Kezban Aslan

A Radial Basis Function Neural Network Model for Classification of Epilepsy Using EEG Signals

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patient’s epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify epilepsy groups such as partial and primary generalized epilepsy by using Radial Basis Function Neural Network (RBFNN) and Multilayer Perceptron Neural Network (MLPNNs). Four hundred eighteen patients with epilepsy diagnoses according to International League against Epilepsy (ILAE 1981) were included in this study. The correct classification of this data was performed by two expert neurologists before they were executed by neural networks. The neural networks were trained by the parameters obtained from the EEG signals and clinic properties of the patients. Experimental results show that the predictions of both neural network models are very satisfying for learning data sets. According to test results, RBFNN (total classification accuracy = 95.2%) has classified more successfully when compared with MLPNN (total classification accuracy = 89.2%). These results indicate that RBFNN model may be used in clinical studies as a decision support tool to confirm the classification of epilepsy groups after the model is developed.

Early left ventricular functional alterations in patients with obstructive sleep apnea syndrome

BACKGROUND The knowledge regarding myocardial alterations in patients with obstructive sleep apnea syndrome (OSAS) in the absence of any known cardiovascular disorders including hypertension is limited. The aim of this study was to assess the early alterations of left ventricular (LV) functions caused by OSAS before the development of hypertension and other cardiovascular manifestations of OSAS. METHODS Eighty consecutive patients who underwent polysomnography (PSG) were enrolled in the study. Patients with hypertension, diabetes mellitus or any other known cardiac diseases were excluded from the study. Subjects were separated into two groups by their apnea/hypopnea index (AHI) (group 1: AHI < 15, and group 2: AHI ≥ 15). Fourty-three patients with normal polysomnographic examination or mild OSAS (group 1) and 37 patients with moderate to severe OSAS (group 2) were compared. After PSG examination, LV functions were assessed by using the conventional and tissue Doppler echocardiographic methods. RESULTS The mean age was similar between the groups. The ratio of male patients was higher in group 2 (male/female: 31/12 in group 1 vs. 34/3 in group 2, p = 0.04). Body mass index was higher in group 2 (p = 0.05). Conventional echocardiography showed that interventricular septum thickness was 9.5 ± 1.1 mm in group 1, and 10.5 ± 1.4 mm in group 2 (p = 0.02). Mean left atrial diameter was 35.6 ± 4.1 mm in group 2, and 33.8 ± 3.1 mm in group 1 (p = 0.04). Ratio of early to late transmitral diastolic velocities was lower in group 2 (p = 0.01), indicating that impairment of diastolic function was more frequent in moderate to severe OSAS patients. Tissue Doppler echocardiography showed that early diastolic myocardial velocity was lower ingroup 2 (21.1 ± 5.6 cm/s in group 1 vs. 18.3 ± 5.3 cm/s in group 2, p = 0.01). CONCLUSIONS Left ventricular diastolic dysfunction, LV hypertrophy and left atrial dilatationoccur in patients with OSAS even before the development of hypertension and other cardiovascular diseases.

Recurrent headache and MRI findings in systemic lupus erythematosus.

BACKGROUND Headache in patients with systemic lupus eryhtematosus (SLE) is considered a common neurological finding, although the relationship is unclear. Another obscure point is the relationship between headache and neuroradiologic findings in these patients. AIM In this study, we aimed to evaluate the correlation between headache characteristics and intracranial lesions in SLE patients. METHODS AND RESULTS Forty-eight SLE patients were chosen from those referred to our clinic depending on the American Collage of Rheumatology (ACR) criteria at the same time or after the diagnosis of SLE. Headache classification was done regarding the ICD-II criteria in the patients. Headache severity was assessed by visual analog scale (VAS), and subjects with VAS > or = 4 were included in the study. Patients were divided into two groups according to magnetic resonance imaging (MRI) findings: abnormal MRI (lesion positive) and normal MRI (lesion negative). On MRI, intracranial lesions were detected in 37.5% (n = 18) of the patients, and no lesion was found in 62.5% (n = 30). Headache characteristics were as tension type in 54.1% (n = 26) and migraine like in 39.6% (n = 19) of all patients. Imaging findings were mostly as periventricular and subcortical focal lesions, ranging from 3-22 mm in diameter. A significant correlation was found between abnormal MRI findings with advanced age and prolonged disease duration (p = 0.018, p = 0.016). CONCLUSIONS As a conclusion, a detailed neurologic evaluation and radiologic investigation, if necessary, should be performed in SLE patients with prolonged disease and advanced age, regardless of headache characteristics.

