Search

BackgroundType 2 diabetes mellitus (T2DM) is a global health problem characterized by insulin resistance and hyperglycemia. Early detection and accurate prediction of T2DM is crucial for effective management and prevention. This study explores the integration of machine learning (ML) and explainable artificial intelligence (XAI) approaches based on metabolomics panel data to identify biomarkers and develop predictive models for T2DM.MethodsMetabolomics data from T2DM (n = 31) and healthy controls (n = 34) were analyzed for biomarker discovery (mostly amino acids, fatty acids, and purines) and T2DM prediction. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO) regression to enhance the model’s accuracy and interpretability. Advanced three tree-based ML algorithms (KTBoost: Kernel-Tree Boosting; XGBoost: eXtreme Gradient Boosting; NGBoost: Natural Gradient Boosting) were employed to predict T2DM using these biomarkers. The SHapley Additive exPlanations (SHAP) method was used to explain the effects of metabolomics biomarkers on the prediction of the model.ResultsThe study identified multiple metabolites associated with T2DM, where LASSO feature selection highlighted important biomarkers. KTBoost [Accuracy: 0.938; CI: (0.880-0.997), Sensitivity: 0.971; CI: (0.847-0.999), Area under the Curve (AUC): 0.965; CI: (0.937-0.994)] demonstrated its effectiveness in using complex metabolomics data for T2DM prediction and achieved better performance than other models. According to KTBoost’s SHAP, high levels of phenylactate (pla) and taurine metabolites, as well as low concentrations of cysteine, laspartate, and lcysteate, are strongly associated with the presence of T2DM.ConclusionThe integration of metabolomics profiling and XAI offers a promising approach to predicting T2DM. The use of tree-based algorithms, in particular KTBoost, provides a robust framework for analyzing complex datasets and improves the prediction accuracy of T2DM onset. Future research should focus on validating these biomarkers and models in larger, more diverse populations to solidify their clinical utility.

ObjectivesThis study was performed to identify predictive markers of worse outcomes in patients with severe COVID-19 in an intensive care unit.MethodsSixty patients with severe COVID-19, hospitalized in the Intensive Care Unit (ICU) between March and July 2021, were stratified into two groups according to the outcome survivors and non-survivors. After admission to the ICU, blood samples were collected directly for biomarker analysis. Routine hematological and biochemical biomarkers, as well as serum levels of cytokines, chemokines, and immunoglobulins, were investigated.ResultsLymphopenia, neutrophilia, and thrombocytopenia were more pronounced in non-surviving patients, while the levels of CRP, AST, creatinine, ferritin, AST, troponin I, urea, magnesium, and potassium were higher in the non-surviving group than the survival group. In addition, serum levels of IL-10, CCL2, CXCL9, and CXCL10 were significantly increased in patients who did not survive. These changes in the biomarkers evaluated were associated with increased mortality in patients with severe COVID-19.ConclusionThe present study confirmed and expanded the validity of laboratory biomarkers as indicators of mortality in severe COVID-19.

Memory loss and dementia are major public health concerns with a substantial economic burden. Oxidative stress has been shown to play a crucial role in the pathophysiology of hippocampal damage-induced memory impairment. To investigate whether the antioxidant and anti-inflammatory compound vanillylacetone (zingerone) can protect against hippocampal damage and memory loss induced by cadmium chloride (CdCl2) administration in rats, we explored the potential involvement of the nuclear factor erythroid 2-related factor 2 (Nrf2) signaling pathway, which is known to modulate oxidative stress and inflammation. Sixty healthy male Wistar rats were divided into five groups: vehicle-treated (control), vanillylacetone, CdCl2, vanillylacetone + CdCl2, vanillylacetone + CdCl2 + brusatol (a selective pharmacological Nrf2 inhibitor) groups. Vanillylacetone effectively attenuated CdCl2-induced damage in the dental gyrus of the hippocampus and improved the memory function assessed by the Morris Water Maze test. Additionally, vanillylacetone markedly decreased the hippocampal tissue levels of inflammatory biomarkers (interleukin-6, tumor necrosis factor-α, intracellular cell adhesive molecules) and apoptosis biomarkers (Bax and cleaved caspase-3). The control and CdCl2-treated groups treated with vanillylacetone showed reduced generation of reactive oxygen species, decreased malondialdehyde levels, and increased superoxide dismutase and glutathione activities, along with significant elevation of nuclear Nrf2 mRNA and protein expression in hippocampal tissue. All the protective effects of vanillylacetone were substantially blocked by the co-administration of brusatol (a selective Nrf2 inhibitor). Vanillylacetone mitigated hippocampal damage and memory loss induced by CdCl2, at least in part, by activating the nuclear transcription factor Nrf2. Additionally, vanillylacetone exerted its potent antioxidant and anti-inflammatory actions.

