Detection of cardiac ischaemia using bispectral analysis approach

Al–Fahoum, Amjed S.; Alfraihat, Ausilah Ahmad Sulieman; Al-Araida, Aseel

doi:10.3109/03091902.2014.925983

Cited by 19 publications

(11 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…One of the most established applications of EEG-based bispectral analysis involves the determination of an index for depth of brain anaesthesia in the form of the bispectral index, which is extensively documented [23,26,30,[36][37][38][39]. However, bispectral analysis has also been successfully and widely applied as a diagnostic tool within studies involving: phases of epileptic seizure [40,41]; identification of epileptic and focal cerebral ischemia [40,42]; sleep detection [43]; evaluation of the degree of brain maturation in neonates [44]; differentiation of quadriceps muscle activation [45]; and normal sinus versus ischemic, tachycardia and fibrillation cardiac rhythms [31,46].…”

Section: Conventional Eeg Analysis Brief Overviewmentioning

confidence: 99%

A New Approach to High-Order Electroencephalogram Phase Analysis Details the Mathematical Mechanisms of Central Nervous System Impulse Encoding

Simeoni¹

2021

UNET JOSS

View full text Add to dashboard Cite

This paper presents a new electroencephalogram (EEG) analysis technique which is applied to example EEGs pertaining to nine human subjects and a broad spectrum of clinical scenarios. While focusing on technique physical efficacy, the paper also paves the way for future clinically-focused studies with revelations of several quantified and detailed findings in relation to high-order central nervous system communicative impulse encoding akin to a sophisticated form of phase-shift keying. The fact that fine encoding details are extracted with confidence from a seemingly modest EEG set supports the paper’s position that vast amounts of accessible information currently goes unrecognised by conventional EEG analysis. The technique commences with high resolution Fourier analysis being twice applied to an EEG, providing newly-identified harmonics. Except for deep sleep where harmonic phase, φ, behaviour becomes highly linear, φ transitional values, ∆φ, measured between harmonics of progressively increasing order are found to cluster rather than follow a normal distribution (e.g., χ2 = 303, df = 12, p < 0.001). Clustering is categorised into ten Families for which many separations between ∆φ values are writable in terms of k = j/4 or j/3 (j = 1, 2, 3 ...), with a preference for k = j/2 (χ2 = 77, df = 1, p < 0.001), amounts of a Family-specific quantum increment value, α∆φ. A parabolic relationship (r > 0.9999, p < 0.001) exists between α∆φ (and the parabola minimum associates with an additional inter-Family or universal quantum increment value, αmin). Ratios of α∆φ typically align within ± 0.5% of simple common fractions (95% CI).

show abstract

Section: Conventional Eeg Analysis Brief Overviewmentioning

confidence: 99%

A New Approach to High-Order Electroencephalogram Phase Analysis Details the Mathematical Mechanisms of Central Nervous System Impulse Encoding

Simeoni¹

2021

UNET JOSS

View full text Add to dashboard Cite

show abstract

“…The bispectral analysis is a sophisticated signal processing approach that measures quadratic nonlinearities (phase-coupling) between signal components. Due to their interdependencies, it revealed unambiguity in many biomedical signals, such as the electrocardiogram (ECG) and electroencephalogram (EEG) [18][19][20][21][22][23][24]. Note that the features obtained using these methods may enhance the performance of the deep learning algorithm.…”

Section: Introductionmentioning

confidence: 99%

An Innovative Bispectral Deep Learning Method for Protein Family Classification

Abu-Qasmieh¹,

Al–Fahoum²,

Alquran³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Proteins are essential for many biological functions. For example, folding amino acid chains reveals their functionalities by maintaining tissue structure, physiology, and homeostasis. Note that quantifiable protein characteristics are vital for improving therapies and precision medicine. The automatic inference of a protein's properties from its amino acid sequence is called "basic structure". Nevertheless, it remains a critical unsolved challenge in bioinformatics, although with recent technological advances and the investigation of protein sequence data. Inferring protein function from amino acid sequences is crucial in biology. This study considers using raw sequencing to explain biological facts using a large corpus of protein sequences and the Globin-like superfamily to generate a vector representation. The power of two representations was used to identify each amino acid, and a coding technique was established for each sequence family. Subsequently, the encoded protein numerical sequences are transformed into an image using bispectral analysis to identify essential characteristics for discriminating between protein sequences and their families. A deep Convolutional Neural Network (CNN) classifies the resulting images and developed non-normalized and normalized encoding techniques. Initially, the dataset was split 70/30 for training and testing. Correspondingly, the dataset was utilized for 70% training, 15% validation, and 15% testing. The suggested methods are evaluated using accuracy, precision, and recall. The non-normalized method had 70% accuracy, 72% precision, and 71% recall. 68% accuracy, 67% precision, and 67% recall after validation. Meanwhile, the normalized approach without validation had 92.4% accuracy, 94.3% precision, and 91.1% recall. Validation showed 90% accuracy, 91.2% precision, and 89.7% recall. Note that both algorithms outperform the rest. The paper presents that bispectrum-based nonlinear analysis using deep learning models outperforms standard machine learning methods and other deep learning methods based on convolutional architecture. They offered the best inference performance as the proposed approach improves categorization and prediction. Several instances show successful multi-class prediction in molecular biology's massive data.

