Minimum Redundancy Maximum Relevance Research Articles

Ultrasound-based radiomics analysis in the assessment of renal fibrosis in patients with chronic kidney disease.

Assessment of renal fibrosis non-invasively in chronic kidney disease (CKD) patients is still a clinical challenge. In this study, we aimed to establish a radiomics model integrating radiomics features derived from ultrasound (US) images with clinical characteristics for the assessment of renal fibrosis severity in CKD patients. A total of 160 patients with CKD who underwent kidney biopsy and renal US examination were prospectively enrolled. Patients were classified into the mild or moderate-severe fibrosis group based on pathology results. Radiomics features were extracted from the US images, and a radiomics signature was constructed using the maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) regression algorithms. Multivariable logistic regression was employed to construct the radiomics model, which incorporated the radiomics signature and the selected clinical variables. The established model was evaluated for discrimination, calibration, and clinical utility in the derivation cohort and internal cross-validation (CV) analysis, respectively. The radiomics signature, consisting of nine identified fibrosis-related features, achieved moderate discriminatory ability with an area under the receiver operating characteristic curve (AUC) of 0.72 (95% confidence interval (CI) 0.64-0.79). By combining the radiomics signature with significant clinical risk factors, the radiomics model showed satisfactory discrimination performance, yielding an AUC of 0.85 (95% CI 0.79-0.91) in the derivation cohort and a mean AUC of 0.84 (95% CI 0.77-0.92) in the internal CV analysis. It also demonstrated fine accuracy via the calibration curve. Furthermore, the decision curve analysis indicated that the model was clinically useful. The proposed radiomics model showed favorable performance in determining the individualized risk of moderate-severe renal fibrosis in patients with CKD, which may facilitate more effective clinical decision-making.

Combining deep features and hand-crafted features for abnormality detection in WCE images

In this paper, a computer-aided method is proposed for abnormality detection in Wireless Capsule Endoscopy (WCE) video frames. Common abnormalities in WCE images include ulcers, bleeding, Angiodysplasia, Lymphoid Hyperplasia, and polyp. In this paper, deep features and Hand-crafted features are combined to detect these abnormalities in WCE images. There are not sufficient images available to train deep structures, therefore the ResNet50 pre-trained model is used to extract deep features. Hand-crafted features are associated with color, shape, and texture. We used a novel idea to reveal unexpected color changes in the background due to existing lesions as a color feature set. Histogram of gradient (HOG) and local binary pattern (LBP) were used respectively for shape and texture features. They are extracted from the region of interest (ROI), i.e. suspicious region. The expectation Maximization (EM) algorithm is used to extract more distinct areas in the background as ROI. The expectation Maximization (EM) algorithm is configured in a way that can extract areas with a distinct texture and color as ROI. The EM algorithm is also initialized with a new fast method which leads to an increase in the accuracy of the method. A large number of features are created by the method, so the minimum redundancy maximum relevance approach is used to select a subset of more effective features. These selected features are then fed to a Support Vector Machine for classification. The results show that the proposed approach can detect mentioned abnormalities in WCE frames with the accuracy of 97.82%

Identification and validation of radiomic features from computed tomography for preoperative classification of neuroblastic tumors in children

BackgroundTo identify radiomic features that can predict the pathological type of neuroblastic tumor in children.MethodsData on neuroblastic tumors in 104 children were retrospectively analyzed. There were 14 cases of ganglioneuroma, 24 cases of ganglioneuroblastoma, and 65 cases of neuroblastoma. Stratified sampling was used to randomly allocate the cases into the training and validation sets in a ratio of 3:1. The maximum relevance–minimum redundancy algorithm was used to identify the top 10 of two clinical features and 851 radiomic features in portal venous–phase contrast-enhanced computed tomography images. Least absolute shrinkage and selection operator regression was used to classify tumors in two binary steps: first as ganglioneuroma compared to the other two types, then as ganglioneuroblastoma compared to neuroblastoma.ResultsBased on 10 clinical-radiomic features, the classifier identified ganglioneuroma compared to the other two tumor types in the validation dataset with sensitivity of 100.0%, specificity of 81.8%, and an area under the receiver operating characteristic curve (AUC) of 0.875. The classifier identified ganglioneuroblastoma versus neuroblastoma with a sensitivity of 83.3%, a specificity of 87.5%, and an AUC of 0.854. The overall accuracy of the classifier across all three types of tumors was 80.8%.ConclusionRadiomic features can help predict the pathological type of neuroblastic tumors in children.

