Autoregressive and cepstral analyses of motor unit action potentials

Quantitative electromyographic signal analysis in the time domain for motor unit action potential (MUAP) classification and disease identification has been well documented over recent years. Considerable work has also been carried out in the frequency domain using classical power spectrum analysis techniques. Although MUAP autoregressive (AR) spectral analysis has been suggested as a diagnostic tool by a number of studies, it has not been thoroughly investigated yet. This work investigates the application of AR modeling and cepstral analysis for the diagnostic assessment of MUAPs recorded from normal (NOR) subjects and subjects suffering with motor neuron disease (MND) and myopathy (MYO). The following feature sets were extracted from the MUAP signal: (i) time domain measures, (ii) AR spectral measures, (iii) AR coefficients, and (iv) cepstral coefficients. Discriminative analysis of the individual features was carried out using the univariate and multiple covariance analysis methods. Both methods showed that: (i) the duration measure is the best discriminative feature among the time domain parameters, and (ii) the median frequency is the best discriminative feature among the AR spectral measures. Furthermore, the classification performance of the above four feature sets was investigated for three classes (NOR, MND and MYO) using artificial neural networks. Results showed that the highest diagnostic yield was obtained with the time domain measures followed by the cepstral coefficients, the AR spectral parameters, and the AR coefficients. In conclusion, MUAP autoregressive and cepstral analyses combined with time domain analysis provide useful information in the assessment of myopathology.     

An MLP-based feature subset selection for HIV-1 protease cleavage site analysis

ObjectiveIn recent years, several machine learning approaches have been applied to modeling the specificity of the human immunodeficiency virus type 1 (HIV-1) protease cleavage domain. However, the high dimensional domain dataset contains a small number of samples, which could misguide classification modeling and its interpretation. Appropriate feature selection can alleviate the problem by eliminating irrelevant and redundant features, and thus improve prediction performance.MethodsWe introduce a new feature subset selection method, FS-MLP, that selects relevant features using multi-layered perceptron (MLP) learning. The method includes MLP learning with a training dataset and then feature subset selection using decompositional approach to analyze the trained MLP. Our method is able to select a subset of relevant features in high dimensional, multi-variate and non-linear domains.ResultsUsing five artificial datasets that represent four data types, we verified the FS-MLP performance with seven other feature selection methods. Experimental results showed that the FS-MLP is superior at high dimensional, multi-variate and non-linear domains. In experiments with HIV-1 protease cleavage dataset, the FS-MLP selected a set of 14 highly relevant features among 160 original features. On a validation set of 131 test instances, classifiers that used the 14 features showed about 95% accuracy which outperformed other seven methods in terms of accuracy and the number of features.ConclusionsOur experimental results indicate that the FS-MLP is effective in analyzing multi-variate, non-linear and high dimensional datasets such as HIV-1 protease cleavage dataset. The 14 relevant features which were selected by the FS-MLP provide us with useful insights into the HIV-1 cleavage site domain as well. The FS-MLP is a useful method for computational sequence analysis in general.     

Exploring chronic airways disease patients’ perspectives on self-management topics

ObjectivesIn this study, we explored chronic airways disease (CAD) patients' responses to health literacy (HL) communication domain questions within disease self-management scenarios, as part of a larger CAD HL measurement tool development study.MethodsAdult asthma and chronic obstructive pulmonary disease (COPD) patients from specialty care respiratory clinics were initially presented with realistic disease management scenarios and asked to share information they would communicate. Participants’ responses were grouped into response categories that were reviewed and verified by key informants. A new cohort of CAD patients then responded to the same scenarios and had their answers placed into the developed response categories by trained interviewers.Results19 initial stage participants' responses informed response categories for the following self-management topics: Inhaler Use (n = 20); Prednisone Use (n = 30); Flu (Influenza) (n = 35); and Weather Forecasting & Air Quality Index (n = 29). 141 participants’ responses were categorised during the second stage.ConclusionsSpecialty care CAD patients displayed an understanding of key information to communicate across disease self-management topic. Our two-step, patient-driven approach may interest researchers investigating health-related communication from patients' perspectives.Practice implicationsFindings may illuminate potential areas to investigate communication gaps among CAD patients; further investigation is warranted among non-specialty care patients.     

