improved Longitudinal Prediction of Progression from Mild Cognitive Impairment to Alzheimer's Disease

Mild cognitive impairment (MCI) is cognitive decline that can indicate future risk of Alzheimer's disease (AD). We developed and validated a machine learning algorithm (MLA), based on a gradient-boosted tree ensemble method, to analyze phenotypic data for individuals 55-88 years old (n = 493) diagnosed with MCI. Data were analyzed within multiple prediction windows and averaged to predict progression to AD within 24-48 months. The MLA outperformed the mini-mental state examination (MMSE) and three comparison models at all prediction windows on most metrics. Exceptions include sensitivity at 18 months (MLA and MMSE each achieved 0.600); and sensitivity at 30 and 42 months (MMSE marginally better). For all prediction windows, the MLA achieved AUROC ≥ 0.857 and NPV ≥ 0.800. With averaged data for the 24-48-month lookahead timeframe, the MLA outperformed MMSE on all metrics. This study demonstrates that machine learning may provide a more accurate risk assessment than the standard of care. This may facilitate care coordination, decrease healthcare expenditures, and maintain quality of life for patients at risk of progressing from MCI to AD.

Multimodal transformer network for incomplete image generation and diagnosis of Alzheimer's disease

Multimodal images such as magnetic resonance imaging (MRI) and positron emission tomography (PET) could provide complementary information about the brain and have been widely investigated for the diagnosis of neurodegenerative disorders such as Alzheimer's disease (AD). However, multimodal brain images are often incomplete in clinical practice. It is still challenging to make use of multimodality for disease diagnosis with missing data. In this paper, we propose a deep learning framework with the multi-level guided generative adversarial network (MLG-GAN) and multimodal transformer (Mul-T) for incomplete image generation and disease classification, respectively. First, MLG-GAN is proposed to generate the missing data, guided by multi-level information from voxels, features, and tasks. In addition to voxel-level supervision and task-level constraint, a feature-level auto-regression branch is proposed to embed the features of target images for an accurate generation. With the complete multimodal images, we propose a Mul-T network for disease diagnosis, which can not only combine the global and local features but also model the latent interactions and correlations from one modality to another with the cross-modal attention mechanism. Comprehensive experiments on three independent datasets (i.e., ADNI-1, ADNI-2, and OASIS-3) show that the proposed method achieves superior performance in the tasks of image generation and disease diagnosis compared to state-of-the-art methods.

Predicting mild cognitive impairments from cognitively normal brains using a novel brain age estimation model based on structural magnetic resonance imaging

Brain age prediction is a practical method used to quantify brain aging and detect neurodegenerative diseases such as Alzheimer's disease (AD). However, very few studies have considered brain age prediction as a biomarker for the conversion of cognitively normal (CN) to mild cognitive impairment (MCI). In this study, we developed a novel brain age prediction model using brain volume and cortical thickness features. We calculated an acceleration of brain age (ABA) derived from the suggested model to estimate different diagnostic groups (CN, MCI, and AD) and to classify CN to MCI and MCI to AD conversion groups. We observed a strong association between ABA and the 3 diagnostic groups. Additionally, the classification models for CN to MCI conversion and MCI to AD conversion exhibited acceptable and robust performances, with area under the curve values of 0.66 and 0.76, respectively. We believe that our proposed model provides a reliable estimate of brain age for elderly individuals and can identify those at risk of progressing from CN to MCI. This model has great potential to reveal a diagnosis associated with a change in cognitive decline.

Hybrid Multimodality Fusion with Cross-Domain Knowledge Transfer to Forecast Progression Trajectories in Cognitive Decline

Magnetic resonance imaging (MRI) and positron emission tomography (PET) are increasingly used to forecast progression trajectories of cognitive decline caused by preclinical and prodromal Alzheimer's disease (AD). Many existing studies have explored the potential of these two distinct modalities with diverse machine and deep learning approaches. But successfully fusing MRI and PET can be complex due to their unique characteristics and missing modalities. To this end, we develop a hybrid multimodality fusion (HMF) framework with cross-domain knowledge transfer for joint MRI and PET representation learning, feature fusion, and cognitive decline progression forecasting. Our HMF consists of three modules: 1) a module to impute missing PET images, 2) a module to extract multimodality features from MRI and PET images, and 3) a module to fuse the extracted multimodality features. To address the issue of small sample sizes, we employ a cross-domain knowledge transfer strategy from the ADNI dataset, which includes 795 subjects, to independent small-scale AD-related cohorts, in order to leverage the rich knowledge present within the ADNI. The proposed HMF is extensively evaluated in three AD-related studies with 272 subjects across multiple disease stages, such as subjective cognitive decline and mild cognitive impairment. Experimental results demonstrate the superiority of our method over several state-of-the-art approaches in forecasting progression trajectories of AD-related cognitive decline.