Transient parkinsonism: Induced by progesterone or pregnancy?

We report on the development of transient parkinsonism after progesterone injection in a pregnant patient with a risk of abortion. Etiological possibilities are discussed, including pregnancy itself, possible toxic effects of the dead fetus, and progesterone injection. Progesterone‐induced parkinsonism seems the most likely diagnosis in this case.

Epileptic seizures triggered by the use of a powered toothbrush

BACKGROUND Reflex epilepsy is characterized by seizures that are triggered in response to a specific stimulus and tooth-brushing epilepsy is an extremely rare form of reflex epilepsy in which the seizures are mainly induced by the act of tooth brushing. In this report, we describe an epilepsy patient whose seizures were exclusively triggered by the use of a powered toothbrush. METHODS AND RESULTS A 31-year old female had been treated for partial epilepsy of left temporal or frontal lobe for 20 years and she did not have seizures for the last 3 years. However, she experienced periods of auras, partial complex seizures, and nocturnal generalized seizures after she started using a powered toothbrush. The interictal electroencephalography revealed slow wave paroxysm over the left temporal or frontal lobe. CONCLUSIONS This case report is, to our knowledge, the first report of reflex epilepsy in which the seizures were triggered by the use of a powered toothbrush. Possible mechanisms to explain the novel type of this rare disorder are discussed.

The application of neural networks in classification of epilepsy using EEG signals

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patients epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify epilepsy groups by using Multi-Layer Perceptron Neural Networks (MLPNNs). 418 patients with epilepsy diagnoses according to International League against Epilepsy (ILAE, 1981) were included in this study. The correct classification of this data was performed by two expert neurologists before they were executed by MLPNNs. The MLPNNs were trained by the parameters obtained from the EEG signals and clinic properties of the patients. We classified the epilepsy into two groups such as partial and primary generalized epilepsy and we achieved an 89.2% correct prediction rate by using MLPNN model. The parameters of the loss of consciousness in the course of seizure, the duration and ritmicity of abnormal activities found in EEG constituted the most significant variables in the classification of epilepsy by using MLPNN. These results indicate that the classification performance of MLPNN model for epilepsy groups is satisfactory and we think that this model may be used in clinical studies as a decision support tool to confirm the classification of epilepsy groups after they are developed.

Can Neural Network Able to Estimate the Prognosis of Epilepsy Patients Accorrding to Risk Factors

The aim of this study is to evaluate the underlying etiologic factors of epilepsy patients and to predict the prognosis of these patients by using a Multi-Layer Perceptron Neural Network (MLPNN) according to risk factors. 758 patients with epilepsy diagnosis are included in this study. The MLPNNs were trained by the parameters of demographic properties of the patients and risk factors of the disease. The results show that the most crucial risk factor of the epilepsy patients was constituted by the febrile convulsion (21.9%), the kinship of parents (22.3%), the history of epileptic relatives (21.6%) and the history of head injury (18.6%). We had 91.1 % correct prediction rate for detection of the prognosis by using the MLPNN algorithm. The results indicate that the correct prediction rate of prognosis of the MLPNN model for epilepsy diseases is found satisfactory.

