Search Results (1,538)

High-dimensional prediction problems with complex non-linear feature interactions present significant algorithmic challenges in machine learning, particularly when dealing with imbalanced datasets and multicollinearity issues. This study proposes an innovative Shapley Additive Explanations (SHAP)-enhanced machine learning framework that integrates SHAP with advanced ensemble methods for interpretable financialization prediction. The methodology simultaneously addresses high-dimensional feature selection using 40 independent variables (19 CSR-related and 21 financialization-related), multicollinearity issues, and model interpretability requirements. Using a comprehensive dataset of 25,642 observations from 3776 Chinese A-share companies (2011–2022), we implement nine optimized machine learning algorithms with hyperparameter tuning via the Hippopotamus Optimization algorithm and five-fold cross-validation. XGBoost demonstrates superior performance with 99.34% explained variance, achieving an RMSE of 0.082 and R² of 0.299. SHAP analysis reveals non-linear U-shaped relationships between key predictors and financialization outcomes, with critical thresholds at approximately 10 for CSR_SocR, 1.5 for CSR_S, and 5 for CSR_CV. SOE status, EPU, ownership concentration, firm size, and housing prices emerge as the most influential predictors. Notable shifts in factor importance occur during the COVID-19 pandemic period (2020–2022). This work contributes a scalable, interpretable machine learning architecture for high-dimensional financial prediction problems, with applications in risk assessment, portfolio optimization, and regulatory monitoring systems. Full article

The COVID-19 pandemic precipitated unprecedented social isolation measures, profoundly disrupting daily life, educational routines, and mental health worldwide. University students, already susceptible to psychological distress, encountered intensified challenges under remote learning and prolonged confinement. This longitudinal study examined fluctuations in anxiety and mood among 102 Brazilian university students during the pandemic, distinguishing between those solely engaged in academic pursuits and those simultaneously balancing work and study. Data collected via the Brunel Mood Scale and State-Trait Anxiety Inventory in April and July 2021 revealed that students exclusively focused on studies exhibited significant increases in depressive symptoms, anger, confusion, and anxiety, alongside diminished vigor. Conversely, participants who combined work and study reported reduced tension, fatigue, confusion, and overall mood disturbance, coupled with heightened vigor across the same period. Notably, women demonstrated greater vulnerability to anxiety and mood fluctuations, with socioeconomic disparities particularly pronounced among females managing dual roles, who reported lower family income. These findings suggest that occupational engagement may serve as a protective factor against psychological distress during crises, underscoring the urgent need for tailored mental health interventions and institutional support to mitigate the enduring impacts of pandemic-related adversities on the student population. Full article

A multilayer linear response model (MLRM) is proposed to generate time-series data based on linear response theory. The proposed MLRM is designed to generate data for anomalous dynamics by extending the conventional single-layer linear response model (SLRM) into multiple layers. While the SLRM is a linear equation with respect to external forces, the MLRM introduces nonlinear interactions, enabling the generation of a wider range of dynamics. The MLRM is applicable to various fields, such as finance, as it does not rely on machine learning techniques and maintains interpretability. We investigated whether the MLRM could generate anomalous dynamics, such as those observed during the coronavirus disease 2019 (COVID-19) pandemic, using pre-pandemic data. Furthermore, an analysis of the log returns and realized volatility derived from the MLRM-generated data demonstrated that both exhibited heavy-tailed characteristics, consistent with empirical observations. These results indicate that the MLRM can effectively reproduce the extreme fluctuations and tail behavior seen during high-volatility periods. Full article

