Specificity Of Model Research Articles

МЕНТОРСТВО ЯК ІНСТРУМЕНТ РОЗВИТКУ ПРОФЕСІЙНИХ МОЖЛИВОСТЕЙ ПРАЦІВНИКІВ ПІДПРИЄМСТВА

The aim of the article is to unveil the potential of mentorship and the specifics of models for developing the professional capabilities of enterprise employees. Mentorship is a method of leveraging the potential of experienced employees who have accumulated a wealth of knowledge and experience, embodying values and attitudes crucial for the enterprise. It has been established that mentorship inherently includes the following primary functions: providing psychosocial support and offering career or professional support, which encompasses tasks related to developing the enterprise's potential. It is proven that mentorship is effective when mentors and mentees trust each other, share their achievements and failures, and interact sincerely. Stability in work, the mentee's self-confidence, and understanding of future steps are criteria for the success of a mentorship program. The article outlines the features of identifying the effectiveness of mentorship with the onset of the war in Ukraine. A significant portion of current mentorship focuses on stabilizing the enterprise's operations and providing psychological support to employees. Effectiveness is determined by the mentee's ability to move forward. The risks associated with implementing mentorship include the possibility of deteriorating interpersonal relationships due to feelings of unfairness among mentees; creating a sense of threat in the mentor, who fears that the mentor-mentee relationship undermines their authority; and the potential for perpetuating unacceptable elements of the enterprise's organizational culture. Possible obstacles to implementing mentorship in an enterprise may include a mentor's unwillingness to share knowledge; generational misunderstandings; low awareness of the mentorship concept; and an inability to transfer knowledge effectively. It is substantiated that the main models of behavior for mentees and mentors that yield results include individual mentorship (one-on-one), group mentorship, reciprocal mentorship, online mentorship, reverse mentorship, and competency-based mentorship. The article presents the advantages, disadvantages, and potential uses of each model. Each of these models can be adapted to the specific needs of the enterprise or individual mentees. The choice of mentorship model depends on the goals, resources, and context of the interaction.

Delineating the impact of childhood traumatic brain injury (TBI) on long-term depressive symptom severity: Does sub-acute brain morphometry prospectively predict 2-year outcome?

Despite evidence of a link between childhood TBI and heightened risk for depressive symptoms, very few studies have examined early risk factors that predict the presence and severity of post-injury depression beyond 1-year post injury. This longitudinal prospective study examined the effect of mild-severe childhood TBI on depressive symptom severity at 2-years post-injury. It also evaluated the potential role of sub-acute brain morphometry and executive function (EF) in prospectively predicting these long-term outcomes. The study involved 81 children and adolescents with TBI, and 40 age-and-sex matched typically developing (TD) controls. Participants underwent high-resolution structural magnetic resonance imaging (MRI) sub-acutely at five weeks post-injury (M = 5.55; SD = 3.05 weeks) and EF assessments were completed at 6-months post-injury. Compared to TD controls, the TBI group had significantly higher overall internalizing symptoms and were significantly more likely to exhibit clinically significant depressive symptoms at 2-year follow-up. The TBI group also displayed significantly lower EF and altered sub-acute brain morphometry in EF-related brain networks, including the default-mode network (DMN), salience network (SN) and central executive network (CEN). Mediation analyses revealed significant indirect effects of CEN morphometry on depression symptom severity, such that lower EF mediated the prospective association between altered CEN morphometry and higher depression symptoms in the TBI group. Parallel mediation analyses including grey matter morphometry of a non-EF brain network (i.e., the mentalising network) were not statistically significant, suggesting some model specificity. The findings indicate that screening for early neurostructural and neurocognitive risk factors may help identify children at elevated risk of depressive symptoms following TBI. For instance, children at greatest risk of post-injury depression symptoms could be identified based in part on neuroimaging of networks implicated in EF and post-acute assessments of executive function, which could support more effective allocation of limited intervention resources.

Unveiling the potential of machine learning in schizophrenia diagnosis: A meta-analytic study of task-based neuroimaging data.