Background: This study aims to assess the efficacy of combining automated machine learning (AutoML) and explainable artificial intelligence (XAI) in identifying metabolomic biomarkers that can differentiate between hepatocellular carcinoma (HCC) and liver cirrhosis in patients with hepatitis C virus (HCV) infection. Methods: We investigated publicly accessible data encompassing HCC patients and cirrhotic controls. The TPOT tool, which is an AutoML tool, was used to optimize the preparation of features and data, as well as to select the most suitable machine learning model. The TreeSHAP approach, which is a type of XAI, was used to interpret the model by assessing each metabolite’s individual contribution to the categorization process. Results: TPOT had superior performance in distinguishing between HCC and cirrhosis compared to other AutoML approaches AutoSKlearn and H2O AutoML, in addition to traditional machine learning models such as random forest, support vector machine, and k-nearest neighbor. The TPOT technique attained an AUC value of 0.81, showcasing superior accuracy, sensitivity, and specificity in comparison to the other models. Key metabolites, including L-valine, glycine, and DL-isoleucine, were identified as essential by TPOT and subsequently verified by TreeSHAP analysis. TreeSHAP provided a comprehensive explanation of the contribution of these metabolites to the model’s predictions, thereby increasing the interpretability and dependability of the results. This thorough assessment highlights the strength and reliability of the AutoML framework in the development of clinical biomarkers. Conclusions: This study shows that AutoML and XAI can be used together to create metabolomic biomarkers that are specific to HCC. The exceptional performance of TPOT in comparison to traditional models highlights its capacity to identify biomarkers. Furthermore, TreeSHAP boosted model transparency by highlighting the relevance of certain metabolites. This comprehensive method has the potential to enhance the identification of biomarkers and generate precise, easily understandable, AI-driven solutions for diagnosing HCC.

Acute Myocardial Infarction (AMI), a common disease that can have serious consequences, occurs when myocardial blood flow stops due to occlusion of the coronary artery. Early and accurate prediction of AMI is critical for rapid prognosis and improved patient outcomes. Metabolomics, the study of small molecules within biological systems, is an effective tool used to discover biomarkers associated with many diseases. This study intended to construct a predictive model for AMI utilizing metabolomics data and an explainable machine learning approach called Explainable Boosting Machines (EBM). The EBM model was trained on a dataset of 102 prognostic metabolites gathered from 99 individuals, including 34 healthy controls and 65 AMI patients. After a comprehensive data preprocessing, 21 metabolites were determined as the candidate predictors to predict AMI. The EBM model displayed satisfactory performance in predicting AMI, with various classification performance metrics. The model’s predictions were based on the combined effects of individual metabolites and their interactions. In this context, the results obtained in two different EBM modeling, including both only individual metabolite features and their interaction effects, were discussed. The most important predictors included creatinine, nicotinamide, and isocitrate. These metabolites are involved in different biological activities, such as energy metabolism, DNA repair, and cellular signaling. The results demonstrate the potential of the combination of metabolomics and the EBM model in constructing reliable and interpretable prediction outputs for AMI. The discussed metabolite biomarkers may assist in early diagnosis, risk assessment, and personalized treatment methods for AMI patients. This study successfully developed a pipeline incorporating extensive data preprocessing and the EBM model to identify potential metabolite biomarkers for predicting AMI. The EBM model, with its ability to incorporate interaction terms, demonstrated satisfactory classification performance and revealed significant metabolite interactions that could be valuable in assessing AMI risk. However, the results obtained from this study should be validated with studies to be carried out in larger and well-defined samples.

