Evaluating imaging biomarkers for neurodegeneration in pre-symptomatic Huntington's disease using machine learning techniques

Rizk‐Jackson, Angela; Stoffers, Diederick; Sheldon, Sarah; Kuperman, Joshua; Dale, Anders M.; Goldstein, Jody; Corey–Bloom, Jody; Poldrack, Russell A.; Aron, Adam R.

doi:10.1016/j.neuroimage.2010.04.273

Cited by 95 publications

(78 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Behavioral and neuropsychological tests and accompanying functional imaging, while applicable to humans, have few good parallels in mice (Ferrante, 2009). For brain, the tissue most affected in HD, imaging of volumetric changes provides the single best direct measure to date of progression in both humans and mice (Rizk-Jackson et al, 2010). Brain shrinkage, however, provides no data on the mechanisms mediating that loss.…”

Section: Introductionmentioning

confidence: 99%

Cortical Metabolites as Biomarkers in the R6/2 Model of Huntington's Disease

Zacharoff

Tkáč

Song³

et al. 2011

J Cereb Blood Flow Metab

View full text Add to dashboard Cite

To improve the ability to move from preclinical trials in mouse models of Huntington's disease (HD) to clinical trials in humans, biomarkers are needed that can track similar aspects of disease progression across species. Brain metabolites, detectable by magnetic resonance spectroscopy (MRS), have been suggested as potential biomarkers in HD. In this study, the R6/2 transgenic mouse model of HD was used to investigate the relative sensitivity of the metabolite profiling and the brain volumetry to anticipate the disease progression. Magnetic resonance imaging (MRI) and 1 H MRS data were acquired at 9.4 T from the R6/2 mice and wild-type littermates at 4, 8, 12, and 15 weeks. Brain shrinkage was detectable in striatum, cortex, thalamus, and hypothalamus by 12 weeks. Metabolite changes in cortex paralleled and sometimes preceded those in striatum. The entire set of metabolite changes was compressed into principal components (PCs) using Partial Least Squares-Discriminant Analysis (PLS-DA) to increase the sensitivity for monitoring disease progression. In comparing the efficacy of volume and metabolite measurements, the cortical PC1 emerged as the most sensitive single biomarker, distinguishing R6/2 mice from littermates at all time points. Thus, neurochemical changes precede volume shrinkage and become potential biomarkers for HD mouse models.

show abstract

Section: Introductionmentioning

confidence: 99%

Cortical Metabolites as Biomarkers in the R6/2 Model of Huntington's Disease

Zacharoff

Tkáč

Song³

et al. 2011

J Cereb Blood Flow Metab

View full text Add to dashboard Cite

show abstract

“…Because individual classification is the sine qua non for eventual translation to clinical use, we followed our community detection analysis with an investigation using support vector machine (SVM)-based multivariate pattern analysis (MVPA) (30,31) to identify how well individual children can be identified as defined by the community detection delineated subtypes. SVMs are supervised classification algorithms rooted in statistical learning theory, capable of recognizing patterns for the purposes of categorization.…”

mentioning

confidence: 99%

Distinct neuropsychological subgroups in typically developing youth inform heterogeneity in children with ADHD

Fair

Bathula

Nikolas

et al. 2012

Proc. Natl. Acad. Sci. U.S.A.

429

422

View full text Add to dashboard Cite

Research and clinical investigations in psychiatry largely rely on the de facto assumption that the diagnostic categories identified in the Diagnostic and Statistical Manual (DSM) represent homogeneous syndromes. However, the mechanistic heterogeneity that potentially underlies the existing classification scheme might limit discovery of etiology for most developmental psychiatric disorders. Another, perhaps less palpable, reality may also be interfering with progress-heterogeneity in typically developing populations. In this report we attempt to clarify neuropsychological heterogeneity in a large dataset of typically developing youth and youth with attention deficit/hyperactivity disorder (ADHD), using graph theory and community detection. We sought to determine whether data-driven neuropsychological subtypes could be discerned in children with and without the disorder. Because individual classification is the sine qua non for eventual clinical translation, we also apply support vector machine-based multivariate pattern analysis to identify how well ADHD status in individual children can be identified as defined by the community detection delineated subtypes. The analysis yielded several unique, but similar subtypes across both populations. Just as importantly, comparing typically developing children with ADHD children within each of these distinct subgroups increased diagnostic accuracy. Two important principles were identified that have the potential to advance our understanding of typical development and developmental neuropsychiatric disorders. The first tenet suggests that typically developing children can be classified into distinct neuropsychological subgroups with high precision. The second tenet proposes that some of the heterogeneity in individuals with ADHD might be "nested" in this normal variation.psychiatric disorders | research domain criteria | cognition | modularity | executive functions