A NEURAL NETWORK-BASED CLASSIFICATION MODEL FOR PARTIAL EPILEPSY BY EEG SIGNALS

Epilepsy is a disorder of cortical excitability and still an important medical problem. The correct diagnosis of a patients epilepsy syndrome clarifies the choice of drug treatment and also allows an accurate assessment of prognosis in many cases. The aim of this study is to evaluate epileptic patients and classify subgroups of partial epilepsy by Multilayer Perceptron Neural Networks (MLPNNs). This is the first study to classify the partial epilepsy groups using the neural network according to EEG signals. 418 patients with epilepsy diagnoses according to International League against Epilepsy (ILAE, 1981) were included in this study. The epilepsy outpatients at the Neurology Department Clinic of Cukurova University Medical School between the years of 2002–2005 were examined and included in the study. The MLPNNs were trained by the parameters obtained from the EEG signals and clinical findings of the patients. Test results show that the MLPNN model is able to classify partial epilepsy with an accuracy of 91.5%. Moreover, new MLPNNs were constructed for determining significant variables on classification. The loss of consciousness in the course of seizure time variable caused the largest decrease in the classification accuracy when it was left out. In conclusion, we think that the classification performance of MLPNN model for partial epilepsy is satisfactory and this model may be used in clinical studies as a decision support tool to determine the partial epilepsy classification of the patients.

Frequency of Restless Legs Syndrome in adults with epilepsy in Turkey

BACKGROUND Restless Legs Syndrome (RLS) is a common disorder characterized by an irresistible urge to move the legs particularly during rest in the evenings often leading to insomnia and daytime impairment. No prior studies estimate the prevalence of RLS in a diverse sample of adults with epilepsy using standard diagnostic criteria. MATERIAL AND METHOD A total of 225 patients with epilepsy (61.8% female; mean age 33.3 ± 12.3 years) seen in the epilepsy clinic of Çukurova University Neurology Department were included. Restless Legs Syndrome diagnosis was based on structured interviews using internationally accepted criteria. Demographic and epilepsy-related variables were obtained through medical record review. RESULTS The prevalence of RLS was 5.8% (n=13). Mean score on the International RLS Study Group rating scale for these subjects was 9.3 ± 3.6 (6-18). Ten (76.9%) patients with RLS scored in the mild range and the remainder in the moderate range of severity. Patients with RLS were not significantly different from others in terms of demographics, epilepsy classification or duration, treatment regimen (polytherapy vs. monotherapy), patient-reported sleep assessment, or relevant laboratory data. CONCLUSION The prevalence of RLS in adults with epilepsy was similar to that observed in the adult general Turkish population (3.18-5.2%), although we excluded subjects with conditions associated with RLS, rendering ours a conservative estimate. While preliminary, these findings support the need for future studies exploring RLS in epilepsy given the potential impact of untreated sleep disorders and sleep deprivation on seizures and quality of life in people with epilepsy.

The effect of electrophysiological and neuroimaging findings on the prognosis of juvenile myoclonic epilepsy proband

Abstract Background: Juvenile myoclonic epilepsy (JME) is a well-defined idiopathic generalized epileptic syndrome, and diagnostic criteria for JME are to have a normal brain imaging and clinical evidence of typical epileptic seizures. The aim of this study is to evaluate electrophysiological and neuroimaging findings of JME and determine their relationship with prognosis. Methods: Thirty-two patients (23 women and nine men) with a mean age of 22 (16–37) years were included in this study. Interictal electroencephalography (EEG), magnetic resonance imaging (MRI) and single photon emission computed tomography (SPECT) were carried out in all patients. Results: Analysis of premedication EEGs revealed primary generalized pattern activity in 75% (n=24) and focal abnormalities in 18·75% (n=6). MRI was abnormal in seven (21·88%) patients (two with arachnoid cyst, two with mild cerebral atrophy, two with ventricular enlargement and one with single gliotic lesion), and SPECT imaging detected hypoperfusion in 15 (47%) patients. Hypoperfusion was mostly found on the parietal lobe. Conclusion: We found that, after medication, only 6·25% of EEGs had primary generalized pattern activity (p<0·0001); nevertheless, the prognosis was good in patients who had typical EEG findings (p=0·106). The prognosis of patients with MRI abnormalities was grave (p=0·023). Twenty percent of the patients who had SPECT abnormalities were seizure free, and 80% of them had been partially controlled (p=0·059). There were no correlations between MRI abnormalities, EEG and SPECT findings.