Estimation of non-alcoholic steatohepatitis (NASH) disease using clinical information based on the optimal combination of intelligent algorithms for feature selection and classification

The early diagnosis of NASH disease can decrease the risk of proceeding elements and treatment costs for patients. This study aims to present an optimal combination of intelligent algorithms using advanced machine learning methods, including different feature selections and classifications based on clinical data and blood factors. In this work, collected data were from 176 patients to investigate NASH disease, and 19 features were extracted. We then sought to find the best combination of features based on different feature selection algorithms such as Feature Forward Selection (FFS), Minimum Redundancy Maximum Relevance (MRMR), and Mutual Information (MI). Finally, we used nine classifier frameworks with different mathematical mechanisms, including random forest (RF), logistic regression (LR), Linear Discriminant Analysis (LDA), AdaBoost, K nearest neighbors (KNN), multilayer perceptron model (MLP), support vector machine (SVM), and decision tree (DT) to estimate NASH disease. Our investigation revealed that the combination of dominant features, namely body mass index (BMI), glutamic pyruvic transaminase (GPT), total cholesterol (TC), high-density lipoprotein (HDL), Ezetimibe, lipoprotein level Lp(a), Loge(Lp(a)), total triglyceride (TG), Creatinine (Cre), HbA1c, Fibrate, and Sex, selected by the MRMR algorithm and classified by the RF method can provide the most appropriate performance based on less computation effort and maximum performance with accuracy, AUC, precision, and recall indices, which are and respectively. This study investigated the configuration of feature selection and classifier that is most suitable for classifying NASH disease based on clinical data and blood factors. The proposed intelligent algorithm based on MRMR and RF classifier can automatically diagnose NASH disease with appropriate performance and present an initial report without any further invasive methods. It also clarifies the diagnostic process and, as a result, the continuation of their prevention and treatment cycle.

Conventional ultrasound and contrast-enhanced ultrasound radiomics in breast cancer and molecular subtype diagnosis.

This study aimed to explore the value of conventional ultrasound (CUS) and contrast-enhanced ultrasound (CEUS) radiomics to diagnose breast cancer and predict its molecular subtype. A total of 170 lesions (121 malignant, 49 benign) were selected from March 2019 to January 2022. Malignant lesions were further divided into six categories of molecular subtype: (non-)Luminal A, (non-)Luminal B, (non-)human epidermal growth factor receptor 2 (HER2) overexpression, (non-)triple-negative breast cancer (TNBC), hormone receptor (HR) positivity/negativity, and HER2 positivity/negativity. Participants were examined using CUS and CEUS before surgery. Regions of interest images were manually segmented. The pyradiomics toolkit and the maximum relevance minimum redundancy algorithm were utilized to extract and select features, multivariate logistic regression models of CUS, CEUS, and CUS combined with CEUS radiomics were then constructed and evaluated by fivefold cross-validation. The accuracy of the CUS combined with CEUS model was superior to CUS model (85.4% vs. 81.3%, p<0.01). The accuracy of the CUS radiomics model in predicting the six categories of breast cancer is 68.2% (82/120), 69.3% (83/120), 83.7% (100/120), 86.7% (104/120), 73.5% (88/120), and 70.8% (85/120), respectively. In predicting breast cancer of Luminal A, HER2 overexpression, HR-positivity, and HER2 positivity, CEUS video improved the predictive performance of CUS radiomics model [accuracy=70.2% (84/120), 84.0% (101/120), 74.5% (89/120), and 72.5% (87/120), p<0.01]. CUS radiomics has the potential to diagnose breast cancer and predict its molecular subtype. Moreover, CEUS video has auxiliary predictive value for CUS radiomics.

