An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification

A wide interest has been observed in the medical health care applications that interpret neuroimaging scans by machine learning systems. This research proposes an intelligent, automatic, accurate, and robust classification technique to classify the human brain magnetic resonance image (MRI) as normal or abnormal, to cater down the human error during identifying the diseases in brain MRIs. In this study, fast discrete wavelet transform (DWT), principal component analysis (PCA), and least squares support vector machine (LS-SVM) are used as basic components. Firstly, fast DWT is employed to extract the salient features of brain MRI, followed by PCA, which reduces the dimensions of the features. These reduced feature vectors also shrink the memory storage consumption by 99.5%. At last, an advanced classification technique based on LS-SVM is applied to brain MR image classification using reduced features. For improving the efficiency, LS-SVM is used with non-linear radial basis function (RBF) kernel. The proposed algorithm intelligently determines the optimized values of the hyper-parameters of the RBF kernel and also applied k-fold stratified cross validation to enhance the generalization of the system. The method was tested by 340 patients’ benchmark datasets of T1-weighted and T2-weighted scans. From the analysis of experimental results and performance comparisons, it is observed that the proposed medical decision support system outperformed all other modern classifiers and achieves 100% accuracy rate (specificity/sensitivity 100%/100%). Furthermore, in terms of computation time, the proposed technique is significantly faster than the recent well-known methods, and it improves the efficiency by 71%, 3%, and 4% on feature extraction stage, feature reduction stage, and classification stage, respectively. These results indicate that the proposed well-trained machine learning system has the potential to make accurate predictions about brain abnormalities from the individual subjects, therefore, it can be used as a significant tool in clinical practice.     

Clinical Utility of a Coronary Heart Disease Risk Prediction Gene Score in UK Healthy Middle Aged Men and in the Pakistani Population

BackgroundNumerous risk prediction algorithms based on conventional risk factors for Coronary Heart Disease (CHD) are available but provide only modest discrimination. The inclusion of genetic information may improve clinical utility.MethodsWe tested the use of two gene scores (GS) in the prospective second Northwick Park Heart Study (NPHSII) of 2775 healthy UK men (284 cases), and Pakistani case-control studies from Islamabad/Rawalpindi (321 cases/228 controls) and Lahore (414 cases/219 controls). The 19-SNP GS included SNPs in loci identified by GWAS and candidate gene studies, while the 13-SNP GS only included SNPs in loci identified by the CARDIoGRAMplusC4D consortium.ResultsIn NPHSII, the mean of both gene scores was higher in those who went on to develop CHD over 13.5 years of follow-up (19-SNP p=0.01, 13-SNP p=7x10^-3). In combination with the Framingham algorithm the GSs appeared to show improvement in discrimination (increase in area under the ROC curve, 19-SNP p=0.48, 13-SNP p=0.82) and risk classification (net reclassification improvement (NRI), 19-SNP p=0.28, 13-SNP p=0.42) compared to the Framingham algorithm alone, but these were not statistically significant. When considering only individuals who moved up a risk category with inclusion of the GS, the improvement in risk classification was statistically significant (19-SNP p=0.01, 13-SNP p=0.04). In the Pakistani samples, risk allele frequencies were significantly lower compared to NPHSII for 13/19 SNPs. In the Islamabad study, the mean gene score was higher in cases than controls only for the 13-SNP GS (2.24 v 2.34, p=0.04). There was no association with CHD and either score in the Lahore study.ConclusionThe performance of both GSs showed potential clinical utility in European men but much less utility in subjects from Pakistan, suggesting that a different set of risk loci or SNPs may be required for risk prediction in the South Asian population.     

Rapid Quantification of 3D Collagen Fiber Alignment and Fiber Intersection Correlations with High Sensitivity

Metastatic cancers aggressively reorganize collagen in their microenvironment. For example, radially orientated collagen fibers have been observed surrounding tumor cell clusters in vivo. The degree of fiber alignment, as a consequence of this remodeling, has often been difficult to quantify. In this paper, we present an easy to implement algorithm for accurate detection of collagen fiber orientation in a rapid pixel-wise manner. This algorithm quantifies the alignment of both computer generated and actual collagen fiber networks of varying degrees of alignment within 5°°. We also present an alternative easy method to calculate the alignment index directly from the standard deviation of fiber orientation. Using this quantitative method for determining collagen alignment, we demonstrate that the number of collagen fiber intersections has a negative correlation with the degree of fiber alignment. This decrease in intersections of aligned fibers could explain why cells move more rapidly along aligned fibers than unaligned fibers, as previously reported. Overall, our paper provides an easier, more quantitative and quicker way to quantify fiber orientation and alignment, and presents a platform in studying effects of matrix and cellular properties on fiber alignment in complex 3D environments.     

