Feature Ranking Research Articles

Monitoring the health status of the population by age groups

A multi-criteria method for selecting informative sets of different features for a quantitative assessment of the population’s health status in 14 age groups is considered. To compare samples from two classes (groups), it is proposed to form a unified description of objects according to two gradations of nominal features. The unified description is used to synthesize latent features and calculate the values of the compactness measure of class objects on the numerical axis. The transformation of quantitative features into nominal gradations is implemented according to the search criterion for the minimum coverage of their values by non-overlapping intervals. The values of the boundaries of the intervals and their number are determined by a recursive algorithm considering the objects belonging to classes. An important property of the transformation is the invariance to measurement scales. A formula is proposed for calculating the membership function of class objects for each feature gradation. Function values are used to unify object descriptions and calculate the stability index of a feature, regardless of its measurement scale. The unification of descriptions by two gradations does not change the stability index but increases the contribution of each gradation to the separation of class objects. The ranking of features about their stability was used both for individual samples and for a set of defined samples. The results of ranking over a set of samples were used to search for patterns in individual features and to form sets from them to calculate the values of latent features of objects. A set of thirteen data samples from representatives of two classes was formed as follows. The first class was represented by objects of the younger age group, and the second class — by objects of different age groups. A set of seven different types of features has been identified. For each of 13 samples, the values of latent features on this set and measures of compactness of class objects on the numerical axis were calculated. A monotonically non-decreasing sequence of values of measures of compactness of data samples that are invariant to the order of precedence of age groups is obtained. The property of monotonicity of sequence values is consistent with empirical estimates of the health state in the process of population aging.

XAI-based cross-ensemble feature ranking methodology for machine learning models

Artificial Intelligence (AI) as one robust technology has been used in various fields, making innovative society possible and changing our lifestyles. However, the black box problem is still one big problem for artificial intelligence. In this study, we first compared the results of kernel Shapley Additive exPlanations (SHAP) for various machine learning models and found that the single SHAP model cannot explain the models at the human knowledge level. Then the factors’ global ranking was calculated using our proposed ensemble methodology. Finally, the new factors’ ranking was compared with other factor ranking method. Our experimental results declare that the proposed cross-ensemble feature ranking methodology provides stable and comparatively reliable feature ranking in both the classification and regression models.

MP09-04 DIAGNOSTIC PERFORMANCE OF A NOVEL RADIOMIC MODEL FOR PREDICTING POST-TREATMENT PROSTATE CANCER RECURRENCE: A COMPARISON TO CAPRA AND MSKCC NOMOGRAMS

You have accessJournal of UrologyCME1 Apr 2023MP09-04 DIAGNOSTIC PERFORMANCE OF A NOVEL RADIOMIC MODEL FOR PREDICTING POST-TREATMENT PROSTATE CANCER RECURRENCE: A COMPARISON TO CAPRA AND MSKCC NOMOGRAMS Linda Huynh, Olivia Taylor, Shuo Wang, Thomas Ahlering, and Michael Baine Linda HuynhLinda Huynh More articles by this author , Olivia TaylorOlivia Taylor More articles by this author , Shuo WangShuo Wang More articles by this author , Thomas AhleringThomas Ahlering More articles by this author , and Michael BaineMichael Baine More articles by this author View All Author Informationhttps://doi.org/10.1097/JU.0000000000003224.04AboutPDF ToolsAdd to favoritesDownload CitationsTrack CitationsPermissionsReprints ShareFacebookLinked InTwitterEmail Abstract INTRODUCTION AND OBJECTIVE: mpMRI-derived radiomic features have been shown to capture sub-visual patterns for quantitative characterization of tumor phenotype. We seek to compare the diagnostic performance of a mpMRI-based radiomic model to currently available nomograms for prediction of post-radical prostatectomy (RP) biochemical recurrence (BCR). METHODS: mpMRI was obtained from 76 patients who had underwent RP for treatment of localized PCa. All patients had ≥2 years follow-up and those with neo-adjuvant or adjuvant treatment were excluded. Radiomic analysis and cross-validation of mpMRI features yielded features significantly correlated with BCR, defined as two consecutive serum PSA ≥0.2ng/ml. These features were aggregated to construct a radiomic model, which was compared to the risk scores generated by inputting patients’ clinicodemographic features into the USCF Cancer of the Prostate Risk Assessment (UCSF-CAPRA) score and Memorial Sloan Kettering Cancer Center (MSKCC) Pre-Radical Prostatectomy nomogram. The performance of each model was compared utilizing receiver-operator curve (ROC) analysis and area under the curve (AUC) was reported. RESULTS: Table 1 illustrates the clinicopathologic characteristics. In feature extraction and ranking, six radiomic features were determined to be important and non-redundant in predicting PCa recurrence (Figure 1). These features were aggregated into the radiomic model and repeated five-fold cross validation yielded a model with AUC of 0.95±0.06, 33% sensitivity, and 100% specificity. UCSF-CAPRA and MSKCC nomograms yielded AUC of 0.72±0.07 and 0.82±0.07, respectively. CONCLUSIONS: The mpMRI-derived radiomic model performed well when compared to the UCSF-CAPRA score and MSKCC Pre-Radical Prostatectomy nomogram. Future projects will incorporate patient demographics and disease characteristics available at the time of initial PCa diagnosis to improve the radiomic model accuracy. Source of Funding: N/A © 2023 by American Urological Association Education and Research, Inc.FiguresReferencesRelatedDetails Volume 209Issue Supplement 4April 2023Page: e105 Advertisement Copyright & Permissions© 2023 by American Urological Association Education and Research, Inc.MetricsAuthor Information Linda Huynh More articles by this author Olivia Taylor More articles by this author Shuo Wang More articles by this author Thomas Ahlering More articles by this author Michael Baine More articles by this author Expand All Advertisement PDF downloadLoading ...