Identification of bullets fired from air guns using machine and deep learning methods

Ballistics (the linkage of bullets and cartridge cases to weapons) is a common type of evidence encountered in criminal cases around the world. The interest lies in determining whether two bullets were fired using the same firearm. This paper proposes an automated method to classify bullets from surface topography and Land Engraved Area (LEA) images of the fired pellets using machine and deep learning methods. The curvature of the surface topography was removed using loess fit and features were extracted using Empirical Mode Decomposition (EMD) followed by various entropy measures. The informative features were identified using minimum Redundancy Maximum Relevance (mRMR), finally the classification was performed using Support Vector Machines (SVM), Decision Tree (DT) and Random Forest (RF) classifiers. The results revealed a good predictive performance. In addition, the deep learning model DenseNet121 was used to classify the LEA images. DenseNet121 provided a higher predictive performance than SVM, DT and RF classifiers. Moreover, the Grad-CAM technique was used to visualise the discriminative regions in the LEA images. These results suggest that the proposed deep learning method can be used to expedite the linkage of projectiles to firearms and assist in ballistic examinations.In this work, the bullets that were compared were air pellets fired from both air rifles and a high velocity air pistol. Air guns were used to collect the data because they were more accessible than other firearms and could be used as a proxy, delivering comparable LEAs. The methods developed here can be used as a proof-of-concept and are easily expandable to bullet and cartridge case identification from any weapon.

Identifying the Influencing Factors of Depressive Symptoms among Nurses in China by Machine Learning: A Multicentre Cross-Sectional Study

Background. Nurses’ high workload can result in depressive symptoms. However, the research has underexplored the internal and external variables, such as organisational support, career identity, and burnout, which may predict depressive symptoms among Chinese nurses via machine learning (ML). Aim. To predict nurses’ depressive symptoms and identify the relevant factors by machine learning (ML) algorithms. Methods. A self-administered smartphone questionnaire was delivered to nurses to evaluate their depressive symptoms; 1,431 questionnaires and 28 internal and external features were collected. In the training set, the use of maximum relevance minimum redundancy ranked the features’ importance. Five ML algorithms were used to establish models to identify nurses’ depressive symptoms using different feature subsets, and the area under the curve (AUC) determined the optimal feature subset. Demographic characteristics were added to the optimal feature subset to establish the combined models. Each model’s performance was evaluated using the test set. Results. The prevalence rate of depressive symptoms among Chinese nurses was 31.86%. The optimal feature subset comprised of sleep disturbance, chronic fatigue, physical fatigue, exhaustion, and perceived organisation support. The five models based on the optimal feature subset had good prediction performance on the test set (AUC: 0.871–0.895 and accuracy: 0.798–0.815). After adding the significant demographic characteristics, the performance of the five combined models slightly improved; the AUC and accuracy increased to 0.904 and 0.826 on the test set, respectively. The logistic regression analysis results showed the best and most stable performance while the univariate analysis results showed that external and internal personal features (AUC: 0.739–0.841) were more effective than demographic characteristics (AUC: 0.572–0.588) for predicting nurses’ depressive symptoms. Conclusions. ML could effectively predict nurses’ depressive symptoms. Interventions to manage physical fatigue, sleep disorders, burnout, and organisational support may prevent depressive symptoms.

Comparison of Feature Selection Methods in Breast Cancer Microarray Data

Aim: We aim to predict metastasis in breast cancer patients with tree-based conventional machine learning algorithms and to observe which feature selection methods is more effective in machine learning methods related to microarray breast cancer data reducing the number of features. Material and Methods: Feature selection methods, least squares absolute shrinkage (LASSO), Boruta and maximum relevance-minimum redundancy (MRMR) and statistical preprocessing steps were first applied before the tree-based learning conventional machine learning methods like Decision-tree, Extremely randomized trees and Gradient Boosting Tree applied on the microarray breast cancer data. Results: Microarray data with 54675 features (202 (101/101 breast cancer patients with/without metastases)) was first reduced to 235 features, then the feature selection algorithms were applied and the most important features were found with tree-based machine learning algorithms. It was observed that the highest recall and F-measure values were obtained from the XGBoost method and the highest precision value was received from the Extra-tree method. The 10 arrays out of 54675 with the highest variable importance were listed. Conclusion: The most accurate results were obtained from the statistical preprocessed data for the XGBoost and Extra-trees machine learning algorithms. Statistical and microarray preprocessing steps would be enough in machine learning analysis of microarray data in breast cancer metastases predictions.

