DMA-HPCNet: Dual Multi-Level Attention Hybrid Pyramid Convolution Neural Network for Alzheimer's Disease Classification.

Computer-aided diagnosis (CAD) plays a crucial role in the clinical application of Alzheimer's disease (AD). In particular, convolutional neural network (CNN)-based methods are highly sensitive to subtle changes caused by brain atrophy in medical images (e.g., magnetic resonance imaging, MRI). Due to computational resource constraints, most CAD methods focus on quantitative features in specific regions, neglecting the holistic nature of the images, which poses a challenge for a comprehensive understanding of pathological changes in AD. To address this issue, we propose a lightweight dual multi-level hybrid pyramid convolutional neural network (DMA-HPCNet) to aid clinical diagnosis of AD. Specifically, we introduced ResNet as the backbone network and modularly extended the hybrid pyramid convolution (HPC) block and the dual multi-level attention (DMA) module. Among them, the HPC block is designed to enhance the acquisition of information at different scales, and the DMA module is proposed to sequentially extract different local and global representations from the channel and spatial domains. Our proposed DMA-HPCNet method was evaluated on baseline MRI slices of 443 subjects from the ADNI dataset. Experimental results show that our proposed DMA-HPCNet model performs efficiently in AD-related classification tasks with low computational cost.

Explainability of three-dimensional convolutional neural networks for functional magnetic resonance imaging of Alzheimer's disease classification based on gradient-weighted class activation mapping.

Currently, numerous studies focus on employing fMRI-based deep neural networks to diagnose neurological disorders such as Alzheimer's Disease (AD), yet only a handful have provided results regarding explainability. We address this gap by applying several prevalent explainability methods such as gradient-weighted class activation mapping (Grad-CAM) to an fMRI-based 3D-VGG16 network for AD diagnosis to improve the model's explainability. The aim is to explore the specific Region of Interest (ROI) of brain the model primarily focuses on when making predictions, as well as whether there are differences in these ROIs between AD and normal controls (NCs). First, we utilized multiple resting-state functional activity maps including ALFF, fALFF, ReHo, and VMHC to reduce the complexity of fMRI data, which differed from many studies that utilized raw fMRI data. Compared to methods utilizing raw fMRI data, this manual feature extraction approach may potentially alleviate the model's burden. Subsequently, 3D-VGG16 were employed for AD classification, where the final fully connected layers were replaced with a Global Average Pooling (GAP) layer, aimed at mitigating overfitting while preserving spatial information within the feature maps. The model achieved a maximum of 96.4% accuracy on the test set. Finally, several 3D CAM methods were employed to interpret the models. In the explainability results of the models with relatively high accuracy, the highlighted ROIs were primarily located in the precuneus and the hippocampus for AD subjects, while the models focused on the entire brain for NC. This supports current research on ROIs involved in AD. We believe that explaining deep learning models would not only provide support for existing research on brain disorders, but also offer important referential recommendations for the study of currently unknown etiologies.

Performance Evaluation of Deep, Shallow and Ensemble Machine Learning Methods for the Automated Classification of Alzheimer's Disease.

Artificial intelligence (AI)-based approaches are crucial in computer-aided diagnosis (CAD) for various medical applications. Their ability to quickly and accurately learn from complex data is remarkable. Deep learning (DL) models have shown promising results in accurately classifying Alzheimer's disease (AD) and its related cognitive states, Early Mild Cognitive Impairment (EMCI) and Late Mild Cognitive Impairment (LMCI), along with the healthy conditions known as Cognitively Normal (CN). This offers valuable insights into disease progression and diagnosis. However, certain traditional machine learning (ML) classifiers perform equally well or even better than DL models, requiring less training data. This is particularly valuable in CAD in situations with limited labeled datasets. In this paper, we propose an ensemble classifier based on ML models for magnetic resonance imaging (MRI) data, which achieved an impressive accuracy of 96.52%. This represents a 3-5% improvement over the best individual classifier. We evaluated popular ML classifiers for AD classification under both data-scarce and data-rich conditions using the Alzheimer's Disease Neuroimaging Initiative and Open Access Series of Imaging Studies datasets. By comparing the results to state-of-the-art CNN-centric DL algorithms, we gain insights into the strengths and weaknesses of each approach. This work will help users to select the most suitable algorithm for AD classification based on data availability.

Real-word application of the AT(N) classification and disease-modifying treatment eligibility in a hospital-based cohort.

