Exploring new subgroups for irritable bowel syndrome using a machine learning algorithm.

Irritable bowel syndrome (IBS) is a complicated gut-brain axis disorder that has typically been classified into subgroups based on the major abnormal stool consistency and frequency. The presence of components other than lower gastrointestinal (GI) symptoms, such as psychological burden, has also been observed in IBS manifestations. The purpose of this research is to redefine IBS subgroups based on upper GI symptoms and psychological factors in addition to lower GI symptoms using an unsupervised machine learning algorithm. The clustering of 988 individuals who met the Rome III criteria for diagnosis of IBS was performed using a mixed-type data clustering algorithm. Nine sub-groups emerged from the proposed clustering: (I) High diarrhea, pain, and psychological burden, (II) High upper GI, moderate lower GI, and psychological burden, (III) High psychological burden and moderate overall GI, (IV) High constipation, moderate upper GI, and high psychological burden, (V) moderate constipation and low psychological burden, (VI) High diarrhea and moderate psychological burden, (VII) moderate diarrhea and low psychological burden, (VIII) Low overall GI, and psychological burden, (IX) Moderate lower GI, and low psychological burden. The proposed procedure led to the discovery of new homogeneous clusters in addition to certain well-known Rome sub-types for IBS.

Hypoxic burden to guide CPAP treatment allocation in patients with obstructive sleep apnoea: a post hoc study of the ISAACC trial.

BACKGROUND: Hypoxic burden (HB) has emerged as a strong predictor of cardiovascular risk in obstructive sleep apnoea (OSA). We aimed to assess the potential of HB to predict the cardiovascular benefit of treating OSA with continuous positive airway pressure (CPAP). METHODS: This was a post hoc analysis of the ISAACC trial (ClinicalTrials.gov: NCT01335087) including non-sleepy patients with acute coronary syndrome (ACS) diagnosed with OSA (apnoea-hypopnoea index ≥15 events·h-1) by respiratory polygraphy. Patients were randomised to CPAP or usual care and followed for a minimum of 1 year. HB was calculated as the total area under all automatically identified desaturations divided by total sleep time. Patients were categorised as having high or low baseline HB according to the median value (73.1%min·h-1). Multivariable Cox regression models were used to assess whether the effect of CPAP on the incidence of cardiovascular outcomes was dependent on the baseline HB level. RESULTS: The population (362 patients assigned to CPAP and 365 patients assigned to usual care) was middle-aged (mean age 59.7 years), overweight/obese and mostly male (84.5%). A significant interaction was found between the treatment arm and the HB categories. In the high HB group, CPAP treatment was associated with a significant reduction in the incidence of cardiovascular events (HR 0.57, 95% CI 0.34-0.96). In the low HB group, CPAP-treated patients exhibited a trend toward a higher risk of cardiovascular outcomes than those receiving usual care (HR 1.33, 95% CI 0.79-2.25). The differential effect of the treatment depending on the baseline HB level followed a dose-response relationship. CONCLUSION: In non-sleepy ACS patients with OSA, high HB levels were associated with a long-term protective effect of CPAP on cardiovascular prognosis.

Re-investigation of functional gastrointestinal disorders utilizing a machine learning approach.