Neural Network Ensemble Based CAD System for Focal Liver Lesions from B-Mode Ultrasound

A neural network ensemble (NNE) based computer-aided diagnostic (CAD) system to assist radiologists in differential diagnosis between focal liver lesions (FLLs), including (1) typical and atypical cases of Cyst, hemangioma (HEM) and metastatic carcinoma (MET) lesions, (2) small and large hepatocellular carcinoma (HCC) lesions, along with (3) normal (NOR) liver tissue is proposed in the present work. Expert radiologists, visualize the textural characteristics of regions inside and outside the lesions to differentiate between different FLLs, accordingly texture features computed from inside lesion regions of interest (IROIs) and texture ratio features computed from IROIs and surrounding lesion regions of interests (SROIs) are taken as input. Principal component analysis (PCA) is used for reducing the dimensionality of the feature space before classifier design. The first step of classification module consists of a five class PCA-NN based primary classifier which yields probability outputs for five liver image classes. The second step of classification module consists of ten binary PCA-NN based secondary classifiers for NOR/Cyst, NOR/HEM, NOR/HCC, NOR/MET, Cyst/HEM, Cyst/HCC, Cyst/MET, HEM/HCC, HEM/MET and HCC/MET classes. The probability outputs of five class PCA-NN based primary classifier is used to determine the first two most probable classes for a test instance, based on which it is directed to the corresponding binary PCA-NN based secondary classifier for crisp classification between two classes. By including the second step of the classification module, classification accuracy increases from 88.7 % to 95 %. The promising results obtained by the proposed system indicate its usefulness to assist radiologists in differential diagnosis of FLLs.     

Method of regulatory network that can explore protein regulations for disease classification

ObjectiveTo develop regulatory network to explore and model the regulatory relationships of protein biomarkers and classify different disease groups.MethodsRegulatory network is constructed to be a hopfield-like network with nodes representing biomarkers and directional connections to be regulations in between. The input to the network is the measured expression levels of biomarkers, and the output is the summation of regulatory strengths from other biomarkers. The network is optimized towards minimizing the energy function that is defined as the measure of the disagreement between the input and output of the network. To simulate more complicated regulations, a sigmoid kernel function is imposed on each node to construct a non-linear regulatory network.ResultsTwo datasets have been used as test beds, one dataset includes patients of nasopharyngeal carcinoma with different responses to chemotherapy drug, and the other consists of patients of severe acute respiratory syndrome, influenza, and control normals. The regulatory networks among protein biomarkers were reconstructed for different disease conditions in each dataset. We demonstrated our methods have better classification capability when comparing with conventional methods including Fisher linear discriminant (FLD), K-nearest neighborhood (KNN), linear support vector machines (linSVM) and radial basis function based support vector machines (rbfSVM).ConclusionThe derived networks can effectively capture the unique regulatory patterns of protein markers associated with different patient groups and hence can be used for disease classification. The discovered regulation relationships can potentially provide insights to revealing the molecular signaling pathways.In this paper, a novel technique of regulatory network is proposed on purpose of modeling biomarker regulations and classifying different disease groups. The network is composed of a certain number of nodes that are directionally connected in between in which nodes denote predictors and connections to be the regulation relationship. The network is optimized towards minimizing its energy function with biomarker expression data acquired from a specific patient group, thus the optimized network can model the regulatory relationship of biomarkers under the same circumstance. To simulate more complicated regulations, a sigmoid kernel function is imposed on each node to construct a non-linear regulatory network. The regulatory network can extract unique features of each disease condition, thus one immediate application of regulatory network is to classifying different diseases. We demonstrated that regulatory network is capable of performing disease classification through comparing with conventional methods including FLD, KNN, linSVM and rbfSVM on two protein datasets. We believe our method is promising in mining knowledge of protein regulations and be powerful for disease classification.     

