The cost-effectiveness of vaccination against COVID-19 in at-risk populations and older adults in the United Kingdom: Projections using a dynamic transmission model.

ABSTRACT This paper outlines a hybrid experimental and computational model to assess and optimize the mechanical behavior of sustainable concrete with silica fume (SF), waste glass powder (WGP), and crumb rubber (CR). Compared to current research, which mainly concentrates on individual or binary systems, this paper explores a ternary blended system and characterizes the intricate interactions among mix parameters with advanced machine learning methods. To establish compressive, flexural and tensile strengths of 7, 28 and 56 days, experimental investigations were carried out. The findings suggest that SF and WGP increase strength because of pozzolanic reactivity and refinement of microstructure, and CR decreases strength because of the weaker interfacial bonding. Several machine learning models, such as Random Forest, XGBoost, Support Vector Machine, Decision Tree, and Ensemble, were built on the basis of strength prediction with the highest level of accuracy being XGBoost and Ensemble (R2 > 0.88). Moreover, optimization with the help of Genetic Algorithms was used to determine the optimal mix proportions leading to the increase in compressive, flexural, and tensile strengths by 34%, 37%, and 46%, respectively. The proposed framework offers a sound and data-driven methodology of designing high-performance and environmentally friendly concrete mixtures.

Solar cookers have evolved into an eco-friendly alternative to conventional cooking methods by reducing dependency on fossil fuels. Because of advancements in materials, insulation techniques, and reflector designs, their efficiency has significantly increased over time. Modern solar cookers incorporate PCM to enhance heat retention and enable cooking during non-sunny hours. PCM technology aids in the storage of thermal energy and improves overall cooking efficiency by absorbing excess heat and releasing it gradually. Recent studies have looked into using machine learning (ML) algorithms to optimize solar cooker performance. Regression models such as ANN, SVR, decision trees, and hybrid ML models have been used to predict temperature changes, optimize design parameters, and improve heat retention. Phase Change Materials (PCM) and Machine Learning (ML) have been combined to greatly increase the solar cookers' efficiency and versatility. ML-based predictive models will be essential in improving heat retention, optimizing reflector angles, and increasing overall thermal efficiency as AI-driven optimization advances further. This will make solar cooking more dependable and accessible for a range of climatic conditions. The present paper studies the advancement in solar cookers, experimental studies, and the best ML models used for predicting temperature, material performance, and cooker efficiency. Below figure shows the data acquisition of both PCM and non PCM for machine learning regression • Evolution of Solar Cookers – Traces the advancements in solar cookers, emphasizing eco-friendly alternatives to fossil-fuel-based cooking. • Improved Efficiency – Discusses innovations in materials, insulation techniques, and reflector designs that have enhanced solar cooking performance. • Phase Change Materials (PCM) for Heat Retention – Explores how PCM helps store thermal energy, enabling cooking even during non-sunny hours. • Machine Learning (ML) in Solar Cooking – Reviews the role of ML models in optimizing solar cookers by predicting temperature variations and improving efficiency. • Use of Regression Models – Highlights applications of ANN, SVR, decision trees, and hybrid ML models in predicting heat retention and optimizing design. • AI-Driven Optimization – Explains how ML techniques help refine reflector angles, material selection, and thermal performance for various climates. • Integration of IoT – Discusses the role of IoT in monitoring and controlling solar cookers for better efficiency and real-time optimization. • Experimental Studies – Summarizes experimental research on PCM-enhanced solar cookers and ML-driven performance enhancements. • Future Trends – Identifies potential advancements in AI, thermal storage, and automation to improve the reliability of solar cooking. • Impact on Sustainability – Emphasizes the contribution of AI and PCM in making solar cookers a viable, eco-friendly solution for global energy needs.

Understanding student mental health: An explainable pattern analysis approach.

Temperature-sensitive medicines require controlled storage and transport conditions because unsuitable temperature and humidity exposure can compromise product quality and drug-delivery reliability. This study presents a low-cost Internet of Things (IoT)-assisted and lightweight machine learning framework for cold-chain risk assessment in temperature-sensitive drug delivery. A realistic cold-chain monitoring dataset was prepared to represent normal refrigerated storage, door-opening disturbance, transport exposure, freezing-risk events, humidity variation, and high-temperature excursions. Temperature, humidity, deviation-based variables, and exposure-duration features were used to classify storage conditions into Safe, Warning, and Unsafe states. Since unsafe excursions were naturally less frequent, bounded sensor-level augmentation was applied to construct an ML-ready dataset while preserving the raw monitoring profile for descriptive analysis. Four lightweight classifiers, namely Logistic Regression, Decision Tree, Random Forest, and support vector machine, were evaluated. Random Forest achieved the highest baseline performance with 0.9659 accuracy and 0.9636 macro F1-score. In feature-set ablation, the derived feature configuration without the direct risk score achieved 0.9636 accuracy and 0.9616 macro F1-score using seven features. The findings indicate that low-cost IoT monitoring combined with lightweight learning can support early warning and decision assistance in resource-constrained temperature-sensitive drug-delivery environments.