BACKGROUND: Functional gastrointestinal disorders (FGIDs), as a group of syndromes with no identified structural or pathophysiological biomarkers, are currently classified by Rome criteria based on gastrointestinal symptoms (GI). However, the high overlap among FGIDs in patients makes treatment and identifying underlying mechanisms challenging. Furthermore, disregarding psychological factors in the current classification, despite their approved relationship with GI symptoms, underlines the necessity of more investigation into grouping FGID patients. We aimed to provide more homogenous and well-separated clusters based on both GI and psychological characteristics for patients with FGIDs using an unsupervised machine learning algorithm. METHODS: Based on a cross-sectional study, 3765 (79%) patients with at least one FGID were included in the current study. In the first step, the clustering utilizing a machine learning algorithm was merely executed based on GI symptoms. In the second step, considering the previous step's results and focusing on the clusters with a diverse combination of GI symptoms, the clustering was re-conducted based on both GI symptoms and psychological factors. RESULTS: The first phase clustering of all participants based on GI symptoms resulted in the formation of pure and non-pure clusters. Pure clusters exactly illustrated the properties of most pure Rome syndromes. Re-clustering the members of the non-pure clusters based on GI and psychological factors (i.e., the second clustering step) resulted in eight new clusters, indicating the dominance of multiple factors but well-discriminated from other clusters. The results of the second step especially highlight the impact of psychological factors in grouping FGIDs. CONCLUSIONS: In the current study, the existence of Rome disorders, which were previously defined by expert opinion-based consensus, was approved, and, eight new clusters with multiple dominant symptoms based on GI and psychological factors were also introduced. The more homogeneous clusters of patients could lead to the design of more precise clinical experiments and further targeted patient care.

Hypoxic Burden Based on Automatically Identified Desaturations Is Associated with Adverse Health Outcomes.

Rationale: Recent studies have shown that sleep apnea-specific intermittent hypoxemia quantified by the hypoxic burden (HB) predicted cardiovascular disease (CVD)-related mortality in community-based and clinical cohorts. Calculation of HB is based on manual scoring of hypopneas and apneas, which is time-consuming and prone to interscorer variability. Objective: To validate a novel method to quantify the HB that is based on automatically scored desaturations. Methods: The sample included 5,655 middle-aged or older adults from the Sleep Heart Health Study (52.8% women; age, 63.2 ± 11.3 yr). The original HB method was based on a subject-specific search window obtained from an ensemble average of oxygen saturation signals (as measured by pulse oximetry) and synchronized with respect to the termination of scored respiratory events. In this study, however, the search window was obtained from ensemble average of oxygen saturation signals that synchronized with respect to the minimum of all automatically identified desaturations (⩾2% and other thresholds, including 3% and 4%, in sensitivity analyses). The time interval between the two maxima around the minimum saturation was defined as the search window. The oximetry-derived HB (HBOxi) was defined as the total area under all desaturation curves (restricted by the search window) divided by the total sleep time. Logistic and Cox regression models assessed the adjusted odds ratio (aOR)/hazard ratio of excessive daytime sleepiness (EDS), hypertension (HTN), and CVD mortality per 1-standard deviation increase in HBOxi after adjusting for several covariates and confounders. Results: The Spearman's rank correlation between HB (median [interquartile range], 34.4 [18.4-59.8] % min/h) and HBOxi (median [interquartile range], 34.5 [21.6-53.8] % min/h) was 0.81 (P < 0.001). Similar to HB, HBOxi was significantly associated with EDS (aOR [95% confidence interval (CI)], 1.17 [1.09-1.26] per standard deviation), HTN (aOR [95% CI], 1.13 [1.05-1.21]), and CVD mortality (adjusted hazard ratio [95% CI], 1.15 [1.01-1.30]) in fully adjusted models. Conclusions: The HBOxi was highly correlated with the HB based on manually scored apneas and hypopneas and was associated with EDS, HTN, and CVD mortality with similar effect sizes as previously reported. This method could be incorporated into wearable technology that accurately records oxygen saturation signals.

Whole exome sequencing identified a novel LAMA2 frameshift variant causing merosin-deficient congenital muscular dystrophy in a patient with cardiomyopathy, and autism-like behavior.

