eduzhai > Applied Sciences > Engineering >

Locked in Syndrome Machine Learning Classification using Sentence Comprehension EEG Data

  • Save

... pages left unread,continue reading

Document pages: 16 pages

Abstract: Locked-in Syndrome patients are often misdiagnosed and face pessimisticprognosis because of similarities with disorders of consciousness, a lack ofobjective biomarkers and a difficult-to-recognize pathogenesis. Biomarkers showpromise in identifying similar conditions, utilizing electroencephalography(EEG) data. This data, particularly in the form of event-related potentials(ERPs), while successful in varying applications, suffers from methodologicalconstraints and interpretation obstacles. The study documented in this body ofwork explores a machine learning paradigm with regards to N400 ERP dataretrieved from a sentence comprehension task to tackle these hindrances andproposes a new auxiliary diagnostic tool for LIS and possibly disorders ofconsciousness. A support vector machine (SVC) and a random forest classifier(RF) were able to classify conscious individuals from unconscious ones withoptimistic performance metrics. Based on these results, the proposed models andcontinuations thereof present valuable opportunities for the development of anauxiliary diagnostic tool for the classification of LIS patients, aidingdiagnosis, improving prognosis, stimulating recovery and reducing mortalityrates.

Please select stars to rate!

         

0 comments Sign in to leave a comment.

    Data loading, please wait...
×