• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.42 no.3 s.303
• /
• pp.47-52
• /
• 2005

Obstructive Sleep Apnea (OSA) is a representative symptom of sleep disorder caused by the obstruction of upper airway. Because OSA causes not only excessive daytime sleepiness and fatigue, hypertension and arrhythmia but also cardiac arrest and sudden death during sleep in the severe case, it is very important to detect the occurrence and the frequency of OSA. OSA is usually diagnosed through the laboratory-based Polysomnography (PSG) which is uncomfortable and expensive. Therefore researches to improve the disadvantages of PSG are needed and studies for the detection of OSA using only one or two parameters are being made as alternatives to PSG. In this paper, we developed an algorithm for the detection of OSA based on Heart Rate Variability (HRV). The proposed method is applied to the ECG data sets provided from PhysioNet which consist of learning set and training set. We extracted features for the detection of OSA such as average and standard deviation of 1 minute R-R interval, power spectrum of R-R interval and S-peak amplitude from data sets. These features are applied to the input of neural network. As a result, we obtained sensitivity of $89.66\%$ and specificity of $95.25\%$. It shows that the features suggested in this study are useful to detect OSA.

• Pediatric Infection and Vaccine
• /
• v.26 no.3
• /
• pp.199-205
• /
• 2019

Enteroviral infections are common in neonates. One important infection pathway is vertical transmission from an infected mother to her neonate. Here, we report the early detection and successful treatment of a vertically transmitted fulminant enteroviral infection associated with myocarditis and hepatitis. The patient had a sudden onset of high fever on the fourth day of life and developed severe, rapidly progressing symptoms of disseminated intravascular coagulopathy (DIC), hepatitis, and myocarditis accompanied by tachyarrhythmia. As it was the peak season for enteroviral infections and both the mother and the patient's 36-month-old sibling had a high fever around the time of delivery, we suspected an enteroviral infection. Thus, we initiated prompt evaluation of enteroviral infection, as well as close observation and intensive care of the neonate. We strongly recommend evaluation for the possibility of vertical enterovirus infection in neonates when the mother is suspected of having a viral infection (e.g., high fever and negative results from bacterial infectious studies) around the time of delivery and when the neonate shows some early symptoms of infectious diseases such as thrombocytopenia, DIC, hepatitis, and myocarditis. Early detection of enteroviral infections and prompt implementation of proper treatment are key to reduce the risk of complications and mortality associated with enteroviral infections in neonates.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.7
• /
• pp.2304-2320
• /
• 2021

Intelligently detecting anomalies in health sensor data streams (e.g., Electrocardiogram, ECG) can improve the development of E-health industry. The physiological signals of patients are collected through sensors. Timely diagnosis and treatment save medical resources, promote physical health, and reduce complications. However, it is difficult to automatically classify the ECG data, as the features of ECGs are difficult to extract. And the volume of labeled ECG data is limited, which affects the classification performance. In this paper, we propose a Generative Adversarial Network (GAN)-based deep learning framework (called CAB) for heart arrhythmia classification. CAB focuses on improving the detection accuracy based on a small number of labeled samples. It is trained based on the class-imbalance ECG data. Augmenting ECG data by a GAN model eliminates the impact of data scarcity. After data augmentation, CAB classifies the ECG data by using a Bidirectional Long Short Term Memory Recurrent Neural Network (Bi-LSTM). Experiment results show a better performance of CAB compared with state-of-the-art methods. The overall classification accuracy of CAB is 99.71%. The F1-scores of classifying Normal beats (N), Supraventricular ectopic beats (S), Ventricular ectopic beats (V), Fusion beats (F) and Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively. Unclassifiable beats (Q) heartbeats are 99.86%, 97.66%, 99.05%, 98.57% and 99.88%, respectively.

• Journal of Biomedical Engineering Research
• /
• v.23 no.1
• /
• pp.1-8
• /
• 2002

Atrial fibrillation(AF). chronic or paroxysmal is the most frequent arrhythmia in human subjects Duration of P wave in signal-averaged electrocardiography(SAECG) reflects intra-atrial conduction time and therefore. could be used as an electrophysiological marker for atrial conduction chance at the earthy stave. So we apply the analysis method using SAECG to diagnose Paroxysmal atrial fibrillation(PAF) . Subjects Participated for the study consisted of two groups: a control group(n=34) of normal healthy volunteers and a group of AF Patients(n=38) with a documented history of PAF but no other history of cardiac disease. We evaluated the effect of several filtering and determination methods to find the starting and ending feints of the P wavy on its duration. To increase the measurement reliability of P wave duration. the automatic detection method was proposed. Also. to increase the detection rate for PAF risk, the decision threshold value was optimized using receiver operation characteristics(ROC) curve. Results showed that the highest statistical difference (p〈0.001) of the P wane duration between controls and subjects was obtained at the Processing condition, using absolute threshold vague(8.75 $\mu N$) , a least mean square(LMS) high pass filter and 30 Hz cutoff frequency. The most outstanding difference(sensitivity 88 % specificity 64.4 %) between controls and subjects was obtained at the decision threshold value of 112 ms.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.10
• /
• pp.2551-2561
• /
• 2014

Several algorithms have been developed to detect AFIB(Atrial Fibrillation) which either rely on the linear and frequency analysis. But they are more complex than time time domain algorithm and difficult to get the consistent rule of irregular RR interval rhythm. In this study, we propose algorithm for optimal value detection of irregular RR interval for AFIB classification based on linear analysis. For this purpose, we detected R wave, RR interval, from noise-free ECG signal through the preprocessing process and subtractive operation method. Also, we set scope for segment length and detected optimal value and then classified AFIB in realtime through liniar analysis such as absolute deviation and absolute difference. The performance of proposed algorithm for AFIB classification is evaluated by using MIT-BIH arrhythmia and AFIB database. The optimal value indicate ${\alpha}=0.75$, ${\beta}=1.4$, ${\gamma}=300ms$ in AFIB classification.