Whole Person Modeling: a transdisciplinary approach to mental health research

The growing global burden of mental illness has prompted calls for innovative research strategies. Theoretical models of mental health include complex contributions of biological, psychosocial, experiential, and other environmental influences. Accordingly, neuropsychiatric research has self-organized into largely isolated disciplines working to decode each individual contribution. However, research directly modeling objective biological measurements in combination with cognitive, psychological, demographic, or other environmental measurements is only now beginning to proliferate. This review aims to (1) to describe the landscape of modern mental health research and current movement towards integrative study, (2) to provide a concrete framework for quantitative integrative research, which we call Whole Person Modeling, (3) to explore existing and emerging techniques and methods used in Whole Person Modeling, and (4) to discuss our observations about the scarcity, potential value, and untested aspects of highly transdisciplinary research in general. Whole Person Modeling studies have the potential to provide a better understanding of multilevel phenomena, deliver more accurate diagnostic and prognostic tests to aid in clinical decision making, and test long standing theoretical models of mental illness. Some current barriers to progress include challenges with interdisciplinary communication and collaboration, systemic cultural barriers to transdisciplinary career paths, technical challenges in model specification, bias, and data harmonization, and gaps in transdisciplinary educational programs. We hope to ease anxiety in the field surrounding the often mysterious and intimidating world of transdisciplinary, data-driven mental health research and provide a useful orientation for students or highly specialized researchers who are new to this area.

Identification of Outcome-Oriented Progression Subtypes from Mild Cognitive Impairment to Alzheimer's Disease Using Electronic Health Records

Alzheimer's disease (AD) is a complex heterogeneous neurodegenerative disease that requires an in-depth understanding of its progression pathways and contributing factors to develop effective risk stratification and prevention strategies. In this study, we proposed an outcome-oriented model to identify progression pathways from mild cognitive impairment (MCI) to AD using electronic health records (EHRs) from the OneFlorida+ Clinical Research Consortium. To achieve this, we employed the long short-term memory (LSTM) network to extract relevant information from the sequential records of each patient. The hierarchical agglomerative clustering was then applied to the learned representation to group patients based on their progression subtypes. Our approach identified multiple progression pathways, each of which represented distinct patterns of disease progression from MCI to AD. These pathways can serve as a valuable resource for researchers to understand the factors influencing AD progression and to develop personalized interventions to delay or prevent the onset of the disease.

Multi-modal cross-attention network for Alzheimer's disease diagnosis with multi-modality data

Alzheimer's disease (AD) is a neurodegenerative disorder, the most common cause of dementia, so the accurate diagnosis of AD and its prodromal stage mild cognitive impairment (MCI) is significant. Recent studies have demonstrated that multiple neuroimaging and biological measures contain complementary information for diagnosis. Many existing multi-modal models based on deep learning simply concatenate each modality's features despite substantial differences in representation spaces. In this paper, we propose a novel multi-modal cross-attention AD diagnosis (MCAD) framework to learn the interaction between modalities for better playing their complementary roles for AD diagnosis with multi-modal data including structural magnetic resonance imaging (sMRI), fluorodeoxyglucose-positron emission tomography (FDG-PET) and cerebrospinal fluid (CSF) biomarkers. Specifically, the imaging and non-imaging representations are learned by the image encoder based on cascaded dilated convolutions and CSF encoder, respectively. Then, a multi-modal interaction module is introduced, which takes advantage of cross-modal attention to integrate imaging and non-imaging information and reinforce relationships between these modalities. Moreover, an extensive objective function is designed to reduce the discrepancy between modalities for effectively fusing the features of multi-modal data, which could further improve the diagnosis performance. We evaluate the effectiveness of our proposed method on the ADNI dataset, and the extensive experiments demonstrate that our MCAD achieves superior performance for multiple AD-related classification tasks, compared to several competing methods. Also, we investigate the importance of cross-attention and the contribution of each modality to the diagnostics performance. The experimental results demonstrate that combining multi-modality data via cross-attention is helpful for accurate AD diagnosis.

Identification of subjective cognitive decline due to Alzheimer's disease using multimodal MRI combining with machine learning

Subjective cognitive decline (SCD) is a preclinical asymptomatic stage of Alzheimer's disease (AD). Accurate diagnosis of SCD represents the greatest challenge for current clinical practice. The multimodal magnetic resonance imaging (MRI) features of 7 brain networks and 90 regions of interests from Chinese and ANDI cohorts were calculated. Machine learning (ML) methods based on support vector machine (SVM) were used to classify SCD plus and normal control. To assure the robustness of ML model, above analyses were repeated in amyloid β (Aβ) and apolipoprotein E (APOE) ɛ4 subgroups. We found that the accuracy of the proposed multimodal SVM method achieved 79.49% and 83.13%, respectively, in Chinese and ANDI cohorts for the diagnosis of the SCD plus individuals. Furthermore, adding Aβ pathology and ApoE ɛ4 genotype information can further improve the accuracy to 85.36% and 82.52%. More importantly, the classification model exhibited the robustness in the crossracial cohorts and different subgroups, which outperforms any single and 2 modalities. The study indicates that multimodal MRI imaging combining with ML classification method yields excellent and powerful performances at categorizing SCD due to AD, suggesting potential for clinical utility.

Detection of Mild Cognitive Impairment from Language Markers with Crossmodal Augmentation

Mild cognitive impairment is the prodromal stage of Alzheimer's disease. Its detection has been a critical task for establishing cohort studies and developing therapeutic interventions for Alzheimer's. Various types of markers have been developed for detection. For example, imaging markers from neuroimaging have shown great sensitivity, while its cost is still prohibitive for large-scale screening of early dementia. Recent advances from digital biomarkers, such as language markers, have provided an accessible and affordable alternative. While imaging markers give anatomical descriptions of the brain, language markers capture the behavior characteristics of early dementia subjects. Such differences suggest the benefits of auxiliary information from the imaging modality to improve the predictive power of unimodal predictive models based on language markers alone. However, one significant barrier to the joint analysis is that in typical cohorts, there are only very limited subjects that have both imaging and language modalities. To tackle this challenge, in this paper, we develop a novel crossmodal augmentation tool, which leverages auxiliary imaging information to improve the feature space of language markers so that a subject with only language markers can benefit from imaging information through the augmentation. Our experimental results show that the multi-modal predictive model trained with language markers and auxiliary imaging information significantly outperforms unimodal predictive models.

