Search

This article discusses the use of in silico prediction methods to understand the binding of peptides to human leucocyte antigen class II (HLAII) molecules. Traditional structure-based methods have faced challenges in accuracy due to the dynamic nature of peptide-HLAII interactions. In recent years, machine learning techniques, such as support vector machines and neural networks, have been used to predict peptide-HLAII binding affinities. The article benchmarks the use of AlphaLink2 and AlphaFold2 Multimer in predicting correct peptide binding motifs, which could have implications for vaccine development and protein deimmunization. However, it is important to note that this preprint has not been peer-reviewed. [Extracted from the article]

Researchers at the University Medical Center Utrecht in the Netherlands have conducted a study on vessel disease, specifically focusing on lesion-symptom mapping (LSM) in cerebral small vessel disease. LSM is used to understand how lesions in the brain impact cognitive performance. The researchers compared the performance of neural networks (NNs) with support vector regression (SVR), a current gold standard method. While the CNN with explainable AI (XAI) did not outperform SVR, it was able to detect relevant lesion locations, showing potential for LSM. This research provides insights into the use of machine learning techniques in understanding vessel disease. [Extracted from the article]

In partial label learning (PLL) problem, each training sample corresponds to a group of candidate labels, in which only one label is the ground-truth label (correct label). Almost all the existing PLL algorithms attempt to eliminate the ambiguity of the candidate label sets by treating all labels indiscriminately. However, this kind of approach lacks the consideration of the complexity between the labels and the instances in the training process. Encouraged by the extensive researches of the self-paced learning (SPL) and transfer learning (TL) in various fields, this paper introduces SPL and TL together to address the PLL problem and proposes a new SPL framework, which is called self-paced method for transfer partial label learning (SPTPLL). The proposed model utilizes transfer learning model to share the parameters and regularization terms of the Support Vector Machine (SVM), which can transfer knowledge from the source task to the target task. Additionally, we implement the self-paced learning scheme by choosing a suitable self-paced function to enhance the robustness of the proposed model. In the process of learning iteration, the priority of training examples with their candidate labels is ranked through self-paced learning to control the learning process. Finally, we demonstrate the superior performance of the proposed method through a large number of experiments compared with state-of-the-art baseline methods. [ABSTRACT FROM AUTHOR]

A recent report from the Chinese University of Hong Kong discusses the use of machine learning in predicting heart disease. The researchers highlight the advancements in machine learning and deep learning that have improved the accuracy of heart disease prediction by utilizing various patient data, such as electrocardiograms, historical diagnoses, and genomic information. However, challenges still remain, including algorithmic safety, ethical considerations, and the need for clinical validation. The researchers suggest that future research should focus on integrating multimodal data, enhancing model interpretability, and addressing privacy concerns to further improve predictive accuracy and clinical utility. [Extracted from the article]

A recent study conducted by researchers at Nanjing Drum Tower Hospital Clinical College of Nanjing Medical University explored the value of multiple preprocessors and classifiers in constructing models for predicting microsatellite instability (MSI) status in colorectal cancer (CRC). The study aimed to accurately and non-invasively predict MSI status, which is crucial for cost savings and guiding clinical treatment strategies. The researchers used a retrospective study of 307 CRC patients and performed feature extraction and model construction using various preprocessors and classifiers. The logistic regression model based on the quantile preprocessor exhibited excellent performance and repeatability, suggesting it may improve the model's predictive capabilities for MSI status in CRC. The study also identified tumor location, N stage clinical status, and hypertension as independent clinical predictors of MSI status. The combined model showed excellent predictive performance and clinical applicability. [Extracted from the article]

A recent report discusses research findings on pneumonia and anastomotic leak after transthoracic esophagectomy for cancer. The study aimed to identify predictive risk factors and procedure-related failure-to-rescue (FTR) using a large dataset. The researchers analyzed 1,355 patients and found that factors associated with pneumonia were more numerous than those associated with anastomotic leak. However, the rates of failure-to-rescue did not significantly differ among different operation types, suggesting that minimally-invasive procedures can be safely implemented with experience. Machine-learning models were unable to accurately predict complications or failure-to-rescue. [Extracted from the article]

A recent study conducted at the University of Wisconsin Madison explores the impact of the tumor microenvironment on cancer growth and development. The study focuses on early breast cancer patients and examines the collagen fibers surrounding the tumor tissue to identify potential biomarkers for diagnosis and prognosis. The researchers propose a novel support vector machine (SVM)-based predictive algorithm to analyze the complex relationship between the fibers and the tumor status. The study offers reproducible implementations of the algorithms in the R package mildsvm. This research has been peer-reviewed and published in the Annals of Applied Statistics. [Extracted from the article]

The article focuses on the development of an AI-based diagnostic model for pertussis pneumonia by researchers at Chongqing University. Topics include the use of machine learning algorithms combined with biochemical blood tests, the comparison of diagnostic accuracy among different algorithms, and the identification of key clinical and biochemical features associated with pertussis, with the XGBoost model showing the highest performance in terms of diagnostic accuracy.

