Investigating the structure-function relationship of the corticomotor system early after stroke using machine learning

Chong, Benjamin; Wang, Alan; Borges, Victor M.; Byblow, Winston D.; Barber, P Alan; Stinear, Cathy M.

doi:10.1016/j.nicl.2021.102935

Cited by 4 publications

(2 citation statements)

References 45 publications

(63 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, the model can be recalled using only partial NI variables or time points to predict the recovery trajectory of the same patient or a new stroke patient. This capability can assist clinicians in personalized treatment planning and rehabilitation strategies [23,24].…”

Section: Potential Applications Of the Proposed Stam-ni Classificatio...mentioning

confidence: 99%

Brain-Inspired Spatio-Temporal Associative Memories for Neuroimaging Data Classification: EEG and fMRI

Kasabov,

Bahrami,

Doborjeh

et al. 2023

Bioengineering

Self Cite

View full text Add to dashboard Cite

Humans learn from a lot of information sources to make decisions. Once this information is learned in the brain, spatio-temporal associations are made, connecting all these sources (variables) in space and time represented as brain connectivity. In reality, to make a decision, we usually have only part of the information, either as a limited number of variables, limited time to make the decision, or both. The brain functions as a spatio-temporal associative memory. Inspired by the ability of the human brain, a brain-inspired spatio-temporal associative memory was proposed earlier that utilized the NeuCube brain-inspired spiking neural network framework. Here we applied the STAM framework to develop STAM for neuroimaging data, on the cases of EEG and fMRI, resulting in STAM-EEG and STAM-fMRI. This paper showed that once a NeuCube STAM classification model was trained on a complete spatio-temporal EEG or fMRI data, it could be recalled using only part of the time series, or/and only part of the used variables. We evaluated both temporal and spatial association and generalization accuracy accordingly. This was a pilot study that opens the field for the development of classification systems on other neuroimaging data, such as longitudinal MRI data, trained on complete data but recalled on partial data. Future research includes STAM that will work on data, collected across different settings, in different labs and clinics, that may vary in terms of the variables and time of data collection, along with other parameters. The proposed STAM will be further investigated for early diagnosis and prognosis of brain conditions and for diagnostic/prognostic marker discovery.

show abstract

Section: Potential Applications Of the Proposed Stam-ni Classificatio...mentioning

confidence: 99%

Brain-Inspired Spatio-Temporal Associative Memories for Neuroimaging Data Classification: EEG and fMRI

Kasabov,

Bahrami,

Doborjeh

et al. 2023

Bioengineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…Veerle found that the model created was capable of producing an average AUC value of 0.76 for eye movement features. Chong [21] conducted research related to stroke to investigate the relationship between the structure and function of the corticomotor system early after stroke using machine learning. Chong obtained research results in the form of an SVM classification model with an 81% accuracy in detecting motor generating potential, although false positives were more common than false negatives.…”

Section: Introductionmentioning

confidence: 99%

Comparison of Classification and Regression Model Approaches on the Main Causes of Stroke with Symbolic Regression Feyn Qlattice

Purwono,

Agung Budi Prasetio,

Burhanuddin bin Mohd Aboobaider

2023

JAHIR

View full text Add to dashboard Cite

Stroke is one of the deadliest diseases in the world, caused by damage to brain tissue resulting from a blockage in the cerebrovascular system. Proper treatment is essential to avoid worsening complications in patients. Several main triggering factors for stroke include hypertension, obesity, smoking habits, lack of physical activity, excessive alcohol consumption, diabetes, and high cholesterol levels. The advancement of information technology allows for early disease prediction through the utilization of AI and Machine Learning technology. The vast amount of data available on medical and health services worldwide can be maximized to identify risk factors for various diseases, including stroke. Machine learning techniques can be employed to predict the causes of stroke. In this study, we were inspired to use the Feyn Qlattice model approach to address stroke. Both classification and regression models were tested in this study. The results indicate that the classification model performs better, achieving an accuracy rate of 0.95. In contrast, the regression model yielded less satisfactory results, with R2, MAE, and RMSE values considered inadequate. This conclusion is supported by the regression plot and residual plot, both of which indicate suboptimal performance. Hence, maximizing the use of the Feyn Qlattice regression model in datasets related to the causes of stroke is recommended

show abstract

Mapping stroke outcomes: A review of brain connectivity atlases

Karnadipa,

Chong,

Shim

et al. 2024

Journal of Neuroimaging

View full text Add to dashboard Cite

The brain connectivity‐based atlas is a promising tool for understanding neural communication pathways in the brain, gaining relevance in predicting personalized outcomes for various brain pathologies. This critical review examines the robustness of the brain connectivity‐based atlas for predicting post‐stroke outcomes. A comprehensive literature search was conducted from 2012 to May 2023 across PubMed, Scopus, EMBASE, EBSCOhost, and Medline databases. Twenty‐one studies were screened, and through analysis of these studies, we identified 18 brain connectivity atlases employed by the studies for lesion analysis in their predictions. The brain atlases were assessed for study cohorts, connectivity measures, identified brain regions, atlas applications, and limitations. Based on the analysis of these studies, most atlases were based on diffusion tensor imaging and resting‐state functional magnetic resonance imaging (MRI). Studies predicting post‐stroke functional outcomes relied on the atlases for multivariate lesion analysis and region of interest identification, often employing atlases derived from young, healthy populations. Current brain connectivity‐based atlases for stroke applications lack standardized methods to define and map brain connectivity across atlases and cover sensorimotor functional connectivity to a limited extent. In conclusion, this review highlights the need to develop more comprehensive, robust, and adaptable brain connectivity‐based atlases specifically tailored to post‐stroke populations.

show abstract

Investigating the structure-function relationship of the corticomotor system early after stroke using machine learning

Abstract: Highlights MRI metrics can classify MEP status with 81% accuracy using support vector machine. Metrics from both T1 and diffusion MRI are important for this classification. Machine learning is a powerful tool for analysing multivariate MRI data.

Cited by 4 publications

References 45 publications

Brain-Inspired Spatio-Temporal Associative Memories for Neuroimaging Data Classification: EEG and fMRI

Brain-Inspired Spatio-Temporal Associative Memories for Neuroimaging Data Classification: EEG and fMRI

Comparison of Classification and Regression Model Approaches on the Main Causes of Stroke with Symbolic Regression Feyn Qlattice

Mapping stroke outcomes: A review of brain connectivity atlases

Contact Info

Product

Resources

About