Monitoring Peripheral Oxygen Saturation (SpO₂) is an important vital sign both in Intensive Care Units (ICUs), during surgery and convalescence, and as part of remote medical consultations after of the COVID-19 pandemic. This has made the development of new SpO₂-measurement tools an area of active research and opportunity. In this paper, we present a new Deep Learning (DL) combined strategy to estimate SpO₂ without contact, using pre-magnified facial videos to reveal subtle color changes related to blood flow and with no calibration per subject required. We applied the Eulerian Video Magnification technique using the Hermite Transform (EVM-HT) as a feature detector to feed a Three-Dimensional Convolutional Neural Network (3D-CNN). Additionally, parameters and hyperparameter Bayesian optimization and an ensemble technique over the dataset magnified were applied. We tested the method on 18 healthy subjects, where facial videos of the subjects, including the automatic detection of the reference from a contact pulse oximeter device, were acquired. As performance metrics for the SpO₂-estimation proposal, we calculated the Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and other parameters from the Bland–Altman (BA) analysis with respect to the reference. Therefore, a significant improvement was observed by adding the ensemble technique with respect to the only optimization, obtaining 14.32% in RMSE (reduction from 0.6204 to 0.5315) and 13.23% in MAE (reduction from 0.4323 to 0.3751). On the other hand, regarding Bland–Altman analysis, the upper and lower limits of agreement for the Mean of Differences (MOD) between the estimation and the ground truth were 1.04 and −1.05, with an MOD (bias) of −0.00175; therefore, MOD $\pm 1.96\sigma$ = −0.00175 ± 1.04. Thus, by leveraging Bayesian optimization for hyperparameter tuning and integrating a Bagging Ensemble, we achieved a significant reduction in the training error (bias), achieving a better generalization over the test set, and reducing the variance in comparison with the baseline model for SpO₂ estimation. Full article

Background/Objectives: Mobile healthcare units (MHUs) comprise flexible, ambulatory healthcare teams that deliver community care services, particularly in underserved or remote areas. In Greece, MHUs were pivotal in epidemiological surveillance during the COVID-19 pandemic and are now evolving into a sustainable and integrated service for much-needed community-based healthcare. To support this expanded role, targeted, competency-based training is essential; however, this can pose challenges, especially in coordinating synchronous learning across geographically dispersed teams and in ensuring engagement using an online format. Methods: A nationwide, online training program was developed to improve the knowledge of the personnel members of the Hellenic National Public Health Organization’s MHUs. This program was structured focusing on four core themes: (i) prevention–health promotion; (ii) provision of care; (iii) social welfare and solidarity initiatives; and (iv) digital health skill enhancement. The program was implemented by the University of Crete’s Center for Training and Lifelong Learning from 16 January to 24 February 2025. A multidisciplinary team of 64 experts delivered 250 h of live and on-demand educational content, including health screenings, vaccination protocols, biomarker monitoring, chronic disease management, treatment adherence, organ donation awareness, counseling on social violence, and eHealth applications. Knowledge acquisition was assessed through a pre- and post-training multiple-choice test related to the core themes. Trainees’ and trainers’ qualitative feedback was evaluated using a 0–10 numerical rating scale (Likert-type). Results: A total of 873 MHU members participated in the study, including both healthcare professionals and administrative staff. The attendance rate was consistently above 90% on a daily basis. The average assessment score increased from 52.8% (pre-training) to 69.8% (post-training), indicating 17% knowledge acquisition. The paired t-test analysis demonstrated that this improvement was statistically significant (t = −8.52, p < 0.001), confirming the program’s effectiveness in enhancing knowledge. As part of the evaluation of qualitative feedback, the program was positively evaluated, with 75–80% of trainees rating key components such as content, structure, and trainer effectiveness as “Very Good” or “Excellent.” In addition, using a 0–10 scale, trainers rated the program relative to organization (9.4/10), content (8.8), and trainee engagement (8.9), confirming the program’s strength and scalability in primary care education. Conclusions: This initiative highlights the effectiveness of a structured, online training program in enhancing MHU knowledge, ensuring standardized, high-quality education that supports current primary healthcare needs. Future studies evaluating whether the increase in knowledge acquisition may also result in an improvement in the personnel’s competencies, and clinical practice will further contribute to assessing whether additional training programs may be helpful. Full article

