Last updated on June 22, 2015. This conference program is tentative and subject to change
Methods: Following ethics approval and informed consent, data were collected from 48 children receiving general anesthesia during dental surgery. The times of change in RR and PPaw events were noted in real-time. A total of 43 RR and 35 PPaw change events were analyzed post hoc in pseudo real-time. The nociception index averages were compared between a baseline period and a response period around each event. A Wilcoxon rank-sum test was used to compare changes.
Results: The change in RR changed the CRC nociception index by an average of -2.2 [95% CI from -10 to 4.7] (P > 0.3), and the change in PPaw changed the CRC nociception index by an average of 5.4 [-1.0 to 11] (P > 0.1). The changes were smaller than those of many traditional HRV measures.
Conclusions: Real-time CRC was blind to the changes in respiration, and was less sensitive than many of the traditional HRV measures. A nociception index based on CRC can thus function across a wider range of respiratory conditions than can many traditional univariate HRV measures. The real-time CRC algorithm shows promise for monitoring nociception during general anesthesia.
With the implementation of bootstrapping, a more Representative result was obtained wherein we demonstrate the training of a hybrid ANN consisting of an array of Multi-Layer Perceptrons (MLPs) with optimal number of hidden neurons. The ANN system was able to correctly class 90.1% of the previously unseen odorants, thus demonstrating very strong evidence for the use of A. Gambiae olfactory receptors coupled with an ANN as an olfactory biosensor.
HRV complexity increased with hyperglycemia indicated by increases in Shannon entropy and MSE and decreases in Renyi entropy for negative orders. Diabetes duration was strongly associated with Renyi entropy which increased for positive orders and decreased for negative orders as a function of disease duration. Shannon entropy, SampEn and MSE did not correlate with disease duration.
EMG signals were recorded from 5 patients with PD and 5 younger healthy controls while performing a series of standardized gait tests. Wireless surface electrodes were placed bilaterally on tibialis anterior and gastrocnemius medialis and lateralis. Accelerometers were positioned on both heels and used for step segmentation. Statistical and frequency features were extracted and used to train a Support Vector Machine classifier.
Sensitivity and specificity were high at 0.90 using leave-one-subject-out cross-validation. Feature selection revealed kurtosis and mean frequency as best features, with a significant difference in kurtosis (p=0.013). Evaluated on a bigger population, this could lead to objective diagnostic and staging tools for PD.