Breast cancer diagnosis using medical imaging remains a critical challenge due to variability in tumor appearance and limitations of single-model prediction systems. While deep learning approaches have yielded encouraging results, concerns with model generalization, robustness, and clinical reliability remain. This study provides a hybrid ensemble deep learning framework for ultrasound-based breast cancer classification, which combines a proprietary Convolutional Neural Network (CNN) with transfer learning models such as VGG16, DenseNet121, and InceptionV3. A total dataset of 5,400 ultrasound images was used. Parameter optimization and preprocessing techniques such as normalization, resizing, and data augmentation were employed. The proposed system uses voting ensemble approaches to combine predictions from individual models. DenseNet121 achieved the highest standalone accuracy (98.2%), whereas the proposed ensemble model demonstrated superior generalization, with an overall accuracy of 96.0%, precision of 96.1%, recall of 96.0%, and F1-score of 95.9%. Soft voting outperformed hard voting in terms of stability and balanced classification performance, whereas hard voting reduced model bias. The data show that ensemble learning increases diagnostic consistency and reliability. The proposed method offers a scalable and robust solution for computer-aided diagnosis systems, with high potential for real-world clinical integration.

This bibliometric survey examines 200 highly cited publications spanning from 2009 to 2025, retrieved from the Scopus database using search terms targeting neuromorphic computing and its applications in healthcare engineering and biomedical systems. The analysis reveals a rapidly maturing interdisciplinary field at the convergence of materials science, device physics, circuit design, computer architecture, and biomedical engineering. Key findings indicate that memristive devices, particularly those based on metal oxides and two-dimensional materials, constitute the dominant hardware platform for neuromorphic computing, with phase-change materials, spintronic devices, and ferroelectric tunnel junctions representing significant alternative approaches. The United States, China, Germany, South Korea, and Switzerland emerge as the most productive nations, with extensive international collaboration networks reflecting the field's multidisciplinary nature. Thematic clustering identifies five major research domains: (1) memristive devices and resistive switching mechanisms, (2) two-dimensional materials for neuromorphic applications, (3) spiking neural networks and neuromorphic architectures, (4) optical and photonic neuromorphic computing, and (5) biomedical and healthcare applications including electronic skin, neural prosthetics, and biosensing. Emerging trends include the integration of neuromorphic computing with edge artificial intelligence for wearable healthcare devices, the development of reservoir computing for real-time biomedical signal processing, and the convergence of neuromorphic systems with biohybrid interfaces. This survey provides a comprehensive mapping of the intellectual landscape, identifies persistent challenges including device variability, scalability, and biocompatibility, and proposes future directions for healthcare-oriented neuromorphic engineering.

This bibliometric survey examines 200 highly cited publications spanning from 2018 to 2025, retrieved from the Scopus database using search terms targeting federated learning applications in healthcare, medical imaging, and clinical diagnostics. The analysis reveals a rapidly maturing interdisciplinary field at the convergence of distributed machine learning, privacy-preserving technologies, and biomedical informatics. Key findings indicate that federated learning has emerged as a transformative paradigm for collaborative AI model training across healthcare institutions without compromising patient data privacy. The United States, China, the United Kingdom, Germany, and India emerge as the most productive nations, with extensive international collaboration networks reflecting the global need for privacy-compliant healthcare AI. Thematic clustering identifies five major research domains: (1) federated learning architectures and algorithms for healthcare, (2) privacy-preserving techniques including differential privacy, homomorphic encryption, and blockchain integration, (3) medical imaging applications (radiology, pathology, dermatology, ophthalmology), (4) electronic health records and predictive analytics, and (5) wearable devices and remote patient monitoring. Emerging trends include the integration of federated learning with explainable AI for clinical interpretability, the convergence of federated learning with digital twins and the healthcare metaverse, and the development of personalized federated learning frameworks for handling non-IID medical data. This survey provides a comprehensive mapping of the intellectual landscape, identifies persistent challenges including data heterogeneity, communication efficiency, and security vulnerabilities, and proposes future directions for privacy-preserving healthcare AI.

