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 2009
Estimation of blood pressure variability using independent component analysis of photoplethysmographic signal.
The maximum cross-correlation coefficient rho(max) between blood pressure variability and heart rate variability, whose frequency components are limited to the Mayer wave-related band, is a useful index to evaluate the state of the autonomic nervous function related to baroreflex. However, measurement of continuous blood pressure with an expensive and bulky measuring device is required to calculate rho(max). ⋯ In the proposed method, independent components are extracted from feature variables specified by the PPG signal by using the independent component analysis (ICA), and then the most appropriate component is chosen out of them so that the rho(max) based on the component can fit its true value. The results from the experiment with a postural change performed in 17 healthy subjects suggested that the proposed method is available for estimating rho(max) by using the ICA to extract blood pressure information from the PPG signal.
-
While liposomes and nanoparticles have been the subject of intense research for more than 40 years, few particles have been translated into clinical practice. Advantages of these particles include the potential to overcome the cardiac, renal or neural toxicity of systemic chemotherapy, the opportunities for multivalent targeting, the gradual yet significant accumulation within tumors due to leaky blood vessels and the myriad of new approaches to locally alter the properties of the particle in the region of interest. Given the complexity of the design and co-optimization of the surface architecture, shell formulation and drug loading, methods to image the pharmacokinetics of nanoparticles in living systems are an essential part of an efficient research methodology. Here, we describe our efforts to label the shell and drug core of lipid-shelled particles with a goal of facilitating translation of activatable particles.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2009
Screening of patients with Obstructive Sleep Apnea Syndrome using C4.5 algorithm based on non linear analysis of respiratory signals during sleep.
To classify patients with possible diagnosis of Obstructive Sleep Apnea Syndrome (OSAS) into groups according to the severity of the disease using a decision tree producing algorithm based on nonlinear analysis of 3 respiratory signals instead of the use of full polysomnography. ⋯ It is possible to have reliable predictions of the severity of OSAS using linear and nonlinear indices from only two respiratory signals during sleep instead of performing full polysomnography. The proposed algorithm could be used for screening patients suspected to suffer from OSAS.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2009
Data mining of patients on weaning trials from mechanical ventilation using cluster analysis and neural networks.
The process of weaning from mechanical ventilation is one of the challenges in intensive care. 149 patients under extubation process (T-tube test) were studied: 88 patients with successful trials (group S), 38 patients who failed to maintain spontaneous breathing and were reconnected (group F), and 23 patients with successful test but that had to be reintubated before 48 hours (group R). Each patient was characterized using 8 time series and 6 statistics extracted from respiratory and cardiac signals. A moving window statistical analysis was applied obtaining for each patient a sequence of patterns of 48 features. ⋯ Neural networks were applied to discriminate between patients from groups S, F and R. The best performance obtained was 84.0% of well classified patients using a linear perceptron trained with a feature selection procedure (that selected 19 of the 48 features) and taking as input the main cluster centroid. However, the classification baseline 69.8% could not be improved when using the original set of patterns instead of the centroids to classify the patients.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2009
Pulse pressure variation estimation using a sequential Monte Carlo method.
We describe a novel automatic algorithm to continuously estimate the pulse pressure variation (PPV) index from arterial blood pressure (ABP) signals. The algorithm utilizes our recently developed sequential Monte Carlo method (SMCM) based on a maximum A-Posterior adaptive marginalized particle filter (MAM-PF). The PPV index is one of most specific and sensitive dynamic indicators of fluid responsiveness in mechanically ventilated patients. We report the assessment results of the proposed algorithm on real ABP signals.