Feasibility of imaging under structured illumination for evaluation of white striping in broiler breast fillets

Muscle myopathies or defects, such as white striping (WS), downgrade the quality of broiler meat, leading to the loss of millions of dollars annually for the U.S. poultry industry. Visual inspection is currently practiced for assessing myopathies in broiler meat, which is however prone to human evaluation error, labor-intensive, and costly. Imaging under uniform or diffuse illumination has been investigated for assessing broiler meat quality, but their performance is not always satisfactory, especially for detecting subtle defects with few visual symptoms. This study presents the first proof-of-concept evaluation of the utility of an innovative technique for improved imaging of structures of biological materials, i.e., structured-illumination reflectance imaging (SIRI), for detecting WS conditions in broiler breast meat. Broiler breast fillets with varying degrees of WS severity were imaged by an in-house assembled SIRI system under sinusoidal illumination at different spatial frequencies (0.05–0.40 cycles/mm). The acquired pattern images were demodulated into direct components (DC) and amplitude components (AC) at each spatial frequency. Texture features were extracted from DC and AC images for building classification models using regularized linear discriminant analysis, which were to classify meat samples into 2, 3, and 4 classes, respectively, according to WS conditions. AC images were found by visual inspection more effective than DC in resolving WS characteristics, depending on the spatial frequency of illumination patterns. Compared to DC, AC yielded the maximum accuracy improvements of 8.33%, 7.93%, and 12.3% in 2-, 3- and 4-class classifications, respectively. Models using ranked features yielded similar improvements of up to 9.53% by AC over DC. The SIRI technique is promising for enhanced detection of WS and potentially other defects of broiler breast meat. • Structured-illumination reflectance imaging (SIRI) was used for poultry quality detection. • Amplitude component (AC) images enabled resolving white striping (WS) of broiler breast meat. • Broiler breast fillets were classified by models into 2, 3 and 4 classes according to WS conditions. • SIRI offered substantial improvements of up to 12% in classifying WS-affected poultry samples.

Ranked feature-based data-driven bearing fault diagnosis using support vector machine and artificial neural network

This article analyzes a data-driven fault diagnosis method for rolling element bearing under different operating conditions. The work is aimed to incorporate the filter-type feature selection algorithms, namely, neighborhood component analysis, minimum redundancy maximum relevance, chi-square, and ReliefF algorithms for the feature ranking of the extracted time-domain statistical features from the collected vibration data of the five different bearing defect conditions (normal, outer race defect, ball defect, inner race defect, and combined inner and ball defect). The vibration data have been recorded and an envelope analysis technique for pre-processing the signal is used to identify the fundamental defect frequencies of all the bearings. The artificial neural network and the support vector machine are used to predict the comparative performance of the feature selection algorithms. The results demonstrate that the neighborhood component analysis algorithm achieves the highest accuracies for the bearing fault detection with both the support vector machine and artificial neural network among all the feature selection methods. Therefore, the effective feature ranking before the fault classification by the machine learning algorithms can lead to an efficient and reliable bearing fault diagnosis.