ABSTRACT Acinetobacter baumannii is a nosocomial multidrug-resistant pathogen that specifically colonizes and infects patients in intensive care units (ICUs). Genome plasticity of A. baumannii may contribute to the rapid development of A. baumannii resistance during patient treatment. There is little clarity on the dynamics of colonization of A. baumannii in humans. We studied 269 serial isolates of A. baumannii colonizing the rectum of 32 adult patients in an ICU; 5 to 16 isolates were obtained from each patient over a period of weeks to months. The isolates were sequenced using the Illumina platform. Multi-locus sequence typing revealed genetic diversity with 13 sequence types (STs); the dominant ST2 accounted for 202 of the 269 isolates and was isolated from each patient. A core genome comparison of isolates was used to elucidate a detailed understanding of the relationship among isolates within an ST and the genomic relationship among STs. One to three STs were observed in the isolates from each patient. Instances of unchanged colonization, sequential lineage colonization, and colonization with multiple lineages of A. baumannii were seen. The number of resistance genes carried by the isolates varied from 2 to 17. The predominant genes corresponded to those encoding resistance to β-lactam and aminoglycoside antibiotics. Generally, there was a strong correlation between ST and a particular antimicrobial resistance gene profile. This study makes an important baseline contribution to information that will help us understand the role of A. baumannii colonization in the development of opportunistic infections in ICU patients. IMPORTANCE Acinetobacter baumannii is a multidrug-resistant nosocomial pathogen that colonizes and infects debilitated patients in the ICU. There is very little information on the genomic characteristics of colonizing strains. This information is important to understand the evolution of lineages of A. baumannii that develop resistance while patients receive antibiotic treatment in the ICU. Our study demonstrated different patterns of colonization of the rectum of ICU patients with different STs of A. baumannii while one ST colonized all patients. Some STs carried more antibiotic resistance genes compared to others. However, there was a correlation between ST and a particular resistance gene profile. Our results further elucidate the dynamics of enteric colonization of this opportunistic pathogen.

In this research, test methods followed by supervised machine learning (SML) modeling were used to examine the effect of glass powder as a partial sand and cement substitute on the water absorption capability of cement mortar. This study also utilized SHapley Additive exPlanations (SHAP) analysis to determine the significance of raw materials. The dataset was derived from experiments and was used to build SML-based prediction models, including support vector machine, bagging, and AdaBoost. According to the test results, using glass powder reduced the water absorption capacity of cement mortar, and the optimum glass powder contents were noted to be 10 % as cement and 15 % as a sand substitute. Additionally, the built SML models indicated good accord with test outcomes and could be applied to calculate the water absorption of cement mortar comprising glass powder. Moreover, the AdaBoost model was found to be more accurate (R2 = 0.98) than the support vector machine (R2 = 0.95) and bagging regressor (R2 = 0.95) models in terms of R2, the difference between test and estimated findings, and the assessment of the errors.

Sustainable development might be promoted if waste eggshells are used in cement-based materials (CBMs) by decreasing waste disposal problems, CO2 emissions, and material costs. In this regard, experimental and machine learning (ML) strategies were used to assess the flexural strength (FS) of CBMs comprising waste eggshell powder (ESP). Initially, experimental methods were carried out to evaluate the FS of ESP-based CBMs. The acquired data was utilized to predict the FS by applying ML algorithms like a decision tree and an AdaBoost regressor. The efficacy of ML techniques was measured by comparing experimental and predicted FS and applying statistical checks and k-fold evaluations. The experiment outcomes demonstrated that the FS of CBMs was improved by the inclusion of ESP at lower replacement ratios. Additionally, based on the assessment of modeling results, the AdaBoost regressor model demonstrated a higher exactness in estimating the FS of CBMs containing ESP compared to the decision tree model. The assessment of error readings also indicated the higher precision of the AdaBoost regressor model than the decision tree. According to the feature importance analysis, the fine aggregate was the component with the lowest impact for FS, whereas cement had the prime impact. The findings showed that as opposed to using ESP as a cement replacement, using ESP as an FA replacement to keep FA in less quantity and cement in larger quantity would result in enhanced strength. The construction industry can gain from ML techniques since they allow for more time- and cost-effective approaches to assessing material attributes.

