The shift in the spatiotemporal relationship between supply and demand of ecosystem services and its drivers in China.

In China, over 65% of human activities are concentrated in cities, resulting in a conflict between the supply and demand of ecosystem services (ESs). To alleviate this problem, many cities have adopted eco-friendly development modes, however, the effectiveness of these models in reducing ESs supply-demand conflicts has not been comprehensively reviewed, and the human and natural drivers behind these relationship shifts remain unclear. To bridge this gap, this study analyzed the shifts in the relationships between supply and demand of ESs across China from 2010 to 2020 at a city level, as well as identified the human and natural drivers behind them. Firstly, the InVEST models were integrated with socioeconomic data to evaluate the supply and demand distribution for three pivotal ESs: water yield (WY), habitat quality (HQ), and soil retention (SR). Then, a four-quadrant diagram approach was proposed to enhance the analysis of their spatiotemporal relationships. Furthermore, random forest models were employed to examine the drivers of the shifts in these relationships. The results showed that WY and SR services witnessed growth until 2015, and then receded, while HQ saw a modest decline from 2010 to 2020. Spatial synergies in the supply and demand of ESs were primarily observed in the southern cities, with a significant northward extension by 2020. From a temporal perspective, the percentage of cities achieving coordination in WY and SR services increased from 32.6% to 57.3%, respectively, in the 2010-2015 period to 42.4% and 63.3% between 2015 and 2020, meanwhile, HQ service conflicts diminished from 58.7% to 53.5%. The changes in socioeconomic and land use factors contributed to 64.3%, 36.1%, and 33.3% of the shifts in the supply-demand relationship for HQ, WY, and SR services, respectively. Our analysis highlights the potential of human-driven ecological management to enhance the balance of this relationship. It can support the design of city-specific policies that foster a balance between ecological processes and socio-economic development.

Forecasting and mapping dengue fever epidemics in China: a spatiotemporal analysis.

BACKGROUND: Dengue fever (DF) has emerged as a significant public health concern in China. The spatiotemporal patterns and underlying influencing its spread, however, remain elusive. This study aims to identify the factors driving these variations and to assess the city-level risk of DF epidemics in China. METHODS: We analyzed the frequency, intensity, and distribution of DF cases in China from 2003 to 2022 and evaluated 11 natural and socioeconomic factors as potential drivers. Using the random forest (RF) model, we assessed the contributions of these factors to local DF epidemics and predicted the corresponding city-level risk. RESULTS: Between 2003 and 2022, there was a notable correlation between local and imported DF epidemics in case numbers (r = 0.41, P < 0.01) and affected cities (r = 0.79, P < 0.01). With the increase in the frequency and intensity of imported epidemics, local epidemics have become more severe. Their occurrence has increased from five to eight months per year, with case numbers spanning from 14 to 6641 per month. The spatial distribution of city-level DF epidemics aligns with the geographical divisions defined by the Huhuanyong Line (Hu Line) and Qin Mountain-Huai River Line (Q-H Line) and matched well with the city-level time windows for either mosquito vector activity (83.59%) or DF transmission (95.74%). The RF models achieved a high performance (AUC = 0.92) when considering the time windows. Importantly, they identified imported cases as the primary influencing factor, contributing significantly (24.82%) to local DF epidemics at the city level in the eastern region of the Hu Line (E-H region). Moreover, imported cases were found to have a linear promoting impact on local epidemics, while five climatic and six socioeconomic factors exhibited nonlinear effects (promoting or inhibiting) with varying inflection values. Additionally, this model demonstrated outstanding accuracy (hitting ratio = 95.56%) in predicting the city-level risks of local epidemics in China. CONCLUSIONS: China is experiencing an increasing occurrence of sporadic local DF epidemics driven by an unavoidably higher frequency and intensity of imported DF epidemics. This research offers valuable insights for health authorities to strengthen their intervention capabilities against this disease.