QLBP: Dynamic patterns-based feature extraction functions for automatic detection of mental health and cognitive conditions using EEG signals

BackgroundSevere psychiatric disorders, including depressive disorders, schizophrenia spectrum disorders, and intellectual disability, have devastating impacts on vital life domains such as mental, psychosocial, and cognitive functioning and are correlated with an increased risk of mortality. Accurate symptom monitoring and early diagnosis are essential to optimize treatment and enhance patient outcomes. Electroencephalography (EEG) is a potential diagnostic and monitoring tool for mental health and cognitive disorders, as EEG signals are ideal inputs for machine learning models. In this paper, we propose a novel machine learning model for mental disorder detection based on EEG signals. Aimelectroencephalography (EEG) signals for the detection of three major mental health conditions, namely intellectual disability (ID), schizophrenia (SZ), and bipolar disorder (BD); and (ii) to introduce two novel conditional local binary pattern-based feature extractors for precise classification of these three classes. Material and methodWe collected a novel electroencephalography (EEG) signal dataset from 69 individuals, including a control group and participants diagnosed with bipolar disorder, schizophrenia, and intellectual disability. To extract informative features from the dataset, we developed two novel conditional feature extraction functions that improve upon traditional local binary pattern (LBP) functions by utilizing maximum and minimum distance vectors to generate patterns. We refer to these functions as quantum LBP (QLBP). Additionally, we employed wavelet packet decomposition to construct a multileveled feature extraction model. We evaluated several feature selection techniques, including neighborhood component analysis (NCA), Chi2, maximum relevance minimum redundancy (MRMR), and ReliefF, to select the most informative features. Finally, we employed iterative hard majority voting (IHMV) to obtain the final predicted results. ResultsUsing our multichannel electroencephalography (EEG) signal dataset, we calculated channel-by-channel results and voted results for the classification of intellectual disability (ID), schizophrenia (SZ), and bipolar disorder (BD) classes. Our proposed model, employing the k-nearest neighbors (kNN) classifier with the leave-one subject out cross-validation (LOSO CV) strategy, achieved high accuracy rates of 97.47 %, 94.36 %, and 93.49 % for the ID, SZ, and BD classes, respectively. ConclusionsEmploying the leave-one subject out cross-validation (LOSO CV) technique, our proposed model achieved classification accuracy rates of over 90 % for all cases, thereby providing strong evidence for the effectiveness of the proposed quantum local binary pattern (QLBP) feature extraction method.

EEG rhythm based emotion recognition using multivariate decomposition and ensemble machine learning classifier

Recently, electroencephalogram (EEG) signals have shown great potential to recognize human emotions. The goal of effective computing is to assist computers in understanding various types of emotions via human–computer interaction (HCI). Multichannel EEG signals are used to measure the electrical activity of the brain in space and time. Automated emotion recognition using multichannel EEG signals is an interesting area of cognitive neuroscience and affective computing research. This research proposes EEG multichannel rhythmic features and ensemble machine learning (EML) classifiers with leave-one-subject-out cross-validation (LOSOCV) for automatic emotion classification from multichannel EEG recordings. Multivariate fast iterative filtering (MvFIF) is used to assess the EEG rhythm sequences. EEG rhythms delta(δ), theta(θ), alpha(α), beta(β), and gamma(γ) are separated based on the mean frequency of the EEG rhythm sequence. Three Hjorth parameters and nine entropy features were extracted from multichannel EEG rhythms. Extracted features are selected using the minimum redundancy maximum relevance (mRMR) approach. The experimental design was performed on two emotional datasets (GAMEEMO and DREAMER). The validation showed that gamma rhythm multichannel features with EML-based subspace K-nearest neighbor (SS KNN) were as high as 93.5%–99.8%, achieving high classification accuracy. The comparisons of δ, θ, α, β, and γ rhythms with EML, support vector machine (SVM), and artificial neural network (ANN) were performed. we also analyzed multi-class emotions (HVHA, HVLA, LVHA, LVLA) with an ensemble-based bagging tree on gamma rhythm. It provides a novel solution for multichannel rhythm-specific features in EEG data analysis.

Machine Learning Improves the Prediction of Responses to Immune Checkpoint Inhibitors in Metastatic Melanoma.