Driving drowsiness detection using spectral signatures of EEG-based neurophysiology.

Introduction: Drowsy driving is a significant factor causing dire road crashes and casualties around the world. Detecting it earlier and more effectively can significantly reduce the lethal aftereffects and increase road safety. As physiological conditions originate from the human brain, so neurophysiological signatures in drowsy and alert states may be investigated for this purpose. In this preface, A passive brain-computer interface (pBCI) scheme using multichannel electroencephalography (EEG) brain signals is developed for spatially localized and accurate detection of human drowsiness during driving tasks. Methods: This pBCI modality acquired electrophysiological patterns of 12 healthy subjects from the prefrontal (PFC), frontal (FC), and occipital cortices (OC) of the brain. Neurological states are recorded using six EEG channels spread over the right and left hemispheres in the PFC, FC, and OC of the sleep-deprived subjects during simulated driving tasks. In post-hoc analysis, spectral signatures of the δ, θ, α, and β rhythms are extracted in terms of spectral band powers and their ratios with a temporal correlation over the complete span of the experiment. Minimum redundancy maximum relevance, Chi-square, and ReliefF feature selection methods are used and aggregated with a Z-score based approach for global feature ranking. The extracted drowsiness attributes are classified using decision trees, discriminant analysis, logistic regression, naïve Bayes, support vector machines, k-nearest neighbors, and ensemble classifiers. The binary classification results are reported with confusion matrix-based performance assessment metrics. Results: In inter-classifier comparison, the optimized ensemble model achieved the best results of drowsiness classification with 85.6% accuracy and precision, 89.7% recall, 87.6% F1-score, 80% specificity, 70.3% Matthews correlation coefficient, 70.2% Cohen's kappa score, and 91% area under the receiver operating characteristic curve with 76-ms execution time. In inter-channel comparison, the best results were obtained at the F8 electrode position in the right FC of the brain. The significance of all the results was validated with a p-value of less than 0.05 using statistical hypothesis testing methods. Conclusions: The proposed scheme has achieved better results for driving drowsiness detection with the accomplishment of multiple objectives. The predictor importance approach has reduced the feature extraction cost and computational complexity is minimized with the use of conventional machine learning classifiers resulting in low-cost hardware and software requirements. The channel selection approach has spatially localized the most promising brain region for drowsiness detection with only a single EEG channel (F8) which reduces the physical intrusiveness in normal driving operation. This pBCI scheme has a good potential for practical applications requiring earlier, more accurate, and less disruptive drowsiness detection using the spectral information of EEG biosignals.

Multimodality MRI radiomics analysis of TP53 mutations in triple negative breast cancer.

To explore the value of T1-weighted imaging (T1WI), T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) radiomics features reflecting TP53 mutations in patients with triple negative breast cancer (TNBC). This retrospective study enrolled 91 patients with TNBC with TP53 testing (64 patients in the training cohort and 27 patients in the validation cohort). A total of 2832 radiomics features were extracted from the first phase of dynamic contrast-enhanced T1WI, T2WI and ADC maps. Analysis of variance (ANOVA) and the Kruskal-Wallis-test were used for feature selection. Then, linear discriminant analysis (LDA), multilayer perceptron (MLP), logistic regression (LR), LR with LASSO, decision tree (DT), naïve Bayes (NB), random forest (RF), and support vector machine (SVM) models were used for classification. The validation AUCs of the eight classifiers ranged from 0.74 (NB) to 0.85 (SVM). SVM attained the highest AUC (0.85) and diagnostic accuracy (0.82) of all tested models. The top 3 ranking features in the SVM model were T1-square-first order-skewness (coefficient: 1.735), T2-wavelet-LHH-GLCM-joint energy, and T2-wavelet-LHH-GLCM-inverse difference moment (coefficient: -0.654, -0.634). Radiomics-based analysis with the SVM model is recommended for the detection of TP53 mutations in TNBC. Furthermore, T1WI- and T2WI-related features could be used as noninvasive biomarkers for predicting TP53 mutations.

