Predicting Longitudinal Outcomes of Alzheimer’s Disease via a Tensor-Based Joint Classification and Regression Model

Brand, Lodewijk; Nichols, Kai; Wang, Hua; Huang, Heng; Shen, Li; Initiative, Alzheimer’s Disease Neuroimaging

doi:10.1142/9789811215636_0002

Cited by 7 publications

(8 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Three different classification techniques, including Bayesian Network (Bayes Net), Logistic Regression (LR), and C4.5 (Decision Tree) have been used for deriving the AD progression models. These algorithms employ dissimilar learning methods to construct the classifier and have been widely used in medical screening and diagnosis [29,38,51,52]. More details on how these classification algorithms work is given in Section 6.…”

Section: ) Similarity Of Features To Obtain Highly Influential Yet Di...mentioning

confidence: 99%

Detection of dementia progression from functional activities data using machine learning techniques

Thabtah¹,

Ong

Peebles

2022

IDT

View full text Add to dashboard Cite

Early screening for Alzheimer’s disease (AD) is crucial for disease management, intervention, and healthcare resource accessibility. Medical assessments of AD diagnosis include the utilisation of biological markers (biomarkers), positron emission tomography (PET) scans, magnetic resonance imaging (MRI) images, and cerebrospinal fluid (CSF). These methods are resource intensive as well as physically invasive, whereas neuropsychological tests are fast, cost effective, and simple to administer for providing early AD diagnosis. However, neuropsychological assessments contain elements related to executive functions, memory, orientation, learning, judgment, and perceptual motor function (among others) that overlap, making it difficult to identify the key elements that trigger the progression of dementia or mild cognitive impairment (MCI). This research investigates the elements of the Functional Activities Questionnaire (FAQ) an early screening method using a data driven approach based on feature selection and classification. The aim is to determine the key items in the FAQ that may trigger AD advancement. To achieve the aim, real data observations of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) project have been processed using the proposed data driven approach. The results derived by the machine learning techniques in the proposed approach on data subsets of the FAQ items with demographics show models with accuracy, sensitivity, and specificity all exceeding 90%. In addition, FAQ elements including Administration and Shopping related activities showed correlations with the progression class; these elements cover four out of the six Diagnostic and Statistical Manual’s (DSM-5’s) neurocognitive domains.

show abstract

Section: ) Similarity Of Features To Obtain Highly Influential Yet Di...mentioning

confidence: 99%

Detection of dementia progression from functional activities data using machine learning techniques

Thabtah¹,

Ong

Peebles

2022

IDT

View full text Add to dashboard Cite

show abstract

“…To determine the prevalence of the use of nonimaging clinical features as potential AD risk factors, we classified the included studies into the following 2 categories: (1) Clinical onlyonly nonimaging clinical variables 36,37 and (2) Clinical þ Imagingimaging and nonimaging clinical variables were integrated to form the complete set of features. [38][39][40][41] We grouped the features into the following categories: neuroimaging features, 35,42,43 cognitive assessments, [44][45][46][47] genetic factors, [48][49][50][51] laboratory test values, [52][53][54] patient demographics, [55][56][57] and clinical notes.…”