A machine learning-assisted fluorescent sensor array utilizing silver nanoclusters for coffee discrimination.

Coffee is a globally consumed commodity of substantial commercial significance. In this study, we constructed a fluorescent sensor array based on two types of polymer templated silver nanoclusters (AgNCs) for the detection of organic acids and coffees. The nanoclusters exhibited different interactions with organic acids and generated unique fluorescence response patterns. By employing principal component analysis (PCA) and random forest (RF) algorithms, the sensor array exhibited good qualitative and quantitative capabilities for organic acids. Then the sensor array was used to distinguish coffees with different processing methods or roast degrees and the recognition accuracy achieved 100%. It could also successfully identify 40 coffee samples from 12 geographical origins. Moreover, it demonstrated another satisfactory performance for the classification of pure coffee samples with their binary and ternary mixtures or other beverages. In summary, we present a novel method for detecting and identifying multiple coffees, which has considerable potential in applications such as quality control and identification of fake blended coffees.

Corrigendum: Bipartite networks represent causality better than simple networks: Evidence, algorithms, and applications.

[This corrects the article DOI: 10.3389/fgene.2024.1371607.].

Random forest-based prediction of intracranial hypertension in patients with traumatic brain injury.

BACKGROUND: Treatment and prevention of intracranial hypertension (IH) to minimize secondary brain injury are central to the neurocritical care management of traumatic brain injury (TBI). Predicting the onset of IH in advance allows for a more aggressive prophylactic treatment. This study aimed to develop random forest (RF) models for predicting IH events in TBI patients. METHODS: We analyzed prospectively collected data from patients admitted to the intensive care unit with invasive intracranial pressure (ICP) monitoring. Patients with persistent ICP > 22 mmHg in the early postoperative period (first 6 h) were excluded to focus on IH events that had not yet occurred. ICP-related data from the initial 6 h were used to extract linear (ICP, cerebral perfusion pressure, pressure reactivity index, and cerebrospinal fluid compensatory reserve index) and nonlinear features (complexity of ICP and cerebral perfusion pressure). IH was defined as ICP > 22 mmHg for > 5 min, and severe IH (SIH) as ICP > 22 mmHg for > 1 h during the subsequent ICP monitoring period. RF models were then developed using baseline characteristics (age, sex, and initial Glasgow Coma Scale score) along with linear and nonlinear features. Fivefold cross-validation was performed to avoid overfitting. RESULTS: The study included 69 patients. Forty-three patients (62.3%) experienced an IH event, of whom 30 (43%) progressed to SIH. The median time to IH events was 9.83 h, and to SIH events, it was 11.22 h. The RF model showed acceptable performance in predicting IH with an area under the curve (AUC) of 0.76 and excellent performance in predicting SIH (AUC = 0.84). Cross-validation analysis confirmed the stability of the results. CONCLUSIONS: The presented RF model can forecast subsequent IH events, particularly severe ones, in TBI patients using ICP data from the early postoperative period. It provides researchers and clinicians with a potentially predictive pathway and framework that could help triage patients requiring more intensive neurological treatment at an early stage.

Data-driven prediction on critical mechanical properties of engineered cementitious composites based on machine learning.

