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 2008
Fetal distress diagnosis using heart rate variability analysis: design of a high frequency variability index.
Routine monitoring of Fetal Heart Rate (FHR) during labor enables diagnosis of fetal distress and appropriate management by the medical staff. Diagnosis of fetal distress relies mainly on a subjective visual assessment of FHR variations using baseline level, oscillations magnitude, decelerations and their time-relation to the parturient uterine contractions. Strong intra and inter-observer discrepancies exist with this widely used technique, and sometimes requires fetal scalp blood sample pH measurement, which is not fully reliable either. ⋯ We tested this new index on 21 fetuses where FHR was recorded during labor for an observational clinical trial. FHR recordings were separated in two groups given the fetal arterial pH obtained after birth: group 1 - no distress, pH >= 7.15, N=16 and group 2 - fetal distress, pH 7.15, N=5. The new index was significantly higher in group 1 than in group 2 (non parametric Mann Whitney U-test, p=0.01).
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2008
Phase space reconstruction approach for ventricular arrhythmias characterization.
Ventricular arrhythmias, especially tachycardia and fibrillation are one of the main causes of sudden cardiac death. Therefore, the development of methodologies, enable to detect their occurrence and to characterize their time evolution, is of fundamental importance. ⋯ Features from current and previous time windows are provided to a dynamic neural network classifier, enabling arrhythmias detection and evolution trends assessment. Sensitivity and specificity values, evaluated from public MIT-BIH databases, show the effectiveness of the proposed strategy.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2008
Model predictive control of depth of anaesthesia: guidelines for controller configuration.
The paper presents a feasibility study on the use of Model based Predictive control (MPC) to regulate the level of Depth of Anaesthesia (DoA) when measured by the BIS index. Pharmacokinetic/pharmacodynamic nonlinear models of DoA when Propofol and Remifentanil are used as hypnotic and analgesic drugs are linearized around the desired working point for DoA in order to obtain a linear state-space model coupled with an extra integrator to include integral action in the control. This state-space model is then used in a MPC algorithm. The main contribution of the paper consists in the characterization of the influence of the different design parameters in the MPC performance when controlling DoA.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2008
Fast prototype of a wireless cardiac rhythm interpretive instrument.
Extended patient monitoring has become increasingly important for detection of cardiac conditions, such as irregularities in the rhythms of the heart, while patient is practicing normal daily activity. This paper presents a design of a single lead wireless cardiac rhythm interpretive instrument that capable of capture the electrocardiogram (ECG) in digital format and transmitted to a remote base-station (i.e. PC) for storage and further interpretation. The design has achieved high quality of ECG and free of interference in the presence of motion.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2008
Imaging of simulated crackle sounds distribution on the chest.
Crackles sounds have been associated with several pulmonary pathologies and diverse algorithms have been proposed for extracting and counting them from the acquired lung sound. These tasks depend among other factors, of the relation between the magnitude of the crackle and the background lung sound. In this work, we explore multivariate signal processing to deal with the tasks and propose a new concept, the discontinuous adventitious sounds imaging. ⋯ In the first case, the AR coefficients feed an artificial neural network (ANN) to classify temporal acoustic information as healthy or sick and; in the second case, a time-variant AR (TVAR) model, obtained by the RLS algorithm, permits to detect changes in the TVAR coefficients to be associated with the number of crackles. For AR-ANN, the ratio of the temporal windows classified as sick to the classified as healthy is used as an index to form the adventitious image, while for TVAR-RLS, an estimation of the number of crackles is obtained to form the corresponding image. The results indicated that fine and coarse crackles could be detected and counted even with very low crackle magnitude so that the formation of a crackle distribution image was consistent.