The emergence of machine learning (ML) techniques has opened up new avenues for identifying biomarkers associated with schizophrenia (SCZ) using task-related fMRI (t-fMRI) designs. To evaluate the effectiveness of this approach, we conducted a comprehensive meta-analysis of 31 t-fMRI studies using a bivariate model. Our findings revealed a high overall sensitivity of 0.83 and specificity of 0.82 for t-fMRI studies. Notably, neuropsychological domains modulated the classification performance, with selective attention demonstrating a significantly higher specificity than working memory (β = 0.98, z = 2.11, P = 0.04). Studies involving older, chronic patients with SCZ reported higher sensitivity (P <0.015) and specificity (P <0.001) than those involving younger, first-episode patients or high-risk individuals for psychosis. Additionally, we found that the severity of negative symptoms was positively associated with the specificity of the classification model (β = 7.19, z = 2.20, P = 0.03). Taken together, these results support the potential of using task-based fMRI data in combination with machine learning techniques to identify biomarkers related to symptom outcomes in SCZ, providing a promising avenue for improving diagnostic accuracy and treatment efficacy. Future attempts to deploy ML classification should consider the factors of algorithm choice, data quality and quantity, as well as issues related to generalization.

Design of a prognostic model for assessing the risk of developing asbestosis based on the results of molecular genetic studies

Introduction. Preventive measures, including the development of a system for diagnosing early signs of changes in the health status of employees and predicting individual risks of developing the disease, aimed at preserving labor resources, reducing disability and extending working life expectancy, are an absolute priority in the field of occupational safety.&#x0D; The aim of the study to develop a prognostic model of the risk of developing asbestosis based on molecular genetic studies in employees of enterprises for the extraction and enrichment of chrysotile asbestos.&#x0D; Materials and methods. Based on studies previously conducted in the Laboratory of Biomedical Research at the Izmerov Research Institute of Occupational Health, scientists have identified a set of informative and significant single-nucleotide polymorphic gene variants for use as predictors in the construction of a prognostic model in the development of asbestos in workers of enterprises for the extraction and enrichment of chrysotile asbestos. We examined 136 people who worked at the enterprise for the extraction and enrichment of chrysotile asbestos. The researchers formed two groups comparable in terms of work experience, dustiness, age and gender: 68 former employees of the main production specialties with an established diagnosis of asbestos and 68 workers without bronchopulmonary pathology.&#x0D; The authors calculated the exposure dose of chrysotile-containing dust and calculated it taking into account the percentage of time spent at the workplace, and also performed a molecular genetic study of single-nucleotide polymorphic variants of the genes IL-1β rs16944, IL-4 rs2243250, TGF-β1 rs1800471, SOD-2 rs4880 and MMP-9 rs17576.&#x0D; Results. A predictive model has been developed to determine the probability of developing asbestosis in workers of an enterprise for the extraction and enrichment of chrysotile asbestos based on the determination of single nucleotide polymorphisms IL-1β rs16944, SOD-2 rs4880 and MMP-9 rs17576. The results of genetic tests are entered into the formula and if the resulting probability of developing asbestosis is equal to or higher than the threshold (0.582), the employee is included in the high-risk group. The sensitivity and specificity of the developed model were 70.1% and 70.6%, respectively.&#x0D; Conclusion. Molecular genetic indicators can act as predictors in the development of asbestosis in workers of the chrysotile extraction and enrichment industry and can be used to form high-risk groups during preventive measures.&#x0D; Ethics. The study was conducted in compliance with ethical standards that guarantee respect for all research subjects and the protection of their health and rights in accordance with the requirements of the Helsinki Declaration of the World Medical Association. All persons included in the study gave informed voluntary consent to the examination in accordance with Federal Law No. 323-FZ dated 11/21/2011 "On the Basics of Public Health Protection in the Russian Federation". The study was approved by the conclusion of the local Ethics committee of Izmerov Research Institute of Occupational Health (minutes of the meeting of the Ethics committee of Izmerov Research Institute of Occupational Health No. 9 dated 11/29/2016).

Власний досвід застосування нейромережевого аналізу в прогнозуванні довготермінового виживання пацієнтів із хронічною серцевою недостатністю