Inducible Nitric Oxide Synthase Promoter Haplotypes and Residential Traffic-Related Air Pollution Jointly Influence Exhaled Nitric Oxide Level in Children

BackgroundExhaled nitric oxide (FeNO), a biomarker of airway inflammation, predicts asthma risk in children. We previously found that the promoter haplotypes in inducible nitric oxide synthase (NOS2) and exposure to residential traffic independently influence FeNO level. Because NOS2 is inducible by environmental exposures such as traffic-related exposure, we tested the hypothesis that common NOS2 promoter haplotypes modulate the relationship between residential traffic-related exposure and FeNO level in children.MethodsIn a cross-sectional population-based study, subjects (N = 2,457; 7–11 year-old) were Hispanic and non-Hispanic white children who participated in the Southern California Children’s Health Study and had FeNO measurements. For residential traffic, lengths of local roads within circular buffers (50m, 100m and 200m radii around homes) around the subjects’ homes were estimated using geographic information system (GIS) methods. We interrogated the two most common NOS2 promoter haplotypes that were found to affect FeNO level.ResultsThe relationship between local road lengths within 100m and 200m circular buffers and FeNO level varied significantly by one of the NOS2 promoter haplotypes (P-values for interaction between road length and NOS2 promoter haplotype = 0.02 and 0.03, respectively). In children who had ≤250m of local road lengths within 100m buffer around their homes, those with two copies of the haplotype had significantly lower FeNO (adjusted geometric mean = 11.74ppb; 95% confidence intervals (CI): 9.99 to 13.80) than those with no copies (adjusted geometric mean = 15.28ppb; 95% CI: 14.04 to 16.63) with statistically significant trend of lower FeNO level with increasing number of haplotype copy (P-value for trend = 0.002). In contrast, among children who had >250m of local road lengths within 100m buffer, FeNO level did not significantly differ by the haplotype copy-number (P-value for trend = 0.34). Similar interactive effects of this haplotype and local road lengths within 200m buffer on FeNO were also observed.ConclusionsHigher exposure from residential traffic nullifies the protective effect of one common NOS2 promoter haplotype on FeNO level. Regulation of traffic-related pollution may protect children’s respiratory health.     

Metabolomics and Incidence of Atrial Fibrillation in African Americans: The Atherosclerosis Risk in Communities (ARIC) Study

Background

Atrial fibrillation (AF) is a common arrhythmia. Application of metabolomic approaches, which may identify novel pathways and biomarkers of disease risk, to a longitudinal epidemiologic study of AF has been limited.

Methods

We determined the prospective association of 118 serum metabolites identified through untargeted metabolomics profiling with the incidence of newly-diagnosed AF in 1919 African-American men and women from the Atherosclerosis Risk in Communities study without AF at baseline (1987–1989). Incident AF cases through 2011 were ascertained from study electrocardiograms, hospital discharge codes, and death certificates.

Results

During a median follow-up of 22 years, we identified 183 incident AF cases. In Cox proportional hazards models adjusted for age, sex, smoking, body mass index, systolic blood pressure, use of antihypertensive medication, diabetes, prevalent heart failure, prevalent coronary heart disease, and kidney function, two conjugated bile acids (glycolithocholate sulfate and glycocholenate sulfate) were significantly associated with AF risk after correcting for multiple comparisons (p<0.0004). Multivariable-adjusted hazard ratios (95% confidence intervals) of AF were 1.22 (1.12–1.32) for glycolithocholate sulfate and 1.22 (1.10–1.35) for glycocholenate sulfate per 1-standard deviation higher levels. Associations were not appreciably different after additional adjustment for alcohol consumption or concentrations of circulating albumin and liver enzymes.

Conclusion

We found an association of higher levels of two bile acids with an increased risk of AF, pointing to a potential novel pathway in AF pathogenesis. Replication of results in independent studies is warranted.     