Development of an interpretable machine learning model-based online tool for risk identification of anxiety symptoms in Chinese older adults.

Accurate differentiation between non-small cell lung cancer (NSCLC) and small cell lung cancer (SCLC) is crucial for optimising treatment strategies and improving patient outcomes in lung cancer management. Early and precise classification supports tailored therapeutic decisions and enhances prognosis prediction. This study develops a novel method to use machine learning models trained with physical science features extracted from pathological images to classify lung cancer into NSCLC and SCLC with high accuracy and robustness. Physical science features were employed to acquire quantitative cellular microarchitecture of cancer cells from histopathological images. Random Forest algorithm was applied to identify the most informative 20 features. Next, the selected top features were used to train and evaluate four machine learning classifiers: Support Vector Machine (SVM), Gradient Boosting, Logistic Regression, and Decision Tree. The dataset included pathological images from 240 histologically confirmed lung cancer cases, divided randomly into training and validation sets (80% train, 20% test). Then, model performance was evaluated using accuracy, recall, F1 score, and area under the receiver operating characteristic curve (AUC), with robustness validation via fivefold cross-validation. Logistic Regression achieved the highest overall performance, with a median accuracy near 90% and an AUC consistently above 0.90 across fivefold cross-validation. SVM and Gradient Boosting followed closely, each surpassing 0.90 in AUC, demonstrating reliable discrimination between NSCLC and SCLC. Decision Tree showed broader variability, though it maintained acceptable recall for SCLC. Random Forest feature selection revealed refractive index percentiles and polarisation histograms as top contributors to model performance. Machine learning models trained on physical science features have the potential to serve as a highly accurate and robust framework for differentiating NSCLC from SCLC.

Who benefits, who is left behind? Intersectional inequities in unmet health care needs before and after the 2010 Swedish choice in primary health care reform using decision trees.

Dizziness and vertigo are common emergency department (ED) presentations, but only 2%-5% receive a serious diagnosis, such as stroke or transient ischemic attack (TIA). Due to the lack of reliable validated prediction tools, many undergo unnecessary imaging and consultations, highlighting the need for improved risk stratification. To develop machine learning (ML) models that predict serious diagnoses in ED patients presenting with dizziness or vertigo. This multicenter cohort study included 6637 ED patients with dizziness, vertigo, or imbalance from September 2014-December 2022. The primary outcome was a serious diagnosis-stroke, TIA, vertebral artery dissection, or brain tumor-within 30 days, adjudicated by a blinded committee. Data were split 80/20 into training and test sets. Four ML models (decision tree, LASSO logistic regression, random forest, XGBoost) were trained on 17 variables using 5-fold cross-validation and evaluated alongside the Sudbury Vertigo Risk score. Performance was assessed using area under the curve (AUC) and diagnostic accuracy measures. Computed tomography (CT) and referral rates were hypothetically compared pre- and post-model application. Among 6637 patients (mean age 78.1; 57.8% female), 3.3% had a serious diagnosis. All ML models demonstrated strong discrimination, with AUCs ranging from 0.92 to 0.97. At a 5% predicted probability threshold, sensitivities ranged from 53%-97% and specificities from 84% to 96%. Logistic regression with LASSO demonstrated a favorable balance between discrimination (AUC: 0.97, sensitivity: 97% and specificity: 91%), although confidence intervals overlapped substantially across models. In a hypothetical model-based analysis, ML-guided classification corresponded to projected reductions in CT utilization and referrals ranging from 53%-85% and 11%-73%, respectively. Select ML models demonstrated discrimination comparable to the Sudbury Vertigo Risk Score while potentially improving specificity and reducing projected resource utilization. These tools show promise, but external validation is needed.

The rapid expansion of IoT devices in maternal health monitoring enables continuous data collection and improved clinical assessment; however, it also introduces significant security and privacy concerns due to the sensitivity of maternal health information. This study investigates how artificial intelligence (AI) and machine learning (ML) can enhance both analytical performance and data protection in IoT-based maternal monitoring systems. The proposed framework employs Random Forest, Decision Tree, Support Vector Machine, and a stacking–bagging ensemble to improve maternal risk prediction and anomaly detection. Privacy-preserving techniques are integrated to secure physiological parameters: homomorphic encryption ensures data confidentiality during processing, while differential privacy limits information leakage from model outputs. Experimental results show that the stacking classifier combined with Random Forest achieved the highest accuracy of 82.3%, demonstrating greater robustness than traditional algorithms. Although differential privacy strengthened data protection, it reduced precision and F1-score, highlighting a trade-off between privacy and accuracy. Overall, integrating ensemble learning with privacy-preserving methods improves the security, accuracy, and reliability of IoT-driven maternal health monitoring systems.

The causal effect of iterative changes in table tennis rules on the technical and tactical system: An empirical test based on Markov chain and decision tree models.