A study conducted at Dortmund Hospital in Germany has developed an artificial-intelligent prediction model for the occurrence of cerebral vasospasms, a dangerous complication of a ruptured cerebral aneurysm. The existing scales used to predict the outcome and occurrence of vasospasms are not reliable. The study used an algorithm based on machine learning and achieved an accuracy of 61%-86% in predicting symptomatic vasospasms. The researchers believe that this algorithm can help identify patients at high risk for vasospasms and allow for early intervention to prevent permanent damage. [Extracted from the article]

Researchers from Qingdao Agricultural University in China have proposed a novel method for food safety testing based on infrared spectroscopy. The method, called negentropy-sorted kernel independent component analysis (NS-kICA), was used to analyze Fourier transform infrared spectroscopy data and rank the components based on non-Gaussian independent components. The researchers found that NS-kICA outperformed conventional feature selection methods, and the support vector machine model was the most effective for recognition performance. These findings are significant for food safety testing and can contribute to achieving high, stable, and efficient results. [Extracted from the article]

A recent study explored the role of DNA methylation in lung adenocarcinoma (LUAD), the most common subtype of lung cancer. The study identified differentially methylated sites (DMSs) and found that hypermethylation in certain regions of the DNA was associated with critical developmental processes and disrupted cellular functions, potentially contributing to tumorigenesis. The study also demonstrated the diagnostic potential of these hypermethylated sites and identified distinct methylation subgroups within LUAD tumors. These findings contribute to our understanding of LUAD and highlight the clinical utility of DNA methylation as a diagnostic tool. However, it is important to note that this study has not yet undergone peer review. [Extracted from the article]

A recent study conducted at the University of Utah has found that ataxic breathing (AB), a known effect of opioids, can be used to detect opioid-induced respiratory depression (OIRD) earlier in normal volunteers. The researchers used a support vector machine learning approach to quantify AB in volunteers receiving increasing doses of remifentanil. They found that AB was frequently present even when traditional measures of OIRD, such as reduced mental alertness and bradypnea, were not detected. These findings suggest that AB could be a useful additional measure in recognizing OIRD and further trials are needed to explore its clinical utility with other opioids. [Extracted from the article]

Researchers at Vilnius Gediminas Technical University in Lithuania have conducted a study on the detection of pathological gaits using electromyography (EMG) signals. The aim of the study was to determine the most appropriate advanced methods for distinguishing the gait of healthy children from those with cerebral palsy. The study used an EMG database of 22 children and employed three classification algorithms: support vector machine (SVM), k-nearest neighbors (KNNs), and decision tree (DT). The highest classification accuracy was achieved using the KNN algorithm, indicating that muscle coactivation can be a reliable parameter in gait classification tasks. [Extracted from the article]

The article reports on a new atrial fibrillation detection method developed by Foshan University, which combines advanced techniques like CEPNCC-BiLSTM and photoelectric pulse wave technology to enhance detection accuracy and reduce false positives. Topics discussed include the limitations of traditional detection methods, the improved efficiency and sensitivity of the new method, and the introduction of the ET-score evaluation system for a comprehensive performance assessment.

A researcher at the Georgia Institute of Technology has published a study on support vector machines (SVM) in the field of magnetic resonance elastography (MRE). MRE is an imaging technique that measures tissue stiffness, but poor image acquisition can occur if there is insufficient contact between the MRE actuator and the patient. The researcher developed a sensor-embedded tissue phantom setup paired with an SVM classifier to automate the MRE actuator testing process. The study found that this setup showed potential for improving the MRE actuator development process by automatically detecting contact-related issues before clinical testing. [Extracted from the article]