The present study introduces a novel approach utilizing machine learning techniques to predict the crucial mechanical properties of engineered cementitious composites (ECCs), spanning from typical to exceptionally high strength levels. These properties, including compressive strength, flexural strength, tensile strength, and tensile strain capacity, can not only be predicted but also precisely estimated. The investigation encompassed a meticulous compilation and examination of 1532 datasets sourced from pertinent research. Four machine learning algorithms, linear regression (LR), K nearest neighbors (KNN), random forest (RF), and extreme gradient boosting (XGB), were used to establish the prediction model of ECC mechanical properties and determine the optimal model. The optimal model was utilized to employ SHapley Additive exPlanations (SHAP) for scrutinizing feature importance and conducting an in-depth parametric analysis. Subsequently, a comprehensive control strategy was devised for ECC mechanical properties. This strategy can provide actionable guidance for ECC design, equipping engineers and professionals in civil engineering and material science to make informed decisions throughout their design endeavors. The results show that the RF model demonstrated the highest prediction accuracy for compressive strength and flexural strength, with R2 values of 0.92 and 0.91 on the test set. The XGB model outperformed in predicting tensile strength and tensile strain capacity, with R2 values of 0.87 and 0.80 on the test set, respectively. The prediction of tensile strain capacity was the least accurate. Meanwhile, the MAE of the tensile strain capacity was a mere 0.84%, smaller than the variability (1.77%) of the test results in previous research. Compressive strength and tensile strength demonstrated high sensitivity to variations in both water-cement ratio (W) and water reducer (WR). In contrast, flexural strength exhibited high sensitivity solely to changes in W. Conversely, the sensitivity of tensile strain capacity to input features was moderate and consistent. The mechanical attributes of ECC emerged from the combined effects of multiple positive and negative features. Notably, WR exerted the most significant influence on compressive strength among all features, whereas polyethylene (PE) fiber emerged as the primary driver affecting flexural strength, tensile strength, and tensile strain capacity.

Predicting performance of students by optimizing tree components of random forest using genetic algorithm.

Prediction of student academic performance is still a problem because of the limitations of the existing methods specifically low generalizability and lack of interpretability. This study suggests a new approach that deals with the current problems and provides more reliable predictions. The proposed approach combines the information gain (IG) and Laplacian score (LS) for feature selection. In this feature selection scheme, combination of IG and LS is used for ranking features and then, Sequential Forward Selection mechanism is used for determining the most relevant indicators. Also, combination of random forest algorithm with a genetic algorithm for is introduced for multi-class classification. This approach strives to attain more accuracy and reliability than current techniques. The case study shows the proposed strategy can predict performance of students with average accuracy of 93.11 % which shows a minimum improvement of 2.25 % compared to the baseline methods. The findings were further confirmed by the analysis of different evaluation metrics (Accuracy, Precision, Recall, F-Measure) to prove the efficiency of the proposed mechanism.

The application of THz-TDS in the characterization of Bayan Obo magnetite ore composition.

The application of terahertz time-domain spectroscopy (THz-TDS) in the quantitative analysis of major minerals in Bayan Obo magnetite ore was explored. The positive correlation between the optical parameters of the original ore and its iron content is confirmed. The detections of three main iron containing minerals, including magnetite, pyrite, and hematite, were simulated using corresponding reagents. The random forest algorithm is used for quantitative analysis, and FeS2 is detected with precision of R2 = 0.7686 and MAE = 0.6307% in ternary mixtures. The experimental results demonstrate that THz-TDS can distinguish specific iron containing minerals and reveal the potential application value of this testing method in exploration and mineral processing fields.

Predicting dyslipidemia incidence: unleashing machine learning algorithms on Lifestyle Promotion Project data.

BACKGROUND: Dyslipidemia, characterized by variations in plasma lipid profiles, poses a global health threat linked to millions of deaths annually. OBJECTIVES: This study focuses on predicting dyslipidemia incidence using machine learning methods, addressing the crucial need for early identification and intervention. METHODS: The dataset, derived from the Lifestyle Promotion Project (LPP) in East Azerbaijan Province, Iran, undergoes a comprehensive preprocessing, merging, and null handling process. Target selection involves five distinct dyslipidemia-related variables. Normalization techniques and three feature selection algorithms are applied to enhance predictive modeling. RESULT: The study results underscore the potential of different machine learning algorithms, specifically multi-layer perceptron neural network (MLP), in reaching higher performance metrics such as accuracy, F1 score, sensitivity and specificity, among other machine learning methods. Among other algorithms, Random Forest also showed remarkable accuracies and outperformed K-Nearest Neighbors (KNN) in metrics like precision, recall, and F1 score. The study's emphasis on feature selection detected meaningful patterns among five target variables related to dyslipidemia, indicating fundamental shared unities among dyslipidemia-related factors. Features such as waist circumference, serum vitamin D, blood pressure, sex, age, diabetes, and physical activity related to dyslipidemia. CONCLUSION: These results cooperatively highlight the complex nature of dyslipidemia and its connections with numerous factors, strengthening the importance of applying machine learning methods to understand and predict its incidence precisely.

