Search Results (48)

Mental health disparities among those who self-identify as gay men in Peru remain a pressing public health concern, yet predictive models for early identification remain limited. This research aims to (1) develop machine learning and deep learning models to predict mental health issues in those who self-identify as gay men, and (2) evaluate the influence of demographic, economic, health-related, behavioral and social factors using interpretability techniques to enhance understanding of the factors shaping mental health outcomes. A dataset of 2186 gay men from the First Virtual Survey for LGBTIQ+ People in Peru (2017) was analyzed, considering demographic, economic, health-related, behavioral, and social factors. Several classification models were developed and compared, including Logistic Regression, Artificial Neural Networks, Random Forest, Gradient Boosting Machines, eXtreme Gradient Boosting, and a One-dimensional Convolutional Neural Network (1D-CNN). Additionally, the Shapley values and Layer-wise Relevance Propagation (LRP) heatmaps methods were used to evaluate the influence of the studied variables on the prediction of mental health issues. The results revealed that the 1D-CNN model demonstrated the strongest performance, achieving the highest classification accuracy and discrimination capability. Explainability analyses underlined prior infectious diseases diagnosis, access to medical assistance, experiences of discrimination, age, and sexual identity expression as key predictors of mental health outcomes. These findings suggest that advanced predictive techniques can provide valuable insights for identifying at-risk individuals, informing targeted interventions, and improving access to mental health care. Future research should refine these models to enhance predictive accuracy, broaden applicability, and support the integration of artificial intelligence into public health strategies aimed at addressing the mental health needs of this population. Full article

The ongoing global population growth and the corresponding rise in energy demand have contributed to increased greenhouse gas (GHG) emissions. The integration of alternative, locally sourced energy solutions such as biogas presents a promising strategy to partially offset conventional energy consumption. In this context, countries like Colombia—characterized by a high availability of organic waste such as palm oil mill effluent (POME), rice straw, and pig manure—have the potential to harness these residues for biogas production. This study integrates experimental assays of anaerobic co-digestion tests with the spatial analysis of substrate distribution through GIS tools, enabling the identification of optimal regions for biogas production. Methane yields reached 412 mL CH₄/g VS, comparable or superior to those reported in similar studies. In addition to laboratory assays, Geographic Information System (GIS) tools were used to generate a weighted heatmap index based on feedstock availability (POME, rice straw, pig manure) across 40 municipalities in Colombia. This integrated approach supports decentralized renewable energy planning and helps identify optimal locations for biogas plant development. Full article

Background: Greece is among the fastest-aging countries globally, with one of the highest proportions of elderly individuals. As a result, the prevalence of mild cognitive impairment (MCI) and dementia is among the highest in Europe. The distribution of affected individuals varies considerably across different regions of the country. Method: We estimated the number of people living with MCI or dementia in Greece and visualized these estimates using heatmaps by regions for four census years: 1991, 2001, 2011, and 2023 (the 2023 census was delayed due to the COVID-19 pandemic). Age- and sex-specific prevalence rates of MCI and dementia were obtained from the Hellenic Longitudinal Investigation of Aging and Diet. These prevalence rates were then applied to population data from each census to estimate the number of affected individuals per region. Results: There was a consistent increase in the number of people living with MCI, rising from 177,898 in 1991 to 311,189 in 2023. Dementia cases increased from 103,535 in 1991 to 206,939 in 2023. Projections based on future census data for 2035 and 2050 suggest that the number of people with MCI will reach 375,000 and 440,000, respectively, while dementia cases will increase to 250,000 in 2035 and 310,000 in 2050. Conclusion: Given that each person with dementia typically requires care from at least two caregivers over time, these projections highlight the profound impact the dementia epidemic will have on Greece. The heatmaps developed in this study can serve as valuable tools for policymakers in designing and implementing clinical care programs tailored to the needs of each region based on the projected burden of disease. Full article