A comparative study of computer-aided classification systems for focal hepatic lesions from B-mode ultrasound

Abstract

A comparative study of three computer-aided classification (CAC) systems for characterization of focal hepatic lesions (FHLs), such as cyst, hemangioma (HEM), hepatocellular carcinoma (HCC) and metastatic carcinoma (MET), along with normal (NOR) liver tissue is carried out in the present work. In order to develop efficient CAC systems a comprehensive and representative dataset consisting of B-mode ultrasound images with (1) typical and atypical cases of cyst, HEM and MET lesions, (2) small and large HCC lesions and (3) NOR liver cases have been used for designing K-nearest neighbour (KNN), probabilistic neural network (PNN) and a back propagation neural network (BPNN) classifiers. For differential diagnosis between atypical FHLs, expert radiologists often visualize the textural characteristics of regions inside and outside the lesion. Accordingly in the present work, texture features and texture ratio features are computed from regions inside and outside the lesions. A feature set consisting of 208 texture features (i.e. 104 texture features and 104 texture ratio features) is subjected to principal component analysis (PCA) for dimensionality reduction; it is observed that maximum accuracy of 87.7% is obtained for a PCA-BPNN-based CAC system in comparison to 86.1% and 85% as obtained by PCA-PNN and PCA-KNN-based CAC systems. The sensitivity of the proposed PCA-BPNN based CAC system for NOR, Cyst, HEM, HCC and MET cases is 82.5%, 96%, 93.3%, 90% and 82.2%, respectively. The sensitivity values with respect to typical, atypical, small HCC and large HCC cases are 85.9%, 88.1%, 100% and 87%, respectively. Keeping in view the comprehensive and representative dataset used for designing the classifier, the results obtained by the proposed PCA-BPNN-based CAC system are quite encouraging and indicate its usefulness to assist experienced radiologists for interpretation and diagnosis of FHLs.     

Pattern identification of biomedical images with time series: Contrasting THz pulse imaging with DCE-MRIs

ObjectiveWe provide a survey of recent advances in biomedical image analysis and classification from emergent imaging modalities such as terahertz (THz) pulse imaging (TPI) and dynamic contrast-enhanced magnetic resonance images (DCE-MRIs) and identification of their underlining commonalities.MethodsBoth time and frequency domain signal pre-processing techniques are considered: noise removal, spectral analysis, principal component analysis (PCA) and wavelet transforms. Feature extraction and classification methods based on feature vectors using the above processing techniques are reviewed. A tensorial signal processing de-noising framework suitable for spatiotemporal association between features in MRI is also discussed.ValidationExamples where the proposed methodologies have been successful in classifying TPIs and DCE-MRIs are discussed.ResultsIdentifying commonalities in the structure of such heterogeneous datasets potentially leads to a unified multi-channel signal processing framework for biomedical image analysis.ConclusionThe proposed complex valued classification methodology enables fusion of entire datasets from a sequence of spatial images taken at different time stamps; this is of interest from the viewpoint of inferring disease proliferation. The approach is also of interest for other emergent multi-channel biomedical imaging modalities and of relevance across the biomedical signal processing community.     

Multi-label classification of chronically ill patients with bag of words and supervised dimensionality reduction algorithms

ObjectiveThis research is motivated by the issue of classifying illnesses of chronically ill patients for decision support in clinical settings. Our main objective is to propose multi-label classification of multivariate time series contained in medical records of chronically ill patients, by means of quantization methods, such as bag of words (BoW), and multi-label classification algorithms. Our second objective is to compare supervised dimensionality reduction techniques to state-of-the-art multi-label classification algorithms. The hypothesis is that kernel methods and locality preserving projections make such algorithms good candidates to study multi-label medical time series.MethodsWe combine BoW and supervised dimensionality reduction algorithms to perform multi-label classification on health records of chronically ill patients. The considered algorithms are compared with state-of-the-art multi-label classifiers in two real world datasets. Portavita dataset contains 525 diabetes type 2 (DT2) patients, with co-morbidities of DT2 such as hypertension, dyslipidemia, and microvascular or macrovascular issues. MIMIC II dataset contains 2635 patients affected by thyroid disease, diabetes mellitus, lipoid metabolism disease, fluid electrolyte disease, hypertensive disease, thrombosis, hypotension, chronic obstructive pulmonary disease (COPD), liver disease and kidney disease. The algorithms are evaluated using multi-label evaluation metrics such as hamming loss, one error, coverage, ranking loss, and average precision.ResultsNon-linear dimensionality reduction approaches behave well on medical time series quantized using the BoW algorithm, with results comparable to state-of-the-art multi-label classification algorithms. Chaining the projected features has a positive impact on the performance of the algorithm with respect to pure binary relevance approaches.ConclusionsThe evaluation highlights the feasibility of representing medical health records using the BoW for multi-label classification tasks. The study also highlights that dimensionality reduction algorithms based on kernel methods, locality preserving projections or both are good candidates to deal with multi-label classification tasks in medical time series with many missing values and high label density.     

