Optimizing Immunodeficiency Disorder Classification With Multi-Layer Perceptron

Clinical diagnostic accuracy of Parkinson's disease (PD) remains suboptimal. Changes in disease concept may have improved clinical diagnostic accuracy in the past decade. However, current clinical diagnostic criteria have not been validated against neuropathological confirmation. This study aims to provide up-to-date clinical diagnostic accuracy data and validate current clinical diagnostic criteria for PD against neuropathology. A retrospective review of medical records of consecutive patients with parkinsonism from the Queen Square Brain Bank was performed between 2009 and 2019. Clinical diagnosis was documented at early (within 5 years of motor symptom onset) and final stages and categorized by movement disorder experts or regular clinicians. Movement Disorder Society Parkinson's disease (MDS-PD) diagnostic criteria were retrospectively applied. Diagnostic accuracy parameters (sensitivity, specificity, positive/negative predictive value, and accuracy) were calculated using neuropathological diagnosis as the gold standard. A total of 267 patients (141 PD and 126 non-PD parkinsonism) were included. Clinical diagnostic accuracy was 97.2% for experts, 92.5% for the MDS clinically probable PD criteria, and 90.3% for clinicians. Similar figures were obtained when applied at an early stage (91.5%, 89.5%, and 84.2% diagnostic accuracy, respectively). MDS clinically established early PD criteria demonstrated very high specificity (98.4%) at early stages. Our results showed an important improvement in PD clinical diagnostic accuracy in clinical practice over the past decade, more marked at early stages of the disease. MDS-PD diagnostic criteria is a valid tool in clinical practice and research for the identification of PD patients showing excellent sensitivity and specificity, although movement disorder experts' diagnosis remains the gold standard PD diagnosis during life. © 2023 International Parkinson and Movement Disorder Society.

The adaptive immune system in vertebrates has evolved to recognize an immense number of pathogens. B and T cells play important role in the antigen recognition by expressing a substantially diverse repertoire of antigen-specific receptors. The recent advances in the high-throughput immune repertoire sequencing has led to a tremendous increase in the antibody and T-cell receptor information. Identification of specific epitopes recognized by the receptors is vital in analyzing the repertoire sequencing data. Here, we present a tool that examines data from an immune receptor repertoire experiment, and identifies receptors (or highly related variants) that are present in the Immune Epitope Database (IEDB). The IEDB is a free resource which compiles experiments characterizing immune epitopes. IEDB also captures the epitope-specific immune receptor sequences and groups them based on their epitope specificity. IEDB currently has information on over 26,000 receptor groups. Users can provide receptor repertoire sequence data in multiple formats, and specify different CDR sequence identity cutoffs to restrict or broaden the receptor search. We expect that this tool will provide new insights into B and T cell responses captured in the receptor repertoire experiments by identifying specific epitopes, and facilitate development of new strategies for monitoring and treating of infectious, allergic and autoimmune diseases.

Within the domain of password security classification, the pursuit of practical and dependable methodologies has prompted the examination of both biological and technological paradigms. The present study investigates the efficacy of Mouth Brooding Fish (MBF) as an innovative method in contrast to conventional Machine Learning (ML) approaches for classifying password security. The research approach entails a rigorous examination of the comparative analysis of MBF and ML algorithms, evaluating their effectiveness in password classification using many criteria, including accuracy, robustness, flexibility, and durability against adversarial assaults. The findings suggest that ML approaches have shown significant effectiveness in classifying passwords. However, using methodologies inspired by the minimum Bayes risk framework demonstrates a higher degree of resistance against typical cyber dangers. The intrinsic biological mechanisms of MBF, encompassing adaptive behaviors and inherent protection, play a role in enhancing the resilience and adaptability of the password security categorization system. The results offer significant insights that can inform the evolution of password security systems, integrating biological principles with technical progress to enhance safeguarding measures in digital environments. To emphasize the advantages of the suggested approach, several ML approaches are investigated, such as Support Vector Machines (SVM), AdaBoost, Multilayer Perceptron (MLP), Gaussian Kernel (GK), and Random Forest (RF). The F-score, accuracy, sensitivity, and specificity metrics for MBF exhibit noteworthy performance compared to the other selected models, with values of 100%.