The aim – predicting the risk of fatal outcome within 3 years in patients with CHF and reduced left ventricular ejection fraction (LVEF) with neural network.Materials and methods. The retrospective analysis of 490 medical histories of patients who were hospitalized in the heart failure department between 2011 and 2018 years with CHF II–IV functional class according to NYHA with LVEF ≤ 40 % on the background of coronary heart disease was conducted. Patients with clinical signs of heart failure II NYHA functional class – 455 (92.8 %) patients and with clinical signs of CHF III NYHA functional class – 35 (7.2 %) patients. The analysis was conducted for 490 patients: 228 (46.5 %) patients had a fatal event within three years, 262 (53.5 %) patients survived three years. Results and discussion. Factor features was selected for building a neural network. The information about 8 factor characteristics (ACE inhibitor (X1), atrium fibrillation (X2), renal dysfunction (X3), age (X4), arterial pressure (X5), (X6), LV diastolic volume index ( X7), LV myocardial mass index (X8)) was used for building of neural network models. Three-layer Multiplayer Perceptron (MLP) model with one hidden layer (logistic activation function) was built in the final. This neural network is a type of multi-layer neural network (multi-network perceptron). Each neuron of this system uses a nonlinear activation function. The sensitivity and specificity of this neural network model was evaluated. The education of this neural network did by the method of backpropagation. The quality of the classification of this model was evaluated with the test set of cases. The area under the curve of the operating characteristics of the neural MLP model for predicting the risk of a fatal event exceeds that area of the 9-factor logistic regression model (p&lt;0.001).Conclusions. The use of neural network analysis increase the accuracy of predicting a fatal outcome for a 3-year period compared to a multifactor logistic regression model. According to the construction of the neural network MLP model, a strong connection of the risk of a fatal event over the course of 3 years with the presence of atrium fibrillation, renal dysfunction, age, LV diastolic volume index, LV myocardial mass index and ACE inhibitor in the treatment was revealed. The quality of the neural network MLP model is high (area under the curve AUC=0.842). Youden Index (Ycrit=0.3049), the sensitivity of the MLP model is 76.8 % (95 % CI 70.7–82.1 %), the specificity of the model is 81.3 % (95 % CI 76.0–85.8 %), predictive significance +PV – 78.1 % (95 % CI 73.3–82.3 %), predictive significance –PV – 80.1 % (95 % CI 75.9–83.7 %). The accuracy of predicting the risk of a fatal outcome within 3 years for the neural network MLP model is higher than for the 9-factor logistic regression model (р&lt;0.001).

INFORMATION MODELING OF CONCRETE: CURRENT STATUS AND DEVELOPMENT PROSPECT S

The publication relates to the problems of digitalization of building materials science. The relevance of developing a digital model of concrete for solving optimization problems of design and synthesis of its structure, clarifying methods for calculating building structures, and improving the technology of their production is shown. The evolution of information modeling of concrete is analyzed in the context of the stages of development of system-building materials science and technology.&#x0D; A review of the main modern methods of computer modeling of concrete structure in domestic and foreign scientific research is provided. It is noted that these methods do not take into account the complexity of the structure of concrete. In the article, concrete is presented as a conglomerate composite with a hierarchically organized structure with dimensions from 10-10 to 10-1 m. It has a minimum of 5-6 scale levels and three types of substructure design. Substructures differ in their scale, genesis and mechanics of manifestation of properties. The first type of substructure is characteristic of the macro-, meso- and micro-scale levels. It is accepted in the form of a two-component “construction” of a spatially continuous matrix and discrete inclusions deterministically and stochastically distributed in it. The second type refers to the submicro-, ultra-micro- and nanoscale levels. It is believed to be in the form of a “microscale spatial structure” of new formations of a cementing substance from consolidated individual crystalline differences. The third type corresponds to the atomic-molecular structure of new formations of the cementing substance.&#x0D; The characteristics of each type of substructure are given according to: the scale of the components; features of formation; mechanics of properties manifestation; design criteria; means of synthesis. An assumption is made about the specificity of modeling each of the three types of concrete substructures and their integration into a single digital model. The task is to develop an information platform for such a model. The platform should include: a theoretical knowledge base; empirical data base; database of analytical, numerical and statistical models; algorithms for designing and synthesizing structures; optimization criteria and boundary conditions; terms of reference for computer modeling of concrete.

Peculiarities of the Legal Status of the Mayors of Lithuanian Municipalities and the Competencies (Abilities) Necessary for them in the Context of the Change of the Municipal Governance Model in 2023