Multi-stage classification of Alzheimer's disease from 18F-FDG-PET images using deep learning techniques

The study aims to implement a convolutional neural network framework that uses the 18F-FDG PET modality of brain imaging to detect multiple stages of dementia, including Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI), and Alzheimer's disease (AD) from Cognitively Normal (CN), and assess the results. 18F-FDG PET imaging modality for brain were procured from Alzheimer's disease neuroimaging initiative's (ADNI) repository. The ResNet50V2 model layers were utilised for feature extraction, with the final convolutional layers fine-tuned for this dataset's multi-classification objectives. Multiple metrics and feature maps were utilized to scrutinize and evaluate the model's statistical and qualitative inference. The multi-classification model achieved an overarching accuracy of 98.44% and Area under the receiver operating characteristic curve of 95% on the testing set. Feature maps aided in deducing finer aspects of the model's overall operation. This framework helped classifying from the 18F-FDG PET brain images, the subtypes of Mild Cognitive Impairment (MCI) which include EMCI, LMCI, from AD, CN groups and achieved an all-inclusive sensitivity of 94% and specificity of 95% respectively.

Multi-modal intermediate integrative methods in neuropsychiatric disorders: A review

The etiology of neuropsychiatric disorders involves complex biological processes at different omics layers, such as genomics, transcriptomics, epigenetics, proteomics, and metabolomics. The advent of high-throughput technology, as well as the availability of large open-source datasets, has ushered in a new era in system biology, necessitating the integration of various types of omics data. The complexity of biological mechanisms, the limitations of integrative strategies, and the heterogeneity of multi-omics data have all presented significant challenges to computational scientists. In comparison to early and late integration, intermediate integration may transform each data type into appropriate intermediate representations using various data transformation techniques, allowing it to capture more complementary information contained in each omics and highlight new interactions across omics layers. Here, we reviewed multi-modal intermediate integrative techniques based on component analysis, matrix factorization, similarity network, multiple kernel learning, Bayesian network, artificial neural networks, and graph transformation, as well as their applications in neuropsychiatric domains. We depicted advancements in these approaches and compared the strengths and weaknesses of each method examined. We believe that our findings will aid researchers in their understanding of the transformation and integration of multi-omics data in neuropsychiatric disorders.

Predict DLBCL patients' recurrence within two years with Gaussian mixture model cluster oversampling and multi-kernel learning

BACKGROUND AND OBJECTIVE

Diffuse large B-cell lymphoma (DLBCL) is common in adults' non-Hodgkin's lymphoma. Relapse mainly occurs within two years after diagnosis and has a poor prognosis. Relapse after two years is less frequent and has a better prognosis. In this work, we constructed a relapse prediction model for diffuse large B-cell lymphoma patients within two years, expecting to provide a reference for Clinicians to implement individualized treatment.

METHOD

We propose a secondary-level class imbalance method based on Gaussian mixture model (GMM) clustering resampling to balance the data. Then use a multi-kernel support vector machine(SVM) to inscribe heterogeneous clinical data. Finally, merging them to identify recurrence patients within two years.

RESULTS

Among all the class imbalance methods in this work, Inverse Weighted -GMM +SMOTEENN has the best performance. Compared with NO-GMM (Directl use the SMOTEENN without the GMM clustering process), its Area Under the ROC Curve(AUC) increases by 8.75%, and ECE and brier scores decrease 2.07% and 3.09%, respectively. Among the four classification algorithms in this work, Multiple kernel learning (MKL) has the most minimized brier scores and expected calibration error(ECE), the largest AUC, accuracy, Recall, precision and F1, has the best discrimination and calibration.

CONCLUSION

Our inverse weighted -GMM+SMOTEENN+MKL (GMM-SENN-MKL) method can handle data class imbalance and clinical heterogeneity data well and can be used to predict recurrence in DLBCL patients.

Latent feature representation learning for Alzheimer's disease classification

Early detection and treatment of Alzheimer's Disease (AD) are significant. Recently, multi-modality imaging data have promoted the development of the automatic diagnosis of AD. This paper proposes a method based on latent feature fusion to make full use of multi-modality image data information. Specifically, we learn a specific projection matrix for each modality by introducing a binary label matrix and local geometry constraints and then project the original features of each modality into a low-dimensional target space. In this space, we fuse latent feature representations of different modalities for AD classification. The experimental results on Alzheimer's Disease Neuroimaging Initiative database demonstrate the proposed methods effectiveness in classifying AD.

Automated Classification of Mild Cognitive Impairment by Machine Learning With Hippocampus-Related White Matter Network

Background

Detection of mild cognitive impairment (MCI) is essential to screen high risk of Alzheimer’s disease (AD). However, subtle changes during MCI make it challenging to classify in machine learning. The previous pathological analysis pointed out that the hippocampus is the critical hub for the white matter (WM) network of MCI. Damage to the white matter pathways around the hippocampus is the main cause of memory decline in MCI. Therefore, it is vital to biologically extract features from the WM network driven by hippocampus-related regions to improve classification performance.