The recognition of immune epitopes is an important molecular mechanism of the vertebrate immune system to discriminate between self and non-self. Increasing amounts of data on immune epitopes are becoming available due to technological advances in epitope-mapping techniques and the availability of genomic information for pathogens. Organizing this data poses a challenge that is similar to the successful effort that was required to organize genomic data, which needed the establishment of centralized databases that complement the primary literature to make the data readily accessible and searchable by researchers. As described in this Innovation article, the Immune Epitope Database and Analysis Resource aims to achieve the same for the more complex and context-dependent information on immune epitopes, and to integrate this data with existing and emerging knowledge resources.

IEDB-3D is the 3D structural component of the Immune Epitope Database (IEDB) available via the ‘Browse by 3D Structure’ page at http://www.iedb.org. IEDB-3D catalogs B- and T-cell epitopes and Major Histocompatibility Complex (MHC) ligands for which 3D structures of complexes with antibodies, T-cell receptors or MHC molecules are available in the Protein Data Bank (PDB). Journal articles that are primary citations of PDB structures and that define immune epitopes are curated within IEDB as any other reference along with accompanying functional assays and immunologically relevant information. For each curated structure, IEDB-3D provides calculated data on intermolecular contacts and interface areas and includes an application, EpitopeViewer, to visualize the structures. IEDB-3D is fully embedded within IEDB, thus allowing structural data, both curated and calculated, and all accompanying information to be queried using multiple search interfaces. These include queries for epitopes recognized in different pathogens, eliciting different functional immune responses, and recognized by different components of the immune system. The query results can be downloaded in Microsoft Excel format, or the entire database, together with structural data both curated and calculated, can be downloaded in either XML or MySQL formats.

Sphincter electromyography (spEMG) is often used as an ancillary test when multiple system atrophy (MSA) is suspected. Our aim was to determine the clinical features associated with spEMG being performed, the influence of the result on the final clinical diagnosis, and its utility as a clinical investigation. A retrospective audit of all cases in the Queen Square Brain Bank between 1989 and 2002 was performed. The clinical features and diagnostic accuracy were compared between patients in whom spEMG was performed and those in whom it was not. From 845 sets of complete clinical records, we identified 37 (4.4%) cases that had been investigated with spEMG. Thirty of these cases had a pathological diagnosis of MSA. Of these 30, 24 had abnormal spEMGs, 5 had a borderline result, and only 1 had a normal spEMG. Sixty-six cases had pathologically proven MSA but no spEMG. Those investigated with spEMG were younger at disease onset (P < 0.001), more frequently male (P = 0.03), and more likely to have had other investigations performed. They had a greater incidence of pyramidal tract signs at final clinical diagnosis, and the final clinical diagnostic accuracy was higher (P = 0.04). Due to the retrospective nature of the study, balanced populations for calculation of sensitivity and specificity were not available. In this selected series of pathologically confirmed cases, investigation with spEMG was one of several factors associated with improved clinical diagnostic accuracy. A normal spEMG is unlikely in pathologically proven MSA, at least in cases with a mean symptom duration of more than 5 years when the test is performed.

