IEEE transactions on bio-medical engineering
-
A method for the detection of seizures in the newborn using the electrocardiogram (ECG) signal is presented. Using a database of eight recordings, a method was developed for automatically annotating each 1-min epoch as "nonseizure" or "seizure". The system uses a linear discriminant classifier to process 41 heartbeat timing interval features. ⋯ On a patient-independent basis the average accuracy was 68.3% with sensitivity of 54.6% and specificity of 77.3%. Shifting the decision threshold for the patient-independent classifier allowed an increase in sensitivity to 78.4% at the expense of decreased specificity (51.6%), leading to increased false detections. The results of our ECG-based method are comparable with those reported for EEG-based neonatal seizure detection systems and offer the benefit of an easier acquisition methodology for seizure detection.
-
In the framework of the electrocardiography (ECG) signals, this paper describes an original approach to identify heartbeat morphologies and to detect R-wave events. The proposed approach is based on a "geometrical matching" rule evaluated using a decision function in a local moving-window procedure. The decision function is a normalized measurement of a similarity criterion comparing the windowed input signal with the reference beat-pattern into a nonlinear-curve space. ⋯ In the first stage, a learning-method based on genetic algorithms allows us estimating the decision function from training beat-pattern. In the second stage, a level-detection algorithm evaluates the decision function to establish the threshold of similarity between the reference pattern and the input signal. Finally, the findings for the MIT-BIH Arrhythmia Database present about 98% of sensitivity and 99% of positive predictivity for the R-waves detection, using low-order polynomial models.
-
IEEE Trans Biomed Eng · Apr 2007
Wavelet packets feasibility study for the design of an ECG compressor.
Most of the recent electrocardiogram (ECG) compression approaches developed with the wavelet transform are implemented using the discrete wavelet transform. Conversely, wavelet packets (WP) are not extensively used, although they are an adaptive decomposition for representing signals. In this paper, we present a thresholding-based method to encode ECG signals using WP. ⋯ The proposed scheme is versatile as far as neither QRS detection nor a priori signal information is required. As such, it can thus be applied to any ECG. Results show that WP perform efficiently and can now be considered as an alternative in ECG compression applications.
-
IEEE Trans Biomed Eng · Apr 2007
Estimation of hidden state variables of the Intracranial system using constrained nonlinear Kalman filters.
Impeded by the rigid skull, assessment of physiological variables of the intracranial system is difficult. A hidden state estimation approach is used in the present work to facilitate the estimation of unobserved variables from available clinical measurements including intracranial pressure (ICP) and cerebral blood flow velocity (CBFV). The estimation algorithm is based on a modified nonlinear intracranial mathematical model, whose parameters are first identified in an offline stage using a nonlinear optimization paradigm. ⋯ It is also applied to a set of CBFV, ICP and arterial blood pressure (ABP) signal segments from brain injury patients. The results indicated that the proposed constrained nonlinear KF achieved the best performance among the evaluated state estimators and that the state estimator combined with the I/O configuration that has ICP as the measured output can potentially be used to estimate CBFV continuously. Finally, the state estimator combined with the I/O configuration that has both ICP and CBFV as outputs can potentially estimate the lumped cerebral arterial radii, which are not measurable in a typical clinical environment.