Pretreatment LDH is a standard prognostic biomarker for advanced melanoma and is associated with response to ICI. We assessed the role of machine learning-based radiomics in predicting responses to ICI and in complementing LDH for prognostication of metastatic melanoma. From 2008-2022, 79 patients with 168 metastatic hepatic lesions were identified. All patients had arterial phase CT images 1-month prior to initiation of ICI. Response to ICI was assessed on follow-up CT at 3 months using RECIST criteria. A machine learning algorithm was developed using radiomics. Maximum relevance minimum redundancy (mRMR) was used to select features. ROC analysis and logistic regression analyses evaluated performance. Shapley additive explanations were used to identify the variables that are the most important in predicting a response. mRMR selection revealed 15 features that are associated with a response to ICI. The machine learning model combining both radiomics features and pretreatment LDH resulted in better performance for response prediction compared to models that included radiomics or LDH alone (AUC of 0.89 (95% CI: [0.76-0.99]) vs. 0.81 (95% CI: [0.65-0.94]) and 0.81 (95% CI: [0.72-0.91]), respectively). Using SHAP analysis, LDH and two GLSZM were the most predictive of the outcome. Pre-treatment CT radiomic features performed equally well to serum LDH in predicting treatment response.

RadWise: A Rank-Based Hybrid Feature Weighting and Selection Method for Proteomic Categorization of Chemoirradiation in Patients with Glioblastoma.

Glioblastomas (GBM) are rapidly growing, aggressive, nearly uniformly fatal, and the most common primary type of brain cancer. They exhibit significant heterogeneity and resistance to treatment, limiting the ability to analyze dynamic biological behavior that drives response and resistance, which are central to advancing outcomes in glioblastoma. Analysis of the proteome aimed at signal change over time provides a potential opportunity for non-invasive classification and examination of the response to treatment by identifying protein biomarkers associated with interventions. However, data acquired using large proteomic panels must be more intuitively interpretable, requiring computational analysis to identify trends. Machine learning is increasingly employed, however, it requires feature selection which has a critical and considerable effect on machine learning problems when applied to large-scale data to reduce the number of parameters, improve generalization, and find essential predictors. In this study, using 7k proteomic data generated from the analysis of serum obtained from 82 patients with GBM pre- and post-completion of concurrent chemoirradiation (CRT), we aimed to select the most discriminative proteomic features that define proteomic alteration that is the result of administering CRT. Thus, we present a novel rank-based feature weighting method (RadWise) to identify relevant proteomic parameters using two popular feature selection methods, least absolute shrinkage and selection operator (LASSO) and the minimum redundancy maximum relevance (mRMR). The computational results show that the proposed method yields outstanding results with very few selected proteomic features, with higher accuracy rate performance than methods that do not employ a feature selection process. While the computational method identified several proteomic signals identical to the clinical intuitive (heuristic approach), several heuristically identified proteomic signals were not selected while other novel proteomic biomarkers not selected with the heuristic approach that carry biological prognostic relevance in GBM only emerged with the novel method. The computational results show that the proposed method yields promising results, reducing 7k proteomic data to 7 selected proteomic features with a performance value of 93.921%, comparing favorably with techniques that do not employ feature selection.

Machine learning clinical decision support for interdisciplinary multimodal chronic musculoskeletal pain treatment.

Chronic musculoskeletal pain is a prevalent condition impacting around 20% of people globally; resulting in patients living with pain, fatigue, restricted social and employment capacity, and reduced quality of life. Interdisciplinary multimodal pain treatment programs have been shown to provide positive outcomes by supporting patients modify their behavior and improve pain management through focusing attention on specific patient valued goals rather than fighting pain. Given the complex nature of chronic pain there is no single clinical measure to assess outcomes from multimodal pain programs. Using Centre for Integral Rehabilitation data from 2019-2021 (n = 2,364), we developed a multidimensional machine learning framework of 13 outcome measures across 5 clinically relevant domains including activity/disability, pain, fatigue, coping and quality of life. Machine learning models for each endpoint were separately trained using the most important 30 of 55 demographic and baseline variables based on minimum redundancy maximum relevance feature selection. Five-fold cross validation identified best performing algorithms which were rerun on deidentified source data to verify prognostic accuracy. Individual algorithm performance ranged from 0.49 to 0.65 AUC reflecting characteristic outcome variation across patients, and unbalanced training data with high positive proportions of up to 86% for some measures. As expected, no single outcome provided a reliable indicator, however the complete set of algorithms established a stratified prognostic patient profile. Patient level validation achieved consistent prognostic assessment of outcomes for 75.3% of the study group (n = 1,953). Clinician review of a sample of predicted negative patients (n = 81) independently confirmed algorithm accuracy and suggests the prognostic profile is potentially valuable for patient selection and goal setting. These results indicate that although no single algorithm was individually conclusive, the complete stratified profile consistently identified patient outcomes. Our predictive profile provides promising positive contribution for clinicians and patients to assist with personalized assessment and goal setting, program engagement and improved patient outcomes.

