Causality in Scale Space as an Approach to Change Detection

Kernel density estimation and kernel regression are useful ways to visualize and assess the structure of data. Using these techniques we define a temporal scale space as the vector space spanned by bandwidth and a temporal variable. In this space significance regions that reflect a significant derivative in the kernel smooth similar to those of SiZer (Significant Zero-crossings of derivatives) are indicated. Significance regions are established by hypothesis tests for significant gradient at every point in scale space. Causality is imposed onto the space by restricting to kernels with left-bounded or finite support and shifting kernels forward. We show that these adjustments to the methodology enable early detection of changes in time series constituting live surveillance systems of either count data or unevenly sampled measurements. Warning delays are comparable to standard techniques though comparison shows that other techniques may be better suited for single-scale problems. Our method reliably detects change points even with little to no knowledge about the relevant scale of the problem. Hence the technique will be applicable for a large variety of sources without tailoring. Furthermore this technique enables us to obtain a retrospective reliable interval estimate of the time of a change point rather than a point estimate. We apply the technique to disease outbreak detection based on laboratory confirmed cases for pertussis and influenza as well as blood glucose concentration obtained from patients with diabetes type 1.     

TREAP: A New Topological Approach to Drug Target Inference

Over 50% of drugs fail in stage 3 clinical trials, many because of a poor understanding of the drug’s mechanisms of action (MoA). A better comprehension of drug MoA will significantly improve research and development (R&D). Current proposed algorithms, such as ProTINA and DeMAND, can be overly complex. Additionally, they are unable to predict whether the drug-induced gene expression or the topology of the networks used to model gene regulation primarily impacts accurate drug target inference. In this work, we evaluate how network and gene expression data affect ProTINA’s accuracy. We find that network topology predominantly determines the accuracy of ProTINA’s predictions. We further show that the size of an interaction network and/or selecting cell-specific networks has a limited effect on accuracy. We then demonstrate that a specific network topology measure, betweenness, can be used to improve drug target prediction. Based on these results, we create a new algorithm, TREAP, that combines betweenness values and adjusted p-values for target inference. TREAP offers an alternative approach to drug target inference and is advantageous because it is not computationally demanding, provides easy-to-interpret results, and is often more accurate at predicting drug targets than current state-of-the-art approaches.     

Myocardial Infarction Detection and Localization Using Optimal Features Based Lead Specific Approach

ObjectivesObjective of this paper is to present a reliable and accurate technique for Myocardial Infarction (MI) detection and localization.Material and methodsStationary wavelet transform has been used to decompose the ECG signal. Energy, entropy and slope based features were extracted at specific wavelet bands from selected lead of ECG. k-Nearest Neighbors (kNN) with Mahalanobis distance function has been used for classification. Sensitivity (Se), specificity (Sp), positive predictivity (+P), accuracy (Acc), and area under the receiver operating characteristics curve (AUC) analyzed over 200 subjects (52 health control, 148 with MI) from Physikalisch-Technische Bundesanstalt (PTB) database has been used for performance analysis. To handle the imbalanced data adaptive synthetic (ADASYN) sampling approach has been adopted.ResultsFor detection of MI, the proposed technique has shown an AUC = 0.99, Se = 98.62%, Sp = 99.40%, PPR = 99.41% and Acc = 99.00% using 12 top ranked features, extracted from multiple leads of ECG and AUC = 0.99, Se = 98.34%, Sp = 99.77%, PPR = 99.77% and Acc = 99.05% using 12 features extracted from a single ECG lead (i.e. lead V5). For localization of MI, the proposed technique has an AUC = 0.99, Se = 98.78%, Sp = 99.86%, PPR = 98.80%, and Acc = 99.76% using 5 top ranked features from multiple leads of ECG and AUC = 0.98, Se = 96.47%, Sp = 99.60%, PPR = 96.49% and Acc = 99.28% using 8 features extracted from a single ECG lead (i.e. lead V3).ConclusionThus for MI detection and localization, the proposed technique is independent of time-domain ECG fiducial markers and can work using specific leads of ECG.     

