An integrated machine learning framework for a discriminative analysis of schizophrenia using multi-biological data

Heterogeneity in the etiology, pathophysiology, and clinical features of schizophrenia challenges clinicians and researchers. A helpful approach could be stratifying patients according to the presence or absence of clinical features of the deficit syndrome (DS). DS is characterized by enduring and primary negative symptoms, a clinically less heterogeneous subtype of the illness, and patients with features of DS are thought to present abnormal brain network characteristics, however, this idea has received limited attention. We investigated functional brain network topology in patients displaying deficit features and those who do not. We applied graph theory analytics to resting-state functional magnetic resonance imaging data of 61 antipsychotic medication-naïve first episode psychosis patients, 18 DS and 43 non-deficit schizophrenia (NDS), and 72 healthy controls (HC). We quantified small-worldness, global and nodal efficiency measures, shortest path length, nodal local efficiency, and synchronization and contrasted them among the 3 groups. DS presented decreased network integration and segregation compared to HC and NDS. DS showed lower global efficiency, longer global path lengths, and lower global local efficiency. Nodal efficiency was lower and the shortest path length was longer in DS in default mode, ventral attention, dorsal attention, frontoparietal, limbic, somatomotor, and visual networks compared to HC. Compared to NDS, DS showed lower efficiency and longer shortest path length in default mode, limbic, somatomotor, and visual networks. Our data supports increasing evidence, based on topological perturbations of the functional connectome, that deficit syndrome may be a distinct form of the illness.

Biological matrix data are essential for computational analysis, providing a structured framework to identify patterns and relationships in biological systems. Many other biological data types, including sequences, networks, and images, can be transformed into matrix representations through feature extraction and encoding. However, their high dimensionality complicates analysis, leading to increased computational complexity and the risk of overfitting, known as the curse of dimensionality. To address these challenges, we developed SIBioX, a matrix-based bioinformatics tool powered by swarm intelligence algorithms. It integrates 54 swarm intelligence methods, 5 conventional feature selection techniques, and 17 machine learning models, enabling comprehensive analysis of biological matrix data. With a user-friendly graphical interface, it supports operations such as feature normalization, selection, classification, clustering, statistical analysis, and data visualization. Additionally, it converts nonmatrix biological data, like gene and protein sequences, into matrix formats for further study. Experimental results demonstrate that SIBioX not only attains high accuracy in feature selection but also effectively reduces dimensionality, thereby streamlining bioinformatics workflows and promoting greater efficiency in biomedical research.

In the present state of affairs, the motive behind every educational organization is to uplift the academic achievement of students. Educational data mining (EDM) is an upward field of research, and it is very helpful for academic institutions to predict the academic performance of the students. Educational datasets are the basis of various predictive models. Quality of these models can be improved by using feature selection (FS). To get the required benefits from the available data, there must be some tools for analysis and prediction. In lieu of the above, machine learning/data mining are most suitable. In educational data mining, for better accuracy of prediction models’ and quality of various educational datasets, feature selection (FS) plays a vital role. Feature selection (FS) algorithms abolish inappropriate information from the repositories of educational background so that performance of classifier in terms of accuracy could be increased and the same could be used for better decision. In lieu of the above, a best feature selection algorithm must be selected. In this paper, two filter selection approaches namely correlation feature selection (CFS) and wrapper-based feature selection have been used to demonstrate the importance of selection of a feature subset for a classification problem. The present paper aims to find the detailed investigation of filter feature selection algorithms along with the classification algorithms on a given dataset. We found result with numerous numbers of features from various Feature selection algorithms and classifiers which will help the researcher to discover the most excellent mixture of filter feature selection algorithms and its associated classifiers. The result indicates that SMO and J48 have the highest accuracy measures with the correlation feature selection algorithms, while Naïve Bayes has the highest accuracy measures with the wrapper subset feature selection algorithms for predicting high, medium and low grade for the students.

