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 2012
Assessment of ICA algorithms for the analysis of crackles sounds.
Blind source separation by independent component analysis has been applied extensively in the biomedical field for extracting different contributing sources in a signal. Regarding lung sounds analysis to isolate the adventitious sounds from normal breathing sound is relevant. ⋯ Afterwards, Infomax was applied to 25 channels of recorded normal breathing sound where simulated fine and coarse crackles were added including acoustic propagation effects. A robust blind crackle separation could improve previous results in generating an adventitious acoustic thoracic imaging.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
Impact of obstructive sleep apnea on sleep-wake stage ratio.
Patients with obstructive sleep apnea (OSA) experience fragmented sleep and exhibit different sleep architectures. While polysomnographic metrics for quantifying sleep architecture are studied, there is little information about the impact of OSA on the ratio of different sleep-wake stages (wake, W; rapid eye movement, REM; non-REM stages 1 to 3, N1 to N3). This study, therefore, aims to investigate the relationship between apnea-hypopnea index (AHI, a measure of OSA severity) and all possible ratios of sleep-wake stages. ⋯ Results show a statistically significant positive, linear and monotonic correlation between AHI and REM/N3, as well as between AHI and N1/W (p-values < 0.05). These findings imply that patients with increased severity of OSA may spend more time in REM than deep sleep, and in light sleep than wake (or less time in deep sleep than REM, and in wake than light sleep). A power-law regression model may possibly explain the relationships of AHI-REM/N3 and AHI-N1/W, and predict the value of AHI using REM/N3 or N1/W.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
An implantable neural stimulator for intraspinal microstimulation.
This paper reports on a wireless stimulator device for use in animal experiments as part of an ongoing investigation into intraspinal stimulation (ISMS) for restoration of walking in humans with spinal cord injury. The principle behind using ISMS is the activation of residual motor-control neural networks within the spinal cord ventral horn below the level of lesion following a spinal cord injury. The attractiveness to this technique is that a small number of electrodes can be used to induce bilateral walking patterns in the lower limbs. ⋯ Recent acute animal experiments have demonstrated the feasibility of using ISMS to produce the coordinated walking patterns. Here we described a wireless implantable stimulation system to be used in chronic animal experiments and for providing the basis for a system suitable for use in humans. Electrical operation of the wireless system is described, including a demonstration of reverse telemetry for monitoring the stimulating electrode voltages.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
Effect of arching spine on deformation of the ligamentum flavum during epidural needle insertion.
When administering epidural anesthesia, anesthesiologists ask patients to arch their back. Arching the spine is thought to enlarge the gap between neighboring vertebral bones. The author hypothesized that tension inside the ligamentum flavum generated by arching the spine would reduce deformation of the ligamentum flavum during epidural needle insertion. ⋯ For the maximum reaction force the coefficient of variance decreased by dividing raw data with thickness of the ligamentum flavum, which meant that the maximum reaction force correlated with thickness of the ligamentum flavum. Less effect on deformation was observed. Hypothesis was correct in the porcine study, while the difference between the porcine and the patient's spine should be examined in the next research.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
A survival prediction model of rats in hemorrhagic shock using the random forest classifier.
Hemorrhagic shock is the cause of one third of deaths resulting from injury in the world. Although many studies have tried to diagnose hemorrhagic shock early and accurately, such attempts were inconclusive due to compensatory mechanisms of humans. The objective of this study was to construct a survival prediction model of rats in hemorrhagic shock using a random forest (RF) model, which is a newly emerged classifier acknowledged for its performance. ⋯ For the LR model, sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (ROC-AUC) were 1, 0.89, 0.94, and 0.98, respectively. For the RF models, sensitivity, specificity, accuracy, and AUC were 0.96, 1, 0.98, and 0.99, respectively. In conclusion, the RF model was superior to the LR model for survival prediction in the rat model.