Novel Approach to Quantitative Detection of Specific rRNA in a Microbial Community, Using Catalytic DNA

We developed a novel method for the quantitative detection of the 16S rRNA of a specific bacterial species in the microbial community by using deoxyribozyme (DNAzyme), which possesses the catalytic function to cleave RNA in a sequence-specific manner. A mixture of heterogeneous 16S rRNA containing the target 16S rRNA was incubated with a species-specific DNAzyme. The cleaved target 16S rRNA was separated from the intact 16S rRNA by electrophoresis, and then their amounts were compared for the quantitative detection of target 16S rRNA. This method was used to determine the abundance of the 16S rRNA of a filamentous bacterium, Sphaerotilus natans, in activated sludge, which is a microbial mixture used in wastewater treatment systems. The result indicated that this DNAzyme-based approach would be applicable to actual microbial communities.     

Prenatal Diagnosis: A Directive Approach to Genetic Counseling Using Decision Analysis

The decision which prospective parents face concerning mid-trimester amniocentesis for prenatal diagnosis was examined by decision analysis. The prospective parents'' decision depends on the likelihood of the birth of a child affected by a genetic disorder, the risk of amniocentesis, and the probability that the diagnoses provided by the amniocentesis will be correct. The couple''s decision must also depend on their attitudes toward each possible outcome. The likelihoods of the outcomes can be obtained from appropriate medical consultation, while the relative costs or burdens of the outcomes should be obtained from the prospective parents. A truly informed decision for this couple can then be formulated from these probabilities and values, thus allowing genetic counseling to be more directive. The technique is illustrated for the prenatal diagnosis of Down''s syndrome, meningomyelocele, and Duchenne muscular dystrophy.     

Cardiovascular Disorder Severity Detection Using Myocardial Anatomic Features Based Optimized Extreme Learning Machine Approach

ObjectivesThis study focuses on integration of anatomical left ventricle myocardium features and optimized extreme learning machine (ELM) for discrimination of subjects with normal, mild, moderate and severe abnormal ejection fraction (EF). The physiological alterations in myocardium have diagnostic relevance to the etiology of cardiovascular diseases (CVD) with reduced EF.Materials and MethodsThis assessment is carried out on cardiovascular magnetic resonance (CMR) images of 104 subjects available in Kaggle Second Annual Data Science Bowl. The Segment CMR framework is used to segment myocardium from cardiac MR images, and it is subdivided into 16 sectors. 86 clinically significant anatomical features are extracted and subjected to ELM framework. Regularization coefficient and hidden neurons influence the prediction accuracy of ELM. The optimal value for these parameters is achieved with the butterfly optimizer (BO). A comparative study of BOELM framework with different activation functions and feature set has been conducted.ResultsAmong the individual feature set, myocardial volume at ED gives a better classification accuracy of 83.3% compared to others. Further, the given BOELM framework is able to provide higher multi-class accuracy of 95.2% with the entire feature set than ELM. Better discrimination of healthy and moderate abnormal subjects is achieved than other sub groups.ConclusionThe combined anatomical sector wise myocardial features assisted BOELM is able to predict the severity levels of CVDs. Thus, this study supports the radiologists in the mass diagnosis of cardiac disorder.     

A Novel Approach for the Detection and Genetic Analysis of Live Melanoma Circulating Tumor Cells

Background

Circulating tumor cell (CTC) detection and genetic analysis may complement currently available disease assessments in patients with melanoma to improve risk stratification and monitoring. We therefore sought to establish the feasibility of a telomerase-based assay for detecting and isolating live melanoma CTCs.

Methods

The telomerase-based CTC assay utilizes an adenoviral vector that, in the presence of elevated human telomerase activity, drives the amplification of green fluorescent protein. Tumor cells are then identified via an image processing system. The protocol was tested on melanoma cells in culture or spiked into control blood, and on samples from patients with metastatic melanoma. Genetic analysis of the isolated melanoma CTCs was then performed for BRAF mutation status.