This article discusses the importance of predicting the quaternary structure and function of proteins in various applications such as pharmaceuticals, drug design, and medical or engineering fields. With the increasing number of protein sequences available, it is crucial to quickly understand the quaternary structural characteristics of proteins for genomics research. The study presents a method using amino acid composition and a support vector machine with a sequential optimization technique to discriminate between hetero-oligomers and non-hetero-oligomers. It is important to note that this preprint has not undergone peer review. [Extracted from the article]

A study conducted in Warangal, India, by researchers from the School of Engineering has developed a hybrid deep learning method for accurately classifying breast lesions as benign or malignant. The method combines a modified Lipschitz-based image augmentation technique, k-fold cross-validation, and a hybrid convolutional neural network (CNN) approach. The deep features extracted from the CNNs are further reduced using a recursive feature elimination technique and then fed into machine learning classifiers. The results show that the proposed model outperforms existing techniques, achieving high accuracy, sensitivity, specificity, precision, and F1 score. This research has been peer-reviewed and provides valuable insights into breast cancer classification. [Extracted from the article]

A recent study conducted by researchers at Southeast University focused on predicting cervical cancer using a machine learning-based approach. Cervical cancer is a leading cause of premature death among women, with the majority of cases occurring in underdeveloped countries. The study utilized early screening and risk trends from individual health records to develop a predictive model. By employing machine learning classifiers and feature selection techniques, the researchers achieved an accuracy rate of 99.19%. The study highlights the effectiveness of the ensemble machine learning classifier in handling classification problems and addressing the issue of high-class imbalance. [Extracted from the article]

Researchers at the University of Ha'il in Saudi Arabia have used artificial intelligence (AI) to model the solubility of the medication Alendronate. By inputting temperature and pressure parameters, the researchers evaluated three different models, with the AdaBoost model showing the highest performance. The research concluded that using this ensemble method, the root mean square error rate was 4.30E-02 and the mean absolute error was 2.96E-02. This study demonstrates the potential of AI in optimizing drug solubility and improving therapeutic effectiveness. [Extracted from the article]

Researchers at Gachon University in Seongnam si, South Korea have developed a novel hybrid approach called Neuro-Health Guardian for precision brain stroke prediction and healthcare analytics. The approach integrates machine learning techniques such as Logistic Regression, Naive Bayes, K-Nearest Neighbors, and Support Vector Machine (SV) to create an ensemble model that accurately predicts stroke risk. The study emphasizes the importance of early stroke detection and intervention to prevent worsening of the condition. The research offers valuable insights for the development of predictive models related to stroke prevention and treatment. [Extracted from the article]

A recent study conducted at the Indian Institute of Technology Kanpur has proposed a new approach to feature extraction in motor imagery-based brain-computer interfaces (BCIs). The traditional method, known as common spatial pattern (CSP), often lacks robustness against variations in electroencephalogram (EEG) signals. The researchers introduced a novel method called SCSP-3, which combines spectral information obtained from power-spectrum estimation with temporal variations. The results showed that SCSP-3 outperformed traditional CSP in terms of accuracy and generalizability, making it a promising alternative for consistent performance across different subject categories. [Extracted from the article]

A recent study conducted by researchers at Motilal Nehru National Institute of Technology Allahabad in Uttar Pradesh, India, focused on using machine learning-based classification models to identify autism spectrum disorder (ASD) using neuroimaging data. The study introduced a novel correlation-based functional connectivity method to extract improved Region of Interest (ROI) coupling features from the Autism Brain Imaging Data Exchange (ABIDE) dataset. The researchers also employed graph embedding domain adaptation (GEDA) to mitigate dataset heterogeneity and enhance classification accuracy. The proposed model achieved an accuracy of 78.1% and AUROC of 83.9% in identifying ASD patients, showing a substantial improvement compared to previous models. The study concluded that there are disruptions in brain connectivity between anterior and posterior brain regions in individuals with ASD. [Extracted from the article]

Researchers from Universitas Muslim Indonesia conducted a study to analyze the performance of three classification models (Decision Tree Classifier, Support Vector Machine, and Naive Bayes Classifier) in predicting lung cancer using the "Lung Cancer Prediction" dataset. The study found that all three models demonstrated good potential in lung cancer prediction, with the Decision Tree Classifier and Naive Bayes Classifier showing similar high performance and the Support Vector Machine exhibiting competitive performance. However, the selection of the best model should consider relevant evaluation metrics and the limitations of each model. Further evaluation and analysis are needed to improve the accuracy and consistency of lung cancer prediction. [Extracted from the article]