Section: Ad Dementia Features and Biomarkersmentioning

confidence: 99%

Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review

Kumar

Schindler

et al. 2021

JAMIA Open

View full text Add to dashboard Cite

Objective Alzheimer disease (AD) is the most common cause of dementia, a syndrome characterized by cognitive impairment severe enough to interfere with activities of daily life. We aimed to conduct a systematic literature review (SLR) of studies that applied machine learning (ML) methods to clinical data derived from electronic health records in order to model risk for progression of AD dementia. Materials and Methods We searched for articles published between January 1, 2010, and May 31, 2020, in PubMed, Scopus, ScienceDirect, IEEE Explore Digital Library, Association for Computing Machinery Digital Library, and arXiv. We used predefined criteria to select relevant articles and summarized them according to key components of ML analysis such as data characteristics, computational algorithms, and research focus. Results There has been a considerable rise over the past 5 years in the number of research papers using ML-based analysis for AD dementia modeling. We reviewed 64 relevant articles in our SLR. The results suggest that majority of existing research has focused on predicting progression of AD dementia using publicly available datasets containing both neuroimaging and clinical data (neurobehavioral status exam scores, patient demographics, neuroimaging data, and laboratory test values). Discussion Identifying individuals at risk for progression of AD dementia could potentially help to personalize disease management to plan future care. Clinical data consisting of both structured data tables and clinical notes can be effectively used in ML-based approaches to model risk for AD dementia progression. Data sharing and reproducibility of results can enhance the impact, adaptation, and generalizability of this research.

show abstract

“…is the tensor of the n projection matrices, one for each participant. Here, to maximize the consistency across all the learned projection matrices for the same cohort of participants (Wang et al 2012d,c;Brand et al 2018Brand et al , 2019Brand et al , 2020a, we use the trace norm regularization of W (1) * and W (2) * in our objective, where…”

Section: Learning Temporally Augmented Representations For Dynamic Im...mentioning

confidence: 99%

“…Public-private partnerships such as the Alzheimer's Disease Neuroimaging Initiative (ADNI) (Petersen et al 2010) have provided a comprehensive dataset consisting of genetic (e.g., static) biomarkers, such as Single Nucleotide Polymorphisms (SNPs), and neuroimaging (e.g., dynamic) biomarkers derived from brain imaging modalities. Recent algorithmic improvements (Wang et al 2012d;Brand et al 2020a) have shown promise in identifying AD from phenotypic changes. Although effective, they have modeled the longitudinal biomarkers as tensors, which inevitably complicates the problem.…”

Section: Introductionmentioning

confidence: 99%

“…Although effective, they have modeled the longitudinal biomarkers as tensors, which inevitably complicates the problem. Other recent works (Lu et al 2018;Brand et al 2019), have leveraged longitudinal modalities to identify temporal relationships across the modalities. However, these approaches can only utilize longitudinal data that is consistent across all participants.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Integrating Static and Dynamic Data for Improved Prediction of Cognitive Declines Using Augmented Genotype-Phenotype Representations

Seo

Brand

Wang

et al. 2021

AAAI

Self Cite

View full text Add to dashboard Cite

Alzheimer’s Disease (AD) is a chronic neurodegenerative disease that causes severe problems in patients’ thinking, memory, and behavior. An early diagnosis is crucial to prevent AD progression; to this end, many algorithmic approaches have recently been proposed to predict cognitive decline. However, these predictive models often fail to integrate heterogeneous genetic and neuroimaging biomarkers and struggle to handle missing data. In this work we propose a novel objective function and an associated optimization algorithm to identify cognitive decline related to AD. Our approach is designed to incorporate dynamic neuroimaging data by way of a participant-specific augmentation combined with multimodal data integration aligned via a regression task. Our approach, in order to incorporate additional side-information, utilizes structured regularization techniques popularized in recent AD literature. Armed with the fixed-length vector representation learned from the multimodal dynamic and static modalities, conventional machine learning methods can be used to predict the clinical outcomes associated with AD. Our experimental results show that the proposed augmentation model improves the prediction performance on cognitive assessment scores for a collection of popular machine learning algorithms. The results of our approach are interpreted to validate existing genetic and neuroimaging biomarkers that have been shown to be predictive of cognitive decline.

show abstract

Predicting Longitudinal Outcomes of Alzheimer’s Disease via a Tensor-Based Joint Classification and Regression Model

Cited by 7 publications

References 36 publications

Detection of dementia progression from functional activities data using machine learning techniques

Detection of dementia progression from functional activities data using machine learning techniques

Machine learning for modeling the progression of Alzheimer disease dementia using clinical data: a systematic literature review

Integrating Static and Dynamic Data for Improved Prediction of Cognitive Declines Using Augmented Genotype-Phenotype Representations

Contact Info

Product

Resources

About