Results

The adenoviral vector was effective for all melanoma cell lines tested with sensitivity of 88.7% (95%CI 85.6-90.4%) and specificity of 99.9% (95%CI 99.8-99.9%). In a pilot trial of patients with metastatic disease, CTCs were identified in 9 of 10 patients, with a mean of 6.0 CTCs/mL. At a cutoff of 1.1 CTCs/mL, the telomerase-based assay exhibits test performance of 90.0% sensitivity and 91.7% specificity. BRAF mutation analysis of melanoma cells isolated from culture or spiked control blood, or from pilot patient samples was found to match the known BRAF mutation status of the cell lines and primary tumors.

Conclusions

To our knowledge, this is the first report of a telomerase-based assay effective for detecting and isolating live melanoma CTCs. These promising findings support further studies, including towards integrating into the management of patients with melanoma receiving multimodality therapy.     

A Novel Support Vector Machine-Based Approach for Rare Variant Detection

Advances in next-generation sequencing technologies have enabled the identification of multiple rare single nucleotide polymorphisms involved in diseases or traits. Several strategies for identifying rare variants that contribute to disease susceptibility have recently been proposed. An important feature of many of these statistical methods is the pooling or collapsing of multiple rare single nucleotide variants to achieve a reasonably high frequency and effect. However, if the pooled rare variants are associated with the trait in different directions, then the pooling may weaken the signal, thereby reducing its statistical power. In the present paper, we propose a backward support vector machine (BSVM)-based variant selection procedure to identify informative disease-associated rare variants. In the selection procedure, the rare variants are weighted and collapsed according to their positive or negative associations with the disease, which may be associated with common variants and rare variants with protective, deleterious, or neutral effects. This nonparametric variant selection procedure is able to account for confounding factors and can also be adopted in other regression frameworks. The results of a simulation study and a data example show that the proposed BSVM approach is more powerful than four other approaches under the considered scenarios, while maintaining valid type I errors.     

A Novel Approach to Quantify Time Series Differences of Gait Data Using Attractor Attributes

In this paper we introduce a new method to expressly use live/corporeal data in quantifying differences of time series data with an underlying limit cycle attractor; and apply it using an example of gait data. Our intention is to identify gait pattern differences between diverse situations and classify them on group and individual subject levels. First we approximated the limit cycle attractors, from which three measures were calculated: δM amounts to the difference between two attractors (a measure for the differences of two movements), δD computes the difference between the two associated deviations of the state vector away from the attractor (a measure for the change in movement variation), and δF, a combination of the previous two, is an index of the change. As an application we quantified these measures for walking on a treadmill under three different conditions: normal walking, dual task walking, and walking with additional weights at the ankle. The new method was able to successfully differentiate between the three walking conditions. Day to day repeatability, studied with repeated trials approximately one week apart, indicated excellent reliability for δM (ICC_ave > 0.73 with no differences across days; p > 0.05) and good reliability for δD (ICC_ave  =  0.414 to 0.610 with no differences across days; p > 0.05). Based on the ability to detect differences in varying gait conditions and the good repeatability of the measures across days, the new method is recommended as an alternative to expensive and time consuming techniques of gait classification assessment. In particular, the new method is an easy to use diagnostic tool to quantify clinical changes in neurological patients.     

A Novel GBM Saliency Detection Model Using Multi-Channel MRI

The automatic computerized detection of regions of interest (ROI) is an important step in the process of medical image processing and analysis. The reasons are many, and include an increasing amount of available medical imaging data, existence of inter-observer and inter-scanner variability, and to improve the accuracy in automatic detection in order to assist doctors in diagnosing faster and on time. A novel algorithm, based on visual saliency, is developed here for the identification of tumor regions from MR images of the brain. The GBM saliency detection model is designed by taking cue from the concept of visual saliency in natural scenes. A visually salient region is typically rare in an image, and contains highly discriminating information, with attention getting immediately focused upon it. Although color is typically considered as the most important feature in a bottom-up saliency detection model, we circumvent this issue in the inherently gray scale MR framework. We develop a novel pseudo-coloring scheme, based on the three MRI sequences, viz. FLAIR, T2 and T1C (contrast enhanced with Gadolinium). A bottom-up strategy, based on a new pseudo-color distance and spatial distance between image patches, is defined for highlighting the salient regions in the image. This multi-channel representation of the image and saliency detection model help in automatically and quickly isolating the tumor region, for subsequent delineation, as is necessary in medical diagnosis. The effectiveness of the proposed model is evaluated on MRI of 80 subjects from the BRATS database in terms of the saliency map values. Using ground truth of the tumor regions for both high- and low- grade gliomas, the results are compared with four highly referred saliency detection models from literature. In all cases the AUC scores from the ROC analysis are found to be more than 0.999 ± 0.001 over different tumor grades, sizes and positions.     