A method for predicting blast-induced ground vibration based on Mamdani Fuzzy Inference System

Blast-induced ground vibration is highly possible to result in serious losses such as destroyed buildings. The crucial parameter of the mentioned vibration is peak particle velocity (PPV). Many equations have been developed to predict PPV, however, worse performance has been reported by multiple literatures. This paper developed a method for predicting PPV based on Mamdani Fuzzy Inference System. Firstly, Minimum Redundancy Maximum Relevance was employed to identify the blasting design parameters which significantly contribute to the PPV induced by blasting. Secondly, K-means method was applied to determine the value ranges of the selected parameters. The selected parameters and corresponding value ranges were combined to input into Mamdani Fuzzy Inference System for obtaining predicted PPV. Totally, 280 samples were collected from a blasting site. 260 out of them were used to train the proposed method and 20 were assigned for test. The proposed method was tested in the comparison with empirical equation USBM, multiple linear regression analysis, pure Mamdani Fuzzy Inference System in terms of the difference between predicted PPV and measured PPV, coefficient of correlation, root-mean-square error, and mean absolute error. The results from that showed that the proposed method has the better performance in PPV prediction.

On the Stability and Homogeneous Ensemble of Feature Selection for Predictive Maintenance: A Classification Application for Tool Condition Monitoring in Milling.

Feature selection (FS) represents an essential step for many machine learning-based predictive maintenance (PdM) applications, including various industrial processes, components, and monitoring tasks. The selected features not only serve as inputs to the learning models but also can influence further decisions and analysis, e.g., sensor selection and understandability of the PdM system. Hence, before deploying the PdM system, it is crucial to examine the reproducibility and robustness of the selected features under variations in the input data. This is particularly critical for real-world datasets with a low sample-to-dimension ratio (SDR). However, to the best of our knowledge, stability of the FS methods under data variations has not been considered yet in the field of PdM. This paper addresses this issue with an application to tool condition monitoring in milling, where classifiers based on support vector machines and random forest were employed. We used a five-fold cross-validation to evaluate three popular filter-based FS methods, namely Fisher score, minimum redundancy maximum relevance (mRMR), and ReliefF, in terms of both stability and macro-F1. Further, for each method, we investigated the impact of the homogeneous FS ensemble on both performance indicators. To gain broad insights, we used four (2:2) milling datasets obtained from our experiments and NASA's repository, which differ in the operating conditions, sensors, SDR, number of classes, etc. For each dataset, the study was conducted for two individual sensors and their fusion. Among the conclusions: (1) Different FS methods can yield comparable macro-F1 yet considerably different FS stability values. (2) Fisher score (single and/or ensemble) is superior in most of the cases. (3) mRMR's stability is overall the lowest, the most variable over different settings (e.g., sensor(s), subset cardinality), and the one that benefits the most from the ensemble.

Obstructive sleep apnea detection with nonlinear analysis of speech

Studies on the detection of Obstructive Sleep Apnea (OSA) from speech recording have brought an important innovation to this field. This study is based on the hypothesis that the deterioration of the muscles and tissues in the vocal tract in OSA patients changes the nonlinear properties of voice. In this study, the features that reveal the nonlinear structure of the speech for OSA detection were investigated. The nonlinear characteristics were evaluated for vowels and consonants, and it was tried to find out in which voice group the nonlinear features were more distinctive in OSA. The nonlinear analysis was applied to a wide variety of voice samples having vocal tract components affected by OSA, and OSA/healthy classifications were realized. The results revealed that nonlinear analysis gives considerable findings in OSA detection, and consonants are more successful than vowels. For classifications, K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) classifiers, 5-fold cross validation procedure and Minimum Redundancy Maximum Relevance (MRMR) feature selection method were used. Using the whole dataset, OSA detection performance for vowels was found as 83.5% with KNN, and 96% with SVM for consonants. Additionally, the test process was carried out by using a distinct group, and 82.5% test accuracy was achieved with only 6 features for consonants. The results indicated that the proposed study supports the hypothesis that the nonlinear behavior of vocal tract changes in subjects with OSA, especially for consonants, and has considerable potential for OSA detection as the pre-diagnosis or screening test in clinical use.

