Search

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]

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]

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]

Background: This study aims to identify unique metabolomics biomarkers associated with Type 2 Diabetes (T2D) and develop an accurate diagnostics model using tree-based machine learning (ML) algorithms integrated with bioinformatics techniques. Methods: Univariate and multivariate analyses such as fold change, a receiver operating characteristic curve (ROC), and Partial Least-Squares Discriminant Analysis (PLS-DA) were used to identify biomarker metabolites that showed significant concentration in T2D patients. Three tree-based algorithms [eXtreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), and Adaptive Boosting (AdaBoost)] that demonstrated robustness in high-dimensional data analysis were used to create a diagnostic model for T2D. Results: As a result of the biomarker discovery process validated with three different approaches, Pyruvate, D-Rhamnose, AMP, pipecolate, Tetradecenoic acid, Tetradecanoic acid, Dodecanediothioic acid, Prostaglandin E3/D3 (isobars), ADP and Hexadecenoic acid were determined as potential biomarkers for T2D. Our results showed that the XGBoost model [accuracy = 0.831, F1-score = 0.845, sensitivity = 0.882, specificity = 0.774, positive predictive value (PPV) = 0.811, negative-PV (NPV) = 0.857 and Area under the ROC curve (AUC) = 0.887] had the slight highest performance measures. Conclusions: ML integrated with bioinformatics techniques offers accurate and positive T2D candidate biomarker discovery. The XGBoost model can successfully distinguish T2D based on metabolites. [ABSTRACT FROM AUTHOR]

Due to the increasing prices of cement and its harmful effect on the environment, the use of cement has become highly unsustainable in concrete. There is a considerable need for promoting the use of cement replacement materials. This study investigates the effect of variable percentages of metakaolin (MK) on the mechanical and durability performance of concrete. Kaolin clay (KC) was used in the current research to prepare the MK by the calcination process; it was ground in a ball mill to its maximum achievable fineness value of 2550 m2/Kg. Four replacement levels of MK, i.e., 5%, 10%, 15%, and 20% by weight of cement, in addition to control samples, at a constant water-to-cement (w/c) ratio of 0.55 were used. For evaluating the mechanical and durability performance, 27 cubes (6 in. × 6 in. × 6 in.) and 6 cylinders (3.875 in. diameter, 2 in. height) were cast for each mix. These samples were tested for compressive strength under standard conditions and in an acidic environment, in addition to being subjected to water permeability, sorptivity, and water absorption tests. Chemical analysis revealed that MK could be used as pozzolana as per the American Society for Testing and Materials (ASTM C 618:2003). The results demonstrated an increased compressive strength of concrete owing to an increased percentage of MK in the mix with aging. In particular, the concrete having 20% MK after curing under standard conditions exhibited 33.43% higher compressive strength at 90 days as compared to similarly aged control concrete. However, with increasing MK, the workability of concrete decreased drastically. After being subjected to an acid attack (immersing concrete cubes in 2% sulfuric acid solution), the samples exhibited a significant decrease in compressive strength at 90 days in comparison to those without acid attack at the same age. The density of acid attack increased with increasing MK with a maximum corresponding to 5% MK concrete. The current findings suggest that the local MK has the potential to produce good-quality concrete in a normal environment. [ABSTRACT FROM AUTHOR]

This study examined the bibliographic data on fiber-reinforced geopolymers (FRGPs) using scientometrics to determine their important features. Manual review articles are inadequate in their capability to connect various segments of literature in an ordered and systematic manner. Scientific mapping, co-citation, and co-occurrence are the difficult aspects of current research. The Scopus database was utilized to find and obtain the data needed to achieve the study's aims. The VOSviewer application was employed to assess the literature records from 751 publications, including citation, bibliographic, keyword, and abstract details. Significant publishing outlets, keywords, prolific researchers in terms of citations and articles published, top-cited documents, and locations actively participating in FRGP investigations were identified during the data review. The possible uses of FRGP were also highlighted. The scientometric analysis revealed that the most frequently used keywords in FRGP research are inorganic polymers, geopolymers, reinforcement, geopolymer, and compressive strength. Additionally, 27 authors have published more than 10 articles on FRGP, and 29 articles have received more than 100 citations up to June 2022. Due to the graphical illustration and quantitative contribution of scholars and countries, this study can support scholars in building joint ventures and communicating innovative ideas and practices. [ABSTRACT FROM AUTHOR]

This research examined machine learning (ML) techniques for predicting the compressive strength (CS) of self-compacting concrete (SCC). Multilayer perceptron (MLP), bagging regressor (BR), and support vector machine (SVM) were utilized for analysis. A total of 169 data points were retrieved from the various published articles. The data set was based on 11 input parameters, such as cement, limestone, fly ash, ground granulated blast-furnace slag, silica fume, rice husk ash, coarse aggregate, fine aggregate, superplasticizers, water, viscosity modifying admixtures, and one output with compressive strength of SCC. In terms of properly predicting the CS of SCC, the BR technique outperformed both the SVM and MLP models, as determined by the research results. In contrast to SVM and MLP, the coefficient of determination (R2) for the BR model was 0.95, whereas for SVM and MLP, the R2 was 0.90 and 0.86, respectively. In addition, a k-fold cross-validation approach was adopted to check the accuracy of the employed models. The statistical measures mean absolute percent error, mean absolute error, and root mean square error ensure the validity of the model. Using sensitivity analysis, the influence of input factors on the intended CS of SCC was also explored. This analysis reveals that the highest contributing parameter towards the CS of SCC was cement with 16.2%, while rice husk ash contributed the least with 4.25% among all the input variables. [ABSTRACT FROM AUTHOR]