The purpose of the article is to present some of the results of a research using a questionnaire survey method conducted in February 2023, which aimed to reveal the peculiarities of the legal status and roles (dominant and others) of mayors of Lithuanian municipalities and find out what necessary competences (abilities) municipal mayors must have and in what forms they must be developed, in the presence of two different municipal governance models (the model that was applied until April 2023 and the model that is applied from April 2023). The idea to conduct such research arose just a few months before the new Local Government Law (in its revised version) entered into force in June 2022, which introduced a new municipal governance model and changed the dominant role of the mayor in the municipality. This research also took place a few weeks before the regular municipal council and mayor elections (which took place on March 5, 2023). The particular target group was chosen for this research - the mayors of Lithuanian municipalities who had served in these positions for four or more terms (referred to as "experienced" mayors during the research). No similar research (in terms of purpose and respondents) has been conducted in Lithuania. The results of the research showed that "experienced" mayors have a good understanding of the specifics of the new municipal governance model to be applied from April 2023. They are essentially prepared to take on a new dominant role (the role of municipal executive institution), replacing the previous dominant role (the role of chairman of the municipal council). The results of the research also showed that "experienced" mayors understand well what necessary competencies (abilities) municipal mayors must have, as municipal governance model and the dominant role of the municipal mayor change in it. The results of the research can be useful for improving the legal regulation of the powers of municipal institutions (municipal council and municipal mayor) and the legal framework for their relationships as well as for organizing the the improvement of the competencies of municipal mayors.

An artificial intelligence model based on transrectal ultrasound images of biopsy needle tract tissues to differentiate prostate cancer.

We aimed to develop an artificial intelligence (AI) model based on transrectal ultrasonography (TRUS) images of biopsy needle tract (BNT) tissues for predicting prostate cancer (PCa) and to compare the PCa diagnostic performance of the radiologist model and clinical model. A total of 1696 2D prostate TRUS images were involved from 142 patients between July 2021 and May 2022. The ResNet50 network model was utilized to train classification models with different input methods: original image (Whole model), BNT (Needle model), and combined image [Feature Pyramid Networks (FPN) model]. The training set, validation set, and test set were randomly assigned, then randomized 5-fold cross-validation between the training set and validation set was performed. The diagnostic effectiveness of AI models and image combination was accessed by an independent testing set. Then, the optimal AI model and image combination were selected to compare the diagnostic efficacy with that of senior radiologists and the clinical model. In the test set, the area under the curve, specificity, and sensitivity of the FPN model were 0.934, 0.966, and 0.829, respectively; the diagnostic efficacy was improved compared with the Whole and Needle models, with statistically significant differences (P < 0.05), and was better than that of senior radiologists (area under the curve: 0.667). The FPN model detected more PCa compared with senior physicians (82.9% vs. 55.8%), with a 61.3% decrease in the false-positive rate and a 23.2% increase in overall accuracy (0.887 vs. 0.655). The proposed FPN model can offer a new method for prostate tissue classification, improve the diagnostic performance, and may be a helpful tool to guide prostate biopsy.

Real-time auto-segmentation of the ureter in video sequences of gynaecological laparoscopic surgery.

Ureteral injury is common during gynaecological laparoscopic surgery. Real-time auto-segmentation can assist gynaecologists in identifying the ureter and reduce intraoperative injury risk. A deep learning segmentation model was crafted for ureter recognition in surgical videos, utilising 3368 frames from 11 laparoscopic surgeries. Class activation maps enhanced the model's interpretability, showing its areas. The model's clinical relevance was validated through an End-User Turing test and verified by three gynaecological surgeons. The model registered a Dice score of 0.86, a Hausdorff 95 distance of 22.60, and processed images in 0.008s on average. In complex surgeries, it pinpointed the ureter's position in real-time. Fifty five surgeons across eight institutions found the model's accuracy, specificity, and sensitivity comparable to human performance. Yet, artificial intelligence experience influenced some subjective ratings. The model offers precise real-time ureter segmentation in laparoscopic surgery and can be a significant tool for gynaecologists to mitigate ureteral injuries.

INCORPORATING ATTENTION SCORE TO IMPROVE FORESIGHT PRUNING ON TRANSFORMER MODELS

With rapid development of technologies and growing number of application of neural networks, the problem of optimization arises. Among other methods to optimize training and inference time, neural network pruning has attracted attention in recent years. The main goal of pruning is to reduce the computational complexity of neural network models while retaining performance metrics on desired level. Among the various approaches to pruning, Single-shot Network Pruning (SNIP) methods was designed as a straightforward and effective approach to optimize number of parameters before training. However, as neural network architectures have evolved, particularly with the growing popularity of transformers, a need to reevaluate traditional pruning methods arises. This paper aims to revisit SNIP pruning method, evaluate its performance on transformer model, and introduce an enhanced version of SNIP, specifically designed for transformer architectures. The paper outlines the mathematical framework of SNIP algorithm, and proposes a modification, based on specifics of transformers models. Transformer models achieved impressive results because of their attention mechanisms for a multitude of tasks such as language modeling, translation, computer vision tasks and many others. The proposed modification takes into account this unique feature and combines this information with traditional loss gradients. Traditional method calculates importance score for weights of the network using only gradients from loss function, in the case of enhanced algorithm. In the enhanced version, the importance score is a composite metric that incorporates not only the gradient from the loss function but also from the attention activations. To evaluate the efficiency of proposed modifications, a series of experiments were conducted on image classification task, using Linformer variation of transformer architectures. The results of experiments demonstrate the efficiency of incorporating attention scores in pruning. Conducted experiments show that model pruned by modified algorithm outperforms model pruned by original SNIP by 34% in validation accuracy, confirming the validity of the improvements introduced.

