MyMedR

Displaying all 12 publications

Abstract:

Sort:

Fulltext Epileptic seizure detection: a comparative study between deep and traditional machine learning techniques

Sahu R, Dash SR, Cacha LA, Poznanski RR, Parida S

J Integr Neurosci, 2020 Mar 30;19(1):1-9.
PMID: 32259881 DOI: 10.31083/j.jin.2020.01.24

Electroencephalography is the recording of brain electrical activities that can be used to diagnose brain seizure disorders. By identifying brain activity patterns and their correspondence between symptoms and diseases, it is possible to give an accurate diagnosis and appropriate drug therapy to patients. This work aims to categorize electroencephalography signals on different channels' recordings for classifying and predicting epileptic seizures. The collection of the electroencephalography recordings contained in the dataset attributes 179 information and 11,500 instances. Instances are of five categories, where one is the symptoms of epilepsy seizure. We have used traditional, ensemble methods and deep machine learning techniques highlighting their performance for the epilepsy seizure detection task. One dimensional convolutional neural network, ensemble machine learning techniques like bagging, boosting (AdaBoost, gradient boosting, and XG boosting), and stacking is implemented. Traditional machine learning techniques such as decision tree, random forest, extra tree, ridge classifier, logistic regression, K-Nearest Neighbor, Naive Bayes (gaussian), and Kernel Support Vector Machine (polynomial, gaussian) are used for classifying and predicting epilepsy seizure. Before using ensemble and traditional techniques, we have preprocessed the data set using the Karl Pearson coefficient of correlation to eliminate irrelevant attributes. Further accuracy of classification and prediction of the classifiers are manipulated using k-fold cross-validation methods and represent the Receiver Operating Characteristic Area Under the Curve for each classifier. After sorting and comparing algorithms, we have found the convolutional neural network and extra tree bagging classifiers to have better performance than all other ensemble and traditional classifiers.

Matched MeSH terms: Seizures/diagnosis*
Fulltext A signal processing based analysis and prediction of seizure onset in patients with epilepsy

Namazi H, Kulish VV, Hussaini J, Hussaini J, Delaviz A, Delaviz F, et al.

Oncotarget, 2016 Jan 5;7(1):342-50.
PMID: 26586477 DOI: 10.18632/oncotarget.6341

One of the main areas of behavioural neuroscience is forecasting the human behaviour. Epilepsy is a central nervous system disorder in which nerve cell activity in the brain becomes disrupted, causing seizures or periods of unusual behaviour, sensations and sometimes loss of consciousness. An estimated 5% of the world population has epileptic seizure but there is not any method to cure it. More than 30% of people with epilepsy cannot control seizure. Epileptic seizure prediction, refers to forecasting the occurrence of epileptic seizures, is one of the most important but challenging problems in biomedical sciences, across the world. In this research we propose a new methodology which is based on studying the EEG signals using two measures, the Hurst exponent and fractal dimension. In order to validate the proposed method, it is applied to epileptic EEG signals of patients by computing the Hurst exponent and fractal dimension, and then the results are validated versus the reference data. The results of these analyses show that we are able to forecast the onset of a seizure on average of 25.76 seconds before the time of occurrence.

Matched MeSH terms: Seizures/diagnosis
Newborn seizure detection based on heart rate variability

Malarvili MB, Mesbah M

IEEE Trans Biomed Eng, 2009 Nov;56(11):2594-603.
PMID: 19628449 DOI: 10.1109/TBME.2009.2026908

In this paper, we investigate the use of heart rate variability (HRV) for automatic newborn seizure detection. The proposed method consists of a sequence of processing steps, namely, obtaining HRV from the ECG, extracting a discriminating HRV feature set, selecting an optimal subset from the full feature set, and, finally, classifying the HRV into seizure/nonseizure using a supervised statistical classifier. Due to the fact that HRV signals are nonstationary, a set of time-frequency features from the newborn HRV is proposed and extracted. In order to achieve efficient HRV-based automatic newborn seizure detection, a two-phase wrapper-based feature selection technique is used to select the feature subset with minimum redundancy and maximum class discriminability. Tested on ECG recordings obtained from eight newborns with identified EEG seizure, the proposed HRV-based neonatal seizure detection algorithm achieved 85.7% sensitivity and 84.6% specificity. These results suggest that the HRV is sensitive to changes in the cardioregulatory system induced by the seizure, and therefore, can be used as a basis for an automatic seizure detection.