Background: Type 2 diabetes mellitus (T2DM) is a global health problem characterized by insulin resistance and hyperglycemia. Early detection and accurate prediction of T2DM is crucial for effective management and prevention. This study explores the integration of machine learning (ML) and explainable artificial intelligence (XAI) approaches based on metabolomics panel data to identify biomarkers and develop predictive models for T2DM. Methods: Metabolomics data from T2DM (n = 31) and healthy controls (n = 34) were analyzed for biomarker discovery (mostly amino acids, fatty acids, and purines) and T2DM prediction. Feature selection was performed using the least absolute shrinkage and selection operator (LASSO) regression to enhance the model's accuracy and interpretability. Advanced three tree-based ML algorithms (KTBoost: Kernel-Tree Boosting; XGBoost: eXtreme Gradient Boosting; NGBoost: Natural Gradient Boosting) were employed to predict T2DM using these biomarkers. The SHapley Additive exPlanations (SHAP) method was used to explain the effects of metabolomics biomarkers on the prediction of the model. Results: The study identified multiple metabolites associated with T2DM, where LASSO feature selection highlighted important biomarkers. KTBoost [Accuracy: 0.938; CI: (0.880-0.997), Sensitivity: 0.971; CI: (0.847-0.999), Area under the Curve (AUC): 0.965; CI: (0.937-0.994)] demonstrated its effectiveness in using complex metabolomics data for T2DM prediction and achieved better performance than other models. According to KTBoost's SHAP, high levels of phenylactate (pla) and taurine metabolites, as well as low concentrations of cysteine, laspartate, and lcysteate, are strongly associated with the presence of T2DM. Conclusion: The integration of metabolomics profiling and XAI offers a promising approach to predicting T2DM. The use of tree-based algorithms, in particular KTBoost, provides a robust framework for analyzing complex datasets and improves the prediction accuracy of T2DM onset. Future research should focus on validating these biomarkers and models in larger, more diverse populations to solidify their clinical utility. [ABSTRACT FROM AUTHOR]

In the construction industry, pursuing sustainable development by using sustainable materials necessitates using renewable resources. Among different renewable materials, mineral-derived natural fibers are relatively cheaper and abundantly available in various countries. This study summarizes the research advancements on concrete reinforced with mineral-derived natural fibers. This review on the incorporation of mineral fibers in concrete evaluates, identifies, and synthesizes research outcomes for creating a summary of current evidence which can contribute to evidence-based practice. Mapping knowledge, c/o-occurrence, and co-citation are hard gears for innovative research. Accordingly, the present study is aimed at exploring the literature on key features of mineral fiber-reinforced concrete by performing a scientometric analysis. The current study implemented an advanced approach for mining, processing, and analyzing data, interpretation, and presentation of available bibliographic data on mineral fibers in concrete. Furthermore, the discussion on the applications and limitations of using mineral fiber-reinforced concrete in the construction industry is also made. The current research may aid academics in exchanging new ideas and techniques and developing collective efforts.