Muscular dystrophy (MD) is a group of multiple muscle diseases, which causes severely impaired motor ability, degeneration and dysfunctions in the musculoskeletal system, respiratory failure and feeding difficulties. LAMA2-related MD is caused by pathogenic variants in the LAMA2 gene, encoding laminin a2 chain, a component of the skeletal muscle extracellular matrix protein laminin-α2ß1γ1. We performed clinical examination and molecular genetic analysis in a patient with congenital MD (CMD), and autism-like phenotype. We performed whole exome sequencing (WES) to find possible genetic etiology of CMD in an Iranian non-consanguineous patient. The pathogenicity of the variants was assessed using various Bioinformatics tools. American College of Medical Genetics and Genomics (ACMG) guidelines were used to interpret the variant and Sanger sequencing in the patient and her family was applied for the confirmation of the variant. WES results showed a novel frameshift homozygous variant (p.Tyr1313LeufsTer4) in the LAMA2 gene leading to the CMD phenotype. This variant resides in a highly conserved region and was found to be co-segregating in the family. It fulfils the criteria of being pathogenic. We successfully identified a novel LAMA2 pathogenic variant in an Iranian patient suffering from CMD and autism using WES. Identification of disease-causing variant in autosomal recessive disorders such as CMD can be useful in genetic counseling, prenatal diagnosis, and predicting prognosis of the disease.

Using Classification and K-means Methods to Predict Breast Cancer Recurrence in Gene Expression Data.

Background: Breast cancer is a type of cancer that starts in the breast tissue and affects about 10% of women at different stages of their lives. In this study, we applied a new method to predict recurrence in biological networks made from gene expression data. Method: The method includes the steps such as data collection, clustering, determining differentiating genes, and classification. The eight techniques consist of random forest, support vector machine and neural network, randomforest + k-means, hidden markov model, joint mutual information, neural network + k-means and suportvector machine + k-menas were implemented on 12172 genes and 200 samples. Results: Thirty genes were considered as differentiating genes which used for the classification. The results showed that random forest + k-means get better performance than other techniques. The two techniques including neural network + k-means and random forest + k-means performed better than other techniques in identifying high risk cases. Conclusion: Thirty of 12,172 genes are considered for classification that the use of clustering has improved the classification techniques performance.

Predicting deleterious missense genetic variants via integrative supervised nonnegative matrix tri-factorization.

Among an assortment of genetic variations, Missense are major ones which a small subset of them may led to the upset of the protein function and ultimately end in human diseases. Various machine learning methods were declared to differentiate deleterious and benign missense variants by means of a large number of features, including structure, sequence, interaction networks, gene disease associations as well as phenotypes. However, development of a reliable and accurate algorithm for merging heterogeneous information is highly needed as it could be captured all information of complex interactions on network that genes participate in. In this study we proposed a new method based on the non-negative matrix tri-factorization clustering method. We outlined two versions of the proposed method: two-source and three-source algorithms. Two-source algorithm aggregates individual deleteriousness prediction methods and PPI network, and three-source algorithm incorporates gene disease associations into the other sources already mentioned. Four benchmark datasets were employed for internally and externally validation of both algorithms of our predictor. The results at all datasets confirmed that, our method outperforms most state of the art variant prediction tools. Two key features of our variant effect prediction method are worth mentioning. Firstly, despite the fact that the incorporation of gene disease information at three-source algorithm can improve prediction performance by comparison with two-source algorithm, our method did not hinder by type 2 circularity error unlike some recent ensemble-based prediction methods. Type 2 circularity error occurs when the predictor annotates variants on the basis of the genes located on. Secondly, the performance of our predictor is superior over other ensemble-based methods for variants positioned on genes in which we do not have enough information about their pathogenicity.

Analysis of sequential ultrasound frames for the measurement of hemodynamic stresses, critical bent buckling pressure, and critical buckling torque of human common carotid atherosclerosis.

