Evaluating Performance of EEG Data-Driven Machine Learning for Traumatic Brain Injury Classification

Abstract

Big data analytics can potentially benefit the assessment and management of complex neurological conditions by extracting information that is difficult to identify manually. In this study, we evaluated the performance of commonly used supervised machine learning algorithms in the classification of patients with traumatic brain injury (TBI) history from those with stroke history and/or normal EEG. Methods: Support vector machine (SVM) and K-nearest neighbors (KNN) models were generated with a diverse feature set from Temple EEG Corpus for both two-class classification of patients with TBI history from normal subjects and three-class classification of TBI, stroke and normal subjects. Results: For two-class classification, an accuracy of 0.94 was achieved in 10-fold cross validation (CV), and 0.76 in independent validation (IV). For three-class classification, 0.85 and 0.71 accuracy were reached in CV and IV respectively. Overall, linear discriminant analysis (LDA) feature selection and SVM models consistently performed well in both CV and IV and for both two-class and three-class classification. Compared to normal control, both TBI and stroke patients showed an overall reduction in coherence and relative PSD in delta frequency, and an increase in higher frequency (alpha, mu, beta and gamma) power. But stroke patients showed a greater degree of change and had additional global decrease in theta power. Conclusions: Our study suggests that EEG data-driven machine learning can be a useful tool for TBI classification. Significance: Our study provides preliminary evidence that EEG ML algorithm can potentially provide specificity to separate different neurological conditions.

[Retracted] Applications of Deep Learning in the Evaluation and Analysis of College Students’ Mental Health

“…However, students in lower level schools have less awareness of mental health and even do not care about their mental health status [9]. e research results of Vivaldi et al show that the college students' mental health research model and data structure combined with convolutional neural network, multi-layer neuron self-coding neural network, and big data analysis algorithm have a high level of evaluation and analysis ability for college students' mental health, but they often do not have a high degree of matching and fit for some college students with special thoughts and psychology [10]. Schilaty et al have conducted research on relevant aspects and fields for the purpose of improving the application scope, value, and accuracy of deep learning in the field of college students' mental health.…”

EEG Sinyallerini İşlemek İçin Makine Öğreniminin Kullanıldığı Konular Üzerine Bir İnceleme

“…EEG]). Travmatik beyin hasarı (TBH) öyküsü olan hastaların inme öyküsü ve/veya normal EEG'si olanlardan sınıflandırılmasında yaygın olarak kullanılan denetimli makine öğrenimi algoritmaları [35].…”

“…Yapılan literatür taraması sonucunda MÖ kullanılarak EEG işareti işleme konuları 18 başlık altında toplanabilir. Bunlar: epilepsi [7,8], duygu durumu [9,10], beyin-bilgisayar arayüzleri [11,12], uyku evreleri [13,14], devinimsel görselleştirme [15,16], zihinsel iş yükü [17,18], Alzheimer [19,20], Sürücü dikkati [1,21], şizofreni [3,22], robotik [23,24], dikkat [2,25], Alkol [26,27], göz kırpmak [4,28], algı [6,29], niyet [30,31], nesnelerin interneti [32,33], kişi kimliği [5,34], beyin hastalığı [35].…”

Clinical investigation of sensing ailments in brain movement through physiological activity using ML technique

“…We employ two seasoned neuroradiologists' custom observations as underlying data and functional mappings as mixes to incorporate them. N. Vivaldi [4] introduced a paper on accessing meaningful information, which is hard to discover directly, data has the potential to aid in the evaluation and monitoring of complicated brain disorders. Throughout this work, we assessed how well frequently employed supervised machine learning techniques distinguished individuals with a diagnosis of haemorrhage and normal EEG from those with a record of brain trauma.…”

“…These various ML techniques must be explored and verified for valid and realistic therapeutic trials in seizures and tomography. Algorithms has become increasingly popular in healthcare, particularly there in domains of neuroscience and epilepsy [4][5]. ML has several benefits over traditional approaches, including precise, automatic, and quick pattern learning, that may be utilised to design and/or refine therapeutically applicable methods in clinical practice and fundamental science.…”