show abstract

“…Bu alanda birçok araştırmacı farklı öznitelikler, sınıflandırma yöntemleri ve farklı veritabanları kullanarak ST kısmındaki değişimleri tespit etmeye çalışmışlardır. Bu çalışmalarda öznitelikler, Dalgacık Dönüşümü [9][10], Karhunen-Loeve Dönüşümü (KLT) [11][12], Genetik Algoritması [13], Saklı Markov Modeli (HMM) [14], Vektörkardiyografi (kalp yöney eğrisi çizim yöntemi) ST-T Metodu [15] ve Saklı Markov Modeli (HMM) ve Gauss Karışım Modeli (GMM) [16] [20] doğruluk değerinin önerilen yöntemden daha iyi sonuç verdiği görülmüştür. Ancak bu çalışmanın pozitif öngörü değerinin önerilen yönteme göre oldukça düşük olduğu görülmüştür ve çalışmanın gerçek zamanlı olup olmadığı hakkında bir bilgiye yer verilmemiştir.…”

Section: Introductionunclassified

ST Değişiminin Wigner-Ville Dağılım Esaslı Erken Tespiti

Kayikcioglu

Ulutaş

Akdeniz

et al. 2017

SDÜ Fen Bil Enst Der

View full text Add to dashboard Cite

Anahtar Kelimeler Elektrokardiyagram(EKG), ST değişimi, Myokard enfarktüs, Wigner-Ville dağılımı, TeletıpÖzet: EKG işaretinde ST değişiminin erken tespit edilmesi myokard enfarktüs önlenmesi açısından oldukça önemlidir. Bu çalışmada ST değişimin erken tespit etmek amacıyla Wigner-Ville dağılımına dayanan bir algoritma geliştirilmiştir. Algoritma MIT-BIH Aritmi ve European ST-T veritabanlarından üretilen büyük bir veride test edilmiştir. MIT-BIH veritabanından V1, V2, V4, V5 derivasyonlarında sağlıklı veya aritmi içeren 111688 R-R aralığı ve European ST-T veritabanından V1, V2, V3, V4, V5 derivasyonlarında 111688 tane ST değişimi olan R-R aralıkları seçilmiştir. Sınıflandırmada performans sonuçları doğruluk, duyarlılık, özgüllük ve pozitif öngörü, sırasıyla %98,78, %98,55, %99,0 ve %99,01 olarak bulunmuş olup bu değerler literatürdeki çalışmalara ait değerlerin üstündedir. Ayrıca önerilen algoritmanın hızı tele-tıp sistemleri için oldukça uygundur. Early Detection of ST Change Based on Wigner-Ville Distrubition Keywords Electrocardiogram (ECG), ST change, Myocardial infarction, Wigner-Ville distribution, TelemedicineAbstract: Early detection of ST change in ECG signals is very important for the prevention of myocardial infarction. In this study, a Wigner-Ville distribution based algorithm was developed for early detection of ST change. The algorithm was tested on big data which was were generated from the MIT-BIH database and the European ST-T database. From the MIT-BIH database, 111688 R-R intervals containing healthy or arrhythmias in V1, V2, V4, V5 leads and R-R intervals with 111688 ST segment changes in V1, V2, V3, V4, V5 derivations from the European ST-T database were selected. Performance results in classification are obtained as for accuracy, sensitivity, specificity and positive predictive, respectively 98,78%, 98,55%, 99,01% and 99,01%, these values are over of those of studies in literature. The speed of the algorthim is also suitable for telemedicine systems.

show abstract

Detection of cardiac ischaemia using bispectral analysis approach

Cited by 19 publications

References 26 publications

A New Approach to High-Order Electroencephalogram Phase Analysis Details the Mathematical Mechanisms of Central Nervous System Impulse Encoding

A New Approach to High-Order Electroencephalogram Phase Analysis Details the Mathematical Mechanisms of Central Nervous System Impulse Encoding

An Innovative Bispectral Deep Learning Method for Protein Family Classification

ST Değişiminin Wigner-Ville Dağılım Esaslı Erken Tespiti

Contact Info

Product

Resources

About