BACKGROUND: Structural properties of the arterial wall are important diagnostic parameters. The current study aimed at investigating the hemodynamic properties and intima-media thickness changes of the common carotid artery in human subjects with atherosclerosis in order to determine the relationships between these indices. METHODS: This study presented methods to detect instantaneous changes in the lumen diameter, intima media thickness, longitudinal movement and acceleration, and velocity of the left side of common carotid artery. These parameters were measured in 155 male patients, categorized into control (n = 42), mild (n = 39), moderate (n = 37), and severe (n = 37) carotid stenosis groups by B-mode and Doppler ultrasonography. Extracted parameters were used to estimate the biomechanical properties of arteries, including radial strain, arterial stiffness index, Young's elastic modulus, circumferential stress, shear stress, axial stress, critical bent buckling pressure, and critical buckling torque. FINDINGS: All biomechanical parameters of common carotid artery were significantly different in patients with mild, moderate, and severe stenosis, compared to the control group (P < 0.05). Moreover, the current results showed a significant correlation between intima media thickness and non-intima media thickness-based biomechanical indices including circumferential strain, stiffness index, and shear stress in different stenosis groups (P < 0.05). INTERPRETATION: We concluded that the conventional and new indicators such as axial stress, critical bent buckling pressure, critical buckling torque could be useful for evaluating atherosclerosis development and also, may provide more information for physicians and interventional radiologists in designing strategies for decreasing risk in interventional treatment such as stent replacement and differentiation of vulnerable plaques.

Genetic variant effect prediction by supervised nonnegative matrix tri-factorization.

Discriminating between deleterious and neutral mutations among numerous non-synonymous single nucleotide variants (nsSNVs) that may be observed through whole exome sequencing (WES) is considered a great challenge. In this regard, many machine learning methods have been developed for the prediction of variant consequences based on the analysis of either protein amino acid sequences or protein structures or their integration with features extracted from various gene level data and phenotype information. Due to the availability of a high number of features and heterogeneity of sources, implementing a suitable integration method plays an important role in predictive models. In this study, we proposed a novel supervised nonnegative matrix tri-factorization (sNMTF) algorithm to integrate current variant prediction scores into the gene level data and disease networks. In this regard, a new feature space was constructed by the integration of all input data using sNMTF to provide appropriate inputs for training a classifier. For the assessment of the proposed model, we utilized two benchmark datasets. The first one contained 11 207 deleterious and 19 839 neutral nsSNPs, whereas for the other dataset we used 4416 and 4960 deleterious and neutral nsSNPs, respectively. In general, the evaluation of our proposed supervised NMTF method on both datasets indicated that, in comparison with the existing nsSNV effect prediction approaches, regardless of whether they are ensemble-based or not, our method exhibited a better performance, which resulted in a higher prediction accuracy on average of 15% than other ensemble scores. In addition, excluding any kind of data that were integrated into the final model led to a substantial decrease in deleterious variant prediction. The proposed model can be used as an extensible framework for integrating more hetergeneous sources.

Selection of Optimal Bioinformatic Tools and Proper Reference for Reducing the Alignment Error in Targeted Sequencing Data.

BACKGROUND: Careful design in the primary steps of a next-generation sequencing study is critical for obtaining successful results in downstream analysis. METHODS: In this study, a framework is proposed to evaluate and improve the sequence mapping in targeted regions of the reference genome. In this regard, simulated short reads were produced from the coding regions of the human genome and mapped to a Customized Target-Based Reference (CTBR) by the alignment tools that have been introduced recently. The short reads produced by different sequencing technologies aligned to the standard genome and also CTBR with and without well-defined mutation types where the amount of unmapped and misaligned reads and runtime was measured for comparison. RESULTS: The results showed that the mapping accuracy of the reads generated from Illumina Hiseq2500 using Stampy as the alignment tool whenever the CTBR was used as reference was significantly better than other evaluated pipelines. Using CTBR for alignment significantly decreased the mapping error in comparison to other expanded or more limited references. While intentional mutations were imported in the reads, Stampy showed the minimum error of 1.67% using CTBR. However, the lowest error obtained by stampy too using whole genome and one chromosome as references was 3.78% and 20%, respectively. Maximum and minimum misalignment errors were observed on chromosome Y and 20, respectively. CONCLUSION: Therefore using the proposed framework in a clinical targeted sequencing study may lead to predict the error and improve the performance of variant calling regarding the genomic regions targeted in a clinical study.

