Medical & biological engineering & computing
-
Med Biol Eng Comput · Jun 2014
Comparison of spinal cord stimulation profiles from intra- and extradural electrode arrangements by finite element modelling.
Spinal cord stimulation currently relies on extradural electrode arrays that are separated from the spinal cord surface by a highly conducting layer of cerebrospinal fluid. It has recently been suggested that intradural placement of the electrodes in direct contact with the pial surface could greatly enhance the specificity and efficiency of stimulation. The present computational study aims at quantifying and comparing the electrical current distributions as well as the spatial recruitment profiles resulting from extra- and intra-dural electrode arrangements. ⋯ The likely recruitment areas are then obtained using the potential as input to an equivalent circuit model of the pre-threshold axonal response. The results show that the current threshold to recruitment of axons in the dorsal column is more than an order of magnitude smaller for intradural than extradural stimulation. Intradural placement of the electrodes also leads to much higher contrast between the stimulation thresholds for the dorsal root entry zone and the dorsal column, allowing better focusing of the stimulus.
-
Med Biol Eng Comput · May 2014
Noninvasive and automatic diagnosis of patients at high risk of swallowing aspiration.
Swallowing aspiration is known as the most clinically significant symptom of swallowing disorders (dysphagia). Noninvasive methods for detection of aspiration (the entry of food into airway due to dysphagia) are of great interest as they will lead to better management of dysphagia; thus, the risk of pneumonia, length of hospital stay and overall health care expenses can be reduced. The risk of aspiration is much higher in severely dysphagic patients. ⋯ We evaluated the method using breath and swallowing sounds recorded from 50 dysphagic individuals, 27 of which demonstrated silent aspiration (without cough or throat clearance) during either fiberoptic endoscopic evaluation of swallowing (FEES) or videofluoroscopic swallowing (VFS) assessment. The classification result of the proposed method was compared with those of the FEES/VFS assessment provided by speech-language pathologists; it showed 91 % sensitivity and 85 % specificity in detection of patients with severe aspiration (high risk dysphagia). The result is promising to suggest the proposed phase-space acoustical analysis method as a quick and noninvasive screening clinical tool to detect patients developing severe aspiration.
-
Med Biol Eng Comput · Feb 2014
Development and validation of a machine learning algorithm and hybrid system to predict the need for life-saving interventions in trauma patients.
Accurate and effective diagnosis of actual injury severity can be problematic in trauma patients. Inherent physiologic compensatory mechanisms may prevent accurate diagnosis and mask true severity in many circumstances. The objective of this project was the development and validation of a multiparameter machine learning algorithm and system capable of predicting the need for life-saving interventions (LSIs) in trauma patients. ⋯ Additionally, 295,994 feature sets from 82 h of trauma patient data showed that the system can obtain 89.8 % accuracy within 5 min of recorded LSIs. Use of machine learning technologies combined with basic detection rules provides a potential approach for accurately assessing the need for LSIs in trauma patients. The performance of this system demonstrates that machine learning technology can be implemented in a real-time fashion and potentially used in a critical care environment.
-
Med Biol Eng Comput · Sep 2013
Mortality prediction of rats in acute hemorrhagic shock using machine learning techniques.
This study sought to determine a mortality prediction model that could be used for triage in the setting of acute hemorrhage from trauma. To achieve this aim, various machine learning techniques were applied using the rat model in acute hemorrhage. Thirty-six anesthetized rats were randomized into three groups according to the volume of controlled blood loss. ⋯ The SVM model showed better sensitivity (1.000) and area under curve (0.972) than the LR, ANN, and RF models for mortality prediction. The important variables selected by the SVM were NI and LC. The SVM model may be very helpful to first responders who need to make accurate triage decisions and rapidly treat hemorrhagic patients in cases of trauma.
-
Med Biol Eng Comput · Sep 2013
Monitoring respiration in wheezy preschool children by pulse oximetry plethysmogram analysis.
The aim of this study was to investigate whether respiratory information can be derived from pulse oximetry plethysmogram (pleth) recordings in acutely wheezy preschool children. A digital pulse oximeter was connected via 'Bluetooth' to a notebook computer in order to acquire pleth data. Low pass filtering and frequency analysis were used to derive respiratory rate from the pleth trace; the ratio of heart rate to respiratory rate (HR/RR) was also calculated. ⋯ For the follow-up measurements, frequency analysis of the pleth waveform showed similarly good agreement in recordings on 15 of the 16 children. Respiratory rate was higher (p < 0.001), and HR/RR ratio was lower (p = 0.03) during acute wheeze than at follow-up. This study suggests that respiratory rate can be derived from pleth traces in wheezy preschool children.