Gokhan Kirbas

The ANN-based computing of drowsy level

We have developed a new method for automatic estimation of vigilance level by using electroencephalogram (EEG), electromyogram (EMG) and eye movement (EOG) signals recorded during transition from wakefulness to sleep. In the previous studies, EEG signals and EEG signals with EMG signals were used for estimating vigilance levels. In the present study, it was aimed to estimate vigilance levels by using EEG, EMG and EOG signals. The changes in EEG, EMG and EOG were diagnosed while transiting from wakefulness to sleep by using wavelet transform and developed artificial neural network (ANN). EEG signals were separated to its subbands using wavelet transform, LEOG (Left EOG), REOG (Right EOG) and chin EMG was used in ANN process for increasing the accuracy of the estimation rate by evaluating their tonic levels and also used in data preparation stage to verify and eliminate the movement artifacts. Then, training and testing data sets consist of the EEG subbands (delta, theta, alpha and beta); LEOG, REOG and EMG signals were applied to the ANN for training and testing the system which gives three situations for the vigilance level of the subject: Awake, drowsy, and sleep. The accuracy of estimation is about 97-98% while the accuracy of the previous study which used only EEG was 95-96% and the study which used EEG with EMG was 98-99%. The reason of decreasing the percentage of present study according to the last study is because of the increase of the input data.

A clinical, radiographic and laboratory evaluation of prognostic factors in 363 patients with malignant pleural mesothelioma.

Background: Malignant pleural mesothelioma (MPM) has a poor prognosis. Objectives: Only few studies in literature investigated the presence of pleural fluid and radiographic findings for the prognosis of MPM. Methods: We retrospectively investigated the hospital charts of 363 MPM patients who were diagnosed from January 1989 to March 2010. Survival time was calculated by the Kaplan-Meier method. Pretreatment clinical, laboratory and radiographic features of each patient at the time of diagnosis were obtained from patients’ charts. Results: The mean age of 363 patients (217 men, 146 women) was 50.6 ± 11.2 years (range 19–85) and the mean survival time was 11.7 ± 8.6 months (range 1–53). Histological types of MPM were epithelial (71.2%), mixed (15.9%) and sarcomatous type (4.9%). The frequency of disease stages were 31.4% for stage 1, 24.2% for stage 2, 28.6% for stage 3 and 15.8% for stage 4. The most frequent symptoms were dyspnea (82.1%), chest pain (68.3%) and weight loss (58.9%). Results of univariate and multivariate analyses revealed that a Karnofsky performance score ≤60, a pleural fluid glucose level ≤40 mg/dl, a C-reactive protein level >50 mg/l, a serum lactate dehydrogenase level >500 U/l, the presence of pleural fluid, pleural thickening >1 cm and a platelet count of >420 × 103/µl were found to be associated with poor prognosis in MPM. Conclusions: Our data suggest that low pleural fluid glucose and high C-reactive protein, the presence of pleural fluid and pleural thickening were associated with poor MPM prognosis. Further prospective studies are needed to highlight prognostic factors more clearly.

Application of adaptive neuro-fuzzy inference system for vigilance level estimation by using wavelet-entropy feature extraction

This paper presents the application of adaptive neuro-fuzzy inference system (ANFIS) model for estimation of vigilance level by using electroencephalogram (EEG) signals recorded during transition from wakefulness to sleep. The developed ANFIS model combined the neural network adaptive capabilities and the fuzzy logic qualitative approach. This study comprises of three stages. In the first stage, three types of EEG signals (alert signal, drowsy signal and sleep signal) were obtained from 30 healthy subjects. In the second stage, for feature extraction, obtained EEG signals were separated to its sub-bands using discrete wavelet transform (DWT). Then, entropy of each sub-band was calculated using Shannon entropy algorithm. In the third stage, the ANFIS was trained with the back-propagation gradient descent method in combination with least squares method. The extracted features of three types of EEG signals were used as input patterns of the three ANFIS classifiers. In order to improve estimation accuracy, the fourth ANFIS classifier (combining ANFIS) was trained using the outputs of the three ANFIS classifiers as input data. The performance of the ANFIS model was tested using the EEG data obtained from 12 healthy subjects that have not been used for the training. The results confirmed that the developed ANFIS classifier has potential for estimation of vigilance level by using EEG signals.