Using hidden Markov model to predict recurrence of breast cancer based on sequential patterns in gene expression profiles.

A new approach is presented to predict breast cancer recurrence through gene expression profiles using hidden Markov models (HMM). In this regard, 322 genes were selected from 44 published gene lists related to breast cancer prognosis. Afterwards, using gene set enrichment analysis, 922 gene sets were found from subsets of genes with the same biological meaning. In order to extract the sequential patterns from gene expression data, we ranked the gene sets using appropriate criteria and used HMM in which the ranked gene sets considered as observation sequences and hidden states represented priority of gene sets for discriminating between expression profiles. In this experiment, seven publicly available microarray datasets, including 1271 breast tumor samples, were used to classify cancer patients into two groups according to risk of recurrence. Our experiments indicated the greater performance and more robustness of the proposed model compared with other widely used classification methods.

Vascular deformation in human atherosclerotic carotid artery evaluated by 2D analysis of ultrasonography.

OBJECTIVES: Common carotid artery (CCA) remodelling in the atherosclerosis process is an inherent necessary element that decreases the progress of significant lumen compromise. The present study used a semi-automated method to assess relationships of intima-media thickness (IMT), lumen diameter (LD) and inter-adventitial diameter (IAD) using ultrasound B-mode images of atherosclerotic carotid artery. METHODS: In the cross-sectional study, 120 male subjects (age range: 40-60 years) were classified into four research groups namely control, mild, moderate, and severe stenosis. The maximum near and far wall IMT, mean of both walls' IMT and IAD, and also LD of the left CCA were extracted for all participants. Pearson correlation coefficient was utilized to investigate relationships of IMT, LD, and IAD. RESULTS: Results revealed that the maximum far and near wall IMT, mean of both walls' IMT and IAD in the CCA were significantly different in stenosis patients and the control group (p< 0.001). However, there were no significant differences among the four studied groups in terms of LD of CCA (p = 0.65). There was a stronger correlation between mean of both walls' IMT and IAD in comparison with mean far wall IMT and IAD (p < 0.001). CONCLUSIONS: Results indicated that changes of IAD in the left CCA were associated with carotid deformation, and thus it can be considered as a predictor of atherosclerosis process.

Design and Implementation of a Customable Automatic Vehicle Location System in Ambulances and Emergency Vehicle Systems.

BACKGROUND: Automatic vehicle location (AVL) refers to a system that calculates the geographical location of any vehicle, i.e., latitude and longitude. Vehicle location information about one or more moving vehicles can be stored in the internal memory and accessed when vehicles are available (offline tracking). It is also possible to get location information on a real-time basis (online tracking). The real-time tracking systems designed to date may incorporate three devices: global positioning system (GPS), geographic information system, and cellular communication platforms that may be either a general packet radio service (GPRS) or any private and local radiofrequency network. METHODS: The GPS-based navigation system has been designed so as to allow for user-friendly real-time tracking applications for any emergency vehicles like ambulances. First, GPS coordinates are obtained from the SIM908 module and sent via to a server transmission control protocol/internet protocol. Server codes, which are written in C#, load Google map to show real-time location. RESULTS: We designed online tracking AVL hardware in the two simple and advanced versions. The latter enables both the ambulance driver and the data center to monitor path real-time besides enabling the vehicle driver to receive and make calls and send or receive messages. The former only sends latitude and longitude to the data server continuously, and the path travelled by vehicle is displayed. CONCLUSION: SIM908 integrates GSM, GPRS, and GPS in one package. It can be a proper choice for real-time economic tracking systems despite its low accuracy in finding geolocations.

A novel feature selection method for microarray data classification based on hidden Markov model.