Methods

Our study proposes a method for feature extraction of the whole-brain WM network. First, 42 MCI and 54 normal control (NC) subjects were recruited using diffusion tensor imaging (DTI), resting-state functional magnetic resonance imaging (rs-fMRI), and T1-weighted (T1w) imaging. Second, mean diffusivity (MD) and fractional anisotropy (FA) were calculated from DTI, and the whole-brain WM networks were obtained. Third, regions of interest (ROIs) with significant functional connectivity to the hippocampus were selected for feature extraction, and the hippocampus (HIP)-related WM networks were obtained. Furthermore, the rank sum test with Bonferroni correction was used to retain significantly different connectivity between MCI and NC, and significant HIP-related WM networks were obtained. Finally, the classification performances of these three WM networks were compared to select the optimal feature and classifier.

Results

(1) For the features, the whole-brain WM network, HIP-related WM network, and significant HIP-related WM network are significantly improved in turn. Also, the accuracy of MD networks as features is better than FA. (2) For the classification algorithm, the support vector machine (SVM) classifier with radial basis function, taking the significant HIP-related WM network in MD as a feature, has the optimal classification performance (accuracy = 89.4%, AUC = 0.954). (3) For the pathologic mechanism, the hippocampus and thalamus are crucial hubs of the WM network for MCI.

Conclusion

Feature extraction from the WM network driven by hippocampus-related regions provides an effective method for the early diagnosis of AD.

Adaptive Multimodal Neuroimage Integration for Major Depression Disorder Detection

Major depressive disorder (MDD) is one of the most common mental health disorders that can affect sleep, mood, appetite, and behavior of people. Multimodal neuroimaging data, such as functional and structural magnetic resonance imaging (MRI) scans, have been widely used in computer-aided detection of MDD. However, previous studies usually treat these two modalities separately, without considering their potentially complementary information. Even though a few studies propose integrating these two modalities, they usually suffer from significant inter-modality data heterogeneity. In this paper, we propose an adaptive multimodal neuroimage integration (AMNI) framework for automated MDD detection based on functional and structural MRIs. The AMNI framework consists of four major components: (1) a graph convolutional network to learn feature representations of functional connectivity networks derived from functional MRIs, (2) a convolutional neural network to learn features of T1-weighted structural MRIs, (3) a feature adaptation module to alleviate inter-modality difference, and (4) a feature fusion module to integrate feature representations extracted from two modalities for classification. To the best of our knowledge, this is among the first attempts to adaptively integrate functional and structural MRIs for neuroimaging-based MDD analysis by explicitly alleviating inter-modality heterogeneity. Extensive evaluations are performed on 533 subjects with resting-state functional MRI and T1-weighted MRI, with results suggesting the efficacy of the proposed method.

Classification of Huntington's Disease Stage with Features Derived from Structural and Diffusion-Weighted Imaging

The purpose of this study was to classify Huntington’s disease (HD) stage using support vector machines and measures derived from T1- and diffusion-weighted imaging. The effects of feature selection approach and combination of imaging modalities are assessed. Fourteen premanifest-HD individuals (Pre-HD; on average > 20 years from estimated disease onset), eleven early-manifest HD (Early-HD) patients, and eighteen healthy controls (HC) participated in the study. We compared three feature selection approaches: (i) whole-brain segmented grey matter (GM; voxel-based measure) or fractional anisotropy (FA) values; (ii) GM or FA values from subcortical regions-of-interest (caudate, putamen, pallidum); and (iii) automated selection of GM or FA values with the algorithm Relief-F. We assessed single- and multi-kernel approaches to classify combined GM and FA measures. Significant classifications were achieved between Early-HD and Pre-HD or HC individuals (accuracy: generally, 85% to 95%), and between Pre-HD and controls for the feature FA of the caudate ROI (74% accuracy). The combination of GM and FA measures did not result in higher performances. We demonstrate evidence on the high sensitivity of FA for the classification of the earliest Pre-HD stages, and successful distinction between HD stages.

MRI Segmentation of Brain Tissue and Course Classification in Alzheimer’s Disease

Alzheimer’s disease (AD) is one of the most common diseases causing cognitive impairment in middle-aged and elderly people, and the high cost of the disease poses a challenge for health systems to cope with the expected increasing number of cases in the future. With the advance of aging of the society, China has the largest number of Alzheimer’s disease patients in the world. Therefore, how to diagnose Alzheimer’s disease early and accurately and intervene positively is an urgent problem. In this paper, the improved MultiRes + UNet network is used to effectively segment the brain tissue in the preprocessing. This method expands the convolutional field by null convolution to integrate the global information, mitigates the differences between encoder–decoder features by using MultiRes block and Res path structure, greatly reducing the memory requirement, and improving its accuracy, applicability, and robustness. The non-local means the attention model is introduced to make the mapped organization categories free from noise interference. In the classification problem, this paper adopts the improved VoxCNN network model for binary classification of AD, EMCI, LMCI, and NC. Experiments showed that the model classification performance and the accuracy rate improved significantly with the combined effect of the improved MultiRes + UNet network and VoxCNN network, the binary classification accuracy was 98.35% for AD vs. NC, 89.46% for AD vs. LMCI, 83.95% for LMCI vs. EMCI, and 88.27% for EMCI vs. NC.

