Multimodal deep learning for Alzheimer's disease dementia assessment

Exploring outdoor activity limitation (OAL) factors among older adults using interpretable machine learning

BACKGROUND

The occurrence of outdoor activity limitation (OAL) among older adults is influenced by multidimensional and confounding factors associated with aging.

AIM

The aim of this study was to apply interpretable machine learning (ML) to develop models for multidimensional aging constraints on OAL and identify the most predictive constraints and dimensions across multidimensional aging data.

METHODS

This study involved 6794 community-dwelling participants older than 65 from the National Health and Aging Trends Study (NHATS). Predictors included related to six dimensions: sociodemographics, health condition, physical capacity, neurological manifestation, daily living habits and abilities, and environmental conditions. Multidimensional interpretable machine learning models were assembled for model construction and analysis.

RESULTS

The multidimensional model demonstrated the best predictive performance (AUC: 0.918) compared to the six sub-dimensional models. Among the six dimensions, physical capacity had the most remarkable prediction (AUC: physical capacity: 0.895, daily habits and abilities: 0.828, physical health: 0.826, neurological performance: 0.789, sociodemographic: 0.773, and environment condition: 0.623). The top-ranked predictors were SPPB score, lifting ability, leg strength, free kneeling, laundry mode, self-rated health, age, attitude toward outdoor recreation, standing time on one foot with eyes open, and fear of falling.

DISCUSSION

Reversible and variable factors, which are higher in the set of high-contribution constraints, should be prioritized as the main contributing group in terms of interventions.

CONCLUSION

The integration of potentially reversible factors, such as neurological performance in addition to physical function into ML models, yields a more accurate assessment of OAL risk, which provides insights for targeted, sequential interventions for older adults with OAL.

Assessing the transportability of clinical prediction models for cognitive impairment using causal models

BACKGROUND

Machine learning models promise to support diagnostic predictions, but may not perform well in new settings. Selecting the best model for a new setting without available data is challenging. We aimed to investigate the transportability by calibration and discrimination of prediction models for cognitive impairment in simulated external settings with different distributions of demographic and clinical characteristics.

METHODS

We mapped and quantified relationships between variables associated with cognitive impairment using causal graphs, structural equation models, and data from the ADNI study. These estimates were then used to generate datasets and evaluate prediction models with different sets of predictors. We measured transportability to external settings under guided interventions on age, APOE ε4, and tau-protein, using performance differences between internal and external settings measured by calibration metrics and area under the receiver operating curve (AUC).

RESULTS

Calibration differences indicated that models predicting with causes of the outcome were more transportable than those predicting with consequences. AUC differences indicated inconsistent trends of transportability between the different external settings. Models predicting with consequences tended to show higher AUC in the external settings compared to internal settings, while models predicting with parents or all variables showed similar AUC.

CONCLUSIONS

We demonstrated with a practical prediction task example that predicting with causes of the outcome results in better transportability compared to anti-causal predictions when considering calibration differences. We conclude that calibration performance is crucial when assessing model transportability to external settings.

A Comprehensive and Versatile Multimodal Deep-Learning Approach for Predicting Diverse Properties of Advanced Materials

A multimodal deep-learning (MDL) framework is presented for predicting physical properties of a ten-dimensional acrylic polymer composite material by merging physical attributes and chemical data. The MDL model comprises four modules, including three generative deep-learning models for material structure characterization and a fourth model for property prediction. The approach handles an 18-dimensional complexity, with ten compositional inputs and eight property outputs, successfully predicting 913 680 property data points across 114 210 composition conditions. This level of complexity is unprecedented in computational materials science, particularly for materials with undefined structures. A framework is proposed to analyze the high-dimensional information space for inverse material design, demonstrating flexibility and adaptability to various materials and scales, provided sufficient data are available. This study advances future research on different materials and the development of more sophisticated models, drawing the authors closer to the ultimate goal of predicting all properties of all materials.