BACKGROUND AND OBJECTIVES: The AT(N) classification system stratifies patients based on biomarker profiles, including amyloid-beta deposition (A), tau pathology (T), and neurodegeneration (N). This study aims to apply the AT(N) classification to a hospital-based cohort of patients with cognitive decline and/or dementia, within and outside the Alzheimer's disease (AD) continuum, to enhance our understanding of the multidimensional aspects of AD and related disorders. Furthermore, we wish to investigate how many cases from our cohort would be eligible for the available disease modifying treatments, such as aducanemab and lecanemab. METHODS: We conducted a retrospective evaluation of 429 patients referred to the Memory Center of IRCCS San Raffaele Hospital in Milan. Patients underwent clinical/neuropsychological assessments, lumbar puncture, structural brain imaging, and positron emission tomography (FDG-PET). Patients were stratified according to AT(N) classification, group comparisons were performed and the number of eligible cases for anti-ß amyloid monoclonal antibodies was calculated. RESULTS: Sociodemographic and clinical features were similar across groups. The most represented group was A + T + N + accounting for 38% of cases, followed by A + T - N + (21%) and A - T - N + (20%). Although the clinical presentation was similar, the A + T + N + group showed more severe cognitive impairment in memory, language, attention, executive, and visuospatial functions compared to other AT(N) groups. Notably, T + patients demonstrated greater memory complaints compared to T - cases. FDG-PET outperformed MRI and CT in distinguishing A + from A - patients. Although 61% of the observed cases were A + , only 17% of them were eligible for amyloid-targeting treatments. DISCUSSION: The AT(N) classification is applicable in a real-world clinical setting. The classification system provided insights into clinical management and treatment strategies. Low cognitive performance and specific regional FDG-PET hypometabolism at diagnosis are highly suggestive for A + T + or A - T + profiles. This work provides also a realistic picture of the proportion of AD patients eligible for disease modifying treatments emphasizing the need for early detection.

Safety, Feasibility, and Potential Clinical Efficacy of 40 Hz Invisible Spectral Flicker versus Placebo in Patients with Mild-to-Moderate Alzheimer's Disease: A Randomized, Placebo-Controlled, Double-Blinded, Pilot Study.

BACKGROUND: Recent studies suggested induction of 40 Hz neural activity as a potential treatment for Alzheimer's disease (AD). However, prolonged exposure to flickering light raises adherence and safety concerns, encouraging investigation of tolerable light stimulation protocols. OBJECTIVE: To investigate the safety, feasibility, and exploratory measures of efficacy. METHODS: This two-stage randomized placebo-controlled double-blinded clinical trial, recruited first cognitive healthy participants (n = 3/2 active/placebo), and subsequently patients with mild-to-moderate AD (n = 5/6, active/placebo). Participants were randomized 1:1 to receive either active intervention with 40 Hz Invisible Spectral Flicker (ISF) or placebo intervention with color and intensity matched non-flickering white light. RESULTS: Few and mild adverse events were observed. Adherence was above 86.1% of intended treatment days, with participants remaining in front of the device for >51.3 min (60 max) and directed gaze >34.9 min. Secondary outcomes of cognition indicate a tendency towards improvement in the active group compared to placebo (mean: -2.6/1.5, SD: 6.58/6.53, active/placebo) at week 6. Changes in hippocampal and ventricular volume also showed no tendency of improvement in the active group at week 6 compared to placebo. At week 12, a potential delayed effect of the intervention was seen on the volume of the hippocampus in the active group compared to placebo (mean: 0.34/-2.03, SD: 3.26/1.18, active/placebo), and the ventricular volume active group (mean: -0.36/2.50, SD: 1.89/2.05, active/placebo), compared to placebo. CONCLUSION: Treatment with 40 Hz ISF offers no significant safety or adherence concerns. Potential impact on secondary outcomes must be tested in larger scale clinical trials.

An Exploration: Alzheimer's Disease Classification Based on Convolutional Neural Network.

Alzheimer's disease (AD) is the most generally known neurodegenerative disorder, leading to a steady deterioration in cognitive ability. Deep learning models have shown outstanding performance in the diagnosis of AD, and these models do not need any handcrafted feature extraction over conventional machine learning algorithms. Since the 2012 AlexNet accomplishment, the convolutional neural network (CNN) has been progressively utilized by the medical community to assist practitioners to early diagnose AD. This paper explores the current cutting edge applications of CNN on single and multimodality (combination of two or more modalities) neuroimaging data for the classification of AD. An exhaustive systematic search is conducted on four notable databases: Google Scholar, IEEE Xplore, ACM Digital Library, and PubMed in June 2021. The objective of this study is to examine the effectiveness of classification approaches on AD to analyze different kinds of datasets, neuroimaging modalities, preprocessing techniques, and data handling methods. However, CNN has achieved great success in the classification of AD; still, there are a lot of challenges particularly due to scarcity of medical imaging data and its possible scope in this field.