Background: Stroke is defined as a focal neurological deficit of sudden onset, typically resulting from cerebrovascular damage. It is a leading cause of morbidity and mortality worldwide, affecting approximately 15 million individuals annually. Survivors often endure significant disabilities, cognitive impairments, and emotional distress. Early intervention is critical, as accurate diagnosis can enable targeted treatment, improving survival rates and reducing long-term disabilities. Objective: This study aims to evaluate the clinical recognition and diagnostic tests used for stroke diagnosis, assessing their accuracy, effectiveness, and the factors influencing stroke identification. Methods: A systematic search of articles was conducted across several databases, including Biomed Central, Google Scholar, PubMed, Cochrane Library, American Physical Therapy Association, and PEDRO, focusing on studies published from 2000 to 2023. Keywords such as "stroke prevalence," "transient ischemic attack," and "myocardial infarction" were used to identify relevant literature. Study selection adhered to PRISMA guidelines, resulting in a total of 30 review articles that discussed clinical recognition, diagnostic accuracy, and outcome measures related to stroke identification. Data extraction included evidence-based studies, systematic reviews, and meta-analyses. Results: The meta-analysis revealed significant differences in the clinical recognition and diagnostic accuracy for stroke identification, underscoring the importance of timely and standardized diagnostic protocols. Conclusion: This study highlights that enhanced clinical recognition and diagnostic accuracy are crucial for the early identification of stroke, which significantly reduces long-term disabilities and improves patient outcomes. Timely implementation of standardized diagnostic protocols can lead to better patient quality of life. Implications: The findings of this study advocate for improved clinical practices and policies to enhance stroke diagnosis and optimize patient outcomes through standardized protocols

Optimized machine learning approaches for identifying vertical temperature gradient on ballastless track in natural environments

BackgroundStructural information about epitopes, particularly the three-dimensional (3D) structures of antigens in complex with immune receptors, presents a valuable source of data for immunology. This information is available in the Protein Data Bank (PDB) and provided in curated form by the Immune Epitope Database and Analysis Resource (IEDB). With continued growth in these data and the importance in understanding molecular level interactions of immunological interest there is a need for new specialized molecular visualization and analysis tools.ResultsThe EpitopeViewer is a platform-independent Java application for the visualization of the three-dimensional structure and sequence of epitopes and analyses of their interactions with antigen-specific receptors of the immune system (antibodies, T cell receptors and MHC molecules). The viewer renders both 3D views and two-dimensional plots of intermolecular interactions between the antigen and receptor(s) by reading curated data from the IEDB and/or calculated on-the-fly from atom coordinates from the PDB. The 3D views and associated interactions can be saved for future use and publication. The EpitopeViewer can be accessed from the IEDB Web site through the quick link 'Browse Records by 3D Structure.'ConclusionThe EpitopeViewer is designed and been tested for use by immunologists with little or no training in molecular graphics. The EpitopeViewer can be launched from most popular Web browsers without user intervention. A Java Runtime Environment (RJE) 1.4.2 or higher is required.

Mining Immune Epitopes in Ménière’s Disease and Sudden Sensorineural Hearing Loss

Hepatitis is a widespread inflammatory condition of the liver, presenting a formidable global health challenge. Accurate and timely detection of hepatitis is crucial for effective patient management, yet existing methods exhibit limitations that underscore the need for innovative approaches. Early-stage detection of hepatitis is now possible with the recent adoption of machine learning and deep learning approaches. With this in mind, the study investigates the use of traditional machine learning models, specifically classifiers such as logistic regression, support vector machines (SVM), decision trees, random forest, multilayer perceptron (MLP), and other models, to predict hepatitis infections. After extensive data preprocessing including outlier detection, dataset balancing, and feature engineering, we evaluated the performance of these models. We explored three modeling approaches: machine learning with default hyperparameters, hyperparameter-tuned models using GridSearchCV, and ensemble modeling techniques. The SVM model demonstrated outstanding performance, achieving 99.25% accuracy and a perfect AUC score of 1.00 with consistency in other metrics with 99.27% precision, and 99.24% for both recall and F1-measure. The MLP and Random Forest proved to be in pace with the superior performance of SVM exhibiting an accuracy of 99.00%. To ensure robustness, we employed a 5-fold cross-validation technique. For deeper insight into model interpretability and validation, we employed an explainability analysis of our best-performed models to identify the most effective feature for hepatitis detection. Our proposed model, particularly SVM, exhibits better prediction performance regarding different performance metrics compared to existing literature.