show abstract

“…Indeed, computational tools already exist to combine biomarkers into new, more powerful indices of disease status. [3][4][5][6] In oncology, such an approach has been used to stratify tumor type and to assess disease status and response to therapy. 7,8 One method for combining biomarkers is through machine learning algorithms in which unrelated variables are integrated by a computer program that is first taught to associate one specific clinical value with a combination of data sets.…”

Section: Discussionmentioning

confidence: 99%

“…Support vector machines (SVMs) are one method for doing this. SVMs, in fact, have already been explored in Alzheimer disease, 3 Parkinson disease, 4 and Huntington disease 5 to assist with the identification of disease onset.…”

Section: Discussionmentioning

confidence: 99%

Machine learning algorithms to classify spinal muscular atrophy subtypes

Srivastava¹,

Darras²,

Wu³

et al. 2012

Neurology

View full text Add to dashboard Cite

Objectives: The development of better biomarkers for disease assessment remains an ongoing effort across the spectrum of neurologic illnesses. One approach for refining biomarkers is based on the concept of machine learning, in which individual, unrelated biomarkers are simultaneously evaluated. In this cross-sectional study, we assess the possibility of using machine learning, incorporating both quantitative muscle ultrasound (QMU) and electrical impedance myography (EIM) data, for classification of muscles affected by spinal muscular atrophy (SMA).Methods: Twenty-one normal subjects, 15 subjects with SMA type 2, and 10 subjects with SMA type 3 underwent EIM and QMU measurements of unilateral biceps, wrist extensors, quadriceps, and tibialis anterior. EIM and QMU parameters were then applied in combination using a support vector machine (SVM), a type of machine learning, in an attempt to accurately categorize 165 individual muscles.Results: For all 3 classification problems, normal vs SMA, normal vs SMA 3, and SMA 2 vs SMA 3, use of SVM provided the greatest accuracy in discrimination, surpassing both EIM and QMU individually. For example, the accuracy, as measured by the receiver operating characteristic area under the curve (ROC-AUC) for the SVM discriminating SMA 2 muscles from SMA 3 muscles was 0.928; in comparison, the ROC-AUCs for EIM and QMU parameters alone were only 0.877 (p Ͻ 0.05) and 0.627 (p Ͻ 0.05), respectively. Conclusions:Combining EIM and QMU data categorizes individual SMA-affected muscles with very high accuracy. Further investigation of this approach for classifying and for following the progression of neuromuscular illness is warranted. Neurology ® 2012;79:358-364 GLOSSARY AUC ϭ area under the curve; EIM ϭ electrical impedance myography; PCA ϭ principal component analysis; QMU ϭ quantitative muscle ultrasound; ROC ϭ receiver operating characteristic; SMA ϭ spinal muscular atrophy; SVM ϭ support vector machine.

show abstract

Evaluating imaging biomarkers for neurodegeneration in pre-symptomatic Huntington's disease using machine learning techniques

Cited by 95 publications

References 41 publications

Cortical Metabolites as Biomarkers in the R6/2 Model of Huntington's Disease

Cortical Metabolites as Biomarkers in the R6/2 Model of Huntington's Disease

Distinct neuropsychological subgroups in typically developing youth inform heterogeneity in children with ADHD

Machine learning algorithms to classify spinal muscular atrophy subtypes

Contact Info

Product

Resources

About