Evaluating the Strength and Impact of Raw Ingredients of Cement Mortar Incorporating Waste Glass Powder Using Machine Learning and SHapley Additive ExPlanations (SHAP) Methods

Prognosis prediction and risk stratification of transarterial chemoembolization or intraarterial chemotherapy for unresectable hepatocellular carcinoma based on machine learning

OBJECTIVE

To develop and validate a risk scoring scale model (RSSM) for stratifying prognostic risk after intra-arterial therapies (IATs) for hepatocellular carcinoma (HCC).

METHODS

Between February 2014 and October 2022, 2338 patients with HCC who underwent initial IATs were consecutively enrolled. These patients were divided into training datasets (TD, n = 1700), internal validation datasets (ITD, n = 428), and external validation datasets (ETD, n = 200). Five-years death was used to predict outcome. Thirty-four clinical information were input and five supervised machine learning (ML) algorithms, including eXtreme Gradient Boosting (XGBoost), Categorical Gradient Boosting (CatBoost), Gradient Boosting Decision Tree (GBDT), Light Gradient Boosting Machine (LGBT), and Random Forest (RF), were compared using the areas under the receiver operating characteristic (AUC) with DeLong test. The variables with top important ML scores were used to build the RSSM by stepwise Cox regression.

RESULTS

The CatBoost model achieved the best discrimination when 12 top variables were input, with the AUC of 0.851 (95% confidence intervals (CI), 0.833-0.868) for TD, 0.817 (95%CI, 0.759-0.857) for ITD, and 0.791 (95%CI, 0.748-0.834) for ETD. The RSSM was developed based on the immune checkpoint inhibitors (ICI) (hazard ratios (HR), 0.678; 95%CI 0.549, 0.837), tyrosine kinase inhibitors (TKI) (HR, 0.702; 95%CI 0.605, 0.814), local therapy (HR, 0.104; 95%CI 0.014, 0.747), response to the first IAT (HR, 4.221; 95%CI 2.229, 7.994), tumor size (HR, 1.054; 95%CI 1.038, 1.070), and BCLC grade (HR, 2.375; 95%CI 1.950, 2.894). Kaplan-Meier analysis confirmed the role of RSSM in risk stratification (p < 0.001).

CONCLUSIONS

The RSSM can stratify accurately prognostic risk for HCC patients received IAT. On the basis, an online calculator permits easy implementation of this model.

CLINICAL RELEVANCE STATEMENT

The risk scoring scale model could be easily implemented for physicians to stratify risk and predict prognosis quickly and accurately, thereby serving as a more favorable tool to strengthen individualized intra-arterial therapies and management in patients with unresectable hepatocellular carcinoma.

KEY POINTS

• The Categorical Gradient Boosting (CatBoost) algorithm achieved the optimal and robust predictive ability (AUC, 0.851 (95%CI, 0.833-0.868) in training datasets, 0.817 (95%CI, 0.759-0.857) in internal validation datasets, and 0.791 (95%CI, 0.748-0.834) in external validation datasets) for prediction of 5-years death of hepatocellular carcinoma (HCC) after intra-arterial therapies (IATs) among five machine learning models. • We used the SHapley Additive exPlanations algorithms to explain the CatBoost model so as to resolve the black boxes of machine learning principles. • A simpler restricted variable, risk scoring scale model (RSSM), derived by stepwise Cox regression for risk stratification after intra-arterial therapies for hepatocellular carcinoma, provides the potential forewarning to adopt combination strategies for high-risk patients.

Interpretable Machine Learning Framework to Predict the Glass Transition Temperature of Polymers

The glass transition temperature of polymers is a key parameter in meeting the application requirements for energy absorption. Previous studies have provided some data from slow, expensive trial-and-error procedures. By recognizing these data, machine learning algorithms are able to extract valuable knowledge and disclose essential insights. In this study, a dataset of 7174 samples was utilized. The polymers were numerically represented using two methods: Morgan fingerprint and molecular descriptor. During preprocessing, the dataset was scaled using a standard scaler technique. We removed the features with small variance from the dataset and used the Pearson correlation technique to exclude the features that were highly connected. Then, the most significant features were selected using the recursive feature elimination method. Nine machine learning techniques were employed to predict the glass transition temperature and tune their hyperparameters. The models were compared using the performance metrics of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). We observed that the extra tree regressor provided the best results. Significant features were also identified using statistical machine learning methods. The SHAP method was also employed to demonstrate the influence of each feature on the model's output. This framework can be adaptable to other properties at a low computational expense.