Adaptive multimodal fusion with attention guided deep supervision net for grading hepatocellular carcinoma

Multimodal medical imaging plays a crucial role in the diagnosis and characterization of lesions. However, challenges remain in lesion characterization based on multimodal feature fusion. First, current fusion methods have not thoroughly studied the relative importance of characterization modals. In addition, multimodal feature fusion cannot provide the contribution of different modal information to inform critical decision-making. In this study, we propose an adaptive multimodal fusion method with an attention-guided deep supervision net for grading hepatocellular carcinoma (HCC). Specifically, our proposed framework comprises two modules: attention-based adaptive feature fusion and attention-guided deep supervision net. The former uses the attention mechanism at the feature fusion level to generate weights for adaptive feature concatenation and balances the importance of features among various modals. The latter uses the weight generated by the attention mechanism as the weight coefficient of each loss to balance the contribution of the corresponding modal to the total loss function. The experimental results of grading clinical HCC with contrast-enhanced MR demonstrated the effectiveness of the proposed method. A significant performance improvement was achieved compared with existing fusion methods. In addition, the weight coefficient of attention in multimodal fusion has demonstrated great significance in clinical interpretation.

Voxel-based morphometry and a deep learning model for the diagnosis of early Alzheimer's disease based on cerebral gray matter changes

This study aimed to analyse cerebral grey matter changes in mild cognitive impairment (MCI) using voxel-based morphometry and to diagnose early Alzheimer's disease using deep learning methods based on convolutional neural networks (CNNs) evaluating these changes. Participants (111 MCI, 73 normal cognition) underwent 3-T structural magnetic resonance imaging. The obtained images were assessed using voxel-based morphometry, including extraction of cerebral grey matter, analyses of statistical differences, and correlation analyses between cerebral grey matter and clinical cognitive scores in MCI. The CNN-based deep learning method was used to extract features of cerebral grey matter images. Compared to subjects with normal cognition, participants with MCI had grey matter atrophy mainly in the entorhinal cortex, frontal cortex, and bilateral frontotemporal lobes (p < 0.0001). This atrophy was significantly correlated with the decline in cognitive scores (p < 0.01). The accuracy, sensitivity, and specificity of the CNN model for identifying participants with MCI were 80.9%, 88.9%, and 75%, respectively. The area under the curve of the model was 0.891. These findings demonstrate that research based on brain morphology can provide an effective way for the clinical, non-invasive, objective evaluation and identification of early Alzheimer's disease.

Classification of Alzheimer’s Disease and Mild-Cognitive Impairment Base on High-Order Dynamic Functional Connectivity at Different Frequency Band

Functional brain connectivity networks obtained from resting-state functional magnetic resonance imaging (rs-fMRI) have been extensively utilized for the diagnosis of Alzheimer’s disease (AD). However, the traditional correlation analysis technique only explores the pairwise relation, which may not be suitable for revealing sufficient and proper functional connectivity links among brain regions. Additionally, previous literature typically focuses on only lower-order dynamics, without considering higher-order dynamic networks properties, and they particularly focus on single frequency range time series of rs-fMRI. To solve these problems, in this article, a new diagnosis scheme is proposed by constructing a high-order dynamic functional network at different frequency level time series (full-band (0.01–0.08 Hz); slow-4 (0.027–0.08 Hz); and slow-5 (0.01–0.027 Hz)) data obtained from rs-fMRI to build the functional brain network for all brain regions. Especially, to tune the precise analysis of the regularized parameters in the Support Vector Machine (SVM), a nested leave-one-out cross-validation (LOOCV) technique is adopted. Finally, the SVM classifier is trained to classify AD from HC based on these higher-order dynamic functional brain networks at different frequency ranges. The experiment results illustrate that for all bands with a LOOCV classification accuracy of 94.10% with a 90.95% of sensitivity, and a 96.75% of specificity outperforms the individual networks. Utilization of the given technique for the identification of AD from HC compete for the most state-of-the-art technology in terms of the diagnosis accuracy. Additionally, results obtained for the all-band shows performance further suggest that our proposed scheme has a high-rate accuracy. These results have validated the effectiveness of the proposed methods for clinical value to the identification of AD.

Scalable Non-Linear Graph Fusion for Prioritizing Cancer-Causing Genes

In the past few decades, both gene expression data and protein-protein interaction (PPI)networks have been extensively studied, due to their ability to depict important characteristics of disease-associated genes. In this regard, the paper presents a new gene prioritization algorithm to identify and prioritize cancer-causing genes, integrating judiciously the complementary information obtained from two data sources. The proposed algorithm selects disease-causing genes by maximizing the importance of selected genes and functional similarity among them. A new quantitative index is introduced to evaluate the importance of a gene. It considers whether a gene exhibits a differential expression pattern across sick and healthy individuals, and has a strong connectivity in the PPI network, which are the important characteristics of a potential biomarker. As disease-associated genes are expected to have similar expression profiles and topological structures, a scalable non-linear graph fusion technique, termed as ScaNGraF, is proposed to learn a disease-dependent functional similarity network from the co-expression and common neighbor based similarity networks. The proposed ScaNGraF, which is based on message passing algorithm, efficiently combines the shared and complementary information provided by different data sources with significantly lower computational cost. A new measure, termed as DiCoIN, is introduced to evaluate the quality of a learned affinity network. The performance of the proposed graph fusion technique and gene selection algorithm is extensively compared with that of some existing methods, using several cancer data sets.