Climate change has become trending news due to its serious impacts on Earth. Initiatives are being taken to lessen the impact of climate change and mitigate it. Among the different initiatives, researchers are aiming to find suitable alternatives for cement. This study is a humble effort to effectively utilize industrial- and agricultural-waste-based pozzolanic materials in concrete to make it economical and environmentally friendly. For this purpose, a ternary blend of binders (i.e., cement, fly ash, and rice husk ash) was employed in concrete. Different variables such as the quantity of different binders, fine and coarse aggregates, water, superplasticizer, and the age of the samples were considered to study their influence on the compressive strength of the ternary blended concrete using gene expression programming (GEP) and artificial neural networking (ANN). The performance of these two models was evaluated using R2, RMSE, and a comparison of regression slopes. It was observed that the GEP model with 100 chromosomes, a head size of 10, and five genes resulted in an optimum GEP model, as apparent from its high R2 value of 0.80 and 0.70 in the TR and TS phase, respectively. However, the ANN model performed better than the GEP model, as evident from its higher R2 value of 0.94 and 0.88 in the TR and TS phase, respectively. Similarly, lower values of RMSE and MAE were observed for the ANN model in comparison to the GEP model. The regression slope analysis revealed that the predicted values obtained from the ANN model were in good agreement with the experimental values, as shown by its higher R2 value (0.89) compared with that of the GEP model (R2 = 0.80). Subsequently, parametric analysis of the ANN model revealed that the addition of pozzolanic materials enhanced the compressive strength of the ternary blended concrete samples. Additionally, we observed that the compressive strength of the ternary blended concrete samples increased rapidly within the first 28 days of casting. [ABSTRACT FROM AUTHOR]

Estimating concrete properties using soft computing techniques has been shown to be a time and cost-efficient method in the construction industry. Thus, for the prediction of steel fiber-reinforced concrete (SFRC) strength under compressive and flexural loads, the current research employed advanced and effective soft computing techniques. In the current study, a single machine learning method known as multiple-layer perceptron neural network (MLPNN) and ensembled machine learning models known as MLPNN-adaptive boosting and MLPNN-bagging are used for this purpose. Water; cement; fine aggregate (FA); coarse aggregate (CA); super-plasticizer (SP); silica fume; and steel fiber volume percent (Vf SF), length (mm), and diameter were the factors considered (mm). This study also employed statistical analysis such as determination coefficient (R2), root mean square error (RMSE), and mean absolute error (MAE) to assess the performance of the algorithms. It was determined that the MLPNN-AdaBoost method is suitable for forecasting SFRC compressive and flexural strengths. The MLPNN technique's higher R2, i.e., 0.94 and 0.95 for flexural and compressive strength, respectively, and lower error values result in more precision than other methods with lower R2 values. SHAP analysis demonstrated that the volume of cement and steel fibers have the greatest feature values for SFRC's compressive and flexural strengths, respectively. [ABSTRACT FROM AUTHOR]

In this work, bimetallic PdxCoy nanoparticles supported on nitrogen-doped reduced graphene oxide catalysts were synthesized and tested for formic acid oxidation as potentially efficient and durable electrocatalysts. Graphene oxide was nitrogen doped through hydrothermal chemical reduction with urea as a nitrogen source. The PdxCoy nanoparticles were deposited on the nitrogen-doped graphene oxide support using the impregnation-reduction method with sodium borohydride as a reducing agent and sodium citrate dihydrate as a stabilizing agent. The structural features, such as phases, composition, oxidation states, and particle sizes, of the nanoparticles were characterized using X-ray diffraction, transmission electron microscopy, scanning electron microscopy–energy-dispersive X-ray spectroscopy, and X-ray photoelectron spectroscopy. The Pd nanoparticle sizes in Pd1Co1/N-rGO, Pd/N-rGO, and Pd1Co1/CNT were 3.5, 12.51, and 4.62 nm, respectively. The electrochemical performance of the catalysts was determined by CO stripping, cyclic voltammetry, and chronoamperometry. Pd1Co1/N-rGO showed the highest mass activity of 4833.12 mA–1 mg Pd, which was twice that of Pd1Co1/CNT. Moreover, Pd1Co1/N-rGO showed a steady-state current density of 700 mA–1 mg Pd after 5000 s in chronoamperometry carried out at +0.35 V. Apart from the well-known bifunctional effect of Co, nitrogen-doped graphene contributed to the performance enhancement of the Pd1Co1/N-rGO catalyst. [ABSTRACT FROM AUTHOR]