Matched MeSH terms: Seizures/diagnosis*
Fulltext Diagnostic dilemma of sacral abscess presented with seizure and altered conscious level in a patient with spinal cord injury

Chek Siang KC, Ahmad Fauzi A, Hasnan N

J Spinal Cord Med, 2017 01;40(1):113-117.
PMID: 26871508 DOI: 10.1080/10790268.2015.1133016

CONTEXT: Infection and septicaemia may clinically presented with seizure and altered conscious level. In spinal cord injury (SCI) population, they are at risk of having pressure ulcer which can be complicated further with infection and septicaemia.
FINDINGS: A 40-year-old man with complete T4 SCI and multiple clean and non-healing pressure ulcers at sacral and bilateral ischial tuberosity regions was initially admitted for negative pressure wound therapy (NPWT) dressing. He had an episode of seizure and subsequently had fluctuating altered conscious level before the diagnosis of deep-seated sacral abscess was made and managed. Prior investigations to rule out common possible sources of infections and management did not resolve the fluctuating event of altered consciousness.
CLINICAL RELEVANCE: We presented an unusual case presentation of septicemia in a patient with SCI with underlying chronic non-healing pressure ulcer. He presented with seizure and fluctuating altered conscious level. Even though a chronic non-healing ulcer appeared clinically clean, a high index of suspicion for deep seated abscess is warranted as one of the possible sources of infection, especially when treatment for other common sources of infections fails to result in clinical improvement.

Matched MeSH terms: Seizures/diagnosis*
Automated seizure prediction

Acharya UR, Hagiwara Y, Adeli H

Epilepsy Behav, 2018 11;88:251-261.
PMID: 30317059 DOI: 10.1016/j.yebeh.2018.09.030

In the past two decades, significant advances have been made on automated electroencephalogram (EEG)-based diagnosis of epilepsy and seizure detection. A number of innovative algorithms have been introduced that can aid in epilepsy diagnosis with a high degree of accuracy. In recent years, the frontiers of computational epilepsy research have moved to seizure prediction, a more challenging problem. While antiepileptic medication can result in complete seizure freedom in many patients with epilepsy, up to one-third of patients living with epilepsy will have medically intractable epilepsy, where medications reduce seizure frequency but do not completely control seizures. If a seizure can be predicted prior to its clinical manifestation, then there is potential for abortive treatment to be given, either self-administered or via an implanted device administering medication or electrical stimulation. This will have a far-reaching impact on the treatment of epilepsy and patient's quality of life. This paper presents a state-of-the-art review of recent efforts and journal articles on seizure prediction. The technologies developed for epilepsy diagnosis and seizure detection are being adapted and extended for seizure prediction. The paper ends with some novel ideas for seizure prediction using the increasingly ubiquitous machine learning technology, particularly deep neural network machine learning.

Matched MeSH terms: Seizures/diagnosis*
Automatic diagnosis of epileptic seizures using entropy-based features and multimodel deep learning approaches

Al-Qazzaz NK, Alrahhal M, Jaafer SH, Ali SHBM, Ahmad SA

Med Eng Phys, 2024 Aug;130:104206.
PMID: 39160030 DOI: 10.1016/j.medengphy.2024.104206

Epilepsy is one of the most common brain diseases, characterised by repeated seizures that occur on a regular basis. During a seizure, a patient's muscles flex uncontrollably, causing a loss of mobility and balance, which can be harmful or even fatal. Developing an automatic approach for warning patients of oncoming seizures necessitates substantial research. Analyzing the electroencephalogram (EEG) output from the human brain's scalp region can help predict seizures. EEG data were analyzed to extract time domain features such as Hurst exponent (Hur), Tsallis entropy (TsEn), enhanced permutation entropy (impe), and amplitude-aware permutation entropy (AAPE). In order to automatically diagnose epileptic seizure in children from normal children, this study conducted two sessions. In the first session, the extracted features from the EEG dataset were classified using three machine learning (ML)-based models, including support vector machine (SVM), K nearest neighbor (KNN), or decision tree (DT), and in the second session, the dataset was classified using three deep learning (DL)-based recurrent neural network (RNN) classifiers in The EEG dataset was obtained from the Neurology Clinic of the Ibn Rushd Training Hospital. In this regard, extensive explanations and research from the time domain and entropy characteristics demonstrate that employing GRU, LSTM, and BiLSTM RNN deep learning classifiers on the All-time-entropy fusion feature improves the final classification results.