Polymorphisms of human platelet alloantigens HPA-1 and HPA-2 associated with severe coronary artery disease

ObjectivesInsofar as platelet membrane glycoprotein (GP) polymorphisms were identified as potential risk factors for coronary artery disease (CAD), we investigated the contribution of human platelet antigen (HPA)-1 (GPIIb/IIIa) and HPA-2 (GPIb/IX) alleles and haplotypes to CAD pathogenesis.MethodsStudy subjects comprised 247 middle-age CAD patients and 316 age-, gender-, and race-matched controls; HPA genotyping was performed by polymerase chain reaction with sequence specific primers.ResultsThe frequencies of HPA-1b (P<.001) and HPA-2b (P<.001) alleles and HPA-1a/1b (P<.001), HPA-1b/1b (P<.001), and HPA-2a/2b (P<.001) genotypes were higher in patients than control subjects. Select HPA haplotypes comprising the HPA-1b/2a (Pc=2.2×10^?4) and HPA-1b/2b (Pc=.001) haplotypes which were positively associated, and the HPA-1a/2a (Pc=3.2×10^?5) which was negatively associated with CAD, confer a disease susceptibility and protective nature to these haplotypes. Multivariate analysis confirmed the positive association of HPA-1b/2a [adjusted odds ratio (aOR)=3.63; 95% CI=2.42–5.43] and HPA-1b/2b (aOR=2.92; 95% CI=1.43–5.94) haplotypes with CAD, after adjustment for a number of covariates.ConclusionsOur results suggest that HPA-1/HPA-2 haplotypes may be considered to be a major risk factor for CAD in middle-aged Tunisians.     

Study of atrial activities for abnormality detection by phase rectified signal averaging technique

Abstract

Non-invasive detection of Atrial Fibrillation (AF) and Atrial Flutter (AFL) from ECG at the time of their onset can prevent forthcoming dangers for patients. In most of the previous detection algorithms, one of the steps includes filtering of the signal to remove noise and artefacts present in the signal. In this paper, a method of AF and AFL detection is proposed from ECG without the conventional filtering stage. Here Phase Rectified Signal Average (PRSA) technique is used with a novel optimized windowing method to achieve an averaged signal without quasi-periodicities. Both time domain and statistical features are extracted from a novel SQ concatenated section of the signal for non-linear Support Vector Machine (SVM) based classification. The performance of the proposed algorithm is tested with the MIT-BIH Arrhythmia database and good performance parameters are obtained, as indicated in the result section.     

Classification of pathologies by reduced sequential potential maps

Body surface potential mapping (BSPM) is an electrocardiographic measureing technique which produces the data as a series of three-dimensional maps. These maps are assumed to contain information which may help classify subjects for diagnostic purposes more effectively than standard ECGs. As quantitative classification of the complete sequences of maps is complex and cumbersome, the present study uses extracted features which characterise the data. The features, which have been presented and evaluated in a recent work, have been extracted after the maps were processed by a compression technique which conserved the spatial details of the maps. The compression by two-level thresholding converted the sequences of maps into sequences of annuli, from which the following features were extracted: time indices, velocity vector magnitude, loci in three-dimensional space of the centres of mass and cross-correlation coefficients between successive annuli in the sequence. Here, three different classification methods are applied to these features: statistical methods, the Fisher linear discriminant method and visual inspection. BSPMs from 54 subjects are used: 25 normal, 11 WPW syndrome and 18 CAD cases. It is found completely accurate classification of the subjects to their groups. The three-dimensional centre of mass is found to be the single best classifier; sucessfully categorising 20/25 of the normals 17/18 of the CAD patients and 11/11 of the WPW patients.     

