Heart rate variability analysis during central hypovolemia using wavelet transformation.

Detection of hypovolemia prior to overt hemodynamic decompensation remains an elusive goal in the treatment of critically injured patients in both civilian and combat settings. Monitoring of heart rate variability has been advocated as a potential means to monitor the rapid changes in the physiological state of hemorrhaging patients, with the most popular methods involving calculation of the R-R interval signal's power spectral density (PSD) or use of fractal dimensions (FD). However, the latter method poses technical challenges, while the former is best suited to stationary signals rather than the non-stationary R-R interval. Both approaches are also limited by high inter- and intra-individual variability, a serious issue when applying these indices to the clinical setting. We propose an approach which applies the discrete wavelet transform (DWT) to the R-R interval signal to extract information at both 500 and 125 Hz sampling rates. The utility of machine learning models based on these features were tested in assessing electrocardiogram signals from volunteers subjected to lower body negative pressure induced central hypovolemia as a surrogate of hemorrhage. These machine learning models based on DWT features were compared against those based on the traditional PSD and FD, at both sampling rates and their performance was evaluated based on leave-one-subject-out fold cross-validation. Results demonstrate that the proposed DWT-based model outperforms individual PSD and FD methods as well as the combination of these two traditional methods at both sample rates of 500 Hz (p value <0.0001) and 125 Hz (p value <0.0001) in detecting the degree of hypovolemia. These findings indicate the potential of the proposed DWT approach in monitoring the physiological changes caused by hemorrhage. The speed and relatively low computational costs in deriving these features may make it particularly suited for implementation in portable devices for remote monitoring.

Brain mapping and detection of functional patterns in fMRI using wavelet transform; application in detection of dyslexia.

BACKGROUND: Functional Magnetic Resonance Imaging (fMRI) has been proven to be useful for studying brain functions. However, due to the existence of noise and distortion, mapping between the fMRI signal and the actual neural activity is difficult. Because of the difficulty, differential pattern analysis of fMRI brain images for healthy and diseased cases is regarded as an important research topic. From fMRI scans, increased blood ows can be identified as activated brain regions. Also, based on the multi-sliced images of the volume data, fMRI provides the functional information for detecting and analyzing different parts of the brain. METHODS: In this paper, the capability of a hierarchical method that performed an optimization algorithm based on modified maximum model (MCM) in our previous study is evaluated. The optimization algorithm is designed by adopting modified maximum correlation model (MCM) to detect active regions that contain significant responses. Specifically, in the study, the optimization algorithm is examined based on two groups of datasets, dyslexia and healthy subjects to verify the ability of the algorithm that enhances the quality of signal activities in the interested regions of the brain. After verifying the algorithm, discrete wavelet transform (DWT) is applied to identify the difference between healthy and dyslexia subjects. RESULTS: We successfully showed that our optimization algorithm improves the fMRI signal activity for both healthy and dyslexia subjects. In addition, we found that DWT based features can identify the difference between healthy and dyslexia subjects. CONCLUSION: The results of this study provide insights of associations of functional abnormalities in dyslexic subjects that may be helpful for neurobiological identification from healthy subject.

A comparative analysis of multi-level computer-assisted decision making systems for traumatic injuries.

BACKGROUND: This paper focuses on the creation of a predictive computer-assisted decision making system for traumatic injury using machine learning algorithms. Trauma experts must make several difficult decisions based on a large number of patient attributes, usually in a short period of time. The aim is to compare the existing machine learning methods available for medical informatics, and develop reliable, rule-based computer-assisted decision-making systems that provide recommendations for the course of treatment for new patients, based on previously seen cases in trauma databases. Datasets of traumatic brain injury (TBI) patients are used to train and test the decision making algorithm. The work is also applicable to patients with traumatic pelvic injuries. METHODS: Decision-making rules are created by processing patterns discovered in the datasets, using machine learning techniques. More specifically, CART and C4.5 are used, as they provide grammatical expressions of knowledge extracted by applying logical operations to the available features. The resulting rule sets are tested against other machine learning methods, including AdaBoost and SVM. The rule creation algorithm is applied to multiple datasets, both with and without prior filtering to discover significant variables. This filtering is performed via logistic regression prior to the rule discovery process. RESULTS: For survival prediction using all variables, CART outperformed the other machine learning methods. When using only significant variables, neural networks performed best. A reliable rule-base was generated using combined C4.5/CART. The average predictive rule performance was 82% when using all variables, and approximately 84% when using significant variables only. The average performance of the combined C4.5 and CART system using significant variables was 89.7% in predicting the exact outcome (home or rehabilitation), and 93.1% in predicting the ICU length of stay for airlifted TBI patients. CONCLUSION: This study creates an efficient computer-aided rule-based system that can be employed in decision making in TBI cases. The rule-bases apply methods that combine CART and C4.5 with logistic regression to improve rule performance and quality. For final outcome prediction for TBI cases, the resulting rule-bases outperform systems that utilize all available variables.

Automated ventricular systems segmentation in brain CT images by combining low-level segmentation and high-level template matching.