Global warming has intensified the frequency and intensity of heatwaves, particularly in urban areas, significantly affecting residents’ daily activities. Extant studies have mainly concentrated on the relationship between socio-economic attributes and the impacts of heatwaves on urban populations. However, the relationship between the built environment and the impacts of heatwaves on urban population distribution has not received much attention. Furthermore, most studies have overlooked the temporal heterogeneity in heatwave impacts on population activities and distribution. Therefore, taking the central urban area of Nanchang as the case, this study investigated the impacts of heatwaves on population distribution and their temporal heterogeneity. Moreover, it identified the nonlinear relationships between built environment factors and population changes during heatwaves by using the XGBoost model and SHAP method. The results revealed that heatwaves exerted the largest impacts on population distribution during weekend nights, followed by weekend daytime and weekday nighttime, with the least impacts observed during weekday daytime. Furthermore, location and transportation factors significantly affected population changes during heatwaves across most time periods, with their influences being associated with policy factors such as the high-temperature leave policy for workers in industrial zones located in urban fringe areas and the cooling zone establishment policy for citizens in subway stations. Moreover, land use and building form factors exhibited significant temporal heterogeneity in their impacts on population changes during heatwaves. This temporal heterogeneity was fundamentally driven by individuals’ heat adaptation behaviors, the spatiotemporal patterns of their daily activities, and the diurnal variations in the built environment’s influence on local thermal environment. These findings provide valuable insights to proactively alleviate the adverse impacts of heatwaves. Full article

Accurate identification of urban agglomeration spatial range is essential for scientific regional planning, optimal resource allocation, and sustainable development, forming the basis for regional development policy. To improve the accuracy of identifying urban agglomeration boundaries, this study fuses nighttime light data, which reflects urban economic levels, with LandScan data representing population distribution and heatmap data indicating population mobility. This fusion allows for identification from a differentiated perspective of population distribution and mobility. We propose a new method for identifying the dynamic boundaries of urban agglomerations through multi-source data fusion. This method not only provides technical support for scientific regional planning but also effectively guides the functional positioning of edge cities and the optimization of resource allocation. The results show that the spatial range identified by NTL_LS has an accuracy of 80.37% and a kappa coefficient of 0.5225, while NTL_HM achieves an accuracy of 89.17% with a kappa coefficient of 0.7342, indicating that the fusion of economic level with population mobility data more accurately reflects the spatial range of urban agglomerations in line with real development patterns. By adopting a differentiated perspective on population distribution and mobility, we propose a new approach to identifying urban agglomeration spatial range. The research results based on this method provide more comprehensive and dynamic decision-making support for optimizing transportation layouts, allocating public resources rationally, and defining the functional positioning of edge cities. Full article

(1) Background: Human–wildlife conflict can lead to adverse consequences for both parties, particularly in areas with a high concentration of wild ungulates. Ungulates cause frequent, severe plant damage by stripping the bark or browsing on the youngest plants. In the latter case, they damage vegetative sprouts and leaves, which can cause a delay in growth or the plant’s death. Tuscany is notable for its significant population of wild boar, which cause substantial damage to vineyards and cereal crops, costing farmers millions annually. In Tuscany, given the highly cultivated landscape of olive trees, damage has also been recorded in these plants. Balancing human and wildlife needs is crucial for minimizing damage and ensuring coexistence. (2) Methods: This study tested innovative electronic playback devices using long-range radio technology (LoRa) to deter wild ungulates and prevent crop damage. These devices use sounds and lights to induce wild animals to be afraid and thus run away from the cultivated plot to be protected. The experiment was conducted on a farm in Chianti, Tuscany, involving four plots of land planted with olive trees: in two test areas, four playback devices and four camera traps were installed, and in the two control areas, only camera traps were installed. Playback devices aimed to deter wild ungulates and camera traps aimed to test their effectiveness. Data from the camera traps were analyzed statistically and behaviorally. (3) Results: Playback devices significantly reduced wild animal activity in the equipped areas. Statistical analysis revealed that the use of acoustic–luminous deterrent devices (PDs) significantly reduced wildlife visits to the olive groves. (4) Conclusion: The study’s findings, supported by heatmaps and frequency analyses, provide insights into wildlife activity patterns and guide the development of targeted, effective wildlife management strategies. Full article

Background: Diabetes is a metabolic disorder characterized by increased blood sugar levels. Early detection of diabetes could help individuals to manage and delay the progression of this disorder effectively. Machine learning (ML) methods are important in forecasting the progression and diagnosis of different medical problems with better accuracy. Although they cannot substitute the work of physicians in the prediction and diagnosis of disease, they can be of great help in identifying hidden patterns based on the results and outcome of disease. Methods: In this research, we retrieved the PIMA dataset from the Kaggle repository, the retrieved dataset was further processed for applied PCA, heatmap, and scatter plot for exploratory data analysis (EDA), which helps to find out the relationship between various features in the dataset using visual representation. Four different ML algorithms Random Forest (RF), Decision Tree (DT), Naïve Bayes (NB), and Logistic regression (LR) were implemented on Rattle using Python for the prediction of diabetes among the female population. Results: Results of our study showed that RF performs better in terms of accuracy of 80%, precision of 82%, error rate of 20%, and sensitivity of 88% as compared to other developed models DT, NB, and LR. Conclusions: Diabetes is a common problem prevailing across the globe, ML-based prediction models can help in the prediction of diabetes much earlier before the worsening of the condition. Full article