Orthogonalized Kernel Debiased Machine Learning for Multimodal Data Analysis

Multimodal imaging has transformed neuroscience research. While it presents unprecedented opportunities, it also imposes serious challenges. Particularly, it is difficult to combine the merits of the interpretability attributed to a simple association model with the flexibility achieved by a highly adaptive nonlinear model. In this article, we propose an orthogonalized kernel debiased machine learning approach, which is built upon the Neyman orthogonality and a form of decomposition orthogonality, for multimodal data analysis. We target the setting that naturally arises in almost all multimodal studies, where there is a primary modality of interest, plus additional auxiliary modalities. We establish the root-N-consistency and asymptotic normality of the estimated primary parameter, the semi-parametric estimation efficiency, and the asymptotic validity of the confidence band of the predicted primary modality effect. Our proposal enjoys, to a good extent, both model interpretability and model flexibility. It is also considerably different from the existing statistical methods for multimodal data integration, as well as the orthogonality-based methods for high-dimensional inferences. We demonstrate the efficacy of our method through both simulations and an application to a multimodal neuroimaging study of Alzheimer's disease.

Assessing clinical progression from subjective cognitive decline to mild cognitive impairment with incomplete multi-modal neuroimages

Accurately assessing clinical progression from subjective cognitive decline (SCD) to mild cognitive impairment (MCI) is crucial for early intervention of pathological cognitive decline. Multi-modal neuroimaging data such as T1-weighted magnetic resonance imaging (MRI) and positron emission tomography (PET), help provide objective and supplementary disease biomarkers for computer-aided diagnosis of MCI. However, there are few studies dedicated to SCD progression prediction since subjects usually lack one or more imaging modalities. Besides, one usually has a limited number (e.g., tens) of SCD subjects, negatively affecting model robustness. To this end, we propose a Joint neuroimage Synthesis and Representation Learning (JSRL) framework for SCD conversion prediction using incomplete multi-modal neuroimages. The JSRL contains two components: 1) a generative adversarial network to synthesize missing images and generate multi-modal features, and 2) a classification network to fuse multi-modal features for SCD conversion prediction. The two components are incorporated into a joint learning framework by sharing the same features, encouraging effective fusion of multi-modal features for accurate prediction. A transfer learning strategy is employed in the proposed framework by leveraging model trained on the Alzheimer's Disease Neuroimaging Initiative (ADNI) with MRI and fluorodeoxyglucose PET from 863 subjects to both the Chinese Longitudinal Aging Study (CLAS) with only MRI from 76 SCD subjects and the Australian Imaging, Biomarkers and Lifestyle (AIBL) with MRI from 235 subjects. Experimental results suggest that the proposed JSRL yields superior performance in SCD and MCI conversion prediction and cross-database neuroimage synthesis, compared with several state-of-the-art methods.

Applied machine learning in Alzheimer's disease research: omics, imaging, and clinical data

Alzheimer's disease (AD) remains a devastating neurodegenerative disease with few preventive or curative treatments available. Modern technology developments of high-throughput omics platforms and imaging equipment provide unprecedented opportunities to study the etiology and progression of this disease. Meanwhile, the vast amount of data from various modalities, such as genetics, proteomics, transcriptomics, and imaging, as well as clinical features impose great challenges in data integration and analysis. Machine learning (ML) methods offer novel techniques to address high dimensional data, integrate data from different sources, model the etiological and clinical heterogeneity, and discover new biomarkers. These directions have the potential to help us better manage the disease progression and develop novel treatment strategies. This mini-review paper summarizes different ML methods that have been applied to study AD using single-platform or multi-modal data. We review the current state of ML applications for five key directions of AD research: disease classification, drug repurposing, subtyping, progression prediction, and biomarker discovery. This summary provides insights about the current research status of ML-based AD research and highlights potential directions for future research.

Multimodal Classification of Alzheimer's Disease and Amnestic Mild Cognitive Impairment: Integrated 18F-FDG PET and DTI Study

BACKGROUND

Alzheimer's disease (AD) is a progressive neurodegenerative disease characterized by cognitive decline and memory impairment. Amnestic mild cognitive impairment (aMCI) is the intermediate stage between normal cognitive aging and early dementia caused by AD. It can be challenging to differentiate aMCI patients from healthy controls (HC) and mild AD patients.

OBJECTIVE

To validate whether the combination of 18F-fluorodeoxyglucose positron emission tomography (18F-FDG PET) and diffusion tensor imaging (DTI) will improve classification performance compared with that based on a single modality.

METHODS

A total of thirty patients with AD, sixty patients with aMCI, and fifty healthy controls were included. AD was diagnosed according to the National Institute of Neurological and Communicative Diseases and Stroke/Alzheimer's Disease and Related Disorders Association (NINCDS-ADRDA) criteria for probable. aMCI diagnosis was based on Petersen's criteria. The 18F-FDG PET and DTI measures were each used separately or in combination to evaluate sensitivity, specificity, and accuracy for differentiating HC, aMCI, and AD using receiver operating characteristic analysis together with binary logistic regression. The rate of accuracy was based on the area under the curve (AUC).

RESULTS

For classifying AD from HC, we achieve an AUC of 0.96 when combining two modalities of biomarkers and 0.93 when using 18F-FDG PET individually. For classifying aMCI from HC, we achieve an AUC of 0.79 and 0.76 using the best individual modality of biomarkers.

CONCLUSION

Our results show that the combination of two modalities improves classification performance, compared with that using any individual modality.