Exploiting machine learning models to identify novel Alzheimer’s disease biomarkers and potential targets

We still do not have an effective treatment for Alzheimer's disease (AD) despite it being the most common cause of dementia and impaired cognitive function. Thus, research endeavors are directed toward identifying AD biomarkers and targets. In this regard, we designed a computational method that exploits multiple hub gene ranking methods and feature selection methods with machine learning and deep learning to identify biomarkers and targets. First, we used three AD gene expression datasets to identify 1/ hub genes based on six ranking algorithms (Degree, Maximum Neighborhood Component (MNC), Maximal Clique Centrality (MCC), Betweenness Centrality (BC), Closeness Centrality, and Stress Centrality), 2/ gene subsets based on two feature selection methods (LASSO and Ridge). Then, we developed machine learning and deep learning models to determine the gene subset that best distinguishes AD samples from the healthy controls. This work shows that feature selection methods achieve better prediction performances than the hub gene sets. Beyond this, the five genes identified by both feature selection methods (LASSO and Ridge algorithms) achieved an AUC = 0.979. We further show that 70% of the upregulated hub genes (among the 28 overlapping hub genes) are AD targets based on a literature review and six miRNA (hsa-mir-16-5p, hsa-mir-34a-5p, hsa-mir-1-3p, hsa-mir-26a-5p, hsa-mir-93-5p, hsa-mir-155-5p) and one transcription factor, JUN, are associated with the upregulated hub genes. Furthermore, since 2020, four of the six microRNA were also shown to be potential AD targets. To our knowledge, this is the first work showing that such a small number of genes can distinguish AD samples from healthy controls with high accuracy and that overlapping upregulated hub genes can narrow the search space for potential novel targets.

Feature impact assessment: a new score to identify relevant metabolomics features in artificial neural networks using validated labels

Artificial Neural Networks (ANN) are increasingly used in metabolomics but are hard to interpret. We aimed at developing a feature impact score that is model-agnostic, simple, and interpretable. Feature Impact Assessment (FIA) is calculated by varying combinations of features within their observed value range and checking for changes in prediction outcomes. FIA was implemented in R and tested on metabolomics datasets. FIA exceeded LIME and SHAP in selecting biologically meaningful features. Values were comparable across different ANN architectures. FIA is a novel score ranking feature impact, helping interpreting ANN in the metabolomics field.

Explainable machine learning for predicting the band gaps of ABX3 perovskites

In this study, we trained and compared explainable machine learning algorithms for predicting the band gaps of perovskite materials that have the formula ABX3 containing both zero and non-zero band gaps. Six supervised learning models: 5 ensemble learning methods and 1 neural network (CompoundNet) were employed to study the non-linear relationship that exists between the band gap and the characteristics of its constituent elements such as electronegativity, covalent radius, first ionization energy, and row in the periodic table. The machine learning (ML) models were trained on datasets obtained from density functional theory (DFT) calculations. The results show that CatBoost and XGBoost models yielded the least predictive errors and the highest coefficient of determination of R2 ≥ 88% than other approaches in the testing phase. Furthermore, the Shapley Additive Explanation (SHAP) was used for explaining the model based on the elemental composition of each perovskite compound from the physics standpoint, and a novel holistic feature ranking of the explained models was proposed. One key insight gained from the SHAP analysis is that the Pauling electronegativity of the B site cation in the cubic perovskites which characteristically plays an important role in the electronic properties of this class of materials is the feature that contributes most to the prediction of the band gaps. These results reveal the potential of ML to predict materials properties quickly and accurately with datasets useful in the engineering of efficient solar cell devices.

Automated Identification and Segmentation of Ellipsoid Zone At-Risk Using Deep Learning on SD-OCT for Predicting Progression in Dry AMD.

The development and testing of a deep learning (DL)-based approach for detection and measurement of regions of Ellipsoid Zone (EZ) At-Risk to study progression in nonexudative age-related macular degeneration (AMD). Used in DL model training and testing were 341 subjects with nonexudative AMD with or without geographic atrophy (GA). An independent dataset of 120 subjects were used for testing model performance for prediction of GA progression. Accuracy, specificity, sensitivity, and intraclass correlation coefficient (ICC) for DL-based EZ At-Risk percentage area measurement was calculated. Random forest-based feature ranking of EZ At-Risk was compared to previously validated quantitative OCT-based biomarkers. The model achieved a detection accuracy of 99% (sensitivity = 99%; specificity = 100%) for EZ At-Risk. Automatic EZ At-Risk measurement achieved an accuracy of 90% (sensitivity = 90%; specificity = 84%) and the ICC compared to ground truth was high (0.83). In the independent dataset, higher baseline mean EZ At-Risk correlated with higher progression to GA at year 5 (p < 0.001). EZ At-Risk was a top ranked feature in the random forest assessment for GA prediction. This report describes a novel high performance DL-based model for the detection and measurement of EZ At-Risk. This biomarker showed promising results in predicting progression in nonexudative AMD patients.