Background: Trace elements (TEs) are essential nutrients for the human body and have a significant impact on fertility and hormone levels in women of reproductive age, underscoring the importance of understanding sociodemographic variations in their concentrations within this population. Objective: To investigate the socio-demographic factors influencing blood concentrations of four essential TEs, including iron, zinc, copper, and selenium among women of reproductive age. Methods: A cross-sectional analysis of women aged 20–44 years was performed using the National Health and Nutrition Examination Survey, 1999–2018. Serum iron data were analyzed for 9211 women across 10 cycles, while serum copper, zinc, and selenium data were available for 1027 women across 3 cycles. Generalized linear and logistic regressions examined the individual associations of socio-demographic factors, including age, race and ethnicity, education, and poverty index ratio, with iron, zinc, copper, and selenium concentrations treated as continuous and categorical outcomes, respectively. A qualitative heatmap explored the joint associations between the socio-demographic factors and the four essential TEs. Results: Reduced iron concentrations and increased risks of insufficiency occurred in older, Black, low-education, or low-income women. Black women were more likely to have lower zinc and selenium concentrations and an increased risk of zinc insufficiency but higher copper concentrations. The qualitative heatmap found that older, Black, low-education, and low-income women generally had lower concentrations of the four TEs, particularly iron (β = −0.10; p < 0.01). Conclusions: Socially disadvantaged women are more likely to present with lower TE concentrations, and these specific population groups should be targeted by replenishment planning by public health initiatives. Full article

Hydrogen is becoming recognized as a clean and sustainable energy carrier, with microbial fermentation and electrolysis serving critical roles in its production. This paper provides a thorough meta-analysis of BioH₂ production across diverse substrates, microbial populations, and experimental settings. Statistical techniques, including ANOVA, principal component analysis (PCA), and heatmaps, were used to evaluate the influence of various parameters on the hydrogen yield. The mean hydrogen generation from the reviewed studies was 168.57 ± 52.09 mL H₂/g substrate, with food waste and glucose demonstrating considerably greater hydrogen production than mixed food waste (p < 0.05). The inhibition of methanogens with inhibitors like 2-bromoethanesulfonate (BES) and chloramphenicol (CES) enhanced hydrogen production by as much as 25%, as demonstrated in microbial electrolysis cell systems. PCA results highlighted Clostridium spp., Thermotoga spp., and Desulfovibrio spp. as the most dominant microbial species, with Clostridium spp. contributing up to 80% of the YH₂ in fermentation systems. The study highlights synergistic interactions between dominant and less dominant microbial species under optimized environmental conditions (pH 5.5–6.0, 65 °C), emphasizing their complementary roles in enhancing H₂ production. Volatile fatty acid regulation, particularly acetate and butyrate accumulation, correlated positively with hydrogen production (r = 0.75, p < 0.01). These findings provide insights into optimizing biohydrogen systems through microbial consortia management and substrate selection, offering a potential way for scalable and efficient H₂ production. Full article

Background/Objectives: Essential oils (EOs) have been exploited by humans for centuries, but many sources remain poorly investigated, mainly due to the low yields associated with conventional extraction. Recently, new techniques have been developed, like solvent-free microwave extraction (SFME), able to enhance efficiency and sustainability. The use of Papaver rhoeas L. in traditional medicine has led researchers to investigate non-volatile fractions, but there are little data available on EOs. Methods: In the present work, we prepared EOs from the petals and leaves of P. rhoeas by SFME. GC/MS analysis of EOs revealed the presence of 106 compounds belonging to 13 different classes. Isomers of the different alkenes were identified thanks to an alkylthiolation reaction. Results: The results highlighted a predominance of saturated and unsaturated hydrocarbons, alcohols, and esters that might suggest a specific relationship with pollinators. Each population has been compared using PCA, heatmap, and barplot tools, highlighting differences in terms of composition by both comparing leaves and flowers and hill and lowland samples. Furthermore, cantharidin, a metabolite usually produced by insects, was detected in the flowers, possible present for attractiveness purposes. Conclusions: These results could contribute to ensuring a better understanding of the pollination process and of the biological activities of EOs from P. rhoeas. Full article