A new report discusses research findings on the integration of quantum computing and machine learning in healthcare. The study, conducted by researchers at Yonsei University in Seoul, South Korea, focused on predicting mortality in patients with early-onset colorectal cancer. The researchers compared the performance of quantum support vector machine (QSVM) models with classical support vector machine (SVM) models and found that the QSVM models outperformed the conventional SVM models in terms of predictive accuracy. The study highlights the potential of quantum computing to improve predictive modeling in healthcare, particularly for rare diseases with limited available data. [Extracted from the article]

This article discusses the role of exosomal microRNAs (exomiRs) in cancer metastasis. ExomiRs are small molecules that are transported between cells and play a crucial role in intercellular communication. In cancer, exomiRs influence tumor progression by regulating processes such as proliferation, angiogenesis, and metastasis. The study aims to characterize the role of exomiRs in influencing the pre-metastatic niche (PMN) in various types of cancer. The analysis reveals that exomiRs are associated with specific cancer-related processes and tumor suppressor genes. Additionally, exomiR targets are significantly associated with patient survival and can be used to classify responders and non-responders to chemotherapy. Overall, this study highlights the diagnostic and therapeutic potential of exomiRs in cancer treatment. [Extracted from the article]

A recent report from the Research Institute Children's Cancer Center Hamburg in Germany discusses the characterization of the immune and stromal microenvironment in pediatric low-grade gliomas. The study analyzed gene-expression data from 400 low-grade gliomas and 193 high-grade gliomas to identify different microenvironment cell populations. The researchers found that low-grade gliomas can be divided into three distinct immunologic tumor microenvironments, which may have implications for future immunotherapeutic research. The study also revealed the negative prognostic relevance of vascular markers in low-grade gliomas. [Extracted from the article]

A study conducted by researchers at Peking University in Beijing, China, aimed to establish a noninvasive model for screening metabolic dysfunction-associated steatotic liver disease (MASLD) in children aged 6-14 years. MASLD is becoming increasingly prevalent among children, especially in regions with high obesity rates. The study identified the waist-to-height ratio (WHtR) as the optimal noninvasive index for predicting MASLD, with a cutoff value of >= 0.48. The combination of WHtR and lipid accumulation product (LAP) was recommended for individual MASLD screening. The study also proposed three MASLD screening recommendations based on obesity prevalence in different regions. [Extracted from the article]

A new report from the Rochester Institute of Technology discusses the use of Back Support Industrial Exoskeletons (BSIEs) to reduce the risk of low-back injury during repetitive trunk flexion tasks. The researchers conducted a study with 14 participants who performed trunk bending tasks with and without fatigue, while their muscle activity and whole-body stability were measured. Machine learning algorithms were used to predict perceived back fatigue based on sensor data. The study found that the XGBoost algorithm performed the best in predicting back fatigue, and the findings can be useful in developing fatigue detection products for industrial scenarios. [Extracted from the article]

A recent study conducted by researchers at Islamic Azad University in Tehran, Iran, focused on the classification of breast cancer masses using non-linear quadratic support vector machine (SVM) and compared it with self-organizing neural network (SONN). The study emphasized the importance of early detection in breast cancer and aimed to develop a method for easier and faster diagnosis. The results showed that the SVM method achieved an overall classification accuracy of 98.2%, indicating its optimal performance in breast cancer data classification. This research provides valuable insights into the potential of machine learning techniques in improving breast cancer diagnosis and treatment. [Extracted from the article]

A study conducted by researchers from Eindhoven University of Technology proposes the use of mathematical algorithms to predict hypertensive disorders in pregnancy, including preeclampsia, eclampsia, and chronic hypertension. The study compares different modeling methodologies, including random forest, decision tree, support vector machine, and the Takagi-Sugeno (T-S) and fuzzy c-means (FCM) methods. The T-S and FCM method achieved the highest predictive ability, with a success rate of 90%. The research concludes that these algorithms can be effective tools for predicting hypertensive disorders in pregnancy. [Extracted from the article]

Researchers at the University of Michigan have conducted a study on sepsis, a potentially life-threatening condition caused by bloodstream infections. The study focused on predicting the risk of poor sepsis-related outcomes using minimal variables. The researchers used various machine learning techniques and physiological signals data, such as electronic health records, electrocardiograms, and arterial line signals, to make predictions. They found that structuring the waveform features as a tensor, a mathematical object, allowed for continuous real-time predictions and preserved important structural and temporal information. The study highlights the potential benefits of using these methods for sepsis prediction. [Extracted from the article]