Blockchain-Based Deep Learning to Process IoT Data Acquisition in Cognitive Data.

Remote health monitoring can help prevent disease at the earlier stages. The Internet of Things (IoT) concepts have recently advanced, enabling omnipresent monitoring. Easily accessible biomarkers for neurodegenerative disorders, namely, Alzheimer's disease (AD) are needed urgently to assist the diagnoses at its early stages. Due to the severe situations, these systems demand high-quality qualities including availability and accuracy. Deep learning algorithms are promising in such health applications when a large amount of data is available. These solutions are ideal for a distributed blockchain-based IoT system. A good Internet connection is critical to the speed of these system responses. Due to their limited processing capabilities, smart gateway devices cannot implement deep learning algorithms. In this paper, we investigate the use of blockchain-based deep neural networks for higher speed and delivery of healthcare data in a healthcare management system. The study exhibits a real-time health monitoring for classification and assesses the response time and accuracy. The deep learning model classifies the brain diseases as benign or malignant. The study takes into account three different classes to predict the brain disease as benign or malignant that includes AD, mild cognitive impairment, and normal cognitive level. The study involves a series of processing where most of the data are utilized for training these classifiers and ensemble model with a metaclassifier classifying the resultant class. The simulation is conducted to test the efficacy of the model over that of the OASIS-3 dataset, which is a longitudinal neuroimaging, cognitive, clinical, and biomarker dataset for normal aging and AD, and it is further trained and tested on the UDS dataset from ADNI. The results show that the proposed method accurately (98%) responds to the query with high speed retrieval of classified results with an increased training accuracy of 0.539 and testing accuracy of 0.559.

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.

Predictive value of ATN biomarker profiles in estimating disease progression in Alzheimer's disease dementia.

We aimed to evaluate the value of ATN biomarker classification system (amyloid beta [A], pathologic tau [T], and neurodegeneration [N]) for predicting conversion from mild cognitive impairment (MCI) to dementia. In a sample of people with MCI (n = 415) we assessed predictive performance of ATN classification using empirical knowledge-based cut-offs for each component of ATN and compared it to two data-driven approaches, logistic regression and RUSBoost machine learning classifiers, which used continuous clinical or biomarker scores. In data-driven approaches, we identified ATN features that distinguish normals from individuals with dementia and used them to classify persons with MCI into dementia-like and normal groups. Both data-driven classification methods performed better than the empirical cut-offs for ATN biomarkers in predicting conversion to dementia. Classifiers that used clinical features performed as well as classifiers that used ATN biomarkers for prediction of progression to dementia. We discuss that data-driven modeling approaches can improve our ability to predict disease progression and might have implications in future clinical trials.

PET Imaging of Tau Pathology and Amyloid-ß, and MRI for Alzheimer's Disease Feature Fusion and Multimodal Classification.

BACKGROUND: Machine learning is a promising tool for biomarker-based diagnosis of Alzheimer's disease (AD). Performing multimodal feature selection and studying the interaction between biological and clinical AD can help to improve the performance of the diagnosis models. OBJECTIVE: This study aims to formulate a feature ranking metric based on the mutual information index to assess the relevance and redundancy of regional biomarkers and improve the AD classification accuracy. METHODS: From the Alzheimer's Disease Neuroimaging Initiative (ADNI), 722 participants with three modalities, including florbetapir-PET, flortaucipir-PET, and MRI, were studied. The multivariate mutual information metric was utilized to capture the redundancy and complementarity of the predictors and develop a feature ranking approach. This was followed by evaluating the capability of single-modal and multimodal biomarkers in predicting the cognitive stage. RESULTS: Although amyloid-ß deposition is an earlier event in the disease trajectory, tau PET with feature selection yielded a higher early-stage classification F1-score (65.4%) compared to amyloid-ß PET (63.3%) and MRI (63.2%). The SVC multimodal scenario with feature selection improved the F1-score to 70.0% and 71.8% for the early and late-stage, respectively. When age and risk factors were included, the scores improved by 2 to 4%. The Amyloid-Tau-Neurodegeneration [AT(N)] framework helped to interpret the classification results for different biomarker categories. CONCLUSION: The results underscore the utility of a novel feature selection approach to reduce the dimensionality of multimodal datasets and enhance model performance. The AT(N) biomarker framework can help to explore the misclassified cases by revealing the relationship between neuropathological biomarkers and cognition.