Breastfeeding shows persistent disparities shaped by complex maternal, infant, and household factors, making prediction challenging. As traditional models struggle to capture such complexity, this study aims to identify predictors of ever breastfeeding and longer breastfeeding duration using multiple machine learning models and to assess the potential of these methods in breastfeeding prediction. Using nationally representative data from the U.K. Household Longitudinal Study, we apply Lasso (Least Absolute Shrinkage and Selection Operator) logistic regression, decision tree, random forest, XGBoost, support vector machine, and neural network models to examine factors associated with whether infants were ever breastfed and whether breastfeeding stopped at or after 3 months. Maternal, household, and birth-related factors all relate to breastfeeding, but maternal socioeconomic factors, especially education and ethnicity, emerge as the strongest predictors. Across the two breastfeeding outcomes, model performance is better for whether infants were ever breastfed than for breastfeeding duration, which is more difficult to predict. Within each outcome, the models show similar performance without substantial differences. Breastfeeding outcomes can be reasonably predicted, and the predictive signal is driven primarily by maternal socioeconomic characteristics, enabling targeted support at relatively low informational cost. However, prediction remains limited, especially for breastfeeding duration, suggesting that while key influences are captured, more nuanced or situational mechanisms remain difficult to anticipate. Lasso logistic regression, with its low complexity and transparent structure, performs comparably to more complex models and may therefore be a more appropriate methodological choice for breastfeeding prediction.

Integrated molecular and clinical profiling of primary mitochondrial oxidative phosphorylation disorders in an Indian cohort: Insights from genetics, neuroimaging, and machine learning.

Rule-based machine learning models, including those derived from decision trees or forests, are often considered inherently interpretable. However, human understanding is hindered by model size, rule complexity, and interdependencies between features. Moreover, rule sets extracted from ensemble models can contain contradictory, incomplete, or counterintuitive logic, even when the overall model achieves high predictive accuracy. This paper introduces a visual analytics methodology designed to support systematic exploration of rule-based model logic and its alignment with domain knowledge. Our approach integrates overview visualizations, interactive filtering, contradiction analysis, and topic modeling. This enables analysts to detect illogical or implausible rules, assess their potential impact, and refine the model to improve its interpretability and trustworthiness. A key distinction of our method is its ability to support reasoning about model behavior both with and without access to labeled data. We demonstrate the approach through two real-world case studies: evaluating logical consistency in a vessel movement classifier and analyzing feature relationships in a COVID-19 prediction model. These studies show how visual analytics can facilitate logic-focused model critique beyond traditional performance metrics and enable valuable domain-relevant insights.

Machine learning reveals drivers of microplastic bioaccumulation in fish from a freshwater reservoir ecosystem.

Air pollution is a serious environmental problem that affects human health. Predicting air quality in advance can help people take preventive actions. In this research, a machine learning based system is developed to predict the Air Quality Index (AQI). The model uses pollution parameters such as PM2.7, PM10, NO2, SO2, CO, and O3. Multiple machine learning algorithms such as Linear Regression, Decision Tree, Random Forest, Support Vector Machine, and K-Nearest Neighbors are used and compared. The best performing model is selected based on accuracy. The system can predict AQI and classify air quality levels such as Good, Moderate, Poor, Very Poor, and Severe.

Predicting PROTAC degradation activity and selectivity of effective E3 ligase through harnessing a combination of AtomPair fingerprints and multiple machine learning algorithms.

Comparison of demographic and clinical features in adolescent-onset vs. adult-onset bipolar disorder an analysis of BIPAS Phase II data.

The transition to sustainable energy positions wind power as a key renewable solution. As demand grows, wind turbines are deployed across diverse terrains. However, wind’s stochastic nature and environmental variability complicate power forecasting, affecting grid stability. The study leverages data-driven techniques to enhance wind power forecasting using high-resolution SCADA system time-series data. Key operational parameters include wind speed, rotor speed, generator speed, nacelle orientation, ambient temperature and power output. A comparative analysis evaluates traditional machine learning models—Linear Regression, Decision Trees, Random Forests, Gradient Boosting and Support Vector Machines—against deep learning models like Long Short-Term Memory (LSTM) networks and a novel Recurrent Neural Network (RNN) architecture. The core contribution is an optimized Bidirectional LSTM-RNN model with permutation layers and attention. These layers capture long-range dependencies and nonlinear interactions in wind data. The structure improves long-range dependency capture and nonlinear interaction modeling. Bidirectionality enables learning from both past and future time steps, while attention mechanisms highlight critical temporal features. Experimental results demonstrate the proposed model’s superior performance, achieving a Mean Absolute Error (MAE) of 0.0994 and Root Mean Square Error (RMSE) of 0.1390, significantly outperforming traditional models (e.g., Random Forest: MAE 86.44, RMSE 220.30) and basic LSTM models (MAE 14.48, RMSE 15.27). Robust cross-validation confirms its ability to generalize across different temporal segments. Feature importance analysis improves interpretability, supporting informed decision-making in wind farm operations. The framework is scalable, modular and well-suited for real-time forecasting applications. The work presents a reliable deep learning model for wind power forecasting, enabling intelligent, data-driven energy management in modern power systems.

Thermo-mechanical performance evaluation of hybrid NiTi/CF-PEKK composite laminates using experiments and machine learning approaches