The results of rehabilitation on motor and functional improvement of the spinal tuberculosis

OBJECTIVES To evaluate the result of rehabilitation on motor and functional improvement in spinal tuberculosis. METHOD Prospective case study. Data were collected from 47 patients with spinal tuberculosis medically and/or surgically treated, and rehabilitated over 6 months of period, after spinal decompression and fusion. The main outcome measures were motor development of the patients who were evaluated at the beginning, in the 1st week, in the 3rd month, and in the 6th month. Functional development of the patients was evaluated at the beginning and in the 6th month. Functional assessment was made according to Modified Barthel Index (MBI), and motor examination was made according to American Spinal Injury Association (ASIA). RESULTS The study population consisted of 47 patients (22 males and 25 females) mean aged 37.9 +/- 18.3 years (range 5-76 years). The most common site of spinal tuberculosis was the thoracic region. Localized back pain, paraparesis, sensory dysfunction and fever were typical clinical manifestations. Surgical management was performed as anterior or posterior drainage of abscess and/or stabilization of the spine. The rehabilitation program was performed in all patients during the preoperative, early postoperative and late postoperative 6 month periods. Muscle-strengthening exercises on necessary localization such as pectoral, abdominal, lower extremities; truncal and sacrospinal extensors were started for the rehabilitation. The motor score for the lower limbs and the MBI scores for activities of daily living (ADL) and mobility improved significantly (P < 0.001). The self-care and mobility categories of the MBI on admission; were 14.8% severely dependent and 10.6% independent. However, at the end of the rehabilitation program, 4.2% were severely dependent and 70.2% independent. IN CONCLUSION Early diagnosis and appropriate medical and/or surgical treatment together with a rehabilitation program will improve the life quality of patients with spinal tuberculosis.

Unusual Combination of Tracheobronchopathia Osteochondroplastica and AA Amyloidosis.

Tracheobronchopathia osteochondroplastica (TO) is a rare disorder of unknown cause characterized by the presence of multiple submucosal osseous and/or cartilaginous nodules that protrude into the lumen of the trachea and large bronchi. A simultaneous diagnosis of TO and amyloidosis is rarely reported. In this report, a case initially suspected to be asthma bronchiole that could not be treated, was radiologically diagnosed as TO, and also secondary amyloidosis is presented. A 53 years, man patient reported a 3 years history of dyspnea. Pulmonary function tests (PFTs) showed an obstructive pattern. Chest X-rays revealed right middle lobe atelectasis. FOB and CT detected nodular lesions in the trachea and in the anterior and lateral walls of the main bronchi. AA amyloidosis was confirmed by endobronchial biopsy. In the abdominal fat pad biopsy, amyloidosis was not detected. Asthma bronchiole was excluded by PFTs. This case illustrates that it is possible for TO and amyloidosis to masquerade as asthma. TO and amyloidosis should be suspected in patients of older ages with asthma and especially with poorly treated asthmatic patients. Although nodular lesions in the anterior and lateral tracheobronchial walls are typical for TO, a biopsy should be obtained to exclude amyloidosis.

The Correlation Analysis Between Airflow And Oxygen Saturation In Obstructive Sleep Apnea Events Using Correlation Function

Diagnosis of Sleep apnea syndrome (SAS) is currently performed by a full night polysomnography study at sleep laboratories. The majority of apnea patients are treated by constant positive airway pressure (CPAP) device. The apnea can be broadly classified into three types: obstructive sleep apnea (OSA), central sleep apnea (CSA) and mixed sleep apnea (MSA). During OSA, the airway is blocked while respiratory efforts continue. During CSA the airway is open, however there are no respiratory efforts. There is an efficient correlation between airflow and SaO2 in sleep apnea events. In this paper, it is aimed to find the correlation degree between airflow and oxygen saturation by using cross corelation function in obstructive sleep apnea events. In the future studies the correlation will be able to detect the sleep apnea and controlling CPAP device automatically as an intelligent system.

Is polysomnographic examination necessary for subjects with diaphragm pathologies

OBJECTIVES: While respiratory distress is accepted as the only indication for diaphragmatic plication surgery, sleep disorders have been underestimated. In this study, we aimed to detect the sleep disorders that accompany diaphragm pathologies. Specifically, the association of obstructive sleep apnea syndrome with diaphragm eventration and diaphragm paralysis was evaluated. METHODS: This study was performed in Süreyyapasa Chest Diseases and Thoracic Surgery Training and Research Hospital between 2014–2016. All patients had symptoms of obstructive sleep apnea (snoring and/or cessation of breath during sleep and/or daytime sleepiness) and underwent diaphragmatic plication via video-assisted mini-thoracotomy. Additionally, all patients underwent pre- and postoperative full-night polysomnography. Pre- and postoperative clinical findings, polysomnography results, Epworth sleepiness scale scores and pulmonary function test results were compared. RESULTS: Twelve patients (7 males) with a mean age of 48 (range, 27-60) years and a mean body mass index of 25 (range, 20-30) kg/m2 were included in the study. Preoperative polysomnography showed obstructive sleep apnea syndrome in 9 of the 12 patients (75%), while 3 of the patients (25%) were regarded as normal. Postoperatively, patient complaints, apnea hypopnea indices, Epworth sleepiness scale scores and pulmonary function test results all demonstrated remarkable improvement. CONCLUSION: All patients suffering from diaphragm pathologies with symptoms should undergo polysomnography, and patients diagnosed with obstructive sleep apnea syndrome should be operated on. In this way, long-term comorbidities of sleep disorders may be prevented.