Wheat breeding programs are currently focusing on using non-destructive and cost-effective hyperspectral sensing tools to expeditiously and accurately phenotype large collections of genotypes. This approach is expected to accelerate the development of the abiotic stress tolerance of genotypes in breeding programs. This study aimed to assess salt tolerance in wheat genotypes using non-destructive canopy spectral reflectance measurements as an alternative to direct laborious and time-consuming phenological selection criteria. Eight wheat genotypes and sixteen F₈ RILs were tested under 150 mM NaCl in real field conditions for two years. Fourteen spectral reflectance indices (SRIs) were calculated from the spectral data, including vegetation SRIs and water SRIs. The effectiveness of these indices in assessing salt tolerance was compared with four morpho-physiological traits using genetic parameters, SSR markers, the Mantel test, hierarchical clustering heatmaps, stepwise multiple linear regression, and principal component analysis (PCA). The results showed significant differences (p ≤ 0.001) among RILs/cultivars for both traits and SRIs. The heritability, genetic gain, and genotypic and phenotypic coefficients of variability for most SRIs were comparable to those of measured traits. The SRIs effectively differentiated between salt-tolerant and sensitive genotypes and exhibited strong correlations with SSR markers (R² = 0.56–0.89), similar to the measured traits and allelic data of 34 SSRs. A strong correlation (r = 0.27, p < 0.0001) was found between the similarity coefficients of SRIs and SSR data, which was higher than that between measured traits and SSR data (r = 0.20, p < 0.0003) based on the Mantel test. The PCA indicated that all vegetation SRIs and most water SRIs were grouped with measured traits in a positive direction and effectively identified the salt-tolerant RILs/cultivars. The PLSR models, which were based on all SRIs, accurately and robustly estimated the various morpho-physiological traits compared to using individual SRIs. The study suggests that various SRIs can be integrated with PLSR in wheat breeding programs as a cost-effective and non-destructive tool for phenotyping and screening large wheat populations for salt tolerance in a short time frame. This approach can replace the need for traditional morpho-physiological traits and accelerate the development of salt-tolerant wheat genotypes. Full article

The main objective of this study was to explore the dietary behaviors of parents and their adult children, focusing on patterns, potential intrinsic and extrinsic predictors of body mass, and determinants of becoming overweight. Non-probability, cross-sectional sampling was used to select participants from a university student population. Young adults (19–21 years of age, n = 144) and their parents were examined. The data of those family pairs with complete sets of results were used. Dietary patterns and physical activity were assessed with questionnaires (QEB and IPAQ), and body height, weight measurements, and body mass indexes were calculated. A cophylogenetic approach with tanglegrams and heatmaps was used to study patterns, while predictors of body mass index were identified using multiple linear regression, stepwise logistic regression, and mediation analysis procedures. Cophenetic statistics confirmed significant incongruence between fathers and sons, confirmed by Baker’s Gamma correlation (r_BG = 0.23, p = 0.021), and mothers and daughters (r_BG = 0.26, p = 0.030). The relationships between the dietary patterns of the fathers and daughters, as well as mothers and sons, were of medium strength (r_BG = 0.33, p = 0.032, r_BG = 0.43, p = 0.031; respectively). Most of the patterns were mixed. Fast food, fried meals, alcoholic drinks, energy drinks, and sweetened beverages were associated significantly with being overweight. Significant intrinsic predictors of excessive weight in young adults were sex (b = 2.31, p < 0.001), PA (b = −0.02, p < 0.001), and eating fermented milk and curd cheese (b = −0.55, p = 0.024), while extrinsic (parental) predictors included eating fast food and fried meals (b = −0.44, p = 0.049). Both physical activity and dietary behaviors independently determined the sons’ overweight status (b = −1.25, p = 0.008; b = −0.04, p < 0.001; respectively); while only PA did in daughters (b = −0.04, p < 0.001). No mediating effects of physical activity were observed. Adult children and parental dietary patterns were divergent, reflecting the influence of multiple factors on a child’s dietary habits. However, this divergence is moderated by sex. Reciprocal interactions between dietary intake—particularly positive dyads such as fruits and vegetables, fermented milk, and curd cheese—and physical activity significantly impacted children’s body mass index (BMI). The study of dietary patterns in conjunction with physical activity (both as independent determinants), particularly in relation to the link between overweight/obese children and overweight/obese parents, presents a separate challenge. Full article

