Which Risk Factors Matter More for Psychological Distress during the COVID-19 Pandemic? An Application Approach of Gradient Boosting Decision Trees

Women's mental health and COVID-19: increased vulnerability and inequalities

Introduction

The impact of COVID-19 on mental health has become a relevant object of research. Studies have demonstrated that women have experienced greater mental health challenges, highlighting the importance of public health systems to address women's specific needs.

Methods

This literature review explores the effects of the coronavirus pandemic on psychological distress among women, aiming to provide a comprehensive understanding of the subject and to explore how these research findings can guide public mental health care responses in crisis settings. A total of 131 studies were analyzed and four dimensions were discussed: study characteristics, factors impacting women's mental health in the pandemic setting, particularities of pregnancy and the postpartum period, and proposed interventions. Most studies exclusively addressed populations of adult women, predominantly during pregnancy and the postpartum period.

Results

Anxiety, depression, and stress were the most common outcomes. Lower education and income, preexisting mental health problems, and living alone or with children were risk factors for higher levels of anxiety and depression.

Discussion

A comprehensive care approach supported by public health policies and focused on intersectional factors, including race, socioeconomic status, and access to resources, is necessary to improve women's mental health care response in future crises.

Examining the importance of neighborhood natural, and built environment factors in predicting older adults' mental well-being: An XGBoost-SHAP approach

BACKGROUND

Previous studies have shown that urban neighborhood environmental factors significantly influence the health outcomes of urban older adults. However, most cross-sectional studies exploring the health effects of these factors have failed to quantify the relative importance of each factor.

METHODS

We use XGBoost machine learning techniques and SHAPley Additive Interpretation (SHAP) to rank the importance of urban neighborhood environmental factors in shaping the mental health of urban older adults. To address self-selection bias in housing choice, we distinguish older adults living in private housing from those living in public as residents in private housing have more freedom to choose where to live.

RESULTS

The results show that both natural and built environmental factors in urban neighborhoods are important predictors of mental well-being scores. Five natural environmental factors (blue space, perceived greenery quantity, NDVI, street view greenness, aesthetic quality) and three built environmental factors (physical activity facilities quality, physical activity facilities quantity, neighborhood disorder) had considerable predictive power for mental well-being scores in two groups. Among them, blue space, perceived greenery quantity and street view greenness quantity became less important after controlling for self-selection bias, possibly because of the unequal distribution of quantity and quality, and the performance of neighborhood disorder, aesthetic quality and physical activity facilities quality was more sensitive in public housing.

CONCLUSIONS

These results highlight the nuanced and differential effects of neighborhood environmental exposures on mental well-being outcomes, depending on housing preferences. The results of this study can provide support for decision makers in urban planning, landscape design and environmental management in order to improve the mental well-being status of urban older adults.

Predicting distant metastasis in nasopharyngeal carcinoma using gradient boosting tree model based on detailed magnetic resonance imaging reports

BACKGROUND

Development of distant metastasis (DM) is a major concern during treatment of nasopharyngeal carcinoma (NPC). However, studies have demonstrated improved distant control and survival in patients with advanced NPC with the addition of chemotherapy to concomitant chemoradiotherapy. Therefore, precise prediction of metastasis in patients with NPC is crucial.

AIM

To develop a predictive model for metastasis in NPC using detailed magnetic resonance imaging (MRI) reports.

METHODS

This retrospective study included 792 patients with non-distant metastatic NPC. A total of 469 imaging variables were obtained from detailed MRI reports. Data were stratified and randomly split into training (50%) and testing sets. Gradient boosting tree (GBT) models were built and used to select variables for predicting DM. A full model comprising all variables and a reduced model with the top-five variables were built. Model performance was assessed by area under the curve (AUC).

RESULTS

Among the 792 patients, 94 developed DM during follow-up. The number of metastatic cervical nodes (30.9%), tumor invasion in the posterior half of the nasal cavity (9.7%), two sides of the pharyngeal recess (6.2%), tubal torus (3.3%), and single side of the parapharyngeal space (2.7%) were the top-five contributors for predicting DM, based on their relative importance in GBT models. The testing AUC of the full model was 0.75 (95% confidence interval [CI]: 0.69-0.82). The testing AUC of the reduced model was 0.75 (95%CI: 0.68-0.82). For the whole dataset, the full (AUC = 0.76, 95%CI: 0.72-0.82) and reduced models (AUC = 0.76, 95%CI: 0.71-0.81) outperformed the tumor node-staging system (AUC = 0.67, 95%CI: 0.61-0.73).

CONCLUSION

The GBT model outperformed the tumor node-staging system in predicting metastasis in NPC. The number of metastatic cervical nodes was identified as the principal contributing variable.