Evaluation of feature selection methods utilizing random forest and logistic regression for lung tissue categorization using HRCT images

AbstractCategorization of lung tissue patterns with interstitial lung diseases (ILD) utilize high‐resolution computed tomography (HRCT) lung images of the TALISMAN dataset which is challenging due to high intra‐class variation and inter‐class ambiguity. To tackle this, major contributions are made in three aspects. First, a novel shape‐based feature is proposed to quantify the amount of fibrotic and nodular components in a lung tissue pattern which helps to minimize intra‐class variation and inter‐class ambiguity. Second, we address the curse of dimensionality which often arises due to huge feature space. Third, to prevent an overfitting issue, the Grid Search optimization algorithm is utilized by tuning the Random Forest hyper‐parameters. In this manuscript, a framework is proposed to categorize lung tissue patterns by integrating four types of feature domains (a) intensity‐based, (b) texture‐based, (c) wavelet‐based, and (d) shape‐based along with the novel shape‐based feature. As a result, we encounter a large feature space (i.e., ), which leads to high dimensionality. To address this issue, we reduce the feature space using filter‐based f‐statistic, reliefF, minimum Redundancy Maximum Relevance (mRMR), and embedded‐based decision trees, regularization models. We found that the regularization model shrinks the feature space by 2.5 times in just 90 s whereas mRMR methods reduce the feature space by 10 times in 13 min. Using the proposed feature set, we employ Random Forest and Logistic Regression as potential classifiers to classify lung tissue patterns. Experiential results reveal that the proposed framework categorizes lung tissue patterns more effectively than state‐of‐the‐art hand‐crafted and deep learning‐based approaches.

The role of epicardial and pericoronary adipose tissue radiomics in identifying patients with non-ST-segment elevation myocardial infarction from unstable angina

ObjectivesThis study aimed to ascertain if the radiomics features of epicardial adipose tissue (EAT) and pericoronary adipose tissue (PCAT) based on coronary computed tomography angiography (CCTA) could identify non-ST-segment elevation myocardial infarction (NSTEMI) from unstable angina (UA). Materials and methodsThis retrospective case-control study included 108 patients with NSTEMI and 108 controls with UA. All patients were separated into training cohort (n = 116), internal validation cohort 1 (n = 50), and internal validation cohort 2 (n = 50) based on the time order of admission. The internal validation cohort 1 used the same scanner and scan parameters as the training cohort, while the internal validation cohort 2 used different canners and scan parameters than the training cohort. The EAT and PCAT radiomics features selected by maximum relevance minimum redundancy (mRMR) and least absolute shrinkage and selection operator (LASSO) were adopted to build logistic regression models. Finally, we developed an EAT radiomics model, three vessel-based (right coronary artery [RCA], left anterior descending artery [LAD], and left circumflex artery [LCX]) PCAT radiomics models, and a combined model by combining the three PCAT radiomics models. Discrimination, calibration, and clinical application were employed to assess the performance of all models. ResultsEight radiomics features of EAT, sixteen of RCA-PCAT, fifteen of LAD-PCAT, and eighteen of LCX-PCAT were selected and used to construct radiomics models. The area under the curves (AUCs) of the EAT, RCA-PCAT, LAD-PCAT, LCX-PCAT and the combined models were 0.708 (95% CI: 0.614–0.802), 0.833 (95% CI:0.759–0.906), 0.720 (95% CI:0.628–0.813), 0.713 (95% CI:0.619–0.807), 0.889 (95% CI:0.832–0.946) in the training cohort, 0.693 (95% CI:0.546–0.840), 0.837 (95% CI: 0.729–0.945), 0.766 (95% CI: 0.625–0.907), 0.675 (95% CI: 0.521–0.829), 0.898 (95% CI: 0.802–0.993) in the internal validation cohort 1, and 0.691 (0.535–0.847), 0.822 (0.701–0.944), 0.760 (0.621–0.899), 0.674 (0.517–0.830), 0.866 (0.769–0.963) in the internal validation cohort 2, respectively. ConclusionCompared with the RCA-PCAT radiomics model, the EAT radiomics model had a limited ability to discriminate between NSTEMI and UA. The combination of the three vessel-based PCAT radiomics may have the potential to distinguish between NSTEMI and UA.