BackgroundStudies have confirmed brain network topology disruption in schizophrenia (SZ). Electroconvulsive therapy (ECT) rapidly improves acute psychiatric symptoms, yet the exact mechanism by which it impacts brain network topology in SZ patients remains unclear. This study aims to explore topological changes in SZ patients' whole-brain functional networks during ECT, ultimately elucidating implicated neurological mechanisms.MethodsThis study collected resting-state functional magnetic resonance imaging (rs-fMRI) data from 53 patients with schizophrenia before and after ECT, as well as data from 46 age-, gender-, and education-matched healthy control participants (HC). Using the Brainnetome Atlas, brain functional networks were constructed for each participant. Graph theory methods were applied to measure global and nodal topological properties. Clinical symptoms of patients were assessed using the Positive And Negative Syndrome Scale (PANSS). Independent sample t-tests were employed to compare topological properties between patients and healthy controls, while paired t-tests were used to assess before and after ECT differences within the patient group. Finally, partial correlation analyses were conducted to examine the relationship between changes in topological properties and changes in PANSS scores among patients before and after ECT.ResultsBefore ECT, compared to the HC group, the patient group demonstrated reduced local efficiency (Eloc) and clustering coefficient (Cp). In the right superior temporal gyrus, degree centrality (Dc) and nodal global efficiency (Ne) were lower, whereas in the left cingulate gyrus, Ne and Dc were higher. Following ECT, Eloc and Cp normalized in the patient group. Additionally, nodal local efficiency (NLe) and nodal clustering coefficient (NCp) increased in the bilateral superior frontal gyrus. Conversely, in the left inferior parietal lobule, Ne and Dc decreased, and nodal shortest path length (NLp) increased. Both NLe and NCp were lower in the bilateral lateral occipital cortex, both before and after ECT. However, no significant correlation was observed between changes in PANSS scores and alterations in global and nodal topological properties before and after ECT treatment.ConclusionsOur study suggests that ECT may improve psychiatric symptoms by modulating the integration and dissociation functions within damaged brain networks in SZ patients. Specifically, the balance between the integration and dissociation functions of the default mode network (DMN), central executive network (CEN), and auditory networks (AN) may play a crucial role in the improvement of psychiatric symptoms.

This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although a significant increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.

Neutrophil-lymphocyte ratio (NLR), platelet-lymphocyte ratio (PLR), monocyte-lymphocyte ratio (MLR), mean platelet volume (MPV), and systemic immune inflammation index (SII) are recently used as indicators of inflammation. NLR, PLR, MLR, and MPV have been evaluated in many studies in patients with schizophrenia and bipolar disorder. However, there are no studies investigating SII. This study aims to evaluate NLR, PLR, MLR, MPV and SII values and complete blood count elements in patients hospitalized with diagnoses of the schizophrenia with psychotic episode and bipolar disorder with manic episode by comparing them with the control group. A total of 149 patients who were hospitalized with the diagnoses of the schizophrenia with psychotic episode and bipolar disorder with manic episode and who met the inclusion criteria were included in our study where the control group was composed of 66 healthy individuals. White blood cell (WBC), neutrophil, lymphocyte, platelet, and monocyte counts were obtained retrospectively from complete blood counts at the time of admission, based on which NLR, PLR, MLR, and SII were calculated. In this study, higher NLR, PLR, and SII values and lower MPV and lymphocyte counts were observed in schizophrenia patients compared to the control group. NLR, PLR, and SII values and neutrophil counts were higher in patients with bipolar disorder compared to the control group. Lower MPV values were found in patients with schizophrenia compared to patients with bipolar disorder. Simple inflammatory and SII values in our study indicate the presence of low-grade systemic inflammation in schizophrenia and bipolar disorder.

Text classification has been highlighted as the key process to organize online texts for better communication in the Digital Media Age. Text classification establishes classification rules based on text features, so the accuracy of feature selection is the basis of text classification. Facing fast-increasing Chinese electronic documents in the digital environment, scholars have accumulated quite a few algorithms for the feature selection for the automatic classification of Chinese texts in recent years. However, discussion about how to adapt existing feature selection algorithms for various types of Chinese texts is still inadequate. To address this, this study proposes three improved feature selection algorithms and tests their performance on different types of Chinese texts. These include an enhanced CHI square with mutual information (MI) algorithm, which simultaneously introduces word frequency and term adjustment (CHMI); a term frequency–CHI square (TF–CHI) algorithm, which enhances weight calculation; and a term frequency–inverse document frequency (TF–IDF) algorithm enhanced with the extreme gradient boosting (XGBoost) algorithm, which improves the algorithm’s ability of word filtering (TF–XGBoost). This study randomly chooses 3000 texts from six different categories of the Sogou news corpus to obtain the confusion matrix and evaluate the performance of the new algorithms with precision and the F1-score. Experimental comparisons are conducted on support vector machine (SVM) and naive Bayes (NB) classifiers. The experimental results demonstrate that the feature selection algorithms proposed in this paper improve performance across various news corpora, although the best feature selection schemes for each type of corpus are different. Further studies of the application of the improved feature selection methods in other languages and the improvement in classifiers are suggested.