MSCDA: Multi-level semantic-guided contrast improves unsupervised domain adaptation for breast MRI segmentation in small datasets

Deep learning (DL) applied to breast tissue segmentation in magnetic resonance imaging (MRI) has received increased attention in the last decade, however, the domain shift which arises from different vendors, acquisition protocols, and biological heterogeneity, remains an important but challenging obstacle on the path towards clinical implementation. In this paper, we propose a novel Multi-level Semantic-guided Contrastive Domain Adaptation (MSCDA) framework to address this issue in an unsupervised manner. Our approach incorporates self-training with contrastive learning to align feature representations between domains. In particular, we extend the contrastive loss by incorporating pixel-to-pixel, pixel-to-centroid, and centroid-to-centroid contrasts to better exploit the underlying semantic information of the image at different levels. To resolve the data imbalance problem, we utilize a category-wise cross-domain sampling strategy to sample anchors from target images and build a hybrid memory bank to store samples from source images. We have validated MSCDA with a challenging task of cross-domain breast MRI segmentation between datasets of healthy volunteers and invasive breast cancer patients. Extensive experiments show that MSCDA effectively improves the model's feature alignment capabilities between domains, outperforming state-of-the-art methods. Furthermore, the framework is shown to be label-efficient, achieving good performance with a smaller source dataset. The code is publicly available at https://github.com/ShengKuangCN/MSCDA.

Machine Learning in Clinical Trials: A Primer with Applications to Neurology

We reviewed foundational concepts in artificial intelligence (AI) and machine learning (ML) and discussed ways in which these methodologies may be employed to enhance progress in clinical trials and research, with particular attention to applications in the design, conduct, and interpretation of clinical trials for neurologic diseases. We discussed ways in which ML may help to accelerate the pace of subject recruitment, provide realistic simulation of medical interventions, and enhance remote trial administration via novel digital biomarkers and therapeutics. Lastly, we provide a brief overview of the technical, administrative, and regulatory challenges that must be addressed as ML achieves greater integration into clinical trial workflows.

Identification and prediction of m7G-related Alzheimer's disease subtypes: insights from immune infiltration and machine learning models

Introduction

Alzheimer's disease (AD) is a complex and progressive neurodegenerative disorder that primarily affects older individuals. N7-methylguanosine (m7G) is a common RNA chemical modification that impacts the development of numerous diseases. Thus, our work investigated m7G-related AD subtypes and established a predictive model.

Methods

The datasets for AD patients, including GSE33000 and GSE44770, were obtained from the Gene Expression Omnibus (GEO) database, which were derived from the prefrontal cortex of the brain. We performed differential analysis of m7G regulators and examined the immune signatures differences between AD and matched-normal samples. Consensus clustering was employed to identify AD subtypes based on m7G-related differentially expressed genes (DEGs), and immune signatures were explored among different clusters. Furthermore, we developed four machine learning models based on the expression profiles of m7G-related DEGs and identified five important genes from the optimal model. We evaluated the predictive power of the 5-gene-based model using an external AD dataset (GSE44770).

Results

A total of 15 genes related to m7G were found to be dysregulated in patients with AD compared to non-AD patients. This finding suggests that there are differences in immune characteristics between these two groups. Based on the differentially expressed m7G regulators, we categorized AD patients into two clusters and calculated the ESTIMATE score for each cluster. Cluster 2 exhibited a higher ImmuneScore than Cluster 1. We performed the receiver operating characteristic (ROC) analysis to compare the performance of four models, and we found that the Random Forest (RF) model had the highest AUC value of 1.000. Furthermore, we tested the predictive efficacy of a 5-gene-based RF model on an external AD dataset and obtained an AUC value of 0.968. The nomogram, calibration curve, and decision curve analysis (DCA) confirmed the accuracy of our model in predicting AD subtypes.

Conclusion

The present study systematically examines the biological significance of m7G methylation modification in AD and investigates its association with immune infiltration characteristics. Furthermore, the study develops potential predictive models to assess the risk of m7G subtypes and the pathological outcomes of patients with AD, which can facilitate risk classification and clinical management of AD patients.