Performance analysis of feature selection and classification in Big Data Information extraction

Purpose: Information extraction from big data is improved by either reducing the number of features in a data set or selecting features using intelligent data analysis. Generally, big data sets are complex to process using traditional approaches. Feature selection is highly essential in big data information extraction because it chooses the subset of features that influence the final classification. Reducing the number of selected features in the data leads to enhanced accuracy and efficiency of data extraction with other attributes used in the mathematical model. This work aims to improve the performance of the classifier using an enhanced binary bat algorithm-based effective feature selection model. formulated to enhance accuracy, efficiency of data extraction with other attributes. An enhanced binary bat algorithm (EBBA) proposed to solve the mentioned problem using local optimization and global optimization factor which improves the performance of optimization. Experiment carried out with different datasets selected to test effective performance of proposed algorithm and demonstrated performance is better with other algorithms. Design: The purpose of this paper is to provide, an effective feature selection model for big data information extraction. An enhanced binary bat algorithm has been proposed to improve attribute selection using local optimization and global optimization methods. Classification of multisource data using selected features using labeled approach. Particular Information extraction for multi view multi label (PIMM) approach is compared with EBBA algorithm. Further to enhance effectiveness of shared and specific information in big data [3] by setting the delta and omega factors in order to fuse different information from different view point, Online analysis of relevance with any redundancy analysis also been incorporated. Findings: All the experiments were carried out with different datasets on the number of iterations and fitness of the attributes to validate the effective performance of the proposed algorithm. Experimental results and graphs show that the proposed methodology improves the overall performance of optimization using PIMM models. Originality: A feature selection model based on the binary bat algorithm has been the focus of this paper. Subset selection and feature ranking are the two important methods used in this approach. Experiments were conducted on datasets to analyze the patterns in the number of iterations and fitness of the attributes over selection. The improvement in feature selection leads to better classification accuracy of the proposed model compared to other nature inspired techniques.

Melt Instability Identification Using Unsupervised Machine Learning Algorithms

AbstractIn industrial extrusion processes, increasing shear rates can lead to higher production rates. However, at high shear rates, extruded polymers and polymer compounds often exhibit melt instabilities ranging from stick‐slip to sharkskin to gross melt fracture. These instabilities result in challenges to meet the specifications on the extrudate shape. Starting with an existing published data set on melt instabilities in polymer extrusion, we assess the suitability of clustering, unsupervised machine learning algorithms combined with feature selection, to extract and identify hidden and important features from this data set, and their possible relationship with melt instabilities. The data set consists of both intrinsic features of the polymer as well as extrinsic features controlled and measured during an extrusion experiment. Using a range of commonly available clustering algorithms, it is demonstrated that the features related to only the intrinsic properties of the data set can be reliably divided into two clusters, and that in turn, these two clusters may be associated with either the stick‐slip or sharkskin instability. Furthermore, using a feature ranking on both the intrinsic and extrinsic features of the data set, it is shown that the intrinsic properties of molecular weight and polydispersity are the strongest indicators of clustering.

Identification of dynamic gene expression profiles during sequential vaccination with ChAdOx1/BNT162b2 using machine learning methods.