Seven oxidative stress-related genes predict the prognosis of hepatocellular carcinoma.

Predicting the prognosis of hepatocellular carcinoma (HCC) is a major medical challenge and of guiding significance for treatment. This study explored the actual relevance of RNA expression in predicting HCC prognosis. Cox's multiple regression was used to establish a risk score staging classification and to predict the HCC patients' prognosis on the basis of data in the Cancer Genome Atlas (TCGA). We screened seven gene biomarkers related to the prognosis of HCC from the perspective of oxidative stress, including Alpha-Enolase 1(ENO1), N-myc downstream-regulated gene 1 (NDRG1), nucleophosmin (NPM1), metallothionein-3, H2A histone family member X, Thioredoxin reductase 1 (TXNRD1) and interleukin 33 (IL-33). Among them we measured the expression of ENO1, NGDP1, NPM1, TXNRD1 and IL-33 to investigate the reliability of the multi-index prediction. The first four markers' expressions increased successively in the paracellular tissues, the hepatocellular carcinoma samples (from patients with better prognosis) and the hepatocellular carcinoma samples (from patients with poor prognosis), while IL-33 showed the opposite trend. The seven genes increased the sensitivity and specificity of the predictive model, resulting in a significant increase in overall confidence. Compared with the patients with higher-risk scores, the survival rates with lower-risk scores are significantly increased. Risk score is more accurate in predicting the prognosis HCC patients than other clinical factors. In conclusion, we use the Cox regression model to identify seven oxidative stress-related genes, investigate the reliability of the multi-index prediction, and develop a risk staging model for predicting the prognosis of HCC patients and guiding precise treatment strategy.

Establishment of machine learning-based tool for early detection of pulmonary embolism

Background and objectivesPulmonary embolism (PE) is a complex disease with high mortality and morbidity rate, leading to increasing society burden. However, current diagnosis is solely based on symptoms and laboratory data despite its complex pathology, which easily leads to misdiagnosis and missed diagnosis by inexperienced doctors. Especially, CT pulmonary angiography, the gold standard method, is not widely available. In this study, we aim to establish a rapid and accurate screening model for pulmonary embolism using machine learning technology. Importantly, data required for disease prediction are easily accessed, including routine laboratory data and medical record information of patients. MethodsWe extracted features from patients' routine laboratory results and medical records, including blood routine, biochemical group, blood coagulation routine and other test results, as well as symptoms and medical history information. Samples with a feature loss rate greater than 0.8 were deleted from the original database. Data from 4723 cases were retained, 231 of which were positive for pulmonary embolism. 50 features were retained through the positive and negative statistical hypothesis testing which was used to build the predictive model. In order to avoid identification as majority-class samples caused by the imbalance of sample proportion, we used the method of Synthetic Minority Oversampling Technique (SMOTE) to increase the amount of information on minority samples. Five typical machine learning algorithms were used to model the screening of pulmonary embolism, including Support Vector Machines, Logistic Regression, Random Forest, XGBoost, and Back Propagation Neural Networks. To evaluate model performance, sensitivity, specificity and AUC curve were analyzed as the main evaluation indicators. Furthermore, a baseline model was established using the characteristics of the pulmonary embolism guidelines as a comparison model. ResultsWe found that XGBoost showed better performance compared to other models, with the highest sensitivity and specificity (0.99 and 0.99, respectively). Moreover, it showed significant improvement in performance compared to the baseline model (sensitivity and specificity were 0.76 and 0.76 respectively). More important, our model showed low missed diagnosis rate (0.46) and high AUC value (0.992). Finally, the calculation time of our model is only about 0.05 s to obtain the possibility of pulmonary embolism. ConclusionsIn this study, five machine learning classification models were established to assess the likelihood of patients suffering from pulmonary embolism, and the XGBoost model most significantly improved the precision, sensitivity, and AUC for pulmonary embolism screening. Collectively, we have established an AI-based model to accurately predict pulmonary embolism at early stage.