Digital twin technology, which creates virtual replicas of physical entities, has emerged as a transformative paradigm in healthcare engineering, enabling personalized medicine, surgical simulation, and real-time patient monitoring. This study presents a comprehensive scien-tometric analysis of 200 highly cited articles retrieved from Scopus using a targeted search string focused on digital twins, virtual patients, and patient avatars in healthcare. The analysis characterizes publication trends, citation impact, leading contributors, thematic clusters, and collaborative networks. Results indicate that research output has accelerated dramatically since 2019, with 2021–2024 representing the most productive period. The highest citation concentrations are found in studies applying digital twins to cardiology, oncology, surgical planning, and healthcare system optimization. The United States, China, Germany, and the United Kingdom dominate production, with strong interdisciplinary collaborations among en-gineering, computer science, and clinical departments. Co-occurrence analysis of author keywords reveals six major thematic clusters: cardiovascular digital twins, surgical simulation and virtual patients, personalized and precision medicine, enabling technologies (IoT, AI, blockchain), healthcare system digital twins, and ethical and regulatory considerations. This scientometric mapping provides researchers, clinicians, and policymakers with an evidence-based roadmap of a rapidly evolving field positioned at the intersection of engineering and medicine.

Early identification of individuals at high risk of stroke is essential for improving prognosis, guiding preventive strategies, and reducing the burden of stroke-related disability. This study presents a comparative machine learning approach for stroke risk prediction using structured healthcare data containing demographic, lifestyle, and clinical variables. The proposed approach evaluates five supervised classification models, namely Random Forest, Support Vector Machine, XGBoost, LightGBM, and CatBoost, to identify the most suitable model for stroke risk classification. A systematic preprocessing pipeline was applied, including median imputation for missing BMI values, categorical feature encoding, stratified data splitting, feature scaling, and Synthetic Minority Over-sampling Technique (SMOTE) to address severe class imbalance in the training data. Model performance was assessed using accuracy, precision, recall, and F1-score Among the evaluated models, CastBoost achieved the most balanced overall performance, while SVM showed higher sensitivity in detecting stroke cases. These findings indicate that model selection should depend on the intended clinical purpose, particularly whether the goal is balanced prediction or improved detection of possible stroke cases. Overall, this study highlights the potential of machine learning to support early stroke risk assessment and preventive healthcare decision-making using routinely available structured health data.

Road transport in the metropolis of Tehran is one of the major sources of air pollutants, greenhouse gas emissions, and traffic noise, thereby creating a direct and measurable burden on urban health through respiratory and cardiovascular morbidity, stress and sleep disturbance, traffic injuries, and inequitable exposure across neighborhoods. Unfavorable fleet composition, relatively low fuel prices, and strong dependence on private cars have turned Tehran into a critical hotspot in Iran in terms of environmental risks and public health impacts. At the same time, this sector has substantial capacity for innovation in vehicle, fuel, and infrastructure technologies and can through well-designed and coordinated policy reduce emissions, improve air quality, and enhance both physical and mental well-being. Focusing on Tehran, this paper proposes a framework for designing a policy mix in road transport that simultaneously addresses technological innovation and the reduction of environmental and urban-health impacts. First, drawing on international literature, policy instruments are classified into four categories: regulatory, economic, support/institutional, and infrastructure; and indicators are introduced to assess their impacts on innovation, greenhouse gas emissions, and urban health. Next, the overall situation of transport and air pollution in Tehran and the dominant role of mobile sources in generating urban air pollutants and carbon dioxide emissions are described. A conceptual practical example is then developed for the passenger car fleet in Tehran, comparing three scenarios: (i) reliance on subsidies for purchasing electric cars, (ii) an exclusive focus on fuel consumption standards and fuel pricing, and (iii) an integrated policy mix. The conceptual results indicate that focusing on a single instrument such as electric-vehicle subsidies without reforming standards, inspection/enforcement, and fuel pricing has limited and inequitable health and environmental impacts, whereas a balanced policy mix can simultaneously reduce fuel consumption, strengthen innovation in the automotive sector, and mitigate the aggravation of urban health inequalities in Tehran.