In this paper, a novel approach is introduced for integrating multiple feature selection criteria by using hidden Markov model (HMM). For this purpose, five feature selection ranking methods including Bhattacharyya distance, entropy, receiver operating characteristic curve, t-test, and Wilcoxon are used in the proposed topology of HMM. Here, we presented a strategy for constructing, learning and inferring the HMM for gene selection, which led to higher performance in cancer classification. In this experiment, three publicly available microarray datasets including diffuse large B-cell lymphoma, leukemia cancer and prostate were used for evaluation. Results demonstrated the higher performance of the proposed HMM-based gene selection against Markov chain rank aggregation and using individual feature selection criterion, where applied to general classifiers. In conclusion, the proposed approach is a powerful procedure for combining different feature selection methods, which can be used for more robust classification in real world applications.

Physicochemical Position-Dependent Properties in the Protein Secondary Structures

Background: Establishing theories for designing arbitrary protein structures is complicated and depends on understanding the principles for protein folding, which is affected by applied features. Computer algorithms can reach high precision and stability in computationally designed enzymes and binders by applying informative features obtained from natural structures. Methods: In this study, a position-specific analysis of secondary structures (α-helix, ß-strand, and tight turn) was performed to reveal novel features for protein structure prediction and protein design. Results: Our results showed that the secondary structures in the N-termini region tend to be more compact than C-termini. Decoying periodicity in length and distribution of amino acids in α-helices is deciphered using the curve-fitting methods. Compared with α-helix, ß-strands do not show distinct periodicities in length. Also, significant differences in position-dependent distribution of physicochemical properties are shown in secondary structures. Conclusion: Position-specific propensities in our study underline valuable parameters that could be used by researchers in the field of structural biology, particularly protein design through site-directed mutagenesis.

Applying Two Different Bioinformatic Approaches to Discover Novel Genes Associated with Hereditary Hearing Loss via Whole-Exome Sequencing: ENDEAVOUR and HomozygosityMapper.

BACKGROUND: Hearing loss (HL) is a highly prevalent heterogeneous deficiency of sensory-neural system with involvement of several dozen genes. Whole-exome sequencing (WES) is capable of discovering known and novel genes involved with HL. MATERIALS AND METHODS: Two pedigrees with HL background from Khuzestan province of Iran were selected. Polymerase chain reaction-sequencing of GJB2 and homozygosity mapping of 16 DFNB loci were performed. One patient of the first and two affected individuals from the second pedigree were subjected to WES. The result files were analyzed using tools on Ubuntu 16.04. Short reads were mapped to reference genome (hg19, NCBI Build 37). Sorting and duplication removals were done. Variants were obtained and annotated by an online software tool. Variant filtration was performed. In the first family, ENDEAVOUR was applied to prioritize candidate genes. In the second family, a combination of shared variants, homozygosity mapping, and gene expression were implemented to launch the disease-causing gene. RESULTS: GJB2 sequencing and linkage analysis established no homozygosity-by-descent at any DFNB loci. Utilizing ENDEAVOUR, BBX: C.C857G (P.A286G), and MYH15: C.C5557T (P.R1853C) were put forward, but none of the variants co-segregated with the phenotype. Two genes, UNC13B and TRAK1, were prioritized in the homozygous regions detected by HomozygosityMapper. CONCLUSION: WES is regarded a powerful approach to discover molecular etiology of Mendelian inherited disorders, but as it fails to enrich GC-rich regions, incapability of capturing noncoding regulatory regions and limited specificity and accuracy of copy number variations detection tools from exome data, it is assumed an insufficient procedure.

An Optimized Framework for Cancer Prediction Using Immunosignature.