Artificial Intelligence in the Early Prediction of Cardiogenic Shock in Acute Heart Failure or Myocardial Infarction Patients: A Systematic Review and Meta-Analysis.

Cardiogenic shock (CS) may have a negative impact on mortality in patients with heart failure (HF) or acute myocardial infarction (AMI). Early prediction of CS can result in improved survival. Artificial intelligence (AI) through machine learning (ML) models haveshown promise in predictive medicine. Here, we conduct a systematic review and meta-analysis to assess the effectiveness of these models in the early prediction of CS. A thorough search of the PubMed, Web of Science, Cochrane, and Scopus databases was conducted from the time of inception until November 2, 2023, to find relevant studies. Our outcomes were area under the curve (AUC), the sensitivity and specificity of the ML model, the accuracy of the ML model, and the predictor variables that had the most impact in predicting CS. Comprehensive Meta-Analysis (CMA) Version 3.0 was used to conduct the meta-analysis. Six studies were considered in our study. The pooled mean AUC was 0.808 (95% confidence interval: 0.727, 0.890). The AUC in the included studies ranged from 0.77 to 0.91. ML models performed well, with accuracy ranging from 0.88 to 0.93 and sensitivity and specificity of 58%-78% and 88%-93%, respectively. Age, blood pressure, heart rate, oxygen saturation, and blood glucose were the most significant variables required by ML models to acquire their outputs. In conclusion, AI has the potential for early prediction of CS, which may lead to a decrease in the high mortality rate associated with it. Future studies are needed to confirm the results.

Machine learning for the prediction of sepsis-related death: a systematic review and meta-analysis

Background and objectivesSepsis is accompanied by a considerably high risk of mortality in the short term, despite the availability of recommended mortality risk assessment tools. However, these risk assessment tools seem to have limited predictive value. With the gradual integration of machine learning into clinical practice, some researchers have attempted to employ machine learning for early mortality risk prediction in sepsis patients. Nevertheless, there is a lack of comprehensive understanding regarding the construction of predictive variables using machine learning and the value of various machine learning methods. Thus, we carried out this systematic review and meta-analysis to explore the predictive value of machine learning for sepsis-related death at different time points.MethodsPubMed, Embase, Cochrane, and Web of Science databases were searched until August 9th, 2022. The risk of bias in predictive models was assessed using the Prediction model Risk of Bias Assessment Tool (PROBAST). We also performed subgroup analysis according to time of death and type of model and summarized current predictive variables used to construct models for sepsis death prediction.ResultsFifty original studies were included, covering 104 models. The combined Concordance index (C-index), sensitivity, and specificity of machine learning models were 0.799, 0.81, and 0.80 in the training set, and 0.774, 0.71, and 0.68 in the validation set, respectively. Machine learning outperformed conventional clinical scoring tools and showed excellent C-index, sensitivity, and specificity in different subgroups. Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) are the preferred machine learning models because they showed more favorable accuracy with similar modeling variables. This study found that lactate was the most frequent predictor but was seriously ignored by current clinical scoring tools.ConclusionMachine learning methods demonstrate relatively favorable accuracy in predicting the mortality risk in sepsis patients. Given the limitations in accuracy and applicability of existing prediction scoring systems, there is an opportunity to explore updates based on existing machine learning approaches. Specifically, it is essential to develop or update more suitable mortality risk assessment tools based on the specific contexts of use, such as emergency departments, general wards, and intensive care units.

Anticipating undiagnosed asthma in symptomatic adults with normal pre- and post-bronchodilator spirometry: a decision tool for bronchial challenge testing

