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 2010
Symbolic learning supporting early diagnosis of melanoma.
We present a classification analysis of the pigmented skin lesion images taken in white light based on the inductive learning methods by Michalski (AQ). Those methods are developed for a computer system supporting the decision making process for early diagnosis of melanoma. ⋯ Classification performance with the wavelet features, although achieved with simple rules, is very high. Symbolic learning applied to our skin lesion data seems to outperform other classical machine learning methods, and is more comprehensive both in understanding, and in application of further improvements.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2010
Heuristics to determine ventilation times of ICU patients from the MIMIC-II database.
Mechanical ventilation is an important life support tool for patients in intensive care units (ICU). For various research purposes related to patient hemodynamic and cardiopulmonary monitoring, it is important to know when a patient is on a ventilator. Unfortunately, the widely used MIMIC-II database contains results from user charted data, where the user did not always store ventilation on and off times explicitly and accurately. ⋯ Hence, we designed a simple set of rules to determine the ventilation times using multiple sources of mechanical ventilator-related settings and physiological measurements by expert heuristics. The rules worked well in comparison with nursing notes regarding ventilation events. We conclude that our rule sets for determining ventilation times may be useful in assisting with MIMIC-II database analysis.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2010
Mechanical analysis of an oscillatory positive expiratory pressure device used in respiratory rehabilitation.
This article aims to characterize the mechanical behavior of the Acapella Blue, a respiratory rehabilitation device designed to aid sputum clearance. In this scope, the present study initially describes in detail the peak-to-peak oscillation amplitude (App) and peak frequency (fp) behavior, as well as positive pressure level (Ppl), in the flow range more comonly found in practice. The parameters were evaluated in all 5 adjustment levels of the equipment in intervals of 50 mL/s. ⋯ The studied device may produce oscillation in the ranges of ciliary movements and respiratory system resonance frequency of patients with respiratory diseases. Data obtained in this work may help to optimize the use of the Acapella Blue device in respiratory rehabilitation. Suggestions for the practical use of the device are also presented.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2010
Electroconvulsive therapy in the presence of deep brain stimulation implants: electric field effects.
The safety of electroconvulsive therapy (ECT) in patients who have deep brain stimulation (DBS) implants represents a significant clinical issue. A major safety concern is the presence of burr holes and electrode anchoring devices in the skull, which may alter the induced electric field distribution in the brain. We simulated the electric field using finite-element method in a five-shell spherical head model. ⋯ We compared electric field strength and focality among the DBS implantation techniques and ECT electrode configurations. The simulation results show an increase in the electric field strength in the brain due to conduction through the burr holes, especially when the burr holes are not fitted with nonconductive caps. For typical burr hole placement for subthalamic nucleus DBS, the effect on the electric field strength and focality is strongest for BF ECT, which runs contrary to the belief that more anterior ECT electrode placements are safer in patients with DBS implants.
-
Conf Proc IEEE Eng Med Biol Soc · Jan 2010
Analysis of heart rate variability dynamics during propofol and dexmedetomidine anesthesia.
It has been observed that heart rate variability (HRV) diminishes during anesthesia, but the exact mechanisms causing it are not completely understood. The aim of this paper was to study the dynamics of HRV during low dose propofol (N=9) and dexmedetomidine (N=8) anesthesia by using state-of-the-art time-varying methods, and thereby ultimately try to improve the safety of anesthesia. ⋯ For dexmedetomidine these changes are more considerable than for propofol. For dexmedetomidine the variability also seems to start decreasing right after loss of consciousness, whereas for propofol HRV continues increasing.