A Novel Approach to Enhancing Ganoderic Acid Production by Ganoderma lucidum Using Apoptosis Induction

Ganoderma lucidum is one of most widely used herbal medicine and functional food in Asia, and ganoderic acids (GAs) are its active ingredients. Regulation of GA biosynthesis and enhancing GA production are critical to using G. lucidum as a medicine. However, regulation of GA biosynthesis by various signaling remains poorly understood. This study investigated the role of apoptosis signaling on GA biosynthesis and presented a novel approach, namely apoptosis induction, to increasing GA production. Aspirin was able to induce cell apoptosis in G. lucidum, which was identified by terminal deoxynucleotidyl transferase mediated dUPT nick end labeling assay positive staining and a condensed nuclear morphology. The maximum induction of lanosta-7,9(11), 24-trien-3α-01-26-oic acid (ganoderic acid 24, GA24) production and total GA production by aspirin were 2.7-fold and 2.8-fold, respectively, after 1 day. Significantly lower levels of GA 24 and total GAs were obtained after regular fungal culture for 1.5 months. ROS accumulation and phosphorylation of Hog-1 kinase, a putative homolog of MAPK p38 in mammals, occurred after aspirin treatment indicating that both factors may be involved in GA biosynthetic regulation. However, aspirin also reduced expression of the squalene synthase and lanosterol synthase coding genes, suggesting that these genes are not critical for GA induction. To the best of our knowledge, this is the first report showing that GA biosynthesis is linked to fungal apoptosis and provides a new approach to enhancing secondary metabolite production in fungi.     

A Novel Genetic Score Approach Using Instruments to Investigate Interactions between Pathways and Environment: Application to Air Pollution

Air pollution has been associated with increased systemic inflammation markers. We developed a new pathway analysis approach to investigate whether gene variants within relevant pathways (oxidative stress, endothelial function, and metal processing) modified the association between particulate air pollution and fibrinogen, C-reactive protein (CRP), intercellular adhesion molecule-1 (ICAM-1), and vascular cell adhesion molecule-1 (VCAM-1). Our study population consisted of 822 elderly participants of the Normative Aging Study (1999–2011). To investigate the role of biological mechanisms and to reduce the number of comparisons in the analysis, we created pathway-specific scores using gene variants related to each pathway. To select the most appropriate gene variants, we used the least absolute shrinkage and selection operator (Lasso) to relate independent outcomes representative of each pathway (8-hydroxydeoxyguanosine for oxidative stress, augmentation index for endothelial function, and patella lead for metal processing) to gene variants. A high genetic score corresponds to a higher allelic risk profile. We fit mixed-effects models to examine modification by the genetic score of the weekly air pollution association with the outcome. Among participants with higher genetic scores within the oxidative stress pathway, we observed significant associations between particle number and fibrinogen, while we did not find any association among participants with lower scores (p_interaction = 0.04). Compared to individuals with low genetic scores of metal processing gene variants, participants with higher scores had greater effects of particle number on fibrinogen (p_interaction = 0.12), CRP (p_interaction = 0.02), and ICAM-1 (p_interaction = 0.08). This two-stage penalization method is easy to implement and can be used for large-scale genetic applications.     

