Evaggelos C. Karvounis

An Automated Methodology for Fetal Heart Rate Extraction From the Abdominal Electrocardiogram

This paper introduces an automated methodology for the extraction of fetal heart rate from cutaneous potential abdominal electrocardiogram (abdECG) recordings. A three-stage methodology is proposed. Having the initial recording, which consists of a small number of abdECG leads in the first stage, the maternal R-peaks and fiducial points (QRS onset and offset) are detected using time-frequency (t-f) analysis and medical knowledge. Then, the maternal QRS complexes are eliminated. In the second stage, the positions of the candidate fetal R-peaks are located using complex wavelets and matching theory techniques. In the third stage, the fetal R-peaks, which overlap with the maternal QRS complexes (eliminated in the first stage) are found using two approaches: a heuristic algorithm technique and a histogram-based technique. The fetal R-peaks detected are used to calculate the fetal heart rate. The methodology is validated using a dataset of eight short and ten long-duration recordings, obtained between the 20th and the 41st week of gestation, and the obtained accuracy is 97.47%. The proposed methodology is advantageous, since it is based on the analysis of few abdominal leads in contrast to other proposed methods, which need a large number of leads.

Detection of Fetal Heart Rate Through 3-D Phase Space Analysis From Multivariate Abdominal Recordings

A novel three-stage methodology for the detection of fetal heart rate (fHR) from multivariate abdominal ECG recordings is introduced. In the first stage, the maternal R-peaks and fiducial points (maternal QRS onset and offset) are detected, using band-pass filtering and phase space analysis. The maternal fiducial points are used to eliminate the maternal QRS complexes from the abdominal ECG recordings. In the second stage, two denoising procedures are applied to enhance the fetal QRS complexes. The phase space characteristics are employed to identify fetal heart beats not overlapping with the maternal QRSs, which are eliminated in the first stage. The extraction of the fHR is accomplished in the third stage, using a histogram-based technique in order to identify the location of the fetal heart beats that overlap with the maternal QRSs. The methodology is evaluated on simulated multichannel ECG signals, generated by a recently proposed model with various SNRs, and on real signals, recorded from pregnant women in various weeks during gestation. In both cases, the obtained results indicate high performance; in the simulated ECGs, the accuracy ranges from 72.78% to 98.61%, depending on the employed SNR, while in the real recordings, the average accuracy is 95.45%. The proposed methodology is advantageous since it copes with the existence of noise from various sources while it is applicable in multichannel abdominal recordings.

Multiscale - Patient-Specific Artery and Atherogenesis Models

In this work, we present a platform for the development of multiscale patient-specific artery and atherogenesis models. The platform, called ARTool, integrates technologies of 3-D image reconstruction from various image modalities, blood flow and biological models of mass transfer, plaque characterization, and plaque growth. Patient images are acquired for the development of the 3-D model of the patient specific arteries. Then, blood flow is modeled within the arterial models for the calculation of the wall shear stress distribution (WSS). WSS is combined with other patient-specific parameters for the development of the plaque progression models. Real-time simulation can be performed for same cases in grid environment. The platform is evaluated using both animal and human data.

A wearable system for long-term ubiquitous monitoring of common motor symptoms in patients with Parkinson's disease

PERFORM is a system for the monitoring, assessment and management of patient with Parkinsons disease (PD). It comprises of three subsystems: (i) Multi-Sensor Monitoring Unit, (ii) the Local Base Unit, and (iii) the Centralized Hospital unit. The wearable, multi-sensor monitoring unit (WMSMU) of the PERFORM system is presented in this work. This unit plays an essential role in the overall PERFORM system since it is responsible to record and pre-process accelerometer and gyroscope signals that are later used by the various components of the Local Base Unit in order to classify and quantify the symptoms and motor status of the PD patients. The WMSMU was evaluated in a large set of pilot studies in PD patients.