BACKGROUND: Accurate analysis of CT brain scans is vital for diagnosis and treatment of Traumatic Brain Injuries (TBI). Automatic processing of these CT brain scans could speed up the decision making process, lower the cost of healthcare, and reduce the chance of human error. In this paper, we focus on automatic processing of CT brain images to segment and identify the ventricular systems. The segmentation of ventricles provides quantitative measures on the changes of ventricles in the brain that form vital diagnosis information. METHODS: First all CT slices are aligned by detecting the ideal midlines in all images. The initial estimation of the ideal midline of the brain is found based on skull symmetry and then the initial estimate is further refined using detected anatomical features. Then a two-step method is used for ventricle segmentation. First a low-level segmentation on each pixel is applied on the CT images. For this step, both Iterated Conditional Mode (ICM) and Maximum A Posteriori Spatial Probability (MASP) are evaluated and compared. The second step applies template matching algorithm to identify objects in the initial low-level segmentation as ventricles. Experiments for ventricle segmentation are conducted using a relatively large CT dataset containing mild and severe TBI cases. RESULTS: Experiments show that the acceptable rate of the ideal midline detection is over 95%. Two measurements are defined to evaluate ventricle recognition results. The first measure is a sensitivity-like measure and the second is a false positive-like measure. For the first measurement, the rate is 100% indicating that all ventricles are identified in all slices. The false positives-like measurement is 8.59%. We also point out the similarities and differences between ICM and MASP algorithms through both mathematically relationships and segmentation results on CT images. CONCLUSION: The experiments show the reliability of the proposed algorithms. The novelty of the proposed method lies in its incorporation of anatomical features for ideal midline detection and the two-step ventricle segmentation method. Our method offers the following improvements over existing approaches: accurate detection of the ideal midline and accurate recognition of ventricles using both anatomical features and spatial templates derived from Magnetic Resonance Images.

Cloud-Scale Genomic Signals Processing for Robust Large-Scale Cancer Genomic Microarray Data Analysis.

As microarray data available to scientists continues to increase in size and complexity, it has become overwhelmingly important to find multiple ways to bring forth oncological inference to the bioinformatics community through the analysis of large-scale cancer genomic (LSCG) DNA and mRNA microarray data that is useful to scientists. Though there have been many attempts to elucidate the issue of bringing forth biological interpretation by means of wavelet preprocessing and classification, there has not been a research effort that focuses on a cloud-scale distributed parallel (CSDP) separable 1-D wavelet decomposition technique for denoising through differential expression thresholding and classification of LSCG microarray data. This research presents a novel methodology that utilizes a CSDP separable 1-D method for wavelet-based transformation in order to initialize a threshold which will retain significantly expressed genes through the denoising process for robust classification of cancer patients. Additionally, the overall study was implemented and encompassed within CSDP environment. The utilization of cloud computing and wavelet-based thresholding for denoising was used for the classification of samples within the Global Cancer Map, Cancer Cell Line Encyclopedia, and The Cancer Genome Atlas. The results proved that separable 1-D parallel distributed wavelet denoising in the cloud and differential expression thresholding increased the computational performance and enabled the generation of higher quality LSCG microarray datasets, which led to more accurate classification results.

An Integration of Decision Tree and Visual Analysis to Analyze Intracranial Pressure.

In Traumatic Brain Injury (TBI), elevated Intracranial Pressure (ICP) causes severe brain damages due to hemorrhage and swelling. Monitoring ICP plays an important role in the treatment of TBI patients because ICP is considered a strong predictor of neurological outcome and a potentially amenable method to treat patients. However, it is difficult to predict and measure accurate ICP due to the complex nature of patients' clinical conditions. ICP monitoring for severe TBI patient is a challenging problem for clinicians because traditionally known ICP monitoring is an invasive procedure by placing a device inside the brain to measure pressure. Therefore, ICP monitoring might have a high infection risk and cause medical complications. In here, an ICP monitoring using texture features is proposed to overcome this limitation. The combination of image processing methods and a decision tree algorithm is utilized to estimate ICP of TBI patients noninvasively. In addition, a visual analytics tool is used to conduct an interactive visual factor analysis and outlier detection.

A signal processing method to explore similarity in protein flexibility.

Understanding mechanisms of protein flexibility is of great importance to structural biology. The ability to detect similarities between proteins and their patterns is vital in discovering new information about unknown protein functions. A Distance Constraint Model (DCM) provides a means to generate a variety of flexibility measures based on a given protein structure. Although information about mechanical properties of flexibility is critical for understanding protein function for a given protein, the question of whether certain characteristics are shared across homologous proteins is difficult to assess. For a proper assessment, a quantified measure of similarity is necessary. This paper begins to explore image processing techniques to quantify similarities in signals and images that characterize protein flexibility. The dataset considered here consists of three different families of proteins, with three proteins in each family. The similarities and differences found within flexibility measures across homologous proteins do not align with sequence-based evolutionary methods.

Combining predictive capabilities of transcranial doppler with electrocardiogram to predict hemorrhagic shock.

Hemorrhagic shock (HS) potentially impacts the chance of survival in most traumatic injuries. Thus, it is highly desirable to maximize the survival rate in cases of blood loss by predicting the occurrence of hemorrhagic shock with biomedical signals. Since analyzing one physiological signal may not enough to accurately predict blood loss severity, two types of physiological signals - Electrocardiography (ECG) and Transcranial Doppler (TCD) - are used to discover the degree of severity. In this study, these degrees are classified as mild, moderate and severe, and also severe and non-severe. The data for this study were generated using the human simulated model of hemorrhage, which is called lower body negative pressure (LBNP). The analysis is done by applying discrete wavelet transformation (DWT). The wavelet-based features are defined using the detail and approximate coefficients and machine learning algorithms are used for classification. The objective of this study is to evaluate the improvement when analyzing ECG and TCD physiological signals together to classify the severity of blood loss. The results of this study show a prediction accuracy of 85.9% achieved by support vector machine in identifying severe/non-severe states.