New hybrid data mining model for credit scoring based on feature selection algorithm and ensemble classifiers

Feature (or variable) selection is the process of identifying the minimal set of features with the highest predictive performance on the target variable of interest. Numerous feature selection algorithms have been developed over the years, but only few have been implemented in R and made publicly available R as packages while offering few options. The R package MXM offers a variety of feature selection algorithms, and has unique features that make it advantageous over its competitors: a) it contains feature selection algorithms that can treat numerous types of target variables, including continuous, percentages, time to event (survival), binary, nominal, ordinal, clustered, counts, left censored, etc; b) it contains a variety of regression models that can be plugged into the feature selection algorithms (for example with time to event data the user can choose among Cox, Weibull, log logistic or exponential regression); c) it includes an algorithm for detecting multiple solutions (many sets of statistically equivalent features, plain speaking, two features can carry statistically equivalent information when substituting one with the other does not effect the inference or the conclusions); and d) it includes memory efficient algorithms for high volume data, data that cannot be loaded into R (In a 16GB RAM terminal for example, R cannot directly load data of 16GB size. By utilizing the proper package, we load the data and then perform feature selection.). In this paper, we qualitatively compare MXM with other relevant feature selection packages and discuss its advantages and disadvantages. Further, we provide a demonstration of MXM’s algorithms using real high-dimensional data from various applications.

AIM: This study aimed to evaluate the potential of hematologic parameters and markers such as neutrophil-lymphocyte ratio (NLR), platelet-lymphocyte ratio (PLR), monocyte-lymphocyte ratio (MLR), systemic immune-inflammation index (SII), and systemic inflammation response index (SIRI) to predict the risk of malignancy in patients whose biopsy results were classified as Atypia of Undetermined Significance/Follicular Lesion of Undetermined Significance (AUS/FLUS). MATERIAL AND METHOD: A total of 188 patients who underwent thyroidectomy at a General Surgery clinic were included in the study. Hematological parameters, including neutrophil count, platelet count, lymphocyte count, monocyte count, and mean platelet volume (MPV) were collected from the hospital database. NLR, PLR, MLR, SII, and SIRI were calculated. Statistical analyses were performed using SPSS v25. RESULTS: 38 patient (20.21%) were male and 150 patients (79.79 %) were female. The mean age was 48.6 (range 23-79, standard deviation (SD) ± 12.41years). Histopathological examination of the thyroidectomy specimens revealed benign findings in 102 patients (54.3%) and malignant findings in 86 patients (45.7%). The mean age of the malignant group was 45.6, while that of the benign group was 51.1 (p = 0.02). The median tumor size was 17 mm in the malignant group and 21 mm in the benign group (p =0.042). Mean neutrophil count were 4.29 ± 1.0 × 109/L in the benign group and 4.69 ± 1.9 × 109/L in malignant group, respectively (p = 0.031). NLR values were calculated as 1.89 for the benign group and 1.99 for the malignant group (p = 0.045). SII values were higher in the malignant group, with a median value of 584.11× 109/L in the malignant group, median value were 504.63× 109/L in the benign group (p=0.037). Multivariate logistic regression analysis revealed that both age (odds ratio (OR) = 0.964; 95% confidence interval (CI)= (0.939 – 0.989); p = 0.05) and neutrophil count (odds ratio (OR) = 1.598; 95% confidence interval (CI)= (1.118 – 2.285); p = 0.01) had a significant impact on the differentiation between benign and malignant thyroid nodules. CONCLUSION: Age and neutrophil count were identified as independent risk factors for malignant thyroid nodules. Among patients with Bethesda Category III thyroid nodules, those under 59.5 years of age and with a neutrophil count above 4.16 x 10^9/L have an increased risk for thyroid malignancy. Platelet count, monocyte count, MPV and inflammatory parameters, such as PLR, MLR, and SIRI, were insufficient for detecting malignancy in Bethesda III nodules. In this group, young age, small nodule size, high neutrophil count, NLR, and SII were identified as risk factors for malignancy. The Thyroid Imaging Reporting and Data System (TI-RADS) characteristics of nodules should also be considered in the management of these patients.