Classification of Mild Cognitive Impairment With Multimodal Data Using Both Labeled and Unlabeled Samples

Mild Cognitive Impairment (MCI) is a preclinical stage of Alzheimer's Disease (AD) and is clinical heterogeneity. The classification of MCI is crucial for the early diagnosis and treatment of AD. In this study, we investigated the potential of using both labeled and unlabeled samples from the Alzheimer's Disease Neuroimaging Initiative (ADNI) cohort to classify MCI through the multimodal co-training method. We utilized both structural magnetic resonance imaging (sMRI) data and genotype data of 364 MCI samples including 228 labeled and 136 unlabeled MCI samples from the ADNI-1 cohort. First, the selected quantitative trait (QT) features from sMRI data and SNP features from genotype data were used to build two initial classifiers on 228 labeled MCI samples. Then, the co-training method was implemented to obtain new labeled samples from 136 unlabeled MCI samples. Finally, the random forest algorithm was used to obtain a combined classifier to classify MCI patients in the independent ADNI-2 dataset. The experimental results showed that our proposed framework obtains an accuracy of 85.50 percent and an AUC of 0.825 for MCI classification, respectively, which showed that the combined utilization of sMRI and SNP data through the co-training method could significantly improve the performances of MCI classification.

Machine learning methods for predicting progression from mild cognitive impairment to Alzheimer's disease dementia: a systematic review

BACKGROUND

An increase in lifespan in our society is a double-edged sword that entails a growing number of patients with neurocognitive disorders, Alzheimer's disease being the most prevalent. Advances in medical imaging and computational power enable new methods for the early detection of neurocognitive disorders with the goal of preventing or reducing cognitive decline. Computer-aided image analysis and early detection of changes in cognition is a promising approach for patients with mild cognitive impairment, sometimes a prodromal stage of Alzheimer's disease dementia.

METHODS

We conducted a systematic review following PRISMA guidelines of studies where machine learning was applied to neuroimaging data in order to predict whether patients with mild cognitive impairment might develop Alzheimer's disease dementia or remain stable. After removing duplicates, we screened 452 studies and selected 116 for qualitative analysis.

RESULTS

Most studies used magnetic resonance image (MRI) and positron emission tomography (PET) data but also magnetoencephalography. The datasets were mainly extracted from the Alzheimer's disease neuroimaging initiative (ADNI) database with some exceptions. Regarding the algorithms used, the most common was support vector machine with a mean accuracy of 75.4%, but convolutional neural networks achieved a higher mean accuracy of 78.5%. Studies combining MRI and PET achieved overall better classification accuracy than studies that only used one neuroimaging technique. In general, the more complex models such as those based on deep learning, combined with multimodal and multidimensional data (neuroimaging, clinical, cognitive, genetic, and behavioral) achieved the best performance.

CONCLUSIONS

Although the performance of the different methods still has room for improvement, the results are promising and this methodology has a great potential as a support tool for clinicians and healthcare professionals.

Early MCI-to-AD Conversion Prediction Using Future Value Forecasting of Multimodal Features

In Alzheimer's disease (AD) progression, it is imperative to identify the subjects with mild cognitive impairment before clinical symptoms of AD appear. This work proposes a technique for decision support in identifying subjects who will show transition from mild cognitive impairment (MCI) to Alzheimer's disease (AD) in the future. We used robust predictors from multivariate MRI-derived biomarkers and neuropsychological measures and tracked their longitudinal trajectories to predict signs of AD in the MCI population. Assuming piecewise linear progression of the disease, we designed a novel weighted gradient offset-based technique to forecast the future marker value using readings from at least two previous follow-up visits. Later, the complete predictor trajectories are used as features for a standard support vector machine classifier to identify MCI-to-AD progressors amongst the MCI patients enrolled in the Alzheimer's disease neuroimaging initiative (ADNI) cohort. We explored the performance of both unimodal and multimodal models in a 5-fold cross-validation setup. The proposed technique resulted in a high classification AUC of 91.2% and 95.7% for 6-month- and 1-year-ahead AD prediction, respectively, using multimodal markers. In the end, we discuss the efficacy of MRI markers as compared to NM for MCI-to-AD conversion prediction.

Multi-auxiliary domain transfer learning for diagnosis of MCI conversion

In the early stage of Alzheimer's disease (AD), mild cognitive impairment (MCI) has a higher risk of progression to AD, so the prediction of whether an MCI subject will progress to AD (known as progressive MCI, PMCI) or not (known as stable MCI, SMCI) within a certain period is particularly important in practice. It is known that such a task could benefit from jointly learning-related auxiliary tasks such as differentiating AD from PMCI or PMCI from normal control (NC) in order to take full advantage of their shared commonality. However, few existing methods along this line fully consider the correlations between the target and auxiliary tasks according to the clinical practice of AD pathology for diagnosis. To deal with this problem, in this paper, treating each task domain as a different one, we borrow the idea from transfer learning and propose a novel multi-auxiliary domain transfer learning (MaDTL) method, which explicitly utilizes the correlations between the target domain (task) and multi-auxiliary domains (tasks) according to the clinical practice. Specifically, the proposed MaDTL method incorporates two key modules. The first one is a multi-auxiliary domain transfer-based feature selection (MaDTFS) model, which can select a discriminative feature subset shared by the target domain and the multi-auxiliary domains. In the MaDTFS model, to combine more training data from multi-auxiliary domains and simultaneously suppress the negative effects resulting from the irrelevant parts of multi-auxiliary domains, we proposed a sparse group correlation Lasso that includes a proposed group correlation Lasso penalty (i.e., [Formula: see text]) and a proposed correlation Lasso penalty (i.e., [Formula: see text]). The second module in MaDTL is a multi-auxiliary domain transfer-based classification (MaDTC) model that improves the voting with linear weighting-based ensemble learning. This model extends the constraints of the linear weighting method so that it can simultaneously combine training data from multi-auxiliary domains and achieve a robust classifier by minimizing negative effects from the irrelevant part of multi-auxiliary domains. Experimental results on 409 subjects from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database with the baseline magnetic resonance imaging (MRI) and cerebrospinal fluid (CSF) data validate the effectiveness of the proposed method by significantly improving the classification accuracy to 80.37% for the identification of MCI-to-AD conversion, outperforming the state-of-the-art methods.