This study aimed to explore how social media usage influenced both parent and adolescent mental health and social identity during and after the COVID-19 pandemic through the theoretical foundational lens of social comparison theory. In-depth interviews with 24 mothers of adolescent children (ages 10–19) were conducted to address the research questions. Qualitative thematic analysis of the interview transcripts revealed eight emerging themes: (1) learning and entertainment, (2) maternal fears related to content binging and cyberbullying, (3) finding connection and comfort through social media during the pandemic, (4) ongoing digital care work as lasting maternal labor, (5) iterative dialogue: platform restrictions and content curation boundaries, (6) upward and downward social comparison, (7) fear of missing out (FoMO), and (8) third-person perception (TPP). The findings show that mothers perceive social media usage as either beneficial or harmful among adolescents (their children); upward and downward social comparison via social media exhibits more dynamic mechanisms. Moreover, this study enhances our theoretical understanding by linking social media usage to social identity, social comparison, and mental health during a global health crisis. Full article

Objectives: This study aims to explore the experiences of bereaved family members during and after the loss of a relative in an intensive care unit (ICU) during the COVID-19 pandemic-related visitation restrictions, as well as to assess their perceptions of a nurse-led bereavement support programme. Methods: Ten participants with a relative who had died in an ICU were recruited in September 2020 during a follow-up bereavement meeting at a tertiary cardiac centre in Switzerland. Descriptive qualitative research was conducted. Face-to-face nurse-led follow-up bereavement meetings, adapted to the pandemic circumstances and conducted as semi-structured interviews, were analysed by a thematic analysis. Findings: Fifteen sub-themes and three main categories were identified. The motivation behind the family members’ participation in the meetings was to ask and learn about their experiences regarding the death of their relative during this abnormal time. The reactions to the meetings varied among the families. Many expressed that the experience of bereavement was particularly challenging and painful, and that the absence of a final farewell to their loved one, as well as the impossibility of having a formally held funeral, made the deaths harder to accept. The families appreciated the interview as it gave them clarification, information, and an awareness of the facts and the care provided, and for several of them it was also a chance to share their emotions and express any difficulties they might have encountered both during and after the patient’s death. Conclusion: The COVID-19 pandemic’s restrictions had a profound impact on families who lost a loved one in an ICU. The nurse-led bereavement support service responded to the needs of grieving families, providing valuable emotional and practical support and re-establishing a healthy relationship between the families and the caregivers that was hindered by pandemic restrictions. The study also shows that a nurse-led bereavement support service can be a valuable component of family-centred care. Full article

COVID-19 school closures forced German high-school graduates (Abitur 2022 cohort) to prepare for their final examinations with lengthy learning times at home. Guided by transactional stress theory, we tested how personal resources—self-regulated learning (SRL) skills and academic self-efficacy—and contextual resources—perceived teacher support and teacher digital competence—jointly predicted perceived stress during exam preparation. A cross-sectional online survey (June–July 2022) yielded complete data from N = 2379 students (68% female; Mage = 18.3). Six latent constructs were measured with 23 items and showed adequate reliability (0.71 ≤ α/ω ≤ 0.89). A six-factor CFA fit the data acceptably (CFI = 0.909, RMSEA = 0.064). The structural equation model (CFI = 0.935, RMSEA = 0.064) explained 35% of the variance in stress and 23% of the variance in SRL—action. Academic self-efficacy (β = −0.31, p < 0.001), perceived support (β = −0.28, p < 0.001), teacher digital competence (β = −0.08, p < 0.001), COVID-19 learning disruptions (β = +0.13, p < 0.001), and gender (male = 0.32 SD lower stress, p < 0.001) had direct effects on stress. SRL—action’s direct path was small and non-significant (β = −0.02). Teacher digital competence also reduced stress indirectly through greater perceived support (standardized indirect β = −0.11, p < 0.001). The results highlight self-efficacy and perceived instructional support as the most potent buffers of pandemic-related stress, whereas cancelled lessons added strain. Boosting teachers’ digital pedagogical skills has a dual payoff—raising students’ sense of support and lowering their stress. Full article