To date, COVID-19 remains a serious global public health problem. Vaccination against SARS-CoV-2 has been adopted by many countries as an effective coping strategy. The strength of the body's immune response in the face of viral infection correlates with the number of vaccinations and the duration of vaccination. In this study, we aimed to identify specific genes that may trigger and control the immune response to COVID-19 under different vaccination scenarios. A machine learning-based approach was designed to analyze the blood transcriptomes of 161 individuals who were classified into six groups according to the dose and timing of inoculations, including I-D0, I-D2-4, I-D7 (day 0, days 2-4, and day 7 after the first dose of ChAdOx1, respectively) and II-D0, II-D1-4, II-D7-10 (day 0, days 1-4, and days 7-10 after the second dose of BNT162b2, respectively). Each sample was represented by the expression levels of 26,364 genes. The first dose was ChAdOx1, whereas the second dose was mainly BNT162b2 (Only four individuals received a second dose of ChAdOx1). The groups were deemed as labels and genes were considered as features. Several machine learning algorithms were employed to analyze such classification problem. In detail, five feature ranking algorithms (Lasso, LightGBM, MCFS, mRMR, and PFI) were first applied to evaluate the importance of each gene feature, resulting in five feature lists. Then, the lists were put into incremental feature selection method with four classification algorithms to extract essential genes, classification rules and build optimal classifiers. The essential genes, namely, NRF2, RPRD1B, NEU3, SMC5, and TPX2, have been previously associated with immune response. This study also summarized expression rules that describe different vaccination scenarios to help determine the molecular mechanism of vaccine-induced antiviral immunity.

Machine-Learning-Derived Entanglement Witnesses

In this work, we show a correspondence between linear support vector machines (SVMs) and entanglement witnesses, and use this correspondence to generate entanglement witnesses for bipartite and tripartite qubit (and qudit) target entangled states. An SVM allows for the construction of a hyperplane that clearly delineates between separable states and the target entangled state; this hyperplane is a weighted sum of observables (``features'') whose coefficients are optimized during the training of the SVM. We demonstrate with this method the ability to obtain witnesses that require only local measurements even when the target state is a nonstabilizer state. Furthermore, we show that SVMs are flexible enough to allow us to rank features, and to reduce the number of features systematically while bounding the inference error. This allows us to derive $W$-state witnesses capable of detecting entanglement with fewer measurement terms than the fidelity method dominant in today's literature. The utility of this approach is demonstrated on quantum hardware furnished through the IBM Quantum Experience.

Machine learning- based lung disease diagnosis from CT images using Gabor features in Littlewood Paley empirical wavelet transform (LPEWT) and LLE

ABSTRACT The term ‘lung disease’ covers a wide range of conditions that affect the lungs, including asthma, COPD, infections like the flu, pneumonia, tuberculosis, lung cancer, COVID, and numerous other breathing issues. Respiratory failure may result from several respiratory disorders. Recently, various methods have been proposed for lung disease detection, but they are not much more efficient. The proposed model has been tested on the COVID dataset. In this work, Littlewood-Paley Empirical Wavelet Transform (LPEWT) based technique is used to decompose images into their sub-bands. Using locally linear embedding (LLE), linear discriminative analysis (LDA), and principal component analysis (PCA), robust features are identified for lung disease detection after texture-based relevant Gabor features are extracted from images. LLE’s outcomes inspire the development of new techniques. The Entropy, ROC, and Student’s t-value methods provide ranks for robust features. Finally, LS-SVM is fed with t-value-based ranked features for classification using Morlet wavelet, Mexican-hat wavelet, and radial basis function. This model, which incorporated tenfold cross-validation, exhibited improved classification accuracy of 95.48%, specificity of 95.37%, sensitivity of 95.43%, and an F1 score of.95. The proposed diagnosis method can be a fast disease detection tool for imaging specialists using medical images.

Towards lowering computational power in IoT systems: Clustering algorithm for high-dimensional data stream using entropy window reduction

In a world of connectivity empowered by the advancement of the Internet of Things (IoT), an infinite number of data streams have emerged. Thus, data stream clustering is crucial for extracting hidden knowledge and data mining. Various data stream clustering methods have lately been introduced. Yet, the majority of such algorithms are affected by the curse of high dimensionality. Lately, a fully online buffer-based clustering algorithm for handling evolving data streams (BOCEDS) was developed. Similarly to other existing density-based clustering methods, BOCEDS is not capable of handling high-dimensional data and has high computational power and high memory utilization. This paper introduces an Entropy Window Reduction (EWR) algorithm, which is an improved version of the BOCEDS technique. EWR is a fully online clustering technique for handling high-dimensional data streams using feature ranking and sorting. This process is accomplished by calculating the entropy of specific features with respect to the time window. The findings of the experiments are compared to the outcomes of BOCEDS, CEDAS, and MuDi-Stream algorithms. The outcomes indicate that the EWR algorithm outperformed the baseline clustering algorithms. The results are demonstrated using the KDDCup’99 dataset in terms of quality and complexity evaluation on the average of F-Measures, Jaccard Index, Fowlkes–Mallows index, Purity, and Rand Index as well as the memory usage and computational power with 88%, 66%, 81%, 100%, and 66%, respectively. The results also show low memory usage and computing power in comparison with the baseline algorithms.