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.

Predicting Brain Amyloid Using Multivariate Morphometry Statistics, Sparse Coding, and Correntropy: Validation in 1,101 Individuals From the ADNI and OASIS Databases

Biomarker assisted preclinical/early detection and intervention in Alzheimer’s disease (AD) may be the key to therapeutic breakthroughs. One of the presymptomatic hallmarks of AD is the accumulation of beta-amyloid (Aβ) plaques in the human brain. However, current methods to detect Aβ pathology are either invasive (lumbar puncture) or quite costly and not widely available (amyloid PET). Our prior studies show that magnetic resonance imaging (MRI)-based hippocampal multivariate morphometry statistics (MMS) are an effective neurodegenerative biomarker for preclinical AD. Here we attempt to use MRI-MMS to make inferences regarding brain Aβ burden at the individual subject level. As MMS data has a larger dimension than the sample size, we propose a sparse coding algorithm, Patch Analysis-based Surface Correntropy-induced Sparse-coding and Max-Pooling (PASCS-MP), to generate a low-dimensional representation of hippocampal morphometry for each individual subject. Then we apply these individual representations and a binary random forest classifier to predict brain Aβ positivity for each person. We test our method in two independent cohorts, 841 subjects from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) and 260 subjects from the Open Access Series of Imaging Studies (OASIS). Experimental results suggest that our proposed PASCS-MP method and MMS can discriminate Aβ positivity in people with mild cognitive impairment (MCI) [Accuracy (ACC) = 0.89 (ADNI)] and in cognitively unimpaired (CU) individuals [ACC = 0.79 (ADNI) and ACC = 0.81 (OASIS)]. These results compare favorably relative to measures derived from traditional algorithms, including hippocampal volume and surface area, shape measures based on spherical harmonics (SPHARM) and our prior Patch Analysis-based Surface Sparse-coding and Max-Pooling (PASS-MP) methods.

Deep Fusion of Brain Structure-Function in Mild Cognitive Impairment

Multimodal fusion of different types of neural image data provides an irreplaceable opportunity to take advantages of complementary cross-modal information that may only partially be contained in single modality. To jointly analyze multimodal data, deep neural networks can be especially useful because many studies have suggested that deep learning strategy is very efficient to reveal complex and non-linear relations buried in the data. However, most deep models, e.g., convolutional neural network and its numerous extensions, can only operate on regular Euclidean data like voxels in 3D MRI. The interrelated and hidden structures that beyond the grid neighbors, such as brain connectivity, may be overlooked. Moreover, how to effectively incorporate neuroscience knowledge into multimodal data fusion with a single deep framework is understudied. In this work, we developed a graph-based deep neural network to simultaneously model brain structure and function in Mild Cognitive Impairment (MCI): the topology of the graph is initialized using structural network (from diffusion MRI) and iteratively updated by incorporating functional information (from functional MRI) to maximize the capability of differentiating MCI patients from elderly normal controls. This resulted in a new connectome by exploring "deep relations" between brain structure and function in MCI patients and we named it as Deep Brain Connectome. Though deep brain connectome is learned individually, it shows consistent patterns of alteration comparing to structural network at group level. With deep brain connectome, our developed deep model can achieve 92.7% classification accuracy on ADNI dataset.

Pattern and degree of individual brain atrophy predicts dementia onset in dominantly inherited Alzheimer's disease

INTRODUCTION

Asymptomatic and mildly symptomatic dominantly inherited Alzheimer's disease mutation carriers (DIAD-MC) are ideal candidates for preventative treatment trials aimed at delaying or preventing dementia onset. Brain atrophy is an early feature of DIAD-MC and could help predict risk for dementia during trial enrollment.

METHODS

We created a dementia risk score by entering standardized gray-matter volumes from 231 DIAD-MC into a logistic regression to classify participants with and without dementia. The score's predictive utility was assessed using Cox models and receiver operating curves on a separate group of 65 DIAD-MC followed longitudinally.

RESULTS

Our risk score separated asymptomatic versus demented DIAD-MC with 96.4% (standard error = 0.02) and predicted conversion to dementia at next visit (hazard ratio = 1.32, 95% confidence interval [CI: 1.15, 1.49]) and within 2 years (area under the curve = 90.3%, 95% CI [82.3%-98.2%]) and improved prediction beyond established methods based on familial age of onset.

DISCUSSION

Individualized risk scores based on brain atrophy could be useful for establishing enrollment criteria and stratifying DIAD-MC participants for prevention trials.