Patterns of incident dementia codes during the COVID-19 pandemic at an integrated healthcare system.

BACKGROUND: The COVID-19 pandemic delayed diagnosis and care for some acute conditions and reduced monitoring for some chronic conditions. It is unclear whether new diagnoses of chronic conditions such as dementia were also affected. We compared the pattern of incident Alzheimer's disease and related dementia (ADRD) diagnosis codes from 2017 to 2019 through 2020, the first pandemic year. METHODS: Retrospective cohort design, leveraging 2015-2020 data on all members 65 years and older with no prior ADRD diagnosis, enrolled in a large integrated healthcare system for at least 2 years. Incident ADRD was defined as the first ICD-10 code at any encounter, including outpatient (face-to-face, video, or phone), hospital (emergency department, observation, or inpatient), or continuing care (home, skilled nursing facility, and long-term care). We also examined incident ADRD codes and use of telehealth by age, sex, race/ethnicity, and spoken language. RESULTS: Compared to overall annual incidence rates for ADRD codes in 2017-2019, 2020 incidence was slightly lower (1.30% vs. 1.40%), partially compensating later in the year for reduced rates during the early months of the pandemic. No racial or ethnic group differences were identified. Telehealth ADRD codes increased fourfold, making up for a 39% drop from face-to-face outpatient encounters. Older age (85+) was associated with higher odds of receiving telecare versus face-to-face care in 2020 (OR:1.50, 95%CI: 1.25-1.80) and a slightly lower incidence of new codes; no racial/ethnic, sex, or language differences were identified in the mode of care. CONCLUSIONS: Rates of incident ADRD codes dropped early in the first pandemic year but rose again to near pre-pandemic rates for the year as a whole, as clinicians rapidly pivoted to telehealth. With refinement of protocols for remote dementia detection and diagnosis, health systems could improve access to equitable detection and diagnosis of ADRD going forward.

Deep learning reveals disease-specific signatures of white matter pathology in tauopathies.

Although pathology of tauopathies is characterized by abnormal tau protein aggregation in both gray and white matter regions of the brain, neuropathological investigations have generally focused on abnormalities in the cerebral cortex because the canonical aggregates that form the diagnostic criteria for these disorders predominate there. This corticocentric focus tends to deemphasize the relevance of the more complex white matter pathologies, which remain less well characterized and understood. We took a data-driven machine-learning approach to identify novel disease-specific morphologic signatures of white matter aggregates in three tauopathies: Alzheimer disease (AD), progressive supranuclear palsy (PSP), and corticobasal degeneration (CBD). We developed automated approaches using whole slide images of tau immunostained sections from 49 human autopsy brains (16 AD,13 CBD, 20 PSP) to identify cortex/white matter regions and individual tau aggregates, and compared tau-aggregate morphology across these diseases. Tau burden in the gray and white matter for individual subjects strongly correlated in a highly disease-specific fashion. We discovered previously unrecognized tau morphologies for AD, CBD and PSP that may be of importance in disease classification. Intriguingly, our models classified diseases equally well based on either white or gray matter tau staining. Our results suggest that tau pathology in white matter is informative, disease-specific, and linked to gray matter pathology. Machine learning has the potential to reveal latent information in histologic images that may represent previously unrecognized patterns of neuropathology, and additional studies of tau pathology in white matter could improve diagnostic accuracy.

Cerebrospinal fluid markers for synaptic function and Alzheimer type changes in late life depression.