Optimizing and hyper-tuning machine learning models for the water absorption of eggshell and glass-based cementitious composite

Cementitious composites' performance degrades in extreme conditions, making it more important to enhance its resilience. To further the adaptability of eco-friendly construction, waste materials are increasingly being repurposed. Cementitious composites deteriorate in both direct and indirect ways due to the facilitation of hostile ion transport by water. The effects of using eggshell and glass powder as partial substitutes for cement and sand in mortar on the water-absorption capacity were investigated using machine learning (ML) modeling techniques such as Gene Expression Programming (GEP) and Multi Expression Programming (MEP). To further assess the importance of inputs, sensitivity analysis and interaction research were carried out. The water absorption property of cementitious composites was precisely estimated by the generated ML models. It was noted that the MEP model, with an R2 of 0.90, and the GEP model, with an R2 of 0.88, accurately predicted results. The sensitivity analysis revealed that the absorption capacity of the mortar was most affected by the presence of eggshell powder, sand, and glass powder. GEP and MEP model's significance lies in the fact that they offer one-of-a-kind mathematical formulas that can be applied to the prediction of features in another database. The mathematical models resulting from this study can help scientists and engineers rapidly assess, enhance, and rationalize mixture proportioning. The built models can theoretically compute the water absorption of cement mortar made from eggshell powder and glass powder based on varied input parameters, resulting in cost and time savings.

Bio-inspired based meta-heuristic approach for predicting the strength of fiber-reinforced based strain hardening cementitious composites

A recently introduced bendable concrete having hundred times greater strain capacity provides promising results in repair of engineering structures, known as strain hardening cementitious composites (SHHCs). The current research creates new empirical prediction models to assess the mechanical properties of strain-hardening cementitious composites (SHCCs) i.e., compressive strength (CS), first crack tensile stress (TS), and first crack flexural stress (FS), using gene expression programming (GEP). Wide-ranging records were considered with twelve variables i.e., cement percentage by weight (C%), fine aggregate percentage by weight (Fagg%), fly-ash percentage by weight (FA%), Water-to-binder ratio (W/B), super-plasticizer percentage by weight (SP%), fiber amount percentage by weight (Fib%), length to diameter ratio (L/D), fiber tensile strength (FTS), fiber elastic modulus (FEM), environment temperature (ET), and curing time (CT). The performance of the models was deduced using correlation coefficient (R) and slope of regression line. The established models were also assessed using relative root mean square error (RRMSE), Mean absolute error (MAE), Root squared error (RSE), root mean square error (RMSE), objective function (OBF), performance index (PI) and Nash-Sutcliffe efficiency (NSE). The resulting mathematical GP-based equations are easy to understand and are consistent disclosing the originality of GEP model with R in the testing phase equals to 0.8623, 0.9269, and 0.8645 for CS, TS and FS respectively. The PI and OBF are both less than 0.2 and are in line with the literature, showing that the models are free from overfitting. Consequently, all proposed models have high generalization with less error measures. The sensitivity analysis showed that C%, Fagg%, and ET are the most significant variables for all three models developed with sensitiveness index higher than 10 %. The result of the research can assist researchers, practitioners, and designers to assess SHCC and will lead to sustainable, faster, and safer construction from environment-friendly waste management point of view.

Explainable Artificial Intelligence to Investigate the Contribution of Design Variables to the Static Characteristics of Bistable Composite Laminates

Material properties, geometrical dimensions, and environmental conditions can greatly influence the characteristics of bistable composite laminates. In the current work, to understand how each input feature contributes to the curvatures of the stable equilibrium shapes of bistable laminates and the snap-through force to change these configurations, the correlation between these inputs and outputs is studied using a novel explainable artificial intelligence (XAI) approach called SHapley Additive exPlanations (SHAP). SHAP is employed to explain the contribution and importance of the features influencing the curvatures and the snap-through force since XAI models change the data into a form that is more convenient for users to understand and interpret. The principle of minimum energy and the Rayleigh-Ritz method is applied to obtain the responses of the bistable laminates used as the input datasets in SHAP. SHAP effectively evaluates the importance of the input variables to the parameters. The results show that the transverse thermal expansion coefficient and moisture variation have the most impact on the model's output for the transverse curvatures and snap-through force. The eXtreme Gradient Boosting (XGBoost) and Finite Element (FM) methods are also employed to identify the feature importance and validate the theoretical approach, respectively.