Quantitative Assessment of Chest CT Patterns in COVID-19 and Bacterial Pneumonia Patients: a Deep Learning Perspective

BackgroundIt is difficult to distinguish subtle differences shown in computed tomography (CT) images of coronavirus disease 2019 (COVID-19) and bacterial pneumonia patients, which often leads to an inaccurate diagnosis. It is desirable to design and evaluate interpretable feature extraction techniques to describe the patient''s condition.MethodsThis is a retrospective cohort study of 170 confirmed patients with COVID-19 or bacterial pneumonia acquired at Yeungnam University Hospital in Daegu, Korea. The Lung and lesion regions were segmented to crop the lesion into 2D patches to train a classifier model that could differentiate between COVID-19 and bacterial pneumonia. The K-means algorithm was used to cluster deep features extracted by the trained model into 20 groups. Each lesion patch cluster was described by a characteristic imaging term for comparison. For each CT image containing multiple lesions, a histogram of lesion types was constructed using the cluster information. Finally, a Support Vector Machine classifier was trained with the histogram and radiomics features to distinguish diseases and severity.ResultsThe 20 clusters constructed from 170 patients were reviewed based on common radiographic appearance types. Two clusters showed typical findings of COVID-19, with two other clusters showing typical findings related to bacterial pneumonia. Notably, there is one cluster that showed bilateral diffuse ground-glass opacities (GGOs) in the central and peripheral lungs and was considered to be a key factor for severity classification. The proposed method achieved an accuracy of 91.2% for classifying COVID-19 and bacterial pneumonia patients with 95% reported for severity classification. The CT quantitative parameters represented by the values of cluster 8 were correlated with existing laboratory data and clinical parameters.ConclusionDeep chest CT analysis with constructed lesion clusters revealed well-known COVID-19 CT manifestations comparable to manual CT analysis. The constructed histogram features improved accuracy for both diseases and severity classification, and showed correlations with laboratory data and clinical parameters. The constructed histogram features can provide guidance for improved analysis and treatment of COVID-19.     

Angiopoietin-2 as a biomarker of non-ST-segment elevation myocardial infarction in patients with or without type 2 diabetes

IntroductionAngiopoietin-2 (Ang-2) is a novel marker of coronary artery disease (CAD) and diabetes (DM). The aim was to evaluate Ang-2 as a potential new biomarker of non-ST elevation myocardial infarction (NSTEMI) in patients with or without type 2 DM (T2DM).Material and methodsThis was a multi-center, prospective study that included 138 (males: 91/66%) consecutive patients hospitalized due to NSTEMI, T2DM, or different cardiac disorders. The subjects were divided into four study groups: group A: 28 patients with NSTEMI and T2DM; group B: 47 patients with NSTEMI without T2DM; group C: 31 patients with T2DM, without a history of CAD; group D: 32 patients as a control group. Patients with NSTEMI underwent urgent coronarography. Clinical characteristics including biomarkers (hs-CRP, hsTnT, NT-proBNP, VEGF, HbA_1c), SYNTAX SCORE, type of intervention (PCI vs. CABG), and number of implanted stents were taken into account in the analysis.ResultsSerum Ang-2 concentrations were significantly higher in patients with NSTEMI (group A: 1769 pg/ml; group B: 1757 pg/ml) and patients with T2DM (group C: 1993 pg/ml) as compared to the patients without CAD and without T2DM (group D: 866.8 pg/ml; p < 0.05). The prognostic accuracy of Ang-2 in NSTEMI diagnosis was determined with the area under the ROC curve (area under curve (AUC) = 0.63).ConclusionsAngiopoietin-2 serum concentration is elevated in the presence of NSTEMI in patients with and without T2DM and does not correspond to the degree of myocardial injury and hemodynamic status. Ang-2 remains elevated also in patients with T2DM without a history of CAD.     

Characterization of aspirin allergies in patients with coronary artery disease

BackgroundAspirin prevents coronary thrombosis and is used extensively in cardiovascular prophylaxis. However, patients with a prior history of an aspirin “reaction” are routinely denied this medication.ObjectiveTo characterize the clinical presentation of a cohort of patients with coronary artery disease (CAD) and aspirin reactions.MethodsBetween 2009 and 2012, using a retrospective computer analysis, information was collected on all patients within a county-wide health care system presenting with CAD and a prior history of aspirin reactions.ResultsOf 9,565 patients with CAD, a prior history of aspirin reactions was recorded in 142 patients. Of these 142 patients, 30 (21%) had histories compatible with cutaneous and/or respiratory reactions. The other patients described adverse effects to aspirin, mostly gastrointestinal intolerance and bleeding. Aspirin-induced anaphylaxis was recorded in patients but may have been misdiagnosed, describing instead respiratory hypersensitivity reactions. Of the 142 patients, only 34 (24%) were receiving daily cardiovascular prophylaxis with aspirin. Of 108 patients not receiving aspirin, 25 (17.6%) were prescribed clopidogrel.ConclusionHistories of aspirin reactions in patients with CAD are uncommon, occurring in only 1.5% of our study population. The 21% of patients with histories compatible with aspirin hypersensitivities can be challenged and, if the results are positive, successfully desensitized. Moreover, almost all patients with gastric intolerance to aspirin can be treated with aspirin and a proton pump inhibitor. However, both approaches, which result in restoration of cardiovascular prophylaxis, were seriously underused in our study population.     