Matched MeSH terms: Seizures/diagnosis
Video-EEG telemetry: apparent manifestation of both epileptic and non-epileptic attacks causing potential diagnostic pitfalls

Raymond AA, Gilmore WV, Scott CA, Fish DR, Smith SJ

Epileptic Disord, 1999 Jun;1(2):101-6.
PMID: 10937139

Video-EEG telemetry is often used to support the diagnosis of non-epileptic seizures (NES). Although rare, some patients may have both epileptic seizures (ES) and NES. It is crucially important to identify such patients to avoid the hazards of inappropriate anticonvulsant withdrawal. To delineate the electroclinical characteristics and diagnostic problems in this group of patients, we studied the clinical, EEG and MRI features of 14 consecutive patients in whom separate attacks, considered to be both NES and ES were recorded using video-EEG telemetry. Only two patients were drug-reduced during the telemetry. Most patients had their first seizure (ES or NES) in childhood (median age 7 years; range: 6 months-24 years); 8/14 patients were female. Brain MRI was abnormal in 10/14 patients. Interictal EEG abnormalities were present in all patients; 13/14 had epileptiform and 1/14 only background abnormalities. Over 70 seizures were recorded in these 14 patients: in 12/14 patients, the first recorded seizure was a NES (p < 0.001), and 7 of these patients had at least one more NES before an ES was recorded. Only 3/14 patients had more than 5 NES before an ES was recorded. Recording a small number of apparently NES in an individual by no means precludes the possibility of additional epilepsy. Particular care should be taken, and multiple (> 5) seizure recording may be advisable, in patients with a young age of seizure onset, interictal EEG abnormalities, or a clear, potential aetiology for epilepsy.

Matched MeSH terms: Seizures/diagnosis*
Refractory seizures in a young army cohort

Loh NK, Lee WL, Yew WW, Tjia TL

Ann Acad Med Singap, 1997 Jul;26(4):471-4.
PMID: 9395813

This survey covered male Singapore citizens born in 1974 who were medically screened at the age of 18 years before enlistment for compulsory military service. Suspected epileptics were referred to government hospitals for further management. Out of 20,542 men, there were 121 epileptics, giving a cumulative incidence of 5 per 1000 by age 18 years. We had information on 106 (87%) of these individuals and were able to interview them and review their hospital records. Seventy-three of the 106 (69%) epileptics had generalised seizures while 14 (13%) had refractory seizures. There was no statistically significant racial bias amongst these epileptics. Unprovoked afebrile seizures occurred early in these patients, half of whom had seizures onset before 7 years of age. Nine refractory epileptics had a history of febrile seizures, 4 of which were complex febrile seizures. Magnetic resonance imaging identified mesial temporal sclerosis in 2 patients and a hypothalamic lesion in 1 patient. Computed tomographic scans revealed focal cortical atrophy in 2 patients. Nine other patients had normal imaging studies. Nine out of 14 (64%) patients with refractory epilepsy had partial seizures; 4 (29%) had generalised seizures and 1 (7%) was unclassified. This is in contrast to the distribution of the entire cohort of epileptics studied. Two out of 9 patients with refractory partial seizures (gelastic epilepsy and mesial temporal sclerosis) had undergone surgery while 6 of the other 7 patients refused to consider surgery.

Matched MeSH terms: Seizures/diagnosis
Cardiorespiratory findings in epilepsy: A recent review on outcomes and pathophysiology