Nature exposure and mental health during the COVID-19 pandemic: A Navigation Guide systematic review with meta-analysis

Prior reviews have highlighted that nature exposure was a valuable coping strategy enhancing mental health during the COVID-19 pandemic. However, no existing reviews have determined the quality of evidence and risk of bias of the empirical studies supporting this claim. To address this gap, we employed a Navigation Guide systematic review and meta-analysis approach to investigate associations between nature exposure and mental health during the pandemic. Searches in PubMed, Web of Science, Scopus, CINAHL, and PsycInfo retrieved relevant articles published between January 1, 2020, and March 4, 2024. We used the Navigation Guide methodology to assess the risk of bias and Grading of Recommendations, Assessment, Development, and Evaluations (GRADE) assessments to evaluate the overall quality of evidence. Our search retrieved 113 studies that met the inclusion criteria and reported diverse types of exposure, including nature availability, nature visit frequency, green space accessibility, and green space type, alongside associations with 12 mental health outcomes. Meta-analyses found access to gardens was associated with lower odds of depression [(Pooled odds ratio [OR] = 0.71, 95%CI = 0.61, 0.82), I2 = 0%, n = 3] and anxiety [(Pooled OR = 0.73, 95%CI = 0.63, 0.84), I2 = 0%, n = 3]. Increased time in green spaces was associated with lower level of stress [(Pooled Corr = -0.11, 95%CI = -0.17, -0.05), I2 = 0%, n = 2]. Higher frequency of visits to nature was associated with improved mental well-being [(Pooled standardized beta = 0.10, 95%CI = 0.07, 0.14), I2 = 0%, n = 2] and general mental health [(Pooled standardized beta = 0.11, 95%CI = 0.03-0.38), I2 = 82%, n = 2]. However, the number of pooled studies was small and the overall quality of evidence was "very low" for all outcomes, and high levels of bias were observed (26% of studies had high, 71% probably high). Nonetheless, given the trends in the results, nature-based solutions emphasizing exposure to gardens and green spaces near the home may have promoted psychological resilience during this public health crisis.

Natural environments, psychosocial health, and health behaviors in a crisis - A scoping review of the literature in the COVID-19 context

The COVID-19 outbreak led to major restrictions globally, affecting people's psychosocial health and their health behaviors. Thus, the purpose of this scoping review was to summarize the available research regarding nature and health in the COVID-19 context. Keywords relating to natural environments and COVID-19 were combined to conduct a systematic online search in six major databases. Eligibility criteria were a) published since 2020 with data collected in the COVID-19 context b) peer-reviewed, c) original empirical data collected on human participants, d) investigated the association between natural environments and psychosocial health or health behaviors, and e) English, German, or Scandinavian languages. Out of 9126 articles being screened, we identified 188 relevant articles, representing 187 distinct studies. Most research focused on adults in the general population and was predominantly conducted in the USA, Europe, and China. Overall, the findings indicate that nature may mitigate the impact of COVID-19 on psychological health and physical activity. Through a systematic thematic analysis of the extracted data, three primary themes were identified: 1) type of nature assessed, 2) psychosocial health and health behaviors investigated, and 3) heterogeneity in the nature-health relationship. Research gaps in the COVID-19 context were identified regarding I) nature characteristics that promote psychosocial health and health behaviors, II) investigations of digital and virtual nature, III) psychological constructs relating to mental health promotion, IV) health-promoting behaviors other than physical activity, V) underlying mechanisms regarding heterogeneity in the nature-health relationship based on human, nature, and geographic characteristics, and VI) research focusing on vulnerable groups. Overall, natural environments demonstrate considerable potential in buffering the impact of stressful events on a population level on mental health. However, future research is warranted to fill the mentioned research gaps and to examine the long-term effects of nature exposure during COVID-19.

Lifestyle, Demographic and Socio-Economic Determinants of Mental Health Disorders of Employees in the European Countries

Ensuring the health and well-being of workers should be a top priority for employers and governments. The aim of the article is to evaluate and rank the importance of mental health determinants: lifestyle, demographic factors and socio-economic status. The research study is based on EHIS 2013-2015 data for a sample of N = 140,791 employees from 30 European countries. The results obtained using machine learning techniques such as gradient-boosted trees and SHAPley values show that the mental health of European employees is strongly determined by the BMI, age and social support from close people. The next vital features are alcohol consumption, an unmet need for health care and sports activity, followed by the affordability of medicine or treatment, income and occupation. The wide range of variables clearly indicates that there is an important role for governments to play in order to minimize the risk of mental disorders across various socio-economic groups. It is also a signal for businesses to help boost the mental health of their employees by creating holistic, mentally friendly working conditions, such as offering time-management training, implementing morning briefings, offering quiet areas, making employees feel valued, educating them about depression and burnout symptoms, and promoting a healthy lifestyle.

Prediction of Mental Health Problem Using Annual Student Health Survey: A Machine Learning Approach (Preprint)

BACKGROUND

One of the reasons why students go to counseling is being called on based on self-reported health survey results. However, there is no concordant standard for such calls.

