Investigating the application of graph theory features in hand movement directions decoding using EEG signals

Hosseini, Seyyed Moosa; Aminitabar, Amir Hossein; Shalchyan, Vahid

doi:10.1016/j.neures.2023.04.002

Cited by 8 publications

(2 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…9b ). Such spectral features can also be combined to graph-theoretical measurements to further improve decoding performance 41 . Non-surprisingly, the result of multi-features classification varied across subjects highlighting how much the decoding accuracy depends on the intracranial implantation in each patient (Fig.…”

Section: Discussionmentioning

confidence: 99%

Human local field potentials in motor and non-motor brain areas encode upcoming movement direction

Combrisson,

Di Rienzo,

Saive

et al. 2024

Commun Biol

View full text Add to dashboard Cite

Limb movement direction can be inferred from local field potentials in motor cortex during movement execution. Yet, it remains unclear to what extent intended hand movements can be predicted from brain activity recorded during movement planning. Here, we set out to probe the directional-tuning of oscillatory features during motor planning and execution, using a machine learning framework on multi-site local field potentials (LFPs) in humans. We recorded intracranial EEG data from implanted epilepsy patients as they performed a four-direction delayed center-out motor task. Fronto-parietal LFP low-frequency power predicted hand-movement direction during planning while execution was largely mediated by higher frequency power and low-frequency phase in motor areas. By contrast, Phase-Amplitude Coupling showed uniform modulations across directions. Finally, multivariate classification led to an increase in overall decoding accuracy (>80%). The novel insights revealed here extend our understanding of the role of neural oscillations in encoding motor plans.

show abstract

Section: Discussionmentioning

confidence: 99%

Human local field potentials in motor and non-motor brain areas encode upcoming movement direction

Combrisson,

Di Rienzo,

Saive

et al. 2024

Commun Biol

View full text Add to dashboard Cite

show abstract

“…9B). Such spectral features can also be combined to graph-theoretical measurements to further improve decoding performance (Hosseini et al, 2023). Non-surprisingly, the result of multi-features classification varied across subjects highlighting how much the decoding accuracy depends on the intracranial implantation in each patient (Fig.…”

Section: Discussionmentioning

confidence: 99%

Local field potentials in human motor and non-motor brain areas encode the direction of upcoming movements: An intracerebral EEG classification study

Combrisson,

Di Rienzo,

Saive

et al. 2023

Preprint

View full text Add to dashboard Cite

Limb movement direction can be inferred from motor cortex activity. In humans, such decoding has been predominantly demonstrated using the spectral power of electrophysiological signals recorded in sensorimotor areas during movement execution. Yet, it remains unclear to what extent intended hand movement direction can be predicted from brain signals recorded during movement planning. Furthermore, whether other oscillatory features beyond power are also involved in direction encoding is not fully understood. Here, we set out to probe the directional-tuning of oscillatory phase, amplitude and Phase-Amplitude Coupling (PAC) during motor planning and execution, using a machine learning framework on multi-site local field potentials (LFPs) in humans. To this end, we recorded intracranial EEG data from implanted epilepsy patients as they performed a four-direction delayed center-out motor task. We found that LFP power significantly predicted hand-movement direction at execution but also during planning. While successful classification during planning primarily involved low-frequency power in a fronto-parietal circuit, decoding during execution was largely mediated by higher frequency activity in motor and premotor areas. Interestingly, LFP phase at very low frequencies (<1.5 Hz) led to significant decoding in premotor brain regions during execution. The machine learning framework also showed PAC to be uniformly modulated across directions through the task. Cross-temporal generalization analyses revealed that several stable brain patterns in prefrontal and premotor brain regions encode directions across both planning and execution. Finally, multivariate classification led to an increase in overall decoding accuracy (>80%) during both planning and execution. The novel insights revealed here extend our understanding of the role of neural oscillations in encoding motor plans.

show abstract

Review of Brain-Computer Interface Applications in Neurological Disorders

Sami,

Rezaee,

Ansari

et al. 2024

Algorithms for Intelligent Systems

View full text Add to dashboard Cite

Investigating the application of graph theory features in hand movement directions decoding using EEG signals

Cited by 8 publications

References 46 publications

Human local field potentials in motor and non-motor brain areas encode upcoming movement direction

Human local field potentials in motor and non-motor brain areas encode upcoming movement direction

Local field potentials in human motor and non-motor brain areas encode the direction of upcoming movements: An intracerebral EEG classification study

Review of Brain-Computer Interface Applications in Neurological Disorders

Contact Info

Product

Resources

About