Comprehensible Machine-Learning-Based Models for the Pre-Emptive Diagnosis of Multiple Sclerosis Using Clinical Data: A Retrospective Study in the Eastern Province of Saudi Arabia

Multiple Sclerosis (MS) is characterized by chronic deterioration of the nervous system, mainly the brain and the spinal cord. An individual with MS develops the condition when the immune system begins attacking nerve fibers and the myelin sheathing that covers them, affecting the communication between the brain and the rest of the body and eventually causing permanent damage to the nerve. Patients with MS (pwMS) might experience different symptoms depending on which nerve was damaged and how much damage it has sustained. Currently, there is no cure for MS; however, there are clinical guidelines that help control the disease and its accompanying symptoms. Additionally, no specific laboratory biomarker can precisely identify the presence of MS, leaving specialists with a differential diagnosis that relies on ruling out other possible diseases with similar symptoms. Since the emergence of Machine Learning (ML) in the healthcare industry, it has become an effective tool for uncovering hidden patterns that aid in diagnosing several ailments. Several studies have been conducted to diagnose MS using ML and Deep Learning (DL) models trained using MRI images, achieving promising results. However, complex and expensive diagnostic tools are needed to collect and examine imaging data. Thus, the intention of this study is to implement a cost-effective, clinical data-driven model that is capable of diagnosing pwMS. The dataset was obtained from King Fahad Specialty Hospital (KFSH) in Dammam, Saudi Arabia. Several ML algorithms were compared, namely Support Vector Machine (SVM), Decision Tree (DT), Logistic Regression (LR), Random Forest (RF), Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), and Extra Trees (ET). The results indicated that the ET model outpaced the rest with an accuracy of 94.74%, recall of 97.26%, and precision of 94.67%.

Evaluating the compressive strength of glass powder-based cement mortar subjected to the acidic environment using testing and modeling approaches

This study conducted experimental and machine learning (ML) modeling approaches to investigate the impact of using recycled glass powder in cement mortar in an acidic environment. Mortar samples were prepared by partially replacing cement and sand with glass powder at various percentages (from 0% to 15%, in 2.5% increments), which were immersed in a 5% sulphuric acid solution. Compressive strength (CS) tests were conducted before and after the acid attack for each mix. To create ML-based prediction models, such as bagging regressor and random forest, for the CS prediction following the acid attack, the dataset produced through testing methods was utilized. The test results indicated that the CS loss of the cement mortar might be reduced by utilizing glass powder. For maximum resistance to acidic conditions, the optimum proportion of glass powder was noted to be 10% as cement, which restricted the CS loss to 5.54%, and 15% as a sand replacement, which restricted the CS loss to 4.48%, compared to the same mix poured in plain water. The built ML models also agreed well with the test findings and could be utilized to calculate the CS of cementitious composites incorporating glass powder after the acid attack. On the basis of the R2 value (random forest: 0.97 and bagging regressor: 0.96), the variance between tests and forecasted results, and errors assessment, it was found that the performance of both the bagging regressor and random forest models was similarly accurate.

In-Depth Analysis of Cement-Based Material Incorporating Metakaolin Using Individual and Ensemble Machine Learning Approaches

In recent decades, a variety of organizational sectors have demanded and researched green structural materials. Concrete is the most extensively used manmade material. Given the adverse environmental effect of cement manufacturing, research has focused on minimizing environmental impact and cement-based product costs. Metakaolin (MK) as an additive or partial cement replacement is a key subject of concrete research. Developing predictive machine learning (ML) models is crucial as environmental challenges rise. Since cement-based materials have few ML approaches, it is important to develop strategies to enhance their mechanical properties. This article analyses ML techniques for forecasting MK concrete compressive strength (fc'). Three different individual and ensemble ML predictive models are presented in detail, namely decision tree (DT), multilayer perceptron neural network (MLPNN), and random forest (RF), along with the most effective factors, allowing for efficient investigation and prediction of the fc' of MK concrete. The authors used a database of MK concrete mechanical features for model generalization, a key aspect of any prediction or simulation effort. The database includes 551 data points with relevant model parameters for computing MK concrete's fc'. The database contains cement, metakaolin, coarse and fine aggregate, water, silica fume, superplasticizer, and age, which affect concrete's fc' but were seldom considered critical input characteristics in the past. Finally, the performance of the models is assessed to pick and deploy the best predicted model for MK concrete mechanical characteristics. K-fold cross validation was employed to avoid overfitting issues of the models. Additionally, ML approaches were utilized to combine SHapley Additive exPlanations (SHAP) data to better understand the MK mix design non-linear behaviour and how each input parameter's weighting influences the total contribution. Results depict that DT AdaBoost and modified bagging are the best ML algorithms for predicting MK concrete fc' with R² = 0.92. Moreover, according to SHAP analysis, age impacts MK concrete fc' the most, followed by coarse aggregate and superplasticizer. Silica fume affects MK concrete's fc' least. ML algorithms estimate MK concrete's mechanical characteristics to promote sustainability.