Interpretable Machine Learning on Metabolomics Data Reveals Biomarkers for Parkinson's Disease

The use of machine learning (ML) with metabolomics provides opportunities for the early diagnosis of disease. However, the accuracy of ML and extent of information obtained from metabolomics can be limited owing to challenges associated with interpreting disease prediction models and analyzing many chemical features with abundances that are correlated and "noisy". Here, we report an interpretable neural network (NN) framework to accurately predict disease and identify significant biomarkers using whole metabolomics data sets without a priori feature selection. The performance of the NN approach for predicting Parkinson's disease (PD) from blood plasma metabolomics data is significantly higher than other ML methods with a mean area under the curve of >0.995. PD-specific markers that predate clinical PD diagnosis and contribute significantly to early disease prediction were identified including an exogenous polyfluoroalkyl substance. It is anticipated that this accurate and interpretable NN-based approach can improve diagnostic performance for many diseases using metabolomics and other untargeted 'omics methods.

Ethical issues when using digital biomarkers and artificial intelligence for the early detection of dementia

Dementia poses a growing challenge for health services but remains stigmatized and under-recognized. Digital technologies to aid the earlier detection of dementia are approaching market. These include traditional cognitive screening tools presented on mobile devices, smartphone native applications, passive data collection from wearable, in-home and in-car sensors, as well as machine learning techniques applied to clinic and imaging data. It has been suggested that earlier detection and diagnosis may help patients plan for their future, achieve a better quality of life, and access clinical trials and possible future disease modifying treatments. In this review, we explore whether digital tools for the early detection of dementia can or should be deployed, by assessing them against the principles of ethical screening programs. We conclude that while the importance of dementia as a health problem is unquestionable, significant challenges remain. There is no available treatment which improves the prognosis of diagnosed disease. Progression from early-stage disease to dementia is neither given nor currently predictable. Available technologies are generally not both minimally invasive and highly accurate. Digital deployment risks exacerbating health inequalities due to biased training data and inequity in digital access. Finally, the acceptability of early dementia detection is not established, and resources would be needed to ensure follow-up and support for those flagged by any new system. We conclude that early dementia detection deployed at scale via digital technologies does not meet standards for a screening program and we offer recommendations for moving toward an ethical mode of implementation. This article is categorized under:Application Areas > Health CareCommercial, Legal, and Ethical Issues > Ethical ConsiderationsTechnologies > Artificial Intelligence.

Light, Water, and Melatonin: The Synergistic Regulation of Phase Separation in Dementia

The swift rise in acceptance of molecular principles defining phase separation by a broad array of scientific disciplines is shadowed by increasing discoveries linking phase separation to pathological aggregations associated with numerous neurodegenerative disorders, including Alzheimer’s disease, that contribute to dementia. Phase separation is powered by multivalent macromolecular interactions. Importantly, the release of water molecules from protein hydration shells into bulk creates entropic gains that promote phase separation and the subsequent generation of insoluble cytotoxic aggregates that drive healthy brain cells into diseased states. Higher viscosity in interfacial waters and limited hydration in interiors of biomolecular condensates facilitate phase separation. Light, water, and melatonin constitute an ancient synergy that ensures adequate protein hydration to prevent aberrant phase separation. The 670 nm visible red wavelength found in sunlight and employed in photobiomodulation reduces interfacial and mitochondrial matrix viscosity to enhance ATP production via increasing ATP synthase motor efficiency. Melatonin is a potent antioxidant that lowers viscosity to increase ATP by scavenging excess reactive oxygen species and free radicals. Reduced viscosity by light and melatonin elevates the availability of free water molecules that allow melatonin to adopt favorable conformations that enhance intrinsic features, including binding interactions with adenosine that reinforces the adenosine moiety effect of ATP responsible for preventing water removal that causes hydrophobic collapse and aggregation in phase separation. Precise recalibration of interspecies melatonin dosages that account for differences in metabolic rates and bioavailability will ensure the efficacious reinstatement of the once-powerful ancient synergy between light, water, and melatonin in a modern world.