• Progress in Superconductivity
• /
• v.7 no.1
• /
• pp.28-35
• /
• 2005

We propose a method to measure atrial arrhythmias (AA) such as atrial fibrillation (Afb) and atrial flutter (Afl) with a SQUID magnetocardiograph (MCG) system. To detect AA is one of challenging topics in MCG. As the AA generally have irregular rhythm and atrio-ventricular conduction, the MCG signal cannot be improved by QRS averaging; therefore a SQUID MCG system having a high SNR is required to measure informative atrial excitation with a single scan. In the case of Afb, diminished f waves are much smaller than normal P waves because the sources are usually located on the posterior wall of the heart. In this study, we utilize an MCG system measuring tangential field components, which is known to be more sensitive to a deeper current source. The average noise spectral density of the whole system in a magnetic shielded room was $10\;fT/{\surd}Hz(a)\;1\;Hz\;and\;5\;fT/{\surd}Hz\;(a)\;100\;Hz$. We measured the MCG signals of patients with chronic Afb and Afl. Before the AA measurement, the comparison between the measurements in supine and prone positions for P waves has been conducted and the experiment gave a result that the supine position is more suitable to measure the atrial excitation. Therefore, the AA was measured in subject's supine position. Clinical potential of AA measurement in MCG is to find an aspect of a reentry circuit and to localize the abnormal stimulation noninvasively. To give useful information about the abnormal excitation, we have developed a method, separative synthetic aperture magnetometry (sSAM). The basic idea of sSAM is to visualize current source distribution corresponding to the atrial excitation, which are separated from the ventricular excitation and the Gaussian sensor noises. By using sSAM, we localized the source of an Afl successfully.

• Journal of Chest Surgery
• /
• v.45 no.2
• /
• pp.110-115
• /
• 2012

Background: Pneumonectomy remains the ultimate curative treatment modality for destroyed lung caused by tuberculosis despite multiple risks involved in the procedure. We retrospectively evaluated patients who underwent pneumonectomy for treatment of sequelae of pulmonary tuberculosis to determine the risk factors of early and long-term outcomes. Materials and Methods: Between January 1980 and December 2008, pneumonectomy or pleuropneumonectomy was performed in 73 consecutive patients with destroyed lung caused by tuberculosis. There were 48 patients with empyema (12 with bronchopleural fistula [BPF]), 11 with aspergilloma and 7 with multidrug resistant tuberculosis. Results: There were 5 operative mortalities (6.8%). One patient had intraoperative uncontrolled arrhythmia, one had a postoperative cardiac arrest, and three had postoperative respiratory failure. A total of 29 patients (39.7%) suffered from postoperative complications. Twelve patients (16.7%) were found to have postpneumonectomy empyema (PPE), 4 patients had wound infections (5.6%), and 7 patients required re-exploration due to postoperative bleeding (9.7%). The prevalence of PPE increased in patients with preoperative empyema (p=0.019). There were five patients with postoperative BPF, four of which occurred in right-side operation. The only risk factor for BPF was the right-side operation (p=0.023). The 5- and 10-year survival rates were 88.9% and 76.2%, respectively. The risk factors for late deaths were old age (${\geq}50$ years, p=0.02) and low predicted postoperative forced expiratory volume in one second (FEV1) (< 1.2 L, p=0.02). Conclusion: Although PPE increases in patients with preoperative empyema and postoperative BPF increases in right-side operation, the mortality rates and long-term survival rates were found to be satisfactory. However, the follow-up care for patients with low predicted postoperative FEV1 should continue for prevention and early detection of pulmonary complication related to impaired pulmonary function.

• Journal of Chest Surgery
• /
• v.38 no.11 s.256
• /
• pp.739-745
• /
• 2005

Background: The Maze procedure considered the most effective method of treatment for atrial fibrillation. However, the sinus conversion rates decreased due to several factors, especially enlarged left atrium. The purpose of this study was to investigate the effects of Maze procedure with aen atrial volume reduction plasty on rheumatic mitral valve disease, Material and Method: From December of 200f to July of 2004, 45 patients received mitral valve and Maze operation. The patients were placed in either group f or group 2, based on the left atrial volume reduction plasty. The presence and onset of sinus rhythm and the incidence of trans mitral A waves were monitored during the postoperative 7 days and throughout the follow up period of 3 and 6 months. Mean follow up periods were 15.8 10.1 months in group 1 and $6.1\pm2.7$ months in group 2. Result: The sinus onset were $9.88\pm12.2$ days in group 1, and $1\pm3.6$ days in group 2 (p<0.01). The sinus conversion rates in the group 1 and 2 were $65\%,\;75\%$ (p=0.07) in the postoperative 7 days, $70.5\%,\;100\%$ (p<0.01) at postoperative 3 months, and $93\%,\;100\%$ (p<0.01) at postoperative 6 months, respectively. The wave detection rates in the postoperative 7days were $31.2\%\;and\;63.6\%$, and continued to improve over time to $83.3\%\;and\;100\%$ by 6months, respectively. Conclusion: The results suggest that Maze procedure with left atrial volume reduction plasty is effective for inducing sinus rhythm and for restoring left atrial contractile function after concomitant rheumatic mitral valve surgery. However further follow up of this patients for long time is necessary.