With the advancement of machine learning algorithms, the electroencephalogram (EEG) signal can be highly useful to identify the motor neuron activity (also known as motor imagery, MI event). Depending on the problem and experimental dataset/protocol, researchers use different classification algorithms to classify motor imagery events. Therefore, the selection of classification algorithms for accurate MI detection is significantly important. This paper attempts to provide a brief comparison of the performance of different classification algorithms for MI detection in EEG data. At first, the EEG data of 30 random subjects were collected from a publicly available dataset. Then a combination of time domain and frequency domain features were extracted from the EEG data. Next, the correlated feature selection (CFS) algorithm was used to rank the features based on the correlation. To further reduce the feature set, forward feature selection (FFS) algorithm that was utilized to find out the significant features. For classification, support vector machine (SVM), logistic regression (LR), naive bayes (NB), and k-nearest neighbor (KNN) were investigated with leave one subject out cross-validation scheme. Finally, the performance of all the classifiers was evaluated using the f1-score. The SVM classifier achieved an average f1-score of 70.26% from 30 subjects' trials. The results suggest that the SVM classifier may perform better than other classifiers. Additionally, the linear kernel of SVM helped to reduce the computational time and complexity of the model. It is expected that the SVM classifier may provide better performance in a wider range of populations.

Based on benchmarking various methods and analyzing multiple real scRNA-seq datasets, a computational platform/workflow and a set of tips for best practices are developed for analyzing causal interactions or relationships in single cells.

Irrelevant feature in heart disease dataset affects the performance of binary classification model. Consequently, eliminating irrelevant and redundant feature (s) from training set with feature selection algorithm significantly improves the performance of classification model on heart disease detection. Sequential feature selection (SFS) is successful algorithm to improve the performance of classification model on heart disease detection and reduces the computational time complexity. In this study, sequential feature selection (SFS) algorithm is implemented for improving the classifier performance on heart disease detection by removing irrelevant features and training a model on optimal features. Furthermore, exhaustive and permutation based feature selection algorithm are implemented and compared with SFS algorithm. The implemented and existing feature selection algorithms are evaluated using real world Pima Indian heart disease dataset and result appears to prove that the SFS algorithm outperforms as compared to exhaustive and permutation based feature selection algorithm. Overall, the result looks promising and more effective heart disease detection model is developed with accuracy of 99.3%.

With the growth of Internet, there has been a tremendous increases in the number of attacks and therefore Intrusion Detection Systems (IDS’s) has become a main stream of information security. The purpose of IDS is to help the computer systems to deal with attacks. This anomaly detection system creates a database of normal behaviour and deviations from the normal behaviour to trigger during the occurrence of intrusions. Based on the source of data, IDS is classified into Host based IDS and Network based IDS. In network based IDS, the individual packets flowing through the network are analyzed where as in host based IDS the activities on the single computer or host are analyzed. The feature selection used in IDS helps to reduce the classification time. In this paper, the IDS for detecting the attacks effectively has been proposed and implemented. For this purpose, a new feature selection algorithm called Optimal Feature Selection algorithm based on Information Gain Ratio has been proposed and implemented. This feature selection algorithm selects optimal number of features from KDD Cup dataset. In addition, two classification techniques namely Support Vector Machine and Rule Based Classification have been used for effective classification of the data set. This system is very efficient in detecting DoS attacks and effectively reduces the false alarm rate. The proposed feature selection and classification algorithms enhance the performance of the IDS in detecting the attacks.

IntroductionGeneralized tonic‐clonic seizure (GTCS) is a condition that is characterized by generalized spike‐wave discharge in bilateral cerebral hemispheres during the seizure. Although previous neuroimaging studies revealed functional abnormalities in the brain activities of children with GTCS, the topological alterations in whole‐brain networks remain poorly understood.MethodsThe present study used graph theory to investigate the topological organization of functional networks in 13 GTCS children and 30 age‐matched healthy controls.ResultsWe found that both groups exhibited a small‐world topology of the functional network. However, children with GTCS showed a significant decrease in nodal local efficiency and clustering coefficient in some key nodes compared with the controls. The connections within the default mode network (DMN) were decreased significantly, and the internetwork connections were increased significantly. The altered topological properties may be an effect of chronic epilepsy. As a result, the optimal topological organization of the functional network was disrupted in the patient group. Notably, clustering coefficient and nodal local efficiency in the bilateral temporal pole of the middle temporal gyrus negatively correlated with the epilepsy duration.ConclusionThese results suggest that the bilateral temporal pole plays an important role in reflecting the effect of chronic epilepsy on the topological properties in GTCS children. The present study demonstrated a disrupted topological organization in children with GTCS. These findings provide new insight into our understanding of this disorder.