Search

Breast cancer is currently one of the most prevalent cancers affecting women globally. Uncontrolled growth and division of breast cells lead to the formation of tumors, marking the onset of breast cancer. Predicting breast cancer is essential for early detection, making treatment plans, and implementing preventive measures, ultimately improving patient outcomes and reducing mortality rates. In recent years, numerous studies have been published to predict breast cancer where researchers use a variety of methods. Most investigations have been conducted using narrow and specific datasets, often resulting in a lack of accuracy. Such methods may not be suitable for clinical use. The study aims to address the limitations of existing models in terms of robustness and generalization across diverse datasets. In our study, we employed two metaheuristic algorithms, namely, genetic algorithm (GA) and chemical reaction optimization (CRO) with machine learning techniques, including support vector machine (SVM), decision tree, random forest, and XGBoost. GA and CRO are used to optimize the feature selection process. It enables machine learning algorithms to predict more accurately. Experiments were conducted on three datasets, namely, Wisconsin Breast Cancer (WBC), Breast Cancer-the University of California, Irvine (BC-UCI), and Breast Cancer Coimbra (BCC) datasets. The datasets contain 569, 286, and 116 instances, respectively. The classifiers with optimized features consistently outperformed the classifiers without feature optimization in terms of accuracy, precision, recall, specificity, and F1 score. Among the compared methods published recently, our method attained the highest accuracies of 99.64% in the WBC dataset and 98% in the BCC dataset, as well as the second highest accuracy of 99.12% in the BC-UCI dataset. Comparative analysis demonstrated the superiority of our approach over existing methods.

Stromal cells are emerging as key drivers of autoimmunity, partially because they produce inflammatory chemokines that orchestrate inflammation. Chemokine expression is regulated transcriptionally but also through posttranscriptional mechanisms, the specific drivers of which are still incompletely defined. CCL2 (MCP1) is a multifunctional chemokine that drives myeloid cell recruitment. During experimental autoimmune encephalomyelitis (EAE), an IL-17–driven model of multiple sclerosis, CCL2 produced by lymph node (LN) stromal cells was essential for immunopathology. Here, we showed that Ccl2 mRNA upregulation in human stromal fibroblasts in response to IL-17 required the RNA-binding protein IGF-2 mRNA-binding protein 2 (IGF2BP2, IMP2), which is expressed almost exclusively in nonhematopoietic cells. IMP2 binds directly to CCL2 mRNA, markedly extending its transcript half-life, and is thus required for efficient CCL2 secretion. Consistent with this, Imp2−/− mice showed reduced CCL2 production in LNs during EAE, causing impairments in monocyte recruitment and Th17 cell polarization. Imp2–/– mice were fully protected from CNS inflammation. Moreover, deletion of IMP2 after EAE onset was sufficient to mitigate disease severity. These data showed that posttranscriptional control of Ccl2 in stromal cells by IMP2 was required to permit IL-17–driven progression of EAE pathogenesis.

The aetiology of non-malaria vector-borne diseases in malaria-endemic, forested, rural, and tribal-dominated areas of Dhalai, Tripura, in north-east India, was studied for the first time in the samples collected from malaria Rapid Diagnostic Kit negative febrile patients by door-to-door visits in the villages and primary health centres. Two hundred and sixty serum samples were tested for the Dengue NS1 antigen and the IgM antibodies of Dengue, Chikungunya, Scrub Typhus (ST), and Japanese Encephalitis (JE) during April 2019–March 2020. Fifteen Dengue, six JE, twelve Chikungunya, nine ST and three Leptospirosis, and mixed infections of three JE + Chikungunya, four Dengue + Chikungunya, three Dengue + JE + Chikungunya, one Dengue + Chikungunya + ST, and one Dengue + ST were found positive by IgM ELISA tests, and four for the Dengue NS1 antigen, all without any travel history. True prevalence values estimated for infections detected by Dengue IgM were 0.134 (95% CI: 0.08–0.2), Chikungunya were 0.084 (95% CI: 0.05–0.13), Scrub were 0.043 (95% CI: 0.01–0.09), and Japanese Encephalitis were 0.045 (95% CI: 0.02–0.09). Dengue and Chikungunya were associated significantly more with a younger age. There was a lack of a defined set of symptoms for any of the Dengue, Chikungunya, JE or ST infections, as indicated by the k-modes cluster analysis. Interestingly, most of these symptoms have an overlapping set with malaria; thereby, it becomes imperative that malaria and these non-malaria vector-borne disease diagnoses are made in a coordinated manner. Findings from this study call for advances in routine diagnostic procedures and the development of a protocol that can accommodate, currently, in practicing the rapid diagnosis of malaria and other vector-borne diseases, which is doable even in the resource-poor settings of rural hospitals and during community fever surveillance.