Maternal and fetal heart rate extraction from abdominal recordings using multi-scale principal components analysis

A three-stage methodology for the extraction of maternal and fetal heart rate using abdominal ECG leads, is presented. In the first stage, the maternal R-peaks and fiducial points (maternal QRS onset and offset) are detected, using multiscale principal components analysis (MSPCA) and the smoothed nonlinear energy operator (SNEO). Maternal fiducial points are used to eliminate the maternal QRS complexes from the abdominal ECG recordings. In the second stage, again MSPCA and SNEO are employed in order to detect the fetal heart beats that do not overlap with the maternal QRSs (eliminated from the first stage). The extraction of the fetal heart rate is accomplished in the last stage, using a histogram based technique in order to identify the positions of the fetal heart beats that overlap with the maternal QRSs. Real signals, recorded from different pregnant women and different weeks of gestation, are used for the evaluation of the proposed methodology and the obtained results indicate high performance (accuracy 95%).

A Gaussian Mixture Model to detect suction events in rotary blood pumps

In this paper, we introduce a new suction detection approach based on online learning of a Gaussian Mixture Model (GMM) with constrained parameters to model the reduction in pump flow signals baseline during suction events. A novel three-step methodology is employed: i) signal windowing, ii) GMM based classification and iii) GMM parameter adaptation. More specifically, the first 5 second segment is used for the parameter initialization and the consequent 1 second windows are classified and used for model adaptation. The proposed approach has been tested in simulation (pump flow) signals and satisfactory results have been obtained.

Automated knowledge-based fuzzy models generation for weaning of patients receiving Ventricular Assist Device (VAD) therapy

The SensorART project focus on the management of heart failure (HF) patients which are treated with implantable ventricular assist devices (VADs). This work presents the way that crisp models are transformed into fuzzy in the weaning module, which is one of the core modules of the specialists decision support system (DSS) in SensorART. The weaning module is a DSS that supports the medical expert on the weaning and remove VAD from the patient decision. Weaning module has been developed following a “mixture of experts” philosophy, with the experts being fuzzy knowledge-based models, automatically generated from initial crisp knowledge-based set of rules and criteria for weaning.

Adverse event prediction in patients with left ventricular assist devices

This work presents the Treatment Tool, which is a component of the Specialists Decision Support Framework (SDSS) of the SensorART platform. The SensorART platform focuses on the management of heart failure (HF) patients, which are treated with implantable, left ventricular assist devices (LVADs). SDSS supports the specialists on various decisions regarding patients with LVADs including decisions on the best treatment strategy, suggestion of the most appropriate candidates for LVAD weaning, configuration of the pump speed settings, while also provides data analysis tools for new knowledge extraction. The Treatment Tool is a web-based component and its functionality includes the calculation of several acknowledged risk scores along with the adverse events appearance prediction for treatment assessment.

Measuring Steatosis in Liver Biopsies Using Machine Learning and Morphological Imaging

Non-Alcohol Liver Disease (NAFLD) is nowadays the most common liver disease in Western Countries. It is the chronic condition of fat expansion in liver, which is not associated with alcohol consumption. Quantitating steatosis in liver biopsies could provide objective measurement of the severity of the disease, instead of using semi-quantitative scoring systems. The current work, introduces an automated method for measuring steatosis in liver biopsies, using both machine learning and classical image processing techniques. Clustering is employed for tissue specimen detection, while an iterative morphological procedure is used for steatosis revealing. The method has been evaluated in a set of 20 liver biopsy images and the obtained results present ∼1% mean percentage error.

Effects of Exercise in Diabetic Rats Using Continuous Wavelet Transform

This paper explores an approach to study entropy differentiations of heart’s activities estimation in Low Frequency (LF) and High Frequency (HF) bands. Dataset composed of 34 ECGs, obtained from healthy and diabetic rats under normal and exercise living conditions. RR intervals extracted efficiently in order to create Heart Rate (HR) time series. Continuous Wavelet Transform (CWT) has been used, as the most appropriate approach, to evaluate the effects of exercise on healthy and diabetic HR variability (HRV). Statistical analysis performed taking into account both wavelet entropy in the low and the high frequency selected bands and the corresponding index LF/HF of the wavelet coefficients. Our results show that wavelet entropy measure based on CWT decomposition can capture significant differences between the specific frequency regions that are intrinsically related to the structure of the RR signal. According to our analysis, diabetic rats living under exercise conditions appear to have a reduced LF/HF entropy ratio compared to healthy population.