A progressive advance in the construction sector is attained by employing ultra-high performance concrete (UHPC) technology. Rigorous efforts have been made in this research domain to have remarkable quality levels with 150 MPa or more strength and significant durability, which was impossible previously. Steel fiber incorporation in UHPC is vital in improving its mechanical characteristics. This review on the incorporation of steel fibers in UHPC evaluates, identifies, and synthesizes research outcomes for creating a summary of current evidence that can contribute to evidence-based practice. This study summarized a review of the literature on steel fibers’ effect on UHPC, intending to explore its essential aspects. The aim is to summarize the literature in this research domain and provide guidance for future research. Moreover, the basic requirements and materials, mixing and casting, mechanical properties, modern applications, advantages and disadvantages, and future perspectives associated with steel fibers reinforced UHPC in the construction sector are discussed. It is revealed from the conducted analysis that the most widely applied keyword is “steel fibers.” Due to the graphical illustration of the contributing studies, the current work may benefit academic scholars in sharing novel techniques and ideas and establishing collaborative efforts. Furthermore, the present work reveals that steel fibers have the potential to enhance the mechanical properties of UHPC; however, the large-scale production and applications of steel fiber-reinforced UHPC are controlled by parameters like fiber content and geometry.

The worldwide enhancement in the accumulation of waste tires and associated upcoming environmental and social concerns are becoming the primary intimidations. Waste tires are considered an undervalued resource globally, and their sheer volume is used to be disposed of in landfills, a primary concern. Instead of disposing of waste materials after recycling, the utilization can have a considerable impact. The trend of extracting steel fibers from waste tires is emerging nowadays. Incorporating waste recycled tire steel (WRTS) fibers, obtained from waste tires in concrete is a potential profit-gaining engineering application. But there are still some challenges, like WRTS fibers' suitable volumetric content and length selection, which need to be addressed by having in-depth exploration. Research has been conducted on incorporating reused waste materials in cementitious composites. Concrete ingredients are meant to provide strength, but adding reused waste materials to concrete helps reduce environmental pollution and make it sustainable and economical. In previous literature, the impact of such waste fibers on the key properties of concrete, such as ultrasonic pulse velocity, compressive, splitting-tensile and flexural strengths, energy absorption, modulus of elasticity, toughness, and ductility, were investigated. Adding WRTS fibers to concrete can enhance its compressive strength by more than 10 % and flexural strength by more than 50 %. This paper aims to review the application of WRTS fiber-reinforced concrete to identify the research gap for researchers in this direction. The available research outcomes and the recycling process of WRTS fibers are summarized and discussed. It is concluded that incorporating WRTS fibers in concrete would result in sustainable development by providing economical and environment-friendly construction materials with improved mechanical properties.

A large fraction of ice sheet discharge enters the ocean subsurface from underneath large floating ice-tongues. Here the authors show that associated nutrient export may be governed by shelf circulation and, especially for Fe, particle-dissolved phase exchanges, which is largely independent from freshwater Fe content.

Background: This study aims to assess the efficacy of combining automated machine learning (AutoML) and explainable artificial intelligence (XAI) in identifying metabolomic biomarkers that can differentiate between hepatocellular carcinoma (HCC) and liver cirrhosis in patients with hepatitis C virus (HCV) infection. Methods: We investigated publicly accessible data encompassing HCC patients and cirrhotic controls. The TPOT tool, which is an AutoML tool, was used to optimize the preparation of features and data, as well as to select the most suitable machine learning model. The TreeSHAP approach, which is a type of XAI, was used to interpret the model by assessing each metabolite's individual contribution to the categorization process. Results: TPOT had superior performance in distinguishing between HCC and cirrhosis compared to other AutoML approaches AutoSKlearn and H2O AutoML, in addition to traditional machine learning models such as random forest, support vector machine, and k-nearest neighbor. The TPOT technique attained an AUC value of 0.81, showcasing superior accuracy, sensitivity, and specificity in comparison to the other models. Key metabolites, including L-valine, glycine, and DL-isoleucine, were identified as essential by TPOT and subsequently verified by TreeSHAP analysis. TreeSHAP provided a comprehensive explanation of the contribution of these metabolites to the model's predictions, thereby increasing the interpretability and dependability of the results. This thorough assessment highlights the strength and reliability of the AutoML framework in the development of clinical biomarkers. Conclusions: This study shows that AutoML and XAI can be used together to create metabolomic biomarkers that are specific to HCC. The exceptional performance of TPOT in comparison to traditional models highlights its capacity to identify biomarkers. Furthermore, TreeSHAP boosted model transparency by highlighting the relevance of certain metabolites. This comprehensive method has the potential to enhance the identification of biomarkers and generate precise, easily understandable, AI-driven solutions for diagnosing HCC. [ABSTRACT FROM AUTHOR]