BACKGROUND: Cancer is a complex disease which can engages the immune system of the patient. In this regard, determination of distinct immunosignatures for various cancers has received increasing interest recently. However, prediction accuracy and reproducibility of the computational methods are limited. In this article, we introduce a robust method for predicting eight types of cancers including astrocytoma, breast cancer, multiple myeloma, lung cancer, oligodendroglia, ovarian cancer, advanced pancreatic cancer, and Ewing sarcoma. METHODS: In the proposed scheme, at first, the database is normalized with a dictionary of normalization methods that are combined with particle swarm optimization (PSO) for selecting the best normalization method for each feature. Then, statistical feature selection methods are used to separate discriminative features and they were further improved by PSO with appropriate weights as the inputs of the classification system. Finally, the support vector machines, decision tree, and multilayer perceptron neural network were used as classifiers. RESULTS: The performance of the hybrid predictor was assessed using the holdout method. According to this method, the minimum sensitivity, specificity, precision, and accuracy of the proposed algorithm were 92.4 ± 1.1, 99.1 ± 1.1, 90.6 ± 2.1, and 98.3 ± 1.0, respectively, among the three types of classification that are used in our algorithm. CONCLUSION: The proposed algorithm considers all the circumstances and works with each feature in its special way. Thus, the proposed algorithm can be used as a promising framework for cancer prediction with immunosignature.

Dual Function of Gold Nanoparticles in Synergism with Mitoxantrone and Microwave Hyperthermia Against Melanoma Cells

Background: This study was performed to evaluate any synergetic effects of mitoxantrone (MX) and gold nanoparticles (GNPs) as dual therapeutic approach, along with microwave (MW) hyperthermia for melanoma cancer. Methods: Various tests were performed on the DFW melanoma cell line in the presence of MX and different concentrations of GNPs, with and without MW irradiation. MTT [3-(4,5-dimethylthiazol­2-yl)-2,5-iphenyltetrazolium bromide] assays were conducted to evaluate the effectiveness of the used therapeutic methods in terms of cell survival. Relative lethal synergism (RLS) was calculated as the ratio of cell death following hyperthermia in the presence of a treatment agent to that after applying hyperthermia in the absence of the same treatment agent. Results: Results showed MX and GNPs under MW irradiation to provide maximum cell death (P < 0.001 compared to the other groups). The mean RLS for MW hyperthermia along with the MX-GNP combination was 4.14, whereas in the absence of GNP the value for MX chemotherapy was 0.94. Conclusion: MX chemotherapy in the presence of different concentrations of GNP did not alter cell survival as compared to in its absence.

A novel feature ranking method for prediction of cancer stages using proteomics data.

Proteomic analysis of cancers' stages has provided new opportunities for the development of novel, highly sensitive diagnostic tools which helps early detection of cancer. This paper introduces a new feature ranking approach called FRMT. FRMT is based on the Technique for Order of Preference by Similarity to Ideal Solution method (TOPSIS) which select the most discriminative proteins from proteomics data for cancer staging. In this approach, outcomes of 10 feature selection techniques were combined by TOPSIS method, to select the final discriminative proteins from seven different proteomic databases of protein expression profiles. In the proposed workflow, feature selection methods and protein expressions have been considered as criteria and alternatives in TOPSIS, respectively. The proposed method is tested on seven various classifier models in a 10-fold cross validation procedure that repeated 30 times on the seven cancer datasets. The obtained results proved the higher stability and superior classification performance of method in comparison with other methods, and it is less sensitive to the applied classifier. Moreover, the final introduced proteins are informative and have the potential for application in the real medical practice.

Appraisal of different ultrasonography indices in patients with carotid artery atherosclerosis.

In this study a semi-automated image-processing based method was designed in which the parameters such as intima-media thickness (IMT), resistive index (RI), pulsatility index (PI), dicrotic notch index (DNI), and mean wavelet entropy (MWE) were evaluated in B-mode and Doppler ultrasound in patients presenting with carotid artery atherosclerosis. In a cross-sectional design, 144 men were divided into four groups of control, mild, moderate and severe stenosis subjects. In all individuals, far wall IMT, RI, PI, DNI, and MWE of the left common carotid artery (CCA) were extracted using the proposed method. Our findings showed that the maximum far wall IMT, RI, PI, DNI in the CCA were significantly different in the patients with mild, moderate, and severe stenosis compared to control group (p-value < 0.05), however, there were no significant differences in MWE among the four groups (p-value > 0.05). The proposed method can help physicians to better identify patients at risk of cardiovascular diseases.