OBJECTIVE

This study aims to develop a machine learning (ML) model to predict students' mental health problems in 1 year and the following year using the health survey's content and answering time (response time, response time stamp, and answer date).

METHODS

Data were obtained from the responses of 3561 (62.58%) of 5690 undergraduate students from University A in Japan (a national university) who completed the health survey in 2020 and 2021. We performed 2 analyses; in analysis 1, a mental health problem in 2020 was predicted from demographics, answers for the health survey, and answering time in the same year, and in analysis 2, a mental health problem in 2021 was predicted from the same input variables as in analysis 1. We compared the results from different ML models, such as logistic regression, elastic net, random forest, XGBoost, and LightGBM. The results with and without answering time conditions were compared using the adopted model.

RESULTS

On the basis of the comparison of the models, we adopted the LightGBM model. In this model, both analyses and conditions achieved adequate performance (eg, Matthews correlation coefficient [MCC] of with answering time condition in analysis 1 was 0.970 and MCC of without answering time condition in analysis 1 was 0.976; MCC of with answering time condition in analysis 2 was 0.986 and that of without answering time condition in analysis 2 was 0.971). In both analyses and in both conditions, the response to the questions about campus life (eg, anxiety and future) had the highest impact (Gain 0.131-0.216; Shapley additive explanations 0.018-0.028). Shapley additive explanations of 5 to 6 input variables from questions about campus life were included in the top 10. In contrast to our expectation, the inclusion of answering time-related variables did not exhibit substantial improvement in the prediction of students' mental health problems. However, certain variables generated based on the answering time are apparently helpful in improving the prediction and affecting the prediction probability.

CONCLUSIONS

These results demonstrate the possibility of predicting mental health across years using health survey data. Demographic and behavioral data, including answering time, were effective as well as self-rating items. This model demonstrates the possibility of synergistically using the characteristics of health surveys and advantages of ML. These findings can improve health survey items and calling criteria.

The Promotion and Optimization of Bank Financial Products Using Consumers’ Psychological Perception

With the rapid economic growth and increased national income year by year, individuals and families have an increasingly greater demand for financial products. Banks’ sales of financial products have become a new economic profit growth point for major banks. Based on consumers’ psychological perception, the influencing factors of consumers’ behavior in purchasing bank financial products are studied. The influencing factor model path of consumer purchase behavior is constructed to find out the factors affecting consumers’ purchase of bank financial products and formulate appropriate promotion strategies according to the influencing factors. Through the research methods of literature analysis, small-scale in-depth interview, questionnaire surveys, and statistical analysis, this exploration selects four variables: independent variable, mediator, control variable, and dependent variable. They are influencing factors of purchasing bank financial products (perceived convenience, risk value of bank financial products, satisfaction of purchasing communication process), consumers’ willingness to buy bank financial products, consumers’ personal characteristics and consumers’ behavior of purchasing bank financial products. Meanwhile, based on 196 valid questionnaires, regression analysis is carried out through a regression model. The results show that the three influencing factors of consumers’ purchase of bank financial products–perceived convenience, risk value of bank financial products, and satisfaction with the purchase communication process significantly impact consumers’ purchase of bank financial products. They can put forward specific promotion suggestions for banks. This exploration aims to study the optimization of bank financial product promotion strategy from the perspective of consumer psychological perception to provide a reference for subsequent related research.

The Interplay between Housing Environmental Attributes and Design Exposures and Psychoneuroimmunology Profile-An Exploratory Review and Analysis Paper in the Cancer Survivors' Mental Health Morbidity Context

Adult cancer survivors have an increased prevalence of mental health comorbidities and other adverse late-effects interdependent with mental illness outcomes compared with the general population. Coronavirus Disease 2019 (COVID-19) heralds an era of renewed call for actions to identify sustainable modalities to facilitate the constructs of cancer survivorship care and health care delivery through physiological supportive domestic spaces. Building on the concept of therapeutic architecture, psychoneuroimmunology (PNI) indicators-with the central role in low-grade systemic inflammation-are associated with major psychiatric disorders and late effects of post-cancer treatment. Immune disturbances might mediate the effects of environmental determinants on behaviour and mental disorders. Whilst attention is paid to the non-objective measurements for examining the home environmental domains and mental health outcomes, little is gathered about the multidimensional effects on physiological responses. This exploratory review presents a first analysis of how addressing the PNI outcomes serves as a catalyst for therapeutic housing research. We argue the crucial component of housing in supporting the sustainable primary care and public health-based cancer survivorship care model, particularly in the psychopathology context. Ultimately, we illustrate a series of interventions aiming at how housing environmental attributes can trigger PNI profile changes and discuss the potential implications in the non-pharmacological treatment of cancer survivors and patients with mental morbidities.