To explore markers for synaptic function and Alzheimer disease (AD) pathology in late life depression (LLD), predementia AD and normal controls (NC). A cross-sectional study to compare cerebrospinal fluid (CSF) levels of neurogranin (Ng), Beta-site amyloid-precursor-protein cleaving enzyme1 (BACE1), Ng/BACE1 ratio and Amyloid-ß 42/40 ratio, phosphorylated-tau and total-tau in LLD with (LLD AD) or without (LLD NoAD) AD pathology, predementia AD and normal controls (NC). We included 145 participants (NC = 41; predementia AD = 66 and LLD = 38). LLD comprised LLD AD (n = 16), LLD NoAD (n = 19), LLD with non-AD typical changes (n = 3, excluded). LLD AD (pADJ < 0.05) and predementia AD (pADJ < 0.0001) showed significantly higher Ng than NC. BACE1 and Ng/BACE1 ratio were altered similarly. Compared to LLD NoAD, LLD AD showed significantly higher Ng (pADJ < 0.001), BACE1 (pADJ < 0.05) and Ng/BACE1 ratio (pADJ < 0.01). All groups had significantly lower Aß 42/40 ratio than NC (predementia AD and LLD AD, p < 0.0001; LLD NoAD, p < 0.05). Both LLD groups performed similarly on tests of memory and executive function, but significantly poorer than NC. Synaptic function in LLD depended on AD pathology. LLD showed an association to Amyloid dysmetabolism. The LLD groups performed poorer cognitively than NC. LLD AD may be conceptualized as "predementia AD with depression".

Classification of Alzheimer's Disease Using Gaussian-Based Bayesian Parameter Optimization for Deep Convolutional LSTM Network.

Alzheimer's disease (AD) is one of the most important causes of mortality in elderly people, and it is often challenging to use traditional manual procedures when diagnosing a disease in the early stages. The successful implementation of machine learning (ML) techniques has also shown their effectiveness and its reliability as one of the better options for an early diagnosis of AD. But the heterogeneous dimensions and composition of the disease data have undoubtedly made diagnostics more difficult, needing a sufficient model choice to overcome the difficulty. Therefore, in this paper, four different 2D and 3D convolutional neural network (CNN) frameworks based on Bayesian search optimization are proposed to develop an optimized deep learning model to predict the early onset of AD binary and ternary classification on magnetic resonance imaging (MRI) scans. Moreover, certain hyperparameters such as learning rate, optimizers, and hidden units are to be set and adjusted for the performance boosting of the deep learning model. Bayesian optimization enables to leverage advantage throughout the experiments: A persistent hyperparameter space testing provides not only the output but also about the nearest conclusions. In this way, the series of experiments needed to explore space can be substantially reduced. Finally, alongside the use of Bayesian approaches, long short-term memory (LSTM) through the process of augmentation has resulted in finding the better settings of the model that too in less iterations with an relative improvement (RI) of 7.03%, 12.19%, 10.80%, and 11.99% over the four systems optimized with manual hyperparameters tuning such that hyperparameters that look more appealing from past data as well as the conventional techniques of manual selection.

Assessment of Tau Pathology as Measured by 18F-THK5317 and 18F-Flortaucipir PET and Their Relation to Brain Atrophy and Cognition in Alzheimer's Disease.

BACKGROUND: In Alzheimer's disease (AD), the abnormal aggregation of hyperphosphorylated tau leads to synaptic dysfunction and neurodegeneration. Recently developed tau PET imaging tracers are candidate biomarkers for diagnosis and staging of AD. OBJECTIVE: We aimed to investigate the discriminative ability of 18F-THK5317 and 18F-flortaucipir tracers and brain atrophy at different stages of AD, and their respective associations with cognition. METHODS: Two cohorts, each including 29 participants (healthy controls [HC], prodromal AD, and AD dementia patients), underwent 18F-THK5317 or 18F-flortaucipir PET, T1-weighted MRI, and neuropsychological assessment. For each subject, we quantified regional 18F-THK5317 and 18F-flortaucipir uptake within six bilateral and two composite regions of interest. We assessed global brain atrophy for each individual by quantifying the brain volume index, a measure of brain volume-to-cerebrospinal fluid ratio. We then quantified the discriminative ability of regional 18F-THK5317, 18F-flortaucipir, and brain volume index between diagnostic groups, and their associations with cognition in patients. RESULTS: Both 18F-THK5317 and 18F-flortaucipir outperformed global brain atrophy in discriminating between HC and both prodromal AD and AD dementia groups. 18F-THK5317 provided the highest discriminative ability between HC and prodromal AD groups. 18F-flortaucipir performed best at discriminating between prodromal and dementia stages of AD. Across all patients, both tau tracers were predictive of RAVL learning, but only 18F-flortaucipir predicted MMSE. CONCLUSION: Our results warrant further in vivo head-to-head and antemortem-postmortem evaluations. These validation studies are needed to select tracers with high clinical validity as biomarkers for early diagnosis, prognosis, and disease staging, which will facilitate their incorporation in clinical practice and therapeutic trials.