Convolution Neural Networks and Self-Attention Learners for Alzheimer Dementia Diagnosis from Brain MRI

Alzheimer's disease (AD) is the most common form of dementia. Computer-aided diagnosis (CAD) can help in the early detection of associated cognitive impairment. The aim of this work is to improve the automatic detection of dementia in MRI brain data. For this purpose, we used an established pipeline that includes the registration, slicing, and classification steps. The contribution of this research was to investigate for the first time, to our knowledge, three current and promising deep convolutional models (ResNet, DenseNet, and EfficientNet) and two transformer-based architectures (MAE and DeiT) for mapping input images to clinical diagnosis. To allow a fair comparison, the experiments were performed on two publicly available datasets (ADNI and OASIS) using multiple benchmarks obtained by changing the number of slices per subject extracted from the available 3D voxels. The experiments showed that very deep ResNet and DenseNet models performed better than the shallow ResNet and VGG versions tested in the literature. It was also found that transformer architectures, and DeiT in particular, produced the best classification results and were more robust to the noise added by increasing the number of slices. A significant improvement in accuracy (up to 7%) was achieved compared to the leading state-of-the-art approaches, paving the way for the use of CAD approaches in real-world applications.

Neurology education in the era of artificial intelligence

PURPOSE OF REVIEW

The practice of neurology is undergoing a paradigm shift because of advances in the field of data science, artificial intelligence, and machine learning. To ensure a smooth transition, physicians must have the knowledge and competence to apply these technologies in clinical practice. In this review, we describe physician perception and preparedness, as well as current state for clinical applications of artificial intelligence and machine learning in neurology.

RECENT FINDINGS

Digital health including artificial intelligence-based/machine learning-based technology has made significant inroads into various aspects of healthcare including neurological care. Surveys of physicians and healthcare stakeholders suggests an overall positive perception about the benefits of artificial intelligence/machine learning in clinical practice. This positive perception is tempered by concerns for lack of knowledge and limited opportunities to build competence in artificial intelligence/machine learning technology. Literature about neurologist's perception and preparedness towards artificial intelligence/machine learning-based technology is scant. There are very few opportunities for physicians particularly neurologists to learn about artificial intelligence/machine learning-based technology.

SUMMARY

Neurologists have not been surveyed about their perception and preparedness to adopt artificial intelligence/machine learning-based technology in clinical practice. We propose development of a practical artificial intelligence/machine learning curriculum to enhance neurologists' competence in these newer technologies.

Detecting mild cognitive impairment and dementia in older adults using naturalistic driving data and interaction-based classification from influence score

Several recent studies indicate that atypical changes in driving behaviors appear to be early signs of mild cognitive impairment (MCI) and dementia. These studies, however, are limited by small sample sizes and short follow-up duration. This study aims to develop an interaction-based classification method building on a statistic named Influence Score (i.e., I-score) for prediction of MCI and dementia using naturalistic driving data collected from the Longitudinal Research on Aging Drivers (LongROAD) project. Naturalistic driving trajectories were collected through in-vehicle recording devices for up to 44 months from 2977 participants who were cognitively intact at the time of enrollment. These data were further processed and aggregated to generate 31 time-series driving variables. Because of high dimensional time-series features for driving variables, we used I-score for variable selection. I-score is a measure to evaluate variables' ability to predict and is proven to be effective in differentiating between noisy and predictive variables in big data. It is introduced here to select influential variable modules or groups that account for compound interactions among explanatory variables. It is explainable regarding to what extent variables and their interactions contribute to the predictiveness of a classifier. In addition, I-score boosts the performance of classifiers over imbalanced datasets due to its association with the F1 score. Using predictive variables selected by I-score, interaction-based residual blocks are constructed over top I-score modules to generate predictors and ensemble learning aggregates these predictors to boost the prediction of the overall classifier. Experiments using naturalistic driving data show that our proposed classification method achieves the best accuracy (96%) for predicting MCI and dementia, followed by random forest (93%) and logistic regression (88%). In terms of F1 score and AUC, our proposed classifier achieves 98% and 87%, respectively, followed by random forest (with an F1 score of 96% and an AUC of 79%) and logistic regression (with an F1 score of 92% and an AUC of 77%). The results indicate that incorporating I-score into machine learning algorithms could considerably improve the model performance for predicting MCI and dementia in older drivers. We also performed the feature importance analysis and found that the right to left turn ratio and the number of hard braking events are the most important driving variables to predict MCI and dementia.