Bronchial Thermoplasty: A Novel Therapeutic Approach to Severe Asthma

Bronchial thermoplasty is a non-drug procedure for severe persistent asthma that delivers thermal energy to the airway wall in a precisely controlled manner to reduce excessive airway smooth muscle. Reducing airway smooth muscle decreases the ability of the airways to constrict, thereby reducing the frequency of asthma attacks. Bronchial thermoplasty is delivered by the Alair System and is performed in three outpatient procedure visits, each scheduled approximately three weeks apart. The first procedure treats the airways of the right lower lobe, the second treats the airways of the left lower lobe and the third and final procedure treats the airways in both upper lobes. After all three procedures are performed the bronchial thermoplasty treatment is complete.Bronchial thermoplasty is performed during bronchoscopy with the patient under moderate sedation. All accessible airways distal to the mainstem bronchi between 3 and 10 mm in diameter, with the exception of the right middle lobe, are treated under bronchoscopic visualization. Contiguous and non-overlapping activations of the device are used, moving from distal to proximal along the length of the airway, and systematically from airway to airway as described previously. Although conceptually straightforward, the actual execution of bronchial thermoplasty is quite intricate and procedural duration for the treatment of a single lobe is often substantially longer than encountered during routine bronchoscopy. As such, bronchial thermoplasty should be considered a complex interventional bronchoscopy and is intended for the experienced bronchoscopist. Optimal patient management is critical in any such complex and longer duration bronchoscopic procedure. This article discusses the importance of careful patient selection, patient preparation, patient management, procedure duration, postoperative care and follow-up to ensure that bronchial thermoplasty is performed safely.Bronchial thermoplasty is expected to complement asthma maintenance medications by providing long-lasting asthma control and improving asthma-related quality of life of patients with severe asthma. In addition, bronchial thermoplasty has been demonstrated to reduce severe exacerbations (asthma attacks) emergency rooms visits for respiratory symptoms, and time lost from work, school and other daily activities due to asthma.Download video file.^{(90M, mov)}     

A Novel Algorithm to Enhance P300 in Single Trials: Application to Lie Detection Using F-Score and SVM

The investigation of lie detection methods based on P300 potentials has drawn much interest in recent years. We presented a novel algorithm to enhance signal-to-noise ratio (SNR) of P300 and applied it in lie detection to increase the classification accuracy. Thirty-four subjects were divided randomly into guilty and innocent groups, and the EEG signals on 14 electrodes were recorded. A novel spatial denoising algorithm (SDA) was proposed to reconstruct the P300 with a high SNR based on independent component analysis. The differences between the proposed method and our/other early published methods mainly lie in the extraction and feature selection method of P300. Three groups of features were extracted from the denoised waves; then, the optimal features were selected by the F-score method. Selected feature samples were finally fed into three classical classifiers to make a performance comparison. The optimal parameter values in the SDA and the classifiers were tuned using a grid-searching training procedure with cross-validation. The support vector machine (SVM) approach was adopted to combine with an F-score because this approach had the best performance. The presented model F-score_SVM reaches a significantly higher classification accuracy for P300 (specificity of 96.05%) and non-P300 (sensitivity of 96.11%) compared with the results obtained without using SDA and compared with the results obtained by other classification models. Moreover, a higher individual diagnosis rate can be obtained compared with previous methods, and the presented method requires only a small number of stimuli in the real testing application.     

AoP-LSE: Antioxidant Proteins Classification Using Deep Latent Space Encoding of Sequence Features

It is of utmost importance to develop a computational method for accurate prediction of antioxidants, as they play a vital role in the prevention of several diseases caused by oxidative stress. In this correspondence, we present an effective computational methodology based on the notion of deep latent space encoding. A deep neural network classifier fused with an auto-encoder learns class labels in a pruned latent space. This strategy has eliminated the need to separately develop classifier and the feature selection model, allowing the standalone model to effectively harness discriminating feature space and perform improved predictions. A thorough analytical study has been presented alongwith the PCA/tSNE visualization and PCA-GCNR scores to show the discriminating power of the proposed method. The proposed method showed a high MCC value of 0.43 and a balanced accuracy of 76.2%, which is superior to the existing models. The model has been evaluated on an independent dataset during which it outperformed the contemporary methods by correctly identifying the novel proteins with an accuracy of 95%.