Quantification of cardiac magnetic field orientation during ventricular de- and repolarization

We compared the stability and discriminatory power of different methods of determining cardiac magnetic field map (MFM) orientation within the context of coronary artery disease (CAD). In 27 healthy subjects and 24 CAD patients, multichannel magnetocardiograms were registered at rest. MFM orientation was determined during QT interval using: (a) locations of the positive and negative centres-of-gravity, (b) locations of the field extrema and (c) the direction of the maximum field gradient. Deviation from normal orientation quantified the ability of each approach to discriminate between healthy and CAD subjects. Although the course of orientation was similar for all methods, receiver operating characteristic analysis showed the best discrimination of CAD patients for the centre-of-gravity approach (area-under-the-curve = 86%), followed by the gradient (84%) and extrema (76%) methods. Consideration of methodological and discriminatory advantages with respect to noninvasive diagnosis of CAD suggests that the centres-of-gravity method is the most suited one.     

A practical reconstructed phase space approach for ECG arrhythmias classification

Abstract

Atrial and ventricular arrhythmias are symptoms of the main common causes of rapid death. The severity of these arrhythmias depends on their occurrence either within the atria or ventricles. These abnormalities of the heart activity may cause an immediate death or cause damage of the heart. In this paper, a new algorithm is proposed for the classification of life threatening cardiac arrhythmias including atrial fibrillation (AF), ventricular tachycardia (VT) and ventricular fibrillation (VF). The proposed technique uses a simple signal processing technique for analysing the non-linear dynamics of the ECG signals in the time domain. The classification algorithm is based upon the distribution of the attractor in the reconstructed phase space (RPS). The behaviour of the ECG signal in the reconstructed phase space is used to determine the classification features of the whole classifier. It is found that different arrhythmias occupy different regions in the reconstructed phase space. Three regions in the RPS are found to be more representative of the considered arrhythmias. Therefore, only three simple features are extracted to be used as classification parameters. To evaluate the performance of the presented classification algorithm, real datasets are obtained from the MIT database. A learning dataset is used to design the classification algorithm and a testing dataset is used to verify the algorithm. The algorithm is designed to guarantee achieving both 100% sensitivity and 100% specificity. The classification algorithm is validated by using 45 ECG signals spanning the considered life threatening arrhythmias. The obtained results show that the classification algorithm attains a sensitivity ranging from 85.7–100%, a specificity ranging from 86.7–100% and an overall accuracy of 95.55%.     

Severe Disease Activity Based on the Paris Classification Is Associated with the Development of Extraintestinal Manifestations in Korean Children and Adolescents with Ulcerative Colitis

BackgroundThere are limited data regarding the extraintestinal manifestations (EIMs) associated with pediatric inflammatory bowel disease (IBD) in Korea. We aimed to investigate the clinical features and factors associated with the development of EIMs in Korean children and adolescents with IBD.MethodsThis multicenter, retrospective study was conducted from 2010 to 2017. Baseline clinicodemographic, laboratory findings, disease activity, disease phenotypes, and EIMs were investigated.ResultsA total of 172 patients were included. One-hundred thirty-seven (79.7%) had Crohn''s disease (CD), and 35 (20.3%) had ulcerative colitis (UC). EIMs occurred in 42 patients (24.4%). EIMs developed in 34/137 diagnosed with CD (24.8%), and in 8/35 diagnosed with UC (22.9%), during a median follow-up duration of 3.2 (interquartile range, 1.9–5.4) years for CD and 3.0 (1.0–4.0) years for UC, respectively. Arthritis/arthralgia was most commonly observed (n = 15, 35.7%), followed by stomatitis/oral ulcer (n = 10, 23.8%), hepatitis (n = 5, 11.9%), nephritis (n = 4, 9.5%), pancreatitis (n = 2, 4.8%), erythema nodosum (n = 2, 4.8%), pyoderma gangrenosum (n = 1, 2.4%), primary sclerosing cholangitis (n = 1, 2.4%), uveitis (n = 1, 2.4%), and ankylosing spondylitis (n = 1, 2.4%). A significant difference in disease severity based on the Paris classification (P = 0.011) and ESR at diagnosis (P = 0.043) was observed between the EIM positive and negative group in patients with UC. According to logistic regression analyses, S1 disease severity based on the Paris classification was the only factor that was significantly associated with the development of EIMs (odds ratio, 16.57; 95% confidence interval, 2.18–287.39; P = 0.017).ConclusionSevere disease activity based on the Paris classification in pediatric patients with UC was significantly associated with EIM development. As disease severity in the Paris classification is a dynamic parameter, treatment should be focused on disease control to minimize the occurrence of EIMs in Korean children and adolescents with UC.     