In this paper, a hybrid multi-layer machine learning model is proposed for early prediction of PD using voice data. The suggested technique combines a number of base learners namely Random Forest, XGBoost, LightGBM, and CatBoost through ensemble methods like Voting Classifier, and Stacking Classifier. A thorough feature engineering, from correlation analysis to feature selection and polynomial feature extraction, was applied to improve the model’s quality. Experiments results show that the hybrid model obtained accuracy of 91.30% with high precision and recall especially for Class-1(Parkinson’s disease). Although very strong in its entirety the limited ability to discriminate healthy subjects (Class 0) (recall around 0.75). Among the selected models, Voting Classifier and CatBoost were robust and presented generalization well for all performance measures. The contribution of this work is two-folds: it demonstrates that ensemble models can be used to enhance diagnostic accuracy, and it addresses three main issues inherent in Parkinson's disease detection. Optimization of the performance of the model in discriminating healthy from Parkinson’s disease individuals is highly valuable, with an emphasis on the generalization and clinical usage.

Stress has become a significant issue in today's society, affecting a person's emotions, thoughts, actions, and communication. Although the human body is designed to cope with stress, prolonged stress can lead to serious health problems such as cancer, cardiovascular disease, depression, and diabetes. However, identifying and tracking a person's stress levels is difficult. Many machine learning methods have been proposed in the literature to address this issue. The primary aim of this study is to develop an accurate and rapid framework for detecting a person's stress levels and estimating their degree of stress. In this proposed study, a machine learning-based approach using an integrated feature selection technique is proposed for human stress detection. The dataset is preprocessed using Label Encoding, and the imbalanced dataset is addressed using SMOTE. The dataset is normalized to ensure consistency. The integrated feature selection technique, Recursive Feature Elimination (RFE), is then applied to select the most crucial features for building the system. Finally, several classification algorithms, such as Decision Tree (DT), Random Forest, Gradient Boosting, AdaBoost, XGBoost, and Extra Tree Classifier, are utilized to identify the stress level of humans. The experiments are conducted on the SWELL-KW dataset.

Due to the Covid -19 pandemic outbreak and the lockdowns in Kerala, India, during the second wave in 2021, children were faced with prolonged school closures, lack of socialization, and family distress, all of which posed considerable psychological pressures on their well-being. To investigate the causal pathways among parental mental health, parenting attitude, family demographic characteristics, and child psychological problems, this research employed a cross-sectional survey that was conducted on 383 parents with their children, aged 5 to 15 years old. By means of Covariance-Based Structural Equation Modelling (CB-SEM) using SmartPLS software, we analyzed a data set consisting of 12 ordinal measures (Likert and ordered categorical) and 3 continuous composite variables (Depression, Anxiety, and sleep disorder) that represent the symptoms of child mental health problems as reported by the parents. In this case, there are four latent variables (Parental Mental Health, Child Information, Parents' Attitude Toward Child, and Child Mental Health) obtained from the validated measurement models. As indicated in the latent covariances, there exists a positive relationship between parental mental distress and child psychological problems (estimate = 1.349, SE = 0.242, p < .001), as well as a stronger correlation between harsh parental practices and child psychological issues (estimate = 3.146, SE = 0.288, p < .001). Moreover, it is found that parental distress is associated with poor parenting attitude (estimate = 0.242, SE = 0.046, p < .001). This suggests that parental mental distress can have a significant mediating effect on poor parental attitude towards children, which increases the likelihood of developing depression, anxiety, and sleep disorder. Family structure plays a comparatively modest role. These findings highlight how severe parenting practices and parental mental health affect children's mental health.

There are many opportunities and challenges in the healthcare system (HCS) due to advanced globalization of today’s technological environment. Assessment of HCS’s performance and ranking them depending on performance analysis is one of the most important challenges. It is the most significant strategic consideration to every Hospital Information System (HIS) management in terms of business intelligence (BI) as critical healthcare services attributes must be considered from a large volume of information, known as Big Data (BD). As these types of decisions involve qualitative and quantitative criteria, multiple-criteria-decision-making (MCDM) technique becomes a useful approach to solve this kind of problem. This paper suggests an intelligent model by integrating fuzzy Shannon entropy and Fuzzy Technique for Order Preference by Similarity to Ideal Solution Method (FTOPSIS) techniques as a decision-making tool for analyzing the performance of HCSs using linguistic values which smoothly assists decision makers dealing with uncertain information or situations without losing existing quality of HIS. The novelty of this paper is to propose a framework for ranking HCS by analyzing their performance to help the improvement of the performance of HIS worldwide by enhancing the BI of HIS where all the meaningful information retrieved by analyzing BD based on decision making by the management. [center][/center]