Akyüz E, Üner AK, Köklü B, Arulsamy A, Shaikh MF

J Neurosci Res, 2021 09;99(9):2059-2073.
PMID: 34109651 DOI: 10.1002/jnr.24861

Epilepsy is a debilitating disorder of uncontrollable recurrent seizures that occurs as a result of imbalances in the brain excitatory and inhibitory neuronal signals, that could stem from a range of functional and structural neuronal impairments. Globally, nearly 70 million people are negatively impacted by epilepsy and its comorbidities. One such comorbidity is the effect epilepsy has on the autonomic nervous system (ANS), which plays a role in the control of blood circulation, respiration and gastrointestinal function. These epilepsy-induced impairments in the circulatory and respiratory systems may contribute toward sudden unexpected death in epilepsy (SUDEP). Although, various hypotheses have been proposed regarding the role of epilepsy on ANS, the linking pathological mechanism still remains unclear. Channelopathies and seizure-induced damages in ANS-control brain structures were some of the causal/pathological candidates of cardiorespiratory comorbidities in epilepsy patients, especially in those who were drug resistant. However, emerging preclinical research suggest that neurotransmitter/receptor dysfunction and synaptic changes in the ANS may also contribute to the epilepsy-related autonomic disorders. Thus, pathological mechanisms of cardiorespiratory dysfunction should be elucidated by considering the modifications in anatomy and physiology of the autonomic system caused by seizures. In this regard, we present a comprehensive review of the current literature, both clinical and preclinical animal studies, on the cardiorespiratory findings in epilepsy and elucidate the possible pathological mechanisms of these findings, in hopes to prevent SUDEP especially in patients who are drug resistant.

Matched MeSH terms: Seizures/diagnosis
Fulltext Seizure induced by tranexamic acid in a patient with chronic kidney disease on maintenance dialysis

Fuah KW, Lim CTS, Pang DCL, Wong JS

Saudi J Kidney Dis Transpl, 2018 2 20;29(1):207-209.
PMID: 29456232 DOI: 10.4103/1319-2442.225177

Tranexamic acid (TXA) is an antifibrinolytic agent commonly used to achieve hemostasis. However, there have been a few case reports suggesting that high-dose intravenous TXA has epileptogenic property. In patients with renal impairment, even administering the usual recommended dose of TXA can induce seizure episodes. We present here a patient on hemodialysis who developed seizures after receiving two doses of TXA over 5 h period.

Matched MeSH terms: Seizures/diagnosis
Adenylosuccinate lyase deficiency in a Malaysian patient, with novel adenylosuccinate lyase gene mutations

Chen BC, McGown IN, Thong MK, Pitt J, Yunus ZM, Khoo TB, et al.

J Inherit Metab Dis, 2010 Dec;33 Suppl 3:S159-62.
PMID: 20177786 DOI: 10.1007/s10545-010-9056-z

Most cases of adenylosuccinate lyase (ADSL OMIM 103050) deficiency reported to date are confined to the various European ethnic groups. We report on the first Malaysian case of ADSL deficiency, which appears also to be the first reported Asian case. The case was diagnosed among a cohort of 450 patients with clinical features of psychomotor retardation, global developmental delay, seizures, microcephaly and/or autistic behaviour. The patient presented with frequent convulsions and severe myoclonic jerk within the first few days of life and severe psychomotor retardation. The high performance liquid chromatography (HPLC) profile of the urine revealed the characteristic biochemical markers of succinyladenosine (S-Ado) and succinyl-aminoimidazole carboximide riboside (SAICAr). The urinary S-Ado/SAICAr ratio was found to be 1.02 (type I ADSL deficiency). The patient was compound heterozygous for two novel mutations, c.445C > G (p.R149G) and c.774_778insG (p.A260GfsX24).

Matched MeSH terms: Seizures/diagnosis
Neurophysiological symptoms and aspartame: What is the connection?

Choudhary AK, Lee YY

Nutr Neurosci, 2018 Jun;21(5):306-316.
PMID: 28198207 DOI: 10.1080/1028415X.2017.1288340

Aspartame (α-aspartyl-l-phenylalanine-o-methyl ester), an artificial sweetener, has been linked to behavioral and cognitive problems. Possible neurophysiological symptoms include learning problems, headache, seizure, migraines, irritable moods, anxiety, depression, and insomnia. The consumption of aspartame, unlike dietary protein, can elevate the levels of phenylalanine and aspartic acid in the brain. These compounds can inhibit the synthesis and release of neurotransmitters, dopamine, norepinephrine, and serotonin, which are known regulators of neurophysiological activity. Aspartame acts as a chemical stressor by elevating plasma cortisol levels and causing the production of excess free radicals. High cortisol levels and excess free radicals may increase the brains vulnerability to oxidative stress which may have adverse effects on neurobehavioral health. We reviewed studies linking neurophysiological symptoms to aspartame usage and conclude that aspartame may be responsible for adverse neurobehavioral health outcomes. Aspartame consumption needs to be approached with caution due to the possible effects on neurobehavioral health. Whether aspartame and its metabolites are safe for general consumption is still debatable due to a lack of consistent data. More research evaluating the neurobehavioral effects of aspartame are required.

Matched MeSH terms: Seizures/diagnosis

Filters

Please provide feedback to Administrator (afdal@afpm.org.my)

External Links