Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2014
ETD: an extended time delay algorithm for ventricular fibrillation detection.
Ventricular fibrillation (VF) is the most serious type of heart attack which requires quick detection and first aid to improve patients' survival rates. To be most effective in using wearable devices for VF detection, it is vital that the detection algorithms be accurate, robust, reliable and computationally efficient. ⋯ In this paper, we propose an extended time-delay (ETD) algorithm for VF detection and conduct experiments comparing the performance of ETD against five good VF detection algorithms, including TD, using the popular Creighton University (CU) database. Our study shows that (1) TD and ETD outperform the other four algorithms considered and (2) with the same sensitivity setting, ETD improves upon TD in three other quality measures for up to 7.64% and in terms of aggregate accuracy, the ETD algorithm shows an improvement of 2.6% of the area under curve (AUC) compared to TD.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2014
Signal quality quantification and waveform reconstruction of arterial blood pressure recordings.
Arterial blood pressure (ABP) is an important vital sign of the cardiovascular system. As with other physiological signals, its measurement can be corrupted by different sources of noise, interference, and artifact. Here, we present an algorithm for the quantification of signal quality and for the reconstruction of the ABP waveform in noise-corrupted segments of the measurement. ⋯ In segments of poor signal quality, the ABP wavelets are then reconstructed on the basis of the expected cycle duration and envelope information derived from neighboring ABP wavelet segments. The algorithm was tested on two datasets of ABP waveform signals containing both invasive radial artery ABP and noninvasive ABP waveforms. Our results show that the approach is efficient in identifying the noisy segments (accuracy, sensitivity and specificity over 95%) and reliable in reconstructing beats that were artificially corrupted.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2014
Assessing the privacy policies in mobile personal health records.
The huge increase in the number and use of smartphones and tablets has led health service providers to take an interest in mHealth. Popular mobile app markets like Apple App Store or Google Play contain thousands of health applications. Although mobile personal health records (mPHRs) have a number of benefits, important challenges appear in the form of adoption barriers. ⋯ The results show important differences in both the mPHRs and the characteristics analyzed. A questionnaire containing six questions concerning privacy policies was defined. Our questionnaire may assist developers and stakeholders to evaluate the security and privacy of their mPHRs.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2014
Localization of subthalamic nucleus borders using macroelectrode local field potential recordings.
Deep brain stimulation of the subthalamic nucleus (STN) is a highly effective treatment for motor symptoms of Parkinson's disease. However, precise intraoperative localization of STN remains a procedural challenge. In the present study, local field potentials (LFPs) were recorded from DBS macroelectrodes during trajectory to STN, in six patients. ⋯ For these sub-bands, RMS of these distances was found to be 1.26 mm and 1.06 mm, respectively. Analysis of other sub-bands did not allow for distinguishing the caudal border of STN. In conclusion, macroelectrode-derived LFP recordings may provide an alternative approach to MER-SUA, for localizing the target STN borders during DBS surgery.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2014
Seizure detection using wavelet decomposition of the prediction error signal from a single channel of intra-cranial EEG.
This paper presents a novel patient-specific algorithm for detection of seizures in epileptic patients from a single-channel intra-cranial electroencephaolograph (iEEG) recording. Instead of extracting features from the EEG signal, first the EEG signal is filtered by a prediction error filter (PEF) to compute a prediction error signal. A two-level wavelet decomposition of the prediction error signal leads to two detail signals and one approximate signal. ⋯ The AdaBoost classifier achieves a sensitivity of 98.75% and an average FPR of 0.075 per hour. These results are obtained with leave-one-out cross-validation. In addition, for 13 out of 18 patients, the AdaBoost classifier requires only one feature, while it requires 4 features for the remaining 5 patients.