A recent study conducted by the Higher Institute of Engineering and Technology explores the use of a wearable textile bra-tenna system for breast cancer detection. The researchers investigate the effectiveness of different polarization signals combined with machine learning techniques to enhance detection accuracy. The system utilizes machine learning algorithms to predict breast cancer in its early stages, achieving high accuracy rates. The study concludes that the Support Vector Machine algorithm performs exceptionally well in both tumor and non-tumor detection scenarios. The research provides valuable insights for doctors in effectively investigating breast cancer. [Extracted from the article]

A recent study conducted at the University of Anbar has found that integrating multiple omics data can greatly improve the accuracy of cancer subclassification, which is a difficult task due to the complexity of the disease. The researchers used Quantum Cat Swarm Optimization (QCSO) for feature selection, along with K-means clustering and Support Vector Machine (SVM) for classification. By using QCSO, they were able to identify the most significant features, resulting in a significant increase in accuracy. This study contributes to the advancement of knowledge in the field of cancer research and biology. [Extracted from the article]

A patent application has been submitted by inventors Renee Deehan-Kenney and Aaron Van Hooser for a disease spectrum classification system. The system uses machine learning algorithms to assess individuals for diseases, disorders, or conditions based on personalized data derived from biological samples. The algorithms generate classifications relative to a range of related classifications, such as severity or prognosis of a disease. The system also provides recommendations for treatment based on the determined progression of the disease and the individual's current classification. The patent application was filed by PatientsLikeMe LLC. [Extracted from the article]

Researchers at Aligarh Muslim University have developed an energy-efficient and fast field programmable gate array (FPGA) architecture for detecting epileptic seizures using minimal computational resources. The system uses two efficient classifiers, quadratic discriminant analysis and linear support vector machine (LSVM), to classify signals into seizure and nonseizure categories. The SVM classifier-based model achieved high accuracy (99.4%) and sensitivity (98.8%) while consuming minimal power and utilizing minimum FPGA resources. This hardware system offers a reliable and energy-efficient solution for detecting seizures in clinical and real-time applications. [Extracted from the article]

A patent has been issued to Identita Inc. for a system and method of biometric authentication using electrocardiogram (ECG) signals. The invention aims to provide a more secure form of identity authentication compared to traditional methods such as access badges or passcodes. The system uses machine learning algorithms, such as support vector machines or neural networks, to process and compare ECG signals from an individual to previously stored reference templates. The invention offers a portable and easy-to-use input device for detecting ECG information, which can be obtained from various parts of the body, including the fingertips or wearable devices. The system can be applied to authenticate authorized drivers of motor vehicles and can also monitor driver health, stress, and drowsiness. [Extracted from the article]

Researchers at the Koneru Lakshmaiah Education Foundation in India have developed a comprehensive glaucoma detection methodology using image processing techniques and machine learning models. The methodology involves the use of deep learning, specifically Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNNs), integrated with multi-class Support Vector Machines (SVMs). The proposed model achieved a glaucoma detection accuracy of 97.2%, a sensitivity of 97.53%, and a specificity of 96.4%. Early detection of glaucoma is crucial for timely intervention and management to reduce the risk of severe visual impairment. [Extracted from the article]

A recent study conducted by researchers at the KPR Institute of Engineering and Technology in Tamil Nadu, India, explores the use of feature extraction and selection techniques to improve the accuracy of Type II Diabetes Mellitus (DM) detection using microarray gene data. The study utilizes three feature extraction methods and meta-heuristic algorithms for feature selection. The researchers evaluate the performance of seven classification techniques and find that the combination of Pearson's Correlation Coefficient (PCC) with Support Vector Machine with Radial Basis Function kernel (SVM-RBF) achieves a promising accuracy of 92.85%. The highest overall accuracy of 97.14% is achieved when Red Deer Optimization (RDO) is used for feature selection alongside PCC and SVM-RBF. These findings demonstrate the potential of feature extraction and selection techniques in improving the accuracy of DM detection. [Extracted from the article]

A study conducted by researchers at the University of Cincinnati provides new insights into osteoradionecrosis (ORN), a complication of head and neck cancer treatment. The study used unsupervised machine learning to analyze data from 1259 patients treated at The University of Texas MD Anderson Cancer Center. The researchers identified clusters of mandibular dose-volume histograms (DVHs) and calculated the risk of ORN for each dose-volume region. The results of the study provide a visual risk-assessment tool for ORN and can help optimize radiation dose levels based on different risk levels. [Extracted from the article]