Classification and prediction tasks are common in health research. With the increasing availability of vast health data repositories (e.g. electronic medical record databases) and advances in computing power, traditional statistical approaches are being augmented or replaced with machine learning (ML) approaches to classify and predict health outcomes. ML describes the automated process of identifying ("learning") patterns in data to perform tasks. Developing an ML model includes selecting between many ML models (e.g. decision trees, support vector machines, neural networks); model specifications such as hyperparameter tuning; and evaluation of model performance. This process is conducted repeatedly to find the model and corresponding specifications that optimize some measure of model performance. ML models can make more accurate classifications and predictions than their statistical counterparts and confer greater flexibility when modelling unstructured data or interactions between covariates; however, many ML models require larger sample sizes to achieve good classification or predictive performance and have been criticized as "black box" for their poor transparency and interpretability. ML holds potential in family medicine for risk profiling of patients' disease risk and clinical decision support to present additional information at times of uncertainty or high demand. In the future, ML approaches are positioned to become commonplace in family medicine. As such, it is important to understand the objectives that can be addressed using ML approaches and the associated techniques and limitations. This article provides a brief introduction into the use of ML approaches for classification and prediction tasks in family medicine.

Performance optimization of wireless networks is typically complicated because of high computational complexity and dynamic channel conditions. Considering a specific case, the recent introduction of intelligent reflecting surface (IRS) can reshape the wireless channels by controlling the scattering elements' phase shifts, namely, passive beamforming. However, due to the large size of scattering elements, the IRS's beamforming optimization becomes intractable. In this article, we focus on machine learning (ML) approaches for complex optimization problems in wireless networks. ML approaches can provide flexibility and robustness against uncertain and dynamic systems. However, practical challenges still remain due to slow convergence in offline training or online learning. This motivated us to design a novel optimization-driven ML framework that exploits the efficiency of model-based optimization and the robustness of model-free ML approaches. Splitting the control variables into two parts allows one part to be updated by the outer loop ML approach while the other part is solved by the inner loop optimization. The case study in IRS-assisted wireless networks confirms that the optimization-driven ML framework can improve learning efficiency and the reward performance significantly compared to conventional model-free ML approaches.

Efficient fertilizer application is vital for enhancing maize production and profitability in Sub-Saharan Africa, where soil fertility varies widely across regions. This study aimed to develop a machine learning approach for generating site-specific fertilizer recommendations for maize production in Ghana and to evaluate its performance against conventional and semi-mechanistic approaches. A random forest machine learning model was trained on 482 maize yield experiments, consisting of 3136 yield observations collected from 1991 to 2020, to predict maize yield response to different fertilizer rates. The model incorporated multiple explanatory variables, including soil properties, climate conditions, and management practices, to generate fertilizer response curves from which fertilizer recommendations were derived for 14 sites across three agro-ecological zones in Ghana where field validation experiments were conducted. On these sites, the recommendations were compared with recommendations derived from the Quantitative Evaluation of the Fertility of Tropical Soils (QUEFTS), Conventional Fertilizer Dose Response (CFDR), and Updated Conventional Fertilizer Dose Response (UCFDR) approaches and validated through field experiments. The machine learning approach generally recommended lower rates of phosphorus and potassium than the other approaches, while nitrogen recommendations were comparable. In the Guinea Savanna zone, the recommendations from the machine learning approach outperformed those from the other approaches, producing higher mean yields for three out of the four sites in the zone. In the Forest-Savanna Transition (FST) zone, the machine learning model recommendations led to higher mean yields at four sites, while the approaches based on QUEFTS and UCFDR performed best at two other sites. In the Semi-deciduous Forest zone, the recommendations of the QUEFTS approach resulted in the highest mean yields at three sites, and CFDR at one site. Despite high input prices during the period of experimentation, the machine learning approach-based recommendations demonstrated higher net profit margins in the FST zone, suggesting cost-effectiveness in this zone. These findings indicate that site-specific fertilizer recommendations are more efficient than blanket recommendations and that machine learning approaches offer a promising and innovative approach for generating cost-effective, site-specific fertilizer recommendations in tropical climates. • ML and QUEFTS approaches provided site-specific fertilizer recommendations. • ML and QUEFTS outperformed conventional fertilizer recommendation approaches. • CFDR and UCFDR were constrained by generalized, non-site-specific recommendations. • Machine learning supports sustainable fertilizer use.

Epitopedia: identifying molecular mimicry between pathogens and known immune epitopes