A Review of the Recent Advances in Alzheimer's Disease Research and the Utilization of Network Biology Approaches for Prioritizing Diagnostics and Therapeutics

Alzheimer's disease (AD) is a polygenic multifactorial neurodegenerative disease that, after decades of research and development, is still without a cure. There are some symptomatic treatments to manage the psychological symptoms but none of these drugs can halt disease progression. Additionally, over the last few years, many anti-AD drugs failed in late stages of clinical trials and many hypotheses surfaced to explain these failures, including the lack of clear understanding of disease pathways and processes. Recently, different epigenetic factors have been implicated in AD pathogenesis; thus, they could serve as promising AD diagnostic biomarkers. Additionally, network biology approaches have been suggested as effective tools to study AD on the systems level and discover multi-target-directed ligands as novel treatments for AD. Herein, we provide a comprehensive review on Alzheimer's disease pathophysiology to provide a better understanding of disease pathogenesis hypotheses and decipher the role of genetic and epigenetic factors in disease development and progression. We also provide an overview of disease biomarkers and drug targets and suggest network biology approaches as new tools for identifying novel biomarkers and drugs. We also posit that the application of machine learning and artificial intelligence to mining Alzheimer's disease multi-omics data will facilitate drug and biomarker discovery efforts and lead to effective individualized anti-Alzheimer treatments.

Multi-feature computational framework for combined signatures of dementia in underrepresented settings

Objective.The differential diagnosis of behavioral variant frontotemporal dementia (bvFTD) and Alzheimer's disease (AD) remains challenging in underrepresented, underdiagnosed groups, including Latinos, as advanced biomarkers are rarely available. Recent guidelines for the study of dementia highlight the critical role of biomarkers. Thus, novel cost-effective complementary approaches are required in clinical settings.Approach. We developed a novel framework based on a gradient boosting machine learning classifier, tuned by Bayesian optimization, on a multi-feature multimodal approach (combining demographic, neuropsychological, magnetic resonance imaging (MRI), and electroencephalography/functional MRI connectivity data) to characterize neurodegeneration using site harmonization and sequential feature selection. We assessed 54 bvFTD and 76 AD patients and 152 healthy controls (HCs) from a Latin American consortium (ReDLat).Main results. The multimodal model yielded high area under the curve classification values (bvFTD patients vs HCs: 0.93 (±0.01); AD patients vs HCs: 0.95 (±0.01); bvFTD vs AD patients: 0.92 (±0.01)). The feature selection approach successfully filtered non-informative multimodal markers (from thousands to dozens).Results. Proved robust against multimodal heterogeneity, sociodemographic variability, and missing data.Significance. The model accurately identified dementia subtypes using measures readily available in underrepresented settings, with a similar performance than advanced biomarkers. This approach, if confirmed and replicated, may potentially complement clinical assessments in developing countries.

Classification of Alzheimer’s Disease Using Dual-Phase 18F-Florbetaben Image with Rank-Based Feature Selection and Machine Learning

18F-florbetaben (FBB) positron emission tomography is a representative imaging test that observes amyloid deposition in the brain. Compared to delay-phase FBB (dFBB), early-phase FBB shows patterns related to glucose metabolism in 18F-fluorodeoxyglucose perfusion images. The purpose of this study is to prove that classification accuracy is higher when using dual-phase FBB (dual FBB) versus dFBB quantitative analysis by using machine learning and to find an optimal machine learning model suitable for dual FBB quantitative analysis data. The key features of our method are (1) a feature ranking method for each phase of FBB with a cross-validated F1 score and (2) a quantitative diagnostic model based on machine learning methods. We compared four classification models: support vector machine, naïve Bayes, logistic regression, and random forest (RF). In composite standardized uptake value ratio, RF achieved the best performance (F1: 78.06%) with dual FBB, which was 4.83% higher than the result with dFBB. In conclusion, regardless of the two quantitative analysis methods, using the dual FBB has a higher classification accuracy than using the dFBB. The RF model is the machine learning model that best classifies a dual FBB. The regions that have the greatest influence on the classification of dual FBB are the frontal and temporal lobes.