Identifying individuals with Alzheimer's disease-like brains based on structural imaging in the Human Connectome Project Aging cohort.

Given the difficulty in factoring out typical age effects from subtle Alzheimer's disease (AD) effects on brain structure, identification of very early, as well as younger preclinical "at-risk" individuals has unique challenges. We examined whether age-correction procedures could be used to better identify individuals at very early potential risk from adults who did not have any existing cognitive diagnosis. First, we obtained cross-sectional age effects for each structural feature using data from a selected portion of the Human Connectome Project Aging (HCP-A) cohort. After age detrending, we weighted AD structural deterioration with patterns quantified from data of the Alzheimer's Disease Neuroimaging Initiative. Support vector machine was then used to classify individuals with brains that most resembled atrophy in AD across the entire HCP-A sample. Additionally, we iteratively adjusted the pipeline by removing individuals classified as AD-like from the HCP-A cohort to minimize atypical brain structural contributions to the age detrending. The classifier had a mean cross-validation accuracy of 94.0% for AD recognition. It also could identify mild cognitive impairment with more severe AD-specific biomarkers and worse cognition. In an independent HCP-A cohort, 8.8% were identified as AD-like, and they trended toward worse cognition. An "AD risk" score derived from the machine learning models also significantly correlated with cognition. This work provides a proof of concept for the potential to use structural brain imaging to identify asymptomatic individuals at young ages who show structural brain patterns similar to AD and are potentially at risk for a future clinical disorder.

Combining Multimodal Behavioral Data of Gait, Speech, and Drawing for Classification of Alzheimer's Disease and Mild Cognitive Impairment.

BACKGROUND: Gait, speech, and drawing behaviors have been shown to be sensitive to the diagnosis of Alzheimer's disease (AD) and mild cognitive impairment (MCI). However, previous studies focused on only analyzing individual behavioral modalities, although these studies suggested that each of these modalities may capture different profiles of cognitive impairments associated with AD. OBJECTIVE: We aimed to investigate if combining behavioral data of gait, speech, and drawing can improve classification performance compared with the use of individual modality and if each of these behavioral data can be associated with different cognitive and clinical measures for the diagnosis of AD and MCI. METHODS: Behavioral data of gait, speech, and drawing were acquired from 118 AD, MCI, and cognitively normal (CN) participants. RESULTS: Combining all three behavioral modalities achieved 93.0% accuracy for classifying AD, MCI, and CN, and only 81.9% when using the best individual behavioral modality. Each of these behavioral modalities was statistically significantly associated with different cognitive and clinical measures for diagnosing AD and MCI. CONCLUSION: Our findings indicate that these behaviors provide different and complementary information about cognitive impairments such that classification of AD and MCI is superior to using either in isolation.

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.

Heterogeneity and Factorial Structure in Alzheimer's Disease: A Cognitive Perspective.

BACKGROUND: Alzheimer's disease (AD) patients show heterogeneous cognitive profiles which suggest the existence of cognitive subgroups. A deeper comprehension of this heterogeneity could contribute to move toward a precision medicine perspective. OBJECTIVE: In this study, we aimed 1) to investigate AD cognitive heterogeneity as a product of the combination of within- (factors) and between-patients (sub-phenotypes) components, and 2) to promote its assessment in clinical practice by defining a small set of critical tests for this purpose. METHODS: We performed factor mixture analysis (FMA) on neurocognitive assessment results of N = 230 patients with a clinical diagnosis of AD. This technique allowed to investigate the structure of cognitive heterogeneity in this sample and to characterize the core features of cognitive sub-phenotypes. Subsequently, we performed a tests selection based on logistic regression to highlight the best tests to detect AD patients in our sample. Finally, the accuracy of the same tests in the discrimination of sub-phenotypes was evaluated. RESULTS: FMA revealed a structure characterized by five latent factors and four groups, which were identifiable by means of a few cognitive tests and were mainly characterized by memory deficits with visuospatial difficulties ("Visuospatial AD"), typical AD cognitive pattern ("Typical AD"), less impaired memory ("Mild AD"), and language/praxis deficits with relatively spared memory ("Nonamnestic AD"). CONCLUSION: The structure of cognitive heterogeneity in our sample of AD patients, as studied by FMA, could be summarized by four sub-phenotypes with distinct cognitive characteristics easily identifiable in clinical practice. Clinical implications under the precision medicine framework are discussed.