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
Estimation of venous oxygenation saturation using the finger Photoplethysmograph (PPG) waveform.
In this study, finger photoplethysmograph data obtained from twelve patients undergoing cardiothoracic surgery were analyzed in order to estimate the venous saturation utilizing the modulations created by the positive pressure ventilation in the AC Photoplethysmograph (PPG) signals. The PPG signals were analyzed in the time-domain using a conventional pulse oximetry algorithm to produce estimations of arterial oxygen saturation. ⋯ The results showed that there was no significant difference in the traditionally-derived (time-domain) arterial saturation and the instantaneous arterial saturation. However, the instantaneous venous saturation was found to be significantly lower than the time-domain estimated and instantaneous arterial saturation (P=<0.001).
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
Prediction of extubation failure for neonates with respiratory distress syndrome using the MIMIC-II clinical database.
Extubation failure (EF) is an ongoing problem in the neonatal intensive care unit (NICU). Nearly 25% of neonates fail their first extubation attempt, requiring re-intubations that are associated with risk factors and financial costs. ⋯ From an initial list of 57 candidate features, our machine learning approach narrowed down to six features useful for building an EF prediction model: monocyte cell count, rapid shallow breathing index, fraction of inspired oxygen (FiO(2)), heart rate, PaO(2)/FiO(2) ratio where PaO(2) is the partial pressure of oxygen in arterial blood, and work of breathing index. Algorithm performance had an area under the receiver operating characteristic curve (AUC) of 0.871 and sensitivity of 70.1% at 90% specificity.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
Moving coil pressure algometer produces consistent force gradient and repeated stimulation.
Computer-controlled pressure stimulation (algometry) offers seemingly good reliability when it comes to pain assessment methods. It is therefore important to ensure through methodological quantification that moving coil pressure algometer (MCPA) exhibits accurate, fast, and precise tissue stimulation techniques. ⋯ Solicited force gradients of 500, 1000, and 1800 g/s showed high correlation values (R(2) > 0.99) for both rubber mat and direct probe-to-sensor contact cases. Through fast switching between different modes of operation of the actuator, force overshoot was reduced from as much as 300 to 20% for the same force magnitude, at the expense of a slight delay in repeated pulse delivery scheme.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
Comparative Study Clinical TrialThe comparison of a novel continuous cardiac output monitor based on pulse wave transit time and echo Doppler during exercise.
A new technology called estimated continuous cardiac output (esCCO) uses pulse wave transit time (PWTT) obtained from an electrocardiogram and pulse oximeter to measure cardiac output (CO) non-invasively and continuously. This study was performed to evaluate the accuracy of esCCO during exercise testing. We compared esCCO with CO measured by the echo Doppler aortic velocity-time integral (VTIao_CO). ⋯ This indicates that PEP included in PWTT has an impact on the accuracy of esCCO measurement. In this study, the validity of esCCO during exercise testing was assessed and shown to be acceptable. The result of this study suggests that we can expand its application.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2012
Comparative study between Sample Entropy and Detrended Fluctuation Analysis performance on EEG records under data loss.
This study compares two signal entropy measures, Sample Entropy (SampEn) and Detrended Fluctuation Analysis (DFA) over real EEG signals after a randomized sample removal. Both measures have demonstrated their ability to discern between, among others: control and pathologic EEG signals, seizure free or not, control and opened eyes EEG, and side of brain signals. Results show that SampEn behaves better when analyzing control signals, while DFA provides better segmentation results between epileptic signals, in the context of sample loss, particularly when discerning between seizure and seizure free signal intervals.