Levodropropizine is a non-narcotic, non-centrally acting antitussive that inhibits the cough reflex triggered by neuropeptides. Despite the active clinical application of levodropropizine, the exploration of its inter-individual pharmacokinetic diversity and of factors that can interpret it is lacking. The purpose of this study was to explore effective covariates associated with variation in the pharmacokinetics of levodropropizine within the population and to perform an interpretation of covariate correlations from a therapeutic perspective. The results of a levodropropizine clinical trial conducted on 40 healthy Korean men were used in this pharmacokinetic analysis, and the calculated pharmacokinetic and physiochemical parameters were screened for effective correlations between factors through heatmap and linear regression analysis. Along with basic compartmental modeling, a correlation analysis was performed between the model-estimated parameter values and the discovered effective candidate covariates for levodropropizine, and the degree of toxicity and safety during the clinical trial of levodropropizine was quantitatively monitored, targeting the hepatotoxicity screening panel. As a result, eosinophil level and body surface area (BSA) were explored as significant (p-value < 0.05) physiochemical parameters associated with the pharmacokinetic diversity of levodropropizine. Specifically, it was confirmed that as eosinophil level and BSA increased, levodropropizine plasma exposure increased and decreased, respectively. Interestingly, changes in an individual’s plasma exposure to levodropropizine depending on eosinophil levels could be interpreted as a therapeutic advantage based on pharmacokinetic benefits linked to the clinical indications for levodropropizine. This study presents effective candidate covariates that can explain the inter-individual pharmacokinetic variability of levodropropizine and provides a useful perspective on the first-line choice of levodropropizine in the treatment of inflammatory respiratory diseases. Full article

Ensuring food security has become of paramount importance due to the rising global population. In particular, the agriculture sector in South Korea faces several challenges such as an aging farming population and a decline in the labor force. These issues have led to the recognition of smart farms as a potential solution. In South Korea, the smart farm is divided into three generations. The first generation primarily concentrates on monitoring and controlling precise cultivation environments by leveraging information and communication technologies (ICT). This is aimed at enhancing convenience for farmers. Moving on to the second generation, it takes advantage of big data and artificial intelligence (AI) to achieve improved productivity. This is achieved through precise cultivation management and automated control of various farming processes. The most advanced level is the 3rd generation, which represents an intelligent robotic farm. In this stage, the entire farming process is autonomously managed without the need for human intervention. This is made possible through energy management systems and the use of robots for various farm operations. However, in the current Korean context, the adoption of smart farms is primarily limited to the first generation, resulting in the limited utilization of advanced technologies such as AI, big data, and cloud computing. Therefore, this research aims to develop the second generation of smart farms within the first generation smart farm environment. To accomplish this, data was collected from nine sensors spanning the period between 20 June to 30 September. Following that, we conducted kernel density estimation analysis, data analysis, and correlation heatmap analysis based on the collected data. Subsequently, we utilized LSTM, BI-LSTM, and GRU as base models to construct a stacking ensemble model. To assess the performance of the proposed model based on the analyzed results, we utilized LSTM, BI-LSTM, and GRU as the existing models. As a result, the stacking ensemble model outperformed LSTM, BI-LSTM, and GRU in all performance metrics for predicting one of the sensor data variables, air temperature. However, this study collected nine sensor data over a relatively short period of three months. Therefore, there is a limitation in terms of considering the long-term data collection and analysis that accounts for the unique seasonal characteristics of Korea. Additionally, the challenge of including various environmental factors influencing crops beyond the nine sensors and conducting experiments in diverse cultivation environments with different crops for model generalization remains. In the future, we plan to address these limitations by extending the data collection period, acquiring diverse additional sensor data, and conducting further research that considers various environmental variables. Full article

Fractures affect nearly 9.45% of the South Korean population, with radiography being the primary diagnostic tool. This research employs a machine-learning methodology that integrates HyperColumn techniques with the convolutional block attention module (CBAM) to enhance fracture detection in X-ray radiographs. Utilizing the EfficientNet-B0 and DenseNet169 models bolstered by the HyperColumn and the CBAM, distinct improvements in fracture site prediction emerge. Significantly, when HyperColumn and CBAM integration is applied, both DenseNet169 and EfficientNet-B0 showed noteworthy accuracy improvements, with increases of approximately 0.69% and 0.70%, respectively. The HyperColumn-CBAM-DenseNet169 model particularly stood out, registering an uplift in the AUC score from 0.8778 to 0.9145. The incorporation of Grad-CAM technology refined the heatmap’s focus, achieving alignment with expert-recognized fracture sites and alleviating the deep-learning challenge of heavy reliance on bounding box annotations. This innovative approach signifies potential strides in streamlining training processes and augmenting diagnostic precision in fracture detection. Full article