A Unified Framework for Creating Domain Dependent Polarity Lexicons from User Generated Reviews

The exponential increase in the explosion of Web-based user generated reviews has resulted in the emergence of Opinion Mining (OM) applications for analyzing the users’ opinions toward products, services, and policies. The polarity lexicons often play a pivotal role in the OM, indicating the positivity and negativity of a term along with the numeric score. However, the commonly available domain independent lexicons are not an optimal choice for all of the domains within the OM applications. The aforementioned is due to the fact that the polarity of a term changes from one domain to other and such lexicons do not contain the correct polarity of a term for every domain. In this work, we focus on the problem of adapting a domain dependent polarity lexicon from set of labeled user reviews and domain independent lexicon to propose a unified learning framework based on the information theory concepts that can assign the terms with correct polarity (+ive, -ive) scores. The benchmarking on three datasets (car, hotel, and drug reviews) shows that our approach improves the performance of the polarity classification by achieving higher accuracy. Moreover, using the derived domain dependent lexicon changed the polarity of terms, and the experimental results show that our approach is more effective than the base line methods.     

Effects of Porosity and Mixed Convection on MHD Two Phase Fluid Flow in an Inclined Channel

The present study deals with the flow and heat transfer analysis of two immiscible fluids in an inclined channel embedded in a porous medium. The channel is divided in two phases such that a third grade fluid occupies the phase I and a viscous fluid occupies the phase II. Both viscous and third grade fluids are electrically conducting. A constant magnetic field is imposed perpendicular to the channel walls. The mathematical model is developed by using Darcy''s and modified Darcy''s laws for viscous and third grade fluids respectively. The transformed ordinary differential equations are solved numerically using a shooting method. The obtained results are presented graphically and influence of emerging parameters is discussed in detail.     

Immune Derangements in Patients with Myelofibrosis: The Role of Treg,Th17, and sIL2Rα

Myelofibrosis (MF), including primary myelofibrosis, post-essential thrombocythemia MF, and post-polycythemia vera MF, has been reported to be associated with autoimmune phenomena. IMiDs have been reported to be effective in some patients with MF, presumably for their immune-modulator effects. We therefore sought to elucidate the immune derangements in patients with MF. We found no differences in T regulatory cells (Treg) and T helper 17 (Th17) cells in MF patients and normal healthy controls. However, we found significantly elevated soluble interleukin 2 alpha (sIL2Rα) in MF patients compared to those with other myeloproliferative neoplasm diseases and normal healthy controls. Our studies with MF patients further revealed that Treg cells were the predominant cells producing sIL2Rα. sIL2Rα and IL2 complex induced the formation of Treg cells but not the formation of Th1 or Th17 cells. sIL2Rα induced CD8⁺ T cell proliferation in the presence of Treg cells. Monocytes or neutrophils had no effect on the production of sIL2Rα by Treg cells. Furthermore, we found plasma sIL2Rα levels were correlated to the auto-immune serology in MPN patients and ruxolitinib significantly inhibits the sIL2Rα production by the Treg cells in MF patients which may explain the effects of ruxolitinib on the relief of constitutional symptoms. All these findings suggest that sIL2Rα likely plays a significant role in autoimmune phenomena seen in patients with MF. Further studies of immune derangement may elucidate the mechanism of IMiD, and exploration of immune modulators may prove to be important for treating myelofibrosis.     

A 3-Component Mixture of Rayleigh Distributions: Properties and Estimation in Bayesian Framework

To study lifetimes of certain engineering processes, a lifetime model which can accommodate the nature of such processes is desired. The mixture models of underlying lifetime distributions are intuitively more appropriate and appealing to model the heterogeneous nature of process as compared to simple models. This paper is about studying a 3-component mixture of the Rayleigh distributionsin Bayesian perspective. The censored sampling environment is considered due to its popularity in reliability theory and survival analysis. The expressions for the Bayes estimators and their posterior risks are derived under different scenarios. In case the case that no or little prior information is available, elicitation of hyperparameters is given. To examine, numerically, the performance of the Bayes estimators using non-informative and informative priors under different loss functions, we have simulated their statistical properties for different sample sizes and test termination times. In addition, to highlight the practical significance, an illustrative example based on a real-life engineering data is also given.