The COVID-19 pandemic sparked changes globally, as leaders scrambled to protect wellbeing and safety. With many U.S. students sent away from their campuses, undergraduate students still grappled with the time-old question: “what will I do after college,” except during an unprecedented time in history rife with heightened career uncertainty. This qualitative study presents the results of a survey administered as part of a mind–body health project conducted in the wake of the pandemic, speaking directly to undergraduate college students’ health-related career aspirations. Two open-ended survey questions—(1) what is your intended career, and (2) how (if at all) has the COVID-19 pandemic changed your perspective about your future career—were administered with thematic analysis conducted. Qualitative analysis using hybrid data and theory-driven approaches revealed several themes around an increased desire to work within health-related fields, decreased desire to work in healthcare, non-medical to medical career shift, and additional undecidedness. Connecting theory to practice, Super’s Life-Space, Life-Span Career Theory and Krumboltz’s Social Learning Theory of Career Decision-Making guide practical implications and grander discussion around career development during periods of crisis. Full article

The COVID-19 pandemic significantly disrupted higher education worldwide, imposing strict isolation measures, transitioning learning online, and exacerbating existing social and economic inequalities. This literature review examines the pandemic’s impact on the mental health of college students, with a focus on those belonging to minority groups, including racial, ethnic, migrant, gender, sexuality-based, and low-income populations. While elevated levels of anxiety, depression, and loneliness were observed across all students, findings indicate that LGBTQ+ and low-income students faced the highest levels of psychological distress, due to compounded stressors such as family rejection, unsafe home environments, and financial insecurity. Racial and ethnic minority students reported increased experiences of discrimination and reduced access to culturally competent mental healthcare. International and migrant students were disproportionately affected by travel restrictions, legal uncertainties, and social disconnection. These disparities underscore the need for higher education institutions to implement targeted, inclusive mental health policies that account for the unique needs of at-risk student populations during health crises. Full article

The COVID-19 pandemic brought unprecedented challenges, particularly for older adults. They were identified as a high-risk group. While research has primarily focused on health measures, less is known about their adaptation processes during this period in the UK and Colombia. This study explores “how older adults in the UK and Colombia adapted during the health crisis after one year”. We conducted interviews with 29 participants in the UK and 32 participants in Colombia, aged 63–95, about their experiences one year after the pandemic. We analysed their anonymised transcripts using constructivist grounded theory. The pandemic highlighted older adults’ ability to learn new skills in the face of adversities. Some found new goals; others found pleasure in optimising existing skills and tasks. Some compensated for the lack of social connectivity by intensifying hobbies. We identified three broad ways older adults adapted. Cognitive adaptation included acceptance, positive reframing, and religious trust. Emotional regulation was experienced not only through deep freeze, weather impact, social support, religion, pet companionship but also emotional struggles. Finally behavioural adaptation was enacted through routine modification, use of virtual technologies, intertwined cognitive–emotional–behavioural adaptation, and previous experiences. However, adaptation varied, with some individuals struggling to adapt, highlighting that while adaptation is possible for some, it is not universal among all older adults. Full article

The global crude oil market, known for its pronounced volatility and nonlinear dynamics, plays a pivotal role in shaping economic stability and informing investment strategies. Contrary to traditional research focused on price forecasting, this study emphasizes the more investor-centric task of predicting returns for West Texas Intermediate (WTI) crude oil. By spotlighting returns, it directly addresses critical investor concerns such as asset allocation and risk management. This study applies advanced machine learning models, including XGBoost, random forest, and neural networks to predict crude oil return, and for the first time, incorporates sustainability and external risk variables, which are shown to enhance predictive performance in capturing the non-stationarity and complexity of financial time-series data. To enhance predictive accuracy, we integrate 55 variables across five dimensions: macroeconomic indicators, financial and futures markets, energy markets, momentum factors, and sustainability and external risk. Among these, the rate of change stands out as the most influential predictor. Notably, XGBoost demonstrates a superior performance, surpassing competing models with an impressive 76% accuracy in direction forecasting. The analysis highlights how the significance of various predictors shifted during the COVID-19 pandemic. This underscores the dynamic and adaptive character of crude oil markets under substantial external disruptions. In addition, by incorporating sustainability factors, the study provides deeper insights into the drivers of market behavior, supporting more informed portfolio adjustments, risk management strategies, and policy development aimed at fostering resilience and advancing sustainable energy transitions. Full article

