Chia-Ping Shen

High-Performance Seizure Detection System Using a Wavelet-Approximate Entropy-fSVM Cascade With Clinical Validation

The classification of electroencephalography (EEG) signals is one of the most important methods for seizure detection. However, verification of an atypical epileptic seizure often can only be done through long-term EEG monitoring for 24 hours or longer. Hence, automatic EEG signal analysis for clinical screening is necessary for the diagnosis of epilepsy. We propose an EEG analysis system of seizure detection, based on a cascade of wavelet-approximate entropy for feature selection, Fisher scores for adaptive feature selection, and support vector machine for feature classification. Performance of the system was tested on open source data, and the overall accuracy reached 99.97%. We further tested the performance of the system on clinical EEG obtained from a clinical EEG laboratory and bedside EEG recordings. The results showed an overall accuracy of 98.73% for routine EEG, and 94.32% for bedside EEG, which verified the high performance and usefulness of such a cascade system for seizure detection. Also, the prediction model, trained by routine EEG, can be successfully generalized to bedside EEG of independent patients.

A Physiology-Based Seizure Detection System for Multichannel EEG

Background Epilepsy is a common chronic neurological disorder characterized by recurrent unprovoked seizures. Electroencephalogram (EEG) signals play a critical role in the diagnosis of epilepsy. Multichannel EEGs contain more information than do single-channel EEGs. Automatic detection algorithms for spikes or seizures have traditionally been implemented on single-channel EEG, and algorithms for multichannel EEG are unavailable. Methodology This study proposes a physiology-based detection system for epileptic seizures that uses multichannel EEG signals. The proposed technique was tested on two EEG data sets acquired from 18 patients. Both unipolar and bipolar EEG signals were analyzed. We employed sample entropy (SampEn), statistical values, and concepts used in clinical neurophysiology (e.g., phase reversals and potential fields of a bipolar EEG) to extract the features. We further tested the performance of a genetic algorithm cascaded with a support vector machine and post-classification spike matching. Principal Findings We obtained 86.69% spike detection and 99.77% seizure detection for Data Set I. The detection system was further validated using the model trained by Data Set I on Data Set II. The system again showed high performance, with 91.18% detection of spikes and 99.22% seizure detection. Conclusion We report a de novo EEG classification system for seizure and spike detection on multichannel EEG that includes physiology-based knowledge to enhance the performance of this type of system.

Epileptic Seizure Detection for Multichannel EEG Signals with Support Vector Machines

Epilepsy is a common chronic neurological disorder characterized by recurrent unprovoked seizures. The electroencephalogram (EEG) signals play an important role in the diagnosis of epilepsy. In addition, multi-channel EEG signals have much more discrimination information than a single channel. However, traditional recognition algorithms of EEG signals are lack of multichannel EEG signals. In this paper, we propose a new method of epileptic seizure detection based on multichannel EEG signals. Both unipolar and bipolar EEG signals are considered in our approach. We make use of approximate entropy (ApEn) and statistic values to extract features. Furthermore, we tested the performance of four different Support Vector Machines (SVMs). The results reveal that the grid SVM achieves the highest totally classification accuracy (98.91%).

A Data-Mining Framework for Transnational Healthcare System

Medical resources are important and necessary in health care. Recently, the development of methods for improving the efficiency of medical resource utilization is an emerging problem. Despite evidence supporting the use of order sets in hospitals, only a small number of health information systems have successfully equipped physicians with analysis of complex order sequences from clinical pathway and clinical guideline. This paper presents a data-mining framework for transnational healthcare system to find alternative practices, including transfusion, pre-admission tests, and evaluation of liver diseases. However, individual countries vary with respect to geographical location, living habits, and culture, so disease risks and treatment methods also vary across countries. To realize the difference, a service-oriented architecture and cloud-computing technology are applied to analyze these medical data. The validity of the proposed system is demonstrated in including Taiwan and Mongolia, to ensure the feasibility of our approach.

Bio-signal analysis system design with support vector machines based on cloud computing service architecture

Today, many bio-signals such as Electroencephalography (EEG) are recorded in digital format. It is an emerging research area of analyzing these digital bio-signals to extract useful health information in biomedical engineering. In this paper, a bio-signal analyzing cloud computing architecture, called BACCA, is proposed. The system has been designed with the purpose of seamless integration into the National Taiwan University Health Information System. Based on the concept of. NET Service Oriented Architecture, the system integrates heterogeneous platforms, protocols, as well as applications. In this system, we add modern analytic functions such as approximated entropy and adaptive support vector machine (SVM). It is shown that the overall accuracy of EEG bio-signal analysis has increased to nearly 98% for different data sets, including open-source and clinical data sets.