Comparison of prevalence of obstructive sleep apnea,restless legs syndrome,and poor sleep quality in patients with coronary artery disease and depression

Background

This study was designed to compare the prevalence of restless leg syndrome (RLS), obstructive sleep apnea (OSA), and poor sleep quality between patients with coronary artery disease (CAD) and those with major depressive disorder (MDD)/somatic symptom disorder (SSD).

Methods

In this study, subjects with CAD were included. The comparison group consisted of subjects with MDD or SSD. After screening for exclusion criteria, a total of 100 subjects from each group were screened for OSA, RLS, and sleep quality. Hindi versions of the Berlin questionnaire, the Cambridge–Hopkins RLS diagnostic questionnaire, and the Pittsburgh Sleep Quality Index (PSQI) were used for screening, respectively. The groups were compared using statistical tests.

Results

Due to missing data, 33 subjects were excluded from final analysis. Final analysis was performed on 167 subjects—82 with CAD and 85 with MDD/SSD. Males outnumbered females in this sample (79?% men and 21?% women) and patients with CAD were older (56.1 ± 10.4 years in CAD vs. 35.5 ± 10.9 years in MDD/SSD). Prevalence of “high risk for OSA” was higher among CAD (34?%) as compared to MDD/SSD subjects (12.9?%), even after controlling for age and gender. The prevalence of RLS was comparable (13.4?% in CAD vs. 9.4?% in MDD/SSD). Daytime dysfunction, sleep quality, use of medication to induce sleep, and sleep latency were worse in the MDD/SSD group as compared to the CAD group.

Conclusion

In conclusion, this study shows that CAD patients are at a higher risk of OSA, while sleep-related parameters are worse in MDD/SSD patients. RLS was comparable between groups. On the whole, the prevalence of OSA, RLS, and poor sleep quality in both groups was higher as compared to the general population.

     

Text classification for assisting moderators in online health communities

ObjectivesPatients increasingly visit online health communities to get help on managing health. The large scale of these online communities makes it impossible for the moderators to engage in all conversations; yet, some conversations need their expertise. Our work explores low-cost text classification methods to this new domain of determining whether a thread in an online health forum needs moderators’ help.MethodsWe employed a binary classifier on WebMD’s online diabetes community data. To train the classifier, we considered three feature types: (1) word unigram, (2) sentiment analysis features, and (3) thread length. We applied feature selection methods based on χ² statistics and under sampling to account for unbalanced data. We then performed a qualitative error analysis to investigate the appropriateness of the gold standard.ResultsUsing sentiment analysis features, feature selection methods, and balanced training data increased the AUC value up to 0.75 and the F1-score up to 0.54 compared to the baseline of using word unigrams with no feature selection methods on unbalanced data (0.65 AUC and 0.40 F1-score). The error analysis uncovered additional reasons for why moderators respond to patients’ posts.DiscussionWe showed how feature selection methods and balanced training data can improve the overall classification performance. We present implications of weighing precision versus recall for assisting moderators of online health communities. Our error analysis uncovered social, legal, and ethical issues around addressing community members’ needs. We also note challenges in producing a gold standard, and discuss potential solutions for addressing these challenges.ConclusionSocial media environments provide popular venues in which patients gain health-related information. Our work contributes to understanding scalable solutions for providing moderators’ expertise in these large-scale, social media environments.