Objectives: This study was performed to identify predictive markers of worse outcomes in patients with severe COVID-19 in an intensive care unit. Methods: Sixty patients with severe COVID-19, hospitalized in the Intensive Care Unit (ICU) between March and July 2021, were stratified into two groups according to the outcome survivors and non-survivors. After admission to the ICU, blood samples were collected directly for biomarker analysis. Routine hematological and biochemical biomarkers, as well as serum levels of cytokines, chemokines, and immunoglobulins, were investigated. Results: Lymphopenia, neutrophilia, and thrombocytopenia were more pronounced in non-surviving patients, while the levels of CRP, AST, creatinine, ferritin, AST, troponin I, urea, magnesium, and potassium were higher in the non-surviving group than the survival group. In addition, serum levels of IL-10, CCL2, CXCL9, and CXCL10 were significantly increased in patients who did not survive. These changes in the biomarkers evaluated were associated with increased mortality in patients with severe COVID-19. Conclusion: The present study confirmed and expanded the validity of laboratory biomarkers as indicators of mortality in severe COVID-19. [ABSTRACT FROM AUTHOR]

Background: Sepsis is characterized by an atypical immune response to infection and is a dangerous health problem leading to significant mortality. Current diagnostic methods exhibit insufficient sensitivity and specificity and require the discovery of precise biomarkers for the early diagnosis and treatment of sepsis. Platelets, known for their hemostatic abilities, also play an important role in immunological responses. This study aims to develop a model integrating machine learning and explainable artificial intelligence (XAI) to identify novel platelet metabolomics markers of sepsis. Methods: A total of 39 participants, 25 diagnosed with sepsis and 14 control subjects, were included in the study. The profiles of platelet metabolites were analyzed using quantitative 1H-nuclear magnetic resonance (NMR) technology. Data were processed using the synthetic minority oversampling method (SMOTE)-Tomek to address the issue of class imbalance. In addition, missing data were filled using a technique based on random forests. Three machine learning models, namely extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), and kernel tree boosting (KTBoost), were used for sepsis prediction. The models were validated using cross-validation. Clinical annotations of the optimal sepsis prediction model were analyzed using SHapley Additive exPlanations (SHAP), an XAI technique. Results: The results showed that the KTBoost model (0.900 accuracy and 0.943 AUC) achieved better performance than the other models in sepsis diagnosis. SHAP results revealed that metabolites such as carnitine, glutamate, and myo-inositol are important biomarkers in sepsis prediction and intuitively explained the prediction decisions of the model. Conclusion: Platelet metabolites identified by the KTBoost model and XAI have significant potential for the early diagnosis and monitoring of sepsis and improving patient outcomes. [ABSTRACT FROM AUTHOR]