Asymmetric expression patterns of brain transthyretin in normal mice and a transgenic mouse model of Alzheimer's disease

Brain asymmetry is linked with several neurological diseases, and transthyretin (TTR) is a protein sequestering beta-amyloid (Abeta) and helping to prevent the Alzheimers disease (AD). We show, by real time reverse transcription-polymerase chain reaction (RT-PCR), in situ hybridization and Western blotting, that TTR exhibits a pattern of adult male-specific, leftward distribution in the mouse brain. This asymmetry appeared to be mainly due to the asymmetric distribution of the choroid plexus cells in the ventricles. Unlike the normal mice, however, the hemispheric levels of TTR transcripts of 2- and 6-month-old Tg2576 mice, a transgenic AD mouse model overexpressing Abeta, were symmetric in both sexes. Furthermore, at the age of 10 months when the pathological AD-like features had developed, the level of TTR transcripts in the left hemisphere of the male Tg2576 became significantly lower than the right one. This lowering of TTR transcript is accompanied with a higher Abeta level in the left hemisphere of the 10-month Tg2576 males. Finally, for both genders, the TTR transcript levels in the two hemispheres of aged Tg2576 mice were lower than either the adult Tg2576 or the aged nontransgenic controls. Based on the above, we suggest scenarios to correlate the changes in the levels and hemispheric patterns of TTR expression to the pathogenesis of AD.

Epilepsy analytic system with cloud computing

Biomedical data analytic system has played an important role in doing the clinical diagnosis for several decades. Today, it is an emerging research area of analyzing these big data to make decision support for physicians. This paper presents a parallelized web-based tool with cloud computing service architecture to analyze the epilepsy. There are many modern analytic functions which are wavelet transform, genetic algorithm (GA), and support vector machine (SVM) cascaded in the system. To demonstrate the effectiveness of the system, it has been verified by two kinds of electroencephalography (EEG) data, which are short term EEG and long term EEG. The results reveal that our approach achieves the total classification accuracy higher than 90%. In addition, the entire training time accelerate about 4.66 times and prediction time is also meet requirements in real time.

A Multiclass Classification Tool Using Cloud Computing Architecture

Multiclass classification is an important technique to many complex biomedicine problems. Genetic algorithms (GA) are proven to be effective to select features prior to multiclass classification by support vector machines (SVM). However, their use is computation intensive. Based on SOA (Service Oriented Architecture) design principles, this paper proposes a cloud computing framework that exploits the inherent parallelism of GA-SVM classification to speed up the work. The performance evaluations on an mRNA benchmark cancer dataset have shown the effectiveness and efficiency of the framework. With a user-friendly web interface, the framework provides researchers an easy way to investigate the unrevealed secrets in the fast-growing repository of biomedical data.

Classification of schizophrenia using Genetic Algorithm-Support Vector Machine (GA-SVM)

Recently, Event-Related Potential (ERP) has being the most popular method in evaluating brain waves of schizophrenia patients. ERP is one of the electroencephalography (EEG), which is measured the change of brain waves after giving patients certain stimulations instead of resting state. However, with traditional statistical analysis method, both P50 and MMN showed significant difference between controls and patients but not in Gamma band. Gamma band is a 30-50 Hz auditory stimulation which had been suggested may be abnormal in schizophrenia patients. Our data are recruited from 5 schizophrenia patients and 5 controls in National Taiwan University Hospital have been tested with this platform. The results showed that detection rate is 88.24% and we also analyzed the importance of features, including Standard Deviation (SD) and Total Variation (TotalVar) in different stage of wavelet transform. Therefore, this proposed methodology could serve as a valuable clinical decision support for physiologists in evaluating schizophrenia.

Ultra-fast Epileptic seizure detection using EMD based on multichannel electroencephalogram

We present a system to detect seizure and spike in Epilepsy Electroencephalogram (EEG) analysis and characterize different epilepsy EEG types. After extracting features from three EEG types, Normal, Seizure and Spike, with Empirical Mode Decomposition (EMD), we do Analysis of variance (ANOVA) to classify conspicuous features and low-resolution features, and build Gaussian distributions of conspicuous features for probability density function (PDF) to do classification. Using EMD, the recognition rate improved from 70% to 90%. With ANOVA, the recognition rate can reach 99%. The linear model accelerates the system from 2 hours to 90 seconds compare to the previous approach.