BackgroundSome patients with asthma demonstrate normal spirometry and remain undiagnosed without further testing.ObjectiveTo determine clinical predictors of asthma in symptomatic adults with normal spirometry, and to generate a tool to help clinicians decide who should undergo bronchial challenge testing (BCT).MethodsUsing random-digit dialling and population-based case-finding, we recruited adults from the community with respiratory symptoms and no previous history of diagnosed lung disease. Participants with normal pre- and post-bronchodilator spirometry subsequently underwent BCT. Asthma was diagnosed in those with symptoms and a methacholine provocative concentration (PC20) of < 8 mg/ml. Sputum and blood eosinophils, and exhaled nitric oxide were measured. Univariate analyses identified potentially predictive variables, which were then used to construct a multivariable logistic regression model to predict asthma. Model sensitivity, specificity, and area under the receiver operating curve (AUC) were calculated.ResultsOf 132 symptomatic individuals with normal spirometry, 34 (26%) had asthma. Of those ultimately diagnosed with asthma, 33 (97%) answered ‘yes’ to a question asking whether they experienced cough, chest tightness or wheezing provoked by exercise or cold air. Other univariate predictors of asthma included female sex, pre-bronchodilator FEV1 percentage predicted, and percent positive change in FEV1 post bronchodilator. A multivariable model containing these predictive variables yielded an AUC of 0.82 (95% CI: 0.72–0.91), a sensitivity of 82%, and a specificity of 66%. The model was used to construct a nomogram to advise clinicians which patients should be prioritized for BCT.ConclusionsFour readily available patient characteristics demonstrated a high sensitivity and AUC for predicting undiagnosed asthma in symptomatic adults with normal pre- and post-bronchodilator spirometry. These characteristics can potentially help clinicians to decide which individuals with normal spirometry should be investigated with bronchial challenge testing. However, further prospective validation of our decision tool is required.

Fusion of laser-induced breakdown spectroscopy technology and deep learning: a new method to identify malignant and benign lung tumors with high accuracy.

Precisely distinguishing between malignant and benign lung tumors is pivotal for suggesting therapeutic strategies and enhancing prognosis, yet this differentiation remains a daunting task. The growth rates, metastatic potentials, and prognoses of benign and malignant tumors differ significantly. Developing specialized treatment protocols tailored to various tumor types is essential for enhancing patient survival outcomes. Employing laser-induced breakdown spectroscopy (LIBS) in conjunction with a deep learning methodology, we attained a high-precision differential diagnosis of malignant and benign lung tumors. First, LIBS spectra of malignant tumors, benign tumors, and normal tissues were collected. The spectra were preprocessed and Z score normalized. Then, the intensities of the Mg II 279.6, Mg I 285.2, Ca II 393.4, Cu II 518.3, and Na I 589.6 nm lines were analyzed in the spectra of the three tissues. The analytical results show that the elemental lines have different contents in the three tissues and can be used as a basis for distinguishing between the three tissues. Finally, the RF-1D ResNet model was constructed by combining the feature importance assessment method of random forest (RF) and one-dimensional residual network (1D ResNet). The classification accuracy, precision, sensitivity, and specificity of the RF-1D ResNet model were 91.1%, 91.6%, 91.3%, and 91.3%, respectively. And the model demonstrates superior performance with an area under the curve (AUC) value of 0.99. The above results show that combining LIBS with deep learning is an effective way to diagnose malignant and benign tumors.

Oversampling methods for machine learning model data training to improve model capabilities to predict the presence of Escherichia coli MG1655 in spinach wash water.

We assessed the efficacy of oversampling techniques to enhance machine learning model performance in predicting Escherichia coli MG1655 presence in spinach wash water. Three oversampling methods were applied to balance two datasets, forming the basis for training random forest (RF), support vector machines (SVMs), and binomial logistic regression (BLR) models. Data underwent method-specific centering and standardization, with outliers replaced by feature-specific means in training datasets. Testing occurred without these preprocessing steps. Model hyperparameters were optimized using a subset of testing data via 10-fold cross-validation. Models were trained on full datasets and tested on newly acquired spinach wash water samples. Synthetic Minority Oversampling Technique (SMOTE) and Adaptive Synthetic Sampling approach (ADASYN) achieved strong results, with SMOTE RF reaching an accuracy of 90.0%, sensitivity of 93.8%, specificity of 87.5%, and an area under the curve (AUC) of 98.2% (without data preprocessing) and ADASYN achieving 86.55% accuracy, 87.5% sensitivity, 83.3% specificity, and a 92.4% AUC. SMOTE and ADASYN significantly improved (p<0.05) SVM and RF models, compared to their non-oversampled counterparts without preprocessing. Data preprocessing had a mixed impact, improving (p<0.05) the accuracy and specificity of the BLR model but decreasing the accuracy and specificity (p<0.05) of the SVM and RF models. The most influential physiochemical feature for E. coli detection in wash water was water conductivity, ranging from 7.9 to 196.2 µS. Following closely was water turbidity, ranging from 2.97 to 72.35 NTU within this study.

Quantitative Dixon and intravoxel incoherent motion diffusion magnetic resonance imaging parameters in lumbar vertebrae for differentiating aplastic anemia and acute myeloid leukemia.