Diabetes mellitus is a worldwide epidemic causes numerous health problems including nephropathy and depression which are caused by oxygen radicals. We investigated the antioxidative effects of agomelatine or vildagliptin on streptozotocin-induced diabetic nephropathy in rats. 50 male albino rats were distributed into five groups, (n = 10/ group): the normal control, A single intraperitoneal injection of streptozotocin was given to the other four groups to induce diabetes at a dose of 60 mg/kg body weight. After diabetes induction, one of the groups was chosen as a positive control. Other rats were treated with either vildagliptin (10 mg/kg) and/or agomelatine (20 mg/kg/day) daily for 4 weeks. We used different biochemical parameters (blood glucose level, insulin levels, oxidative stress markers) as well as histological analysis on the kidney tissues of the experimental animals. Statistical evaluation was performed by One-way ANOVA for comparison of those groups followed by Duncan's post hoc test for multiple group comparison. Diabetes induced nephropathy via oxidative pathway as this was confirmed by increased serum levels of urea, uric acid and creatinine with decrease in serum total antioxidant Capacity (TAC) in diabetic rats compared to control rats. Also, there were significant increase in renal levels of malondialdehyde (MDA) and nitric oxide (NO); significant decrease in the levels of renal glutathione (GSH) and superoxide dismutase (SOD) in diabetic group compared to the control group. Administration of either vildagliptin and/or agomelatine or both to diabetic rats alleviated the previous indices as confirmed by the biochemical and histological changes with better improvement in (vildagliptin+agomelatine) to that of vildagliptin treatment alone. Conclusion: Combination of agomelatine and vildagliptin could ameliorate diabetic nephropathy through inhibition of oxidative stress. [ABSTRACT FROM AUTHOR]

Acute Myocardial Infarction (AMI), a common disease that can have serious consequences, occurs when myocardial blood flow stops due to occlusion of the coronary artery. Early and accurate prediction of AMI is critical for rapid prognosis and improved patient outcomes. Metabolomics, the study of small molecules within biological systems, is an effective tool used to discover biomarkers associated with many diseases. This study intended to construct a predictive model for AMI utilizing metabolomics data and an explainable machine learning approach called Explainable Boosting Machines (EBM). The EBM model was trained on a dataset of 102 prognostic metabolites gathered from 99 individuals, including 34 healthy controls and 65 AMI patients. After a comprehensive data preprocessing, 21 metabolites were determined as the candidate predictors to predict AMI. The EBM model displayed satisfactory performance in predicting AMI, with various classification performance metrics. The model's predictions were based on the combined effects of individual metabolites and their interactions. In this context, the results obtained in two different EBM modeling, including both only individual metabolite features and their interaction effects, were discussed. The most important predictors included creatinine, nicotinamide, and isocitrate. These metabolites are involved in different biological activities, such as energy metabolism, DNA repair, and cellular signaling. The results demonstrate the potential of the combination of metabolomics and the EBM model in constructing reliable and interpretable prediction outputs for AMI. The discussed metabolite biomarkers may assist in early diagnosis, risk assessment, and personalized treatment methods for AMI patients. This study successfully developed a pipeline incorporating extensive data preprocessing and the EBM model to identify potential metabolite biomarkers for predicting AMI. The EBM model, with its ability to incorporate interaction terms, demonstrated satisfactory classification performance and revealed significant metabolite interactions that could be valuable in assessing AMI risk. However, the results obtained from this study should be validated with studies to be carried out in larger and well-defined samples. [ABSTRACT FROM AUTHOR]

Brain metastasis (BM) from breast cancer has poor prognosis despite new advances and multi-modality treatments. No current data is guiding the use of palbociclib in the management of hormone receptor (HR)-positive breast cancer patients with BM as these patients were excluded systematically from all phase 3 trials. Here, we report an evident clinical response from combining palbociclib with endocrine therapy in HR-positive, human epidermal growth factor receptor 2 (HER2)-negative breast cancer with BM.

High convergence level of strategic alignment between business and information technology helps companies enhance operational excellence. This research aims to identify strategic alignment maturity criteria level and their impacts on operational excellence in Jordanian industrial companies. The population of the study consists of all managers at top and middle management and a purposive sample is used to answer questionnaire items. In this survey, 288 valid responses are collected for analysis using SPSS (20) and smart PLS "V. 3". The study reveals that there is a significantly positive impact of strategic alignment maturity criteria (communication, competency-value Measurement, governance, partnership, scope & architecture and skills) on operational excellence. The most maturity criteria have a mid-level of maturity except scope & architecture and competency-value measurement criteria which maintain a low level. Thus, the study concluded that the researched companies have to recognize the business value of information technology (IT) investment and harmonizing IT architecture with business structure.