Assessment of Alzheimer-related pathologies of dementia using machine learning feature selection

Although a variety of brain lesions may contribute to the pathological assessment of dementia, the relationship of these lesions to dementia, how they interact and how to quantify them remains uncertain. Systematically assessing neuropathological measures by their degree of association with dementia may lead to better diagnostic systems and treatment targets. This study aims to apply machine learning approaches to feature selection in order to identify critical features of Alzheimer-related pathologies associated with dementia. We applied machine learning techniques for feature ranking and classification to objectively compare neuropathological features and their relationship to dementia status during life using a cohort (n=186) from the Cognitive Function and Ageing Study (CFAS). We first tested Alzheimer’s Disease and tau markers and then other neuropathologies associated with dementia. Seven feature ranking methods using different information criteria consistently ranked 22 out of the 34 neuropathology features for importance to dementia classification. Although highly correlated, Braak neurofibrillary tangle stage, beta-amyloid and cerebral amyloid angiopathy features were ranked the highest. The best-performing dementia classifier using the top eight neuropathological features achieved 79% sensitivity, 69% specificity and 75% precision. However, when assessing all seven classifiers and the 22 ranked features, a substantial proportion (40.4%) of dementia cases was consistently misclassified. These results highlight the benefits of using machine learning to identify critical indices of plaque, tangle and cerebral amyloid angiopathy burdens that may be useful for classifying dementia.

A risk prediction model based on machine learning for early cognitive impairment in hypertension: Development and validation study.

Clinical practice guidelines recommend early identification of cognitive impairment in individuals with hypertension with the help of risk prediction tools based on risk factors. The aim of this study was to develop a superior machine learning model based on easily collected variables to predict the risk of early cognitive impairment in hypertensive individuals, which could be used to optimize early cognitive impairment risk assessment strategies. For this cross-sectional study, 733 patients with hypertension (aged 30-85, 48.98% male) enrolled in multi-center hospitals in China were divided into a training group (70%) and a validation group (30%). After least absolute shrinkage and selection operator (LASSO) regression analysis with 5-fold cross-validation determined the modeling variables, three machine learning classifiers, logistic regression (LR), XGBoost (XGB), and gaussian naive bayes (GNB), were developed. The area under the ROC curve (AUC), accuracy, sensitivity, specificity, and F1 score were used to evaluate the model performance. Shape Additive explanation (SHAP) analysis was performed to rank feature importance. Further decision curve analysis (DCA) assessed the clinical performance of the established model and visualized it by nomogram. Hip circumference, age, education levels, and physical activity were considered significant predictors of early cognitive impairment in hypertension. The AUC (0.88), F1 score (0.59), accuracy (0.81), sensitivity (0.84), and specificity (0.80) of the XGB model were superior to LR and GNB classifiers. The XGB model based on hip circumference, age, educational level, and physical activity has superior predictive performance and it shows promise in predicting the risk of cognitive impairment in hypertensive clinical settings.

Random Forest Importance-Based Feature Ranking and Subset Selection for Slope Stability Assessment using the Ranger Implementation

Stability problems of slopes can arise from various factors such as geometrical, geological, seismic etc. For many years, conventional methods such as limit equilibrium method, numerical methods, and statistical methods have been successfully utilized to predict the stability of slopes. On the other hand, several machine learning (ML) attempts have been made for predicting slope stability using datasets available in the literature. The present study aims to build classification models for the assessment of the stability of slopes using the Ranger algorithm. A total of 168 cases with six input parameters (slope height, unit weight, slope angle, cohesion, pore water pressure ratio, and internal friction angle) are used to generate models. In the first step, random forest (RF) feature importance scores of the six features are determined and five different prediction models were produced by reducing the feature numbers of the dataset. The developed models are then assessed using performance metrics and results are compared to choose the best prediction model. According to the obtained results, the feature importance-based feature ranking and subset selection approach (i.e., RF feature importance) affect the performance of the models. It is observed that from the RF feature importance scores, the unit weight is found to be the most influencing feature that affects the stability of slopes for the studied dataset. In addition, the Ranger model developed with five features (Model IV) achieves the highest test accuracy with a value of 90%.