A recent study conducted by researchers at the National University of Science and Technology in Bucharest, Romania, explores the effects of carbon ion and X-ray radiation on chondrosarcoma cells. The study compares the optical changes in the nuclei of these cells caused by the two types of radiation and establishes an automated method for evaluating these alterations without the need for chemical marking. The researchers used hyperspectral images and support vector machine classifiers to detect and analyze the changes. The study concludes that carbon ion radiation produces more discernible alterations in the nuclei compared to X-ray radiation, and the use of optical data with machine learning offers a rapid and label-free method for evaluating radiation-induced alterations in chondrosarcoma nuclei. [Extracted from the article]

The article explores new methods for detecting post-traumatic stress disorder (PTSD) using electroencephalogram (EEG) data. Topics discussed include the application of boosting methods combined with k-means clustering and Support Vector Machines (SVM) for diagnostic purposes, the identification of key EEG channels associated with PTSD, and the potential of these techniques for improving PTSD diagnosis and understanding.

A study conducted by researchers at Kurdistan University of Medical Sciences evaluated the reproducibility of machine learning models that combine radiomics and deep features to effectively classify different types of brain hemorrhages. The study used a dataset of 720 patients and extracted radiomics features and deep features from CT brain images. The researchers utilized various feature selection techniques and classifiers to evaluate the models, and found that deep features showed higher accuracy. The study highlights the potential of using machine learning models with deep features as valuable screening tools for interpreting head CT scans in patients with brain hemorrhages. [Extracted from the article]

Researchers at the University of Selcuk in Konya, Turkey have conducted a study on diagnosing epilepsy using machine learning and Welch spectral analysis. Epilepsy is a neurological disorder characterized by recurring seizures, which are sudden and uncontrollable electrical disturbances in the brain. The study used machine learning methods such as Random Forest, Naive Bayes, Support Vector Machine, Levenberg-Marguardt, and Long Short Term Memory for classification, and the Welch method for feature extraction. The Random Forest method achieved the highest accuracy at 99.87%, followed by LSTM at 99.39%. The study concluded that machine learning methods show promise for diagnosing epilepsy. [Extracted from the article]

A report from Hanoi Medical University discusses the development of machine learning-based prediction models for Down Syndrome in the first two trimesters of pregnancy in Vietnam. The models were designed to be low-cost and effective, and adaptable to different healthcare scenarios with limited screening capacities. The study included 7,076 pregnant women, and found that combined ultrasound and biochemical testing achieved the highest accuracy in the second trimester, while models based only on biochemical testing performed well in the first trimester. The research suggests that national screening for Down Syndrome may be feasible in settings without enough equipment and specialists, with further validation and fine-tuning of the models. [Extracted from the article]

Researchers at Anhui Medical University in China have conducted a computational analysis of the solubility of the anti-cancer drug Temozolomide in supercritical carbon dioxide (SC-CO2). They used a dataset of pressure and temperature as input parameters and Temozolomide solubility as the output. Three regression models were employed to predict solubility, with the Support Vector Machine (SVM) regression model displaying the highest accuracy. The research suggests that SC-CO2 could be an efficient solvent for cancer therapy. [Extracted from the article]

A recent report from Isfahan University of Medical Sciences in Iran discusses the application of a support vector machine classification model to identify inhibitors of vascular endothelial growth factor receptor (VEGFR), which plays a crucial role in angiogenesis. The study aimed to use a computational approach to separate potent inhibitors from inactive ones, using a correlation-based feature selection algorithm to reduce the number of molecular features. The support vector machine model with the radial basis function kernel, along with the correlation-based feature selection method, resulted in a higher accuracy compared to other feature selection methods. The research concludes that the correlation-based feature selection method is more accurate than other methods. [Extracted from the article]

A recent study conducted by researchers at the University of Belgrade in Serbia explored the potential use of serum metabolites as biomarkers for depression and the effectiveness of fluoxetine treatment in socially isolated rats. The researchers used a metabolomics approach to analyze the metabolic changes in the rats' serum following chronic social isolation and fluoxetine treatment. They identified several metabolites that could serve as potential markers of depressive-like behavior and effective fluoxetine treatment. The study suggests that these findings could contribute to the development of diagnostic tools and classification of stress-induced depressive phenotypes. [Extracted from the article]