We sought to evaluate the use of quantitative Dixon (Q-Dixon) and intravoxel incoherent motion diffusion imaging (IVIM) for the differential diagnosis of aplastic anemia (AA) and acute myeloid leukemia (AML). Between August 2021 and October 2023, we enrolled 68 diagnosed patients, including 36 patients with AA and 32 patients with AML, as well as 26 normal controls. All patients underwent 3-Tesla magnetic resonance imaging, which included IVIM and T2*-corrected Q-Dixon imaging at the L2-4 level. The iliac crest biopsy's pathology was used as the diagnostic criterion. The interobserver measurement repeatability was evaluated using the intraclass correlation coefficient (ICC). One-way analysis of variance, Spearman analysis, and receiver operating characteristic curve analysis were used. The fat fraction (FF) and perfusion fraction (f) values were statistically significantly different between the three groups (p < 0.001 and p = 0.007). The FF and f values in the AA group were higher than those in the AML group. The true apparent diffusion coefficient (D) value was substantially negatively correlated to the FF and R2* values (r = -0.601, p < 0.001; r = -0.336, p = 0.002). The f value was positively correlated with both FF and pseudo-apparent diffusion coefficient (D*) values (r = 0.376, p < 0.001; r = 0.263, p = 0.017) and negatively correlated with the D value (r = -0.320, p = 0.003). The FF and f values were negatively correlated with the degree of myelodysplasia (r = -0.597, p < 0.001; r = -0.454, p = 0.004), and the D value was positively correlated with the degree of myelodysplasia (r = 0.395, p = 0.001). For the differential diagnosis of AA and AML, the Q-Dixon model's sensitivity (93.75%) and specificity (84%) confirmed that it outperformed the IVIM model. Q-Dixon parameters have the potential to be used as new biomarkers to differentiate AA from AML.

The impact of political, military, and social factors on the repositioning of Belarus within the regional security architecture

The next phase of Russian aggression against Ukraine demonstrated that despite lacking a large military, territorial, population, or raw material potential, Belarus could play a significant role in the project to construct a new regional, continental, and even global security architecture. The purpose of this article is to discuss the problem of repositioning Belarus, which was affected not only by the multidimensional change in Belarusian-Ukrainian relations as a result of the war but also by long-term efforts to elevate Belarusian-EU relations. In this area, the fundamental research question is whether the war in Ukraine, the breach of the so-called Budapest Memorandum and the deepening of the multifaceted Russian-Belarusian integration within the Union State (including the militarisation of Belarus and the allocation of tactical nuclear weapons) will cause the projects for the redefinition of Belarus-EU relations (which are instrumental in reducing the intensity of political turbulence in the region) to disappear from the EU diplomatic agenda for a long time, with a direct negative impact on the future of European security. The article verifies the hypothesis that due to the specificity of the Belarusian authoritarian model, despite the systematically deepening Russian-Belarusian integration and the ever-expanding sanctions policy towards Belarus, (2) due to the shape of Belarusian-Ukrainian relations after 2014 and the periodically satisfactory Belarusian-EU relations, (1) there are still prospects for Belarus to pursue foreign policy diversification and repositioning of the European vector in it.

Deep-learning model for diagnostic clue: detecting the dural tail sign for meningiomas on contrast-enhanced T1 weighted images.

Meningiomas are the most common primary central nervous system tumors, and magnetic resonance imaging (MRI), especially contrast-enhanced T1 weighted image (CE T1WI), is used as a fundamental imaging modality for the detection and analysis of the tumors. In this study, we propose an automated deep-learning model for meningioma detection using the dural tail sign. The dataset included 123 patients with 3,824 dural tail signs on sagittal CE T1WI. The dataset was divided into training and test datasets based on specific time point, and 78 and 45 patients were comprised for the training and test dataset, respectively. To compensate for the small sample size of the training dataset, 39 additional patients with 69 dural tail signs from the open dataset were appended to the training dataset. A You Only Look Once (YOLO) v4 network was trained with sagittal CE T1WI to detect dural tail signs. The normal group dataset, comprised of 51 patients with no abnormal finding on MRI, was employed to evaluate the specificity of the trained model. The sensitivity and false positive average were 82.22% and 29.73, respectively, in the test dataset. The specificity and false positive average were 17.65% and 3.16, respectively, in the normal dataset. Most of the false-positive cases in the test dataset were enhancing vessels, misinterpreted as dural thickening. The proposed model demonstrates an automated detection system for the dural tail sign to identify meningioma in general screening MRI. Our model can facilitate and alleviate radiologists' reading process by notifying the possibility of incidental dural mass based on dural tail sign detection.