The rapid shift to online education during the COVID-19 pandemic exacerbated mental health risks for students, particularly those experiencing multidimensional poverty—a potential contributor to psychological distress in digital learning environments. This study examines how poverty-driven techno-distress (technology-related stress) impacts university students’ mental health, focusing on 202 Chilean learners engaged in remote classes. Using partial least squares structural equation modeling (PLS-SEM), we analyzed multidimensional poverty and its association with techno-distress, measured through validated scales. The results suggest that poverty conditions are associated with 32.5% of technostress variance (R² = 0.325), while techno-distress may indirectly relate to 18.7% of students’ dissatisfaction with academic life—a proxy for emerging mental health risks. Importance–performance map analysis (IPMA) identified housing habitability (e.g., overcrowding, inadequate study spaces) and healthcare access as priority intervention targets, surpassing purely digital factors. These findings indicate that techno-distress in online education may function as a systemic stressor, potentially amplifying pre-existing inequities linked to poverty. For educators and policymakers, this highlights the urgency of early interventions addressing students’ physical environments alongside pedagogical strategies. By framing techno-distress as a public health challenge rooted in socioeconomic disparities, this work advances preventive approaches to safeguard student well-being in increasingly hybrid educational landscapes. Full article

Portfolio optimisation is a crucial decision-making task. Traditionally static, this problem is more realistically addressed as dynamic, reflecting frequent trading within financial markets. The dynamic nature of the portfolio optimisation problem makes it susceptible to rapid market changes or financial contagions, which may cause drifts in historical data. While reinforcement learning (RL) offers a framework that allows for the formulation of portfolio optimisation as a dynamic problem, existing RL approaches lack the ability to adapt to rapid market changes, such as pandemics, and fail to capture the resulting concept drift. This study introduces a recurrent proximal policy optimisation (PPO) algorithm, leveraging recurrent neural networks (RNNs), specifically the long short-term memory network (LSTM) for pattern recognition. Initial results conclusively demonstrate the recurrent PPO’s efficacy in generating quality portfolios. However, its performance declined during the COVID-19 pandemic, highlighting susceptibility to rapid market changes. To address this, an incremental recurrent PPO is developed, leveraging incremental learning to adapt to concept drift triggered by the pandemic. This enhanced algorithm not only learns from ongoing market data but also consistently identifies optimal portfolios despite significant market volatility, offering a robust tool for real-time financial decision-making. Full article

Vaccination with ChAdOx1 nCoV-19 is an important countermeasure to fight the COVID-19 pandemic. This vaccine enhances human immunoprotection against SARS-CoV-2 by inducing an immune response against the SARS-CoV-2 S protein. However, the immune-related genes induced by vaccination remain to be identified. This study employs feature ranking algorithms, an incremental feature selection method, and classification algorithms to analyze transcriptomic data from an experimental group vaccinated with the ChAdOx1 nCoV-19 vaccine and a control group vaccinated with the MenACWY meningococcal vaccine. According to different time points, vaccination status, and SARS-CoV-2 infection status, the transcriptomic data was divided into five groups, including a pre-vaccination group, ChAdOx1-onset group, MenACWY-onset group, ChAdOx1-7D group, and MenACWY-7D group. Each group contained samples with 13,383 RNA features and 1662 small RNA features. The results identified key genes that could indicate the efficacy of the ChAdOx1 nCoV-19 vaccine, and a classifier was developed to classify samples into the above groups. Additionally, effective classification rules were established to distinguish between different vaccination statuses. It was found that subjects vaccinated with ChAdOx1 nCoV-19 vaccine and infected with SARS-CoV-2 were characterized by up-regulation of HIST1H3G expression and down-regulation of CASP10 expression. In addition, IGHG1, FOXM1, and CASP10 genes were strongly associated with ChAdOx1 nCoV-19 vaccine efficacy. Compared with previous omics-driven studies, the machine learning algorithms used in this study were able to analyze transcriptome data faster and more comprehensively to identify potential markers associated with vaccine effect and investigate ChAdOx1 nCoV-19 vaccine-induced gene expression changes. These observations contribute to an understanding of the immune protection and inflammatory responses induced by the ChAdOx1 nCoV-19 vaccine during symptomatic episodes and provide a rationale for improving vaccine efficacy. Full article