IIL13Pred: improved prediction of IL-13 inducing peptides using popular machine learning classifiers

BackgroundInflammatory mediators play havoc in several diseases including the novel Coronavirus disease 2019 (COVID-19) and generally correlate with the severity of the disease. Interleukin-13 (IL-13), is a pleiotropic cytokine that is known to be associated with airway inflammation in asthma and reactive airway diseases, in neoplastic and autoimmune diseases. Interestingly, the recent association of IL-13 with COVID-19 severity has sparked interest in this cytokine. Therefore characterization of new molecules which can regulate IL-13 induction might lead to novel therapeutics.ResultsHere, we present an improved prediction of IL-13-inducing peptides. The positive and negative datasets were obtained from a recent study (IL13Pred) and the Pfeature algorithm was used to compute features for the peptides. As compared to the state-of-the-art which used the regularization based feature selection technique (linear support vector classifier with the L1 penalty), we used a multivariate feature selection technique (minimum redundancy maximum relevance) to obtain non-redundant and highly relevant features. In the proposed study (improved IL-13 prediction (iIL13Pred)), the use of the mRMR feature selection method is instrumental in choosing the most discriminatory features of IL-13-inducing peptides with improved performance. We investigated seven common machine learning classifiers including Decision Tree, Gaussian Naïve Bayes, k-Nearest Neighbour, Logistic Regression, Support Vector Machine, Random Forest, and extreme gradient boosting to efficiently classify IL-13-inducing peptides. We report improved AUC, and MCC scores of 0.83 and 0.33 on validation data as compared to the current method.ConclusionsExtensive benchmarking experiments suggest that the proposed method (iIL13Pred) could provide improved performance metrics in terms of sensitivity, specificity, accuracy, the area under the curve - receiver operating characteristics (AUCROC) and Matthews correlation coefficient (MCC) than the existing state-of-the-art approach (IL13Pred) on the validation dataset and an external dataset comprising of experimentally validated IL-13-inducing peptides. Additionally, the experiments were performed with an increased number of experimentally validated training datasets to obtain a more robust model. A user-friendly web server (www.soodlab.com/iil13pred) is also designed to facilitate rapid screening of IL-13-inducing peptides.

A nomogram model based on pre-treatment and post-treatment MR imaging radiomics signatures: application to predict progression-free survival for nasopharyngeal carcinoma

BackgroundTo establish a novel model using radiomics analysis of pre-treatment and post-treatment magnetic resonance (MR) images for prediction of progression-free survival in the patients with stage II–IVA nasopharyngeal carcinoma (NPC) in South China.MethodsOne hundred and twenty NPC patients who underwent chemoradiotherapy were enrolled (80 in the training cohort and 40 in the validation cohort). Acquiring data and screening features were performed successively. Totally 1133 radiomics features were extracted from the T2-weight images before and after treatment. Least absolute shrinkage and selection operator regression, recursive feature elimination algorithm, random forest, and minimum-redundancy maximum-relevancy (mRMR) method were used for feature selection. Nomogram discrimination and calibration were evaluated. Harrell’s concordance index (C-index) and receiver operating characteristic (ROC) analyses were applied to appraise the prognostic performance of nomograms. Survival curves were plotted using Kaplan–Meier method.ResultsIntegrating independent clinical predictors with pre-treatment and post-treatment radiomics signatures which were calculated in conformity with radiomics features, we established a clinical-and-radiomics nomogram by multivariable Cox regression. Nomogram consisting of 14 pre-treatment and 7 post-treatment selected features has been proved to yield a reliable predictive performance in both training and validation groups. The C-index of clinical-and-radiomics nomogram was 0.953 (all P < 0.05), which was higher than that of clinical (0.861) or radiomics nomograms alone (based on pre-treatment statistics: 0.942; based on post-treatment statistics: 0.944). Moreover, we received Rad-score of pre-treatment named RS1 and post-treatment named RS2 and all were used as independent predictors to divide patients into high-risk and low-risk groups. Kaplan–Meier analysis showed that lower RS1 (less than cutoff value, − 1.488) and RS2 (less than cutoff value, − 0.180) were easier to avoid disease progression (all P < 0.01). It showed clinical benefit with decision curve analysis.ConclusionsMR-based radiomics measured the burden on primary tumor before treatment and the tumor regression after chemoradiotherapy, and was used to build a model to predict progression-free survival (PFS) in the stage II–IVA NPC patients. It can also help to distinguish high-risk patients from low-risk patients, thus guiding personalized treatment decisions effectively.