Trafik kazası öyküsü olan obstrüktif uyku apne sendromlu hastalarda uyku parametrelerinin değerlendirilmesi

Objective: In this study, traffic accident with a history of obstructive sleep apnea syndrome (OSAS) in patients with polysomnographic parameters was investigated. Methods: A total of 77 OSAS patients were included in the study. All-night polysomnographic recordings obtained from patients with enuresis parameters and the presence of traffic accidents recorded in standard form. Results: The mean age of patients was 45.15 ± 11.53 years. 53% of the patients were male and 47% female. The mean apnea hypopnea index (AHI) in patients was 13.54 events/h. History of traffic accidents was found in 12% patients. Apnea hypopnea index, supine AHI, arousal index and oxygen desaturation index were found significantly different parameters between history of traffic accidents group and non-history of traffic accidents group (p <0.05). Conclusion: In this study, patients with OSAS severity of the disease with a history of traffic accidents were associ ated the relationship between the parameters. This relationship with the severity of the disease might be due to the negative effects on attention. J Clin Exp Invest 2013; 4 (2): 204-207

The classification of alertness level from EEG signals by using TMS320C6713 DSK and MATLAB

In this study, electroencephalogram (EEG) signals recorded during transition from wakefulness to sleep and Matlab-Simulink and TMS320C6713 DSP Starter Kit (DSK) of Texas Instruments Inc. are used for classification of alertness level. First, EEG signals taken from 8 healthy subjects were separated as alert, drowsy, and sleep signals in the form of 5 s epochs with the aid of expert doctor. The subbands(feature vector) of each EEG signals were obtained by using Discrete Wavelet Transform. Some statistical operations were used to reduce dimensions of feature vectors and obtained vectors were chosen as input feature vectors of multilayer neural network which is used as classifier. The Simulink model for real time classification process was run on DSK. The tests showed that the results of classification with DSK are same with the results of classification simulation without using DSK. Total classification accuracy obtained in the test results of proposed model showed that the model can be used in the estimation of alertness level.

Sendrom X fizyopatolojisinde uyku-apne sendromu\'nun rolü

Regional anaesthesia has advantages such as, control of postoperative pain, early mobilization, and does not affect respiratory function. In recent years, regional anaesthesia had improved by the application of the peripheral nerve stimulator and ultrasound guided blocks, new local anaesthetic drugs with the use of additional adjunctive agents. Especially in emergency conditions, combination of regional anaesthesia may avoid the complications of general anesthesia in patients with chronic disease who suffer from upper and lower extremity injuries. In this paper, we present two cases who underwent combined regional anaesthesia techniques for the lower and upper extremity surgery.Iki tarafli ses teli felci (ISTF) siklikla tiroid ve paratiroid cerrahisi gibi iyatrojenik bir hasar sonucu olusur. Fakat serebral infarkt sonrasi hava yolu tikanikligina neden olan BVKP nadir olarak bildirilmistir. Bu yazida tekrarlayan serebral infarktin, gec ortaya cikan ve hayati tehdit eden bir komplikasyonu olarak solunum durmasi ile sonuclanan bir ISTF olgusu sunduk. Atmis yedi yasinda erkek hasta, son 3-4 aydir giderek artan solunum yetmezligi sikayetiyle acil servisimize basvurdu. Ozgecmisinde kalp yetmezligi ve kronik obstruktif akciger hastaligi oykusu olmayan hasta, yaklasik bir yil once bir ayda iki kez serebral infarkt gecirmisti. Yapilan solunum sistemi muayenesinde bilateral wheezing ve stridor; norolojik muayenesinde ise sag tarafta kuvvet kaybi mevcuttu. Ust solunum yolu obstruksiyonunu degerlendirilmek uzere endoskopik laringoskopi yapildi. Laringoskopide iki tarafli ses tellerinin orta hatta sabit ve hareketsiz oldugu goruldu. Solunum yetmezliginde artma ve tekrarlayan solunum durmasi nedeniyle hastaya trakeostomi acildi. Operasyon sonrasi hastanin solunum yetmezligi geriledi. Solunum fonksiyonlari normale donen hasta taburcu edildi.Dysphagia aortica is a rare etiological factor of dysphagia resulting from extrinsic compression of the esophagus by thoracic aorta. There is no gold standard diagnostic proscedure for dysphagia aortica. Dysphagia aortica is usually escaped to attention in the differential diagnosis of dyssphagia. Here, we reported compression of the esophagus by thoracic aorta in a 54 years-old male patient who comsplained from dysphagia.