Impact of climate change on future flood susceptibility projections under shared socioeconomic pathway scenarios in South Asia using artificial intelligence algorithms.

This study investigated the impact of climate change on flood susceptibility in six South Asian countries Afghanistan, Bangladesh, Bhutan, Bharat (India), Nepal, and Pakistan-under two distinct Shared Socioeconomic Pathway (SSP) scenarios: SSP1-2.6 and SSP5-5.8, for 2041-2060 and 2081-2100. To predict flood susceptibility, we employed three artificial intelligence (AI) algorithms: the K-nearest neighbor (KNN), conditional inference random forest (CIRF), and regularized random forest (RRF). Predictions were based on data from 2452 historical flood events, alongside climatic variables measured over monthly, seasonal, and annual timeframes. The innovative aspect of this research is the emphasis on using climatic variables across these progressively condensed timeframes, specifically addressing eight precipitation factors. The performance evaluation, employing the area under the receiver operating characteristic curve (AUC) metric, identified the RRF model as the most accurate, with the highest AUC of 0.94 during the testing phase, followed by the CIRF (AUC = 0.91) and the KNN (AUC = 0.86). An analysis of variable importance highlighted the substantial role of certain climatic factors, namely precipitation in the warmest quarter, annual precipitation, and precipitation during the wettest month, in the modeling of flood susceptibility in South Asia. The resultant flood susceptibility maps demonstrated the influence of climate change scenarios on susceptibility classifications, signalling a dynamic landscape of flood-prone areas over time. The findings revealed variable trends under different climate change scenarios and periods, with marked differences in the percentage of areas classified as having high and very high flood susceptibility. Overall, this study advances our understanding of how climate change affects flood susceptibility in South Asia and offers an essential tool for assessing and managing flood risks in the region.

Campylobacter assessment along the Spanish food chain: Identification of key points.

AIMS: Campylobacteriosis, caused by Campylobacter spp., is one of the most important foodborne zoonotic diseases in the world and a common cause of gastroenteritis. In the European Union, campylobacteriosis is considered the most common zoonotic disease, with over 10,000 cases in 2020 alone. This high occurrence highlights the need of more efficient surveillance methods and identification of key points. METHODS AND RESULTS: Herein, we evaluated and identified key points of Campylobacter spp. occurrence along the Spanish food chain during 2015-2020, based on the following variables: product, stage and region. We analysed a dataset provided by the Spanish Agency for Food Safety and Nutrition using a machine learning algorithm (random forests). Campylobacter presence was influenced by the three selected explanatory variables, especially by product, followed by region and stage. Among the studied products, meat, especially poultry and sheep, presented the highest probability of occurrence of Campylobacter, where the bacterium was present in the initial, intermediate and final stages (e.g., wholesale, retail) of the food chain. The presence in final stages may represent direct consumer exposure to the bacteria. CONCLUSSIONS: By using the random forest method, this study contributes to the identification of Campylobacter key points and the evaluation of control efforts in the Spanish food chain.

A morphoscopic exploration of cranial sexual dimorphism among modern South Africans using computed tomography scans.

Continual re-evaluation of standards for forensic anthropological analyses are necessary, particularly as new methods are explored or as populations change. Indian South Africans are not a new addition to the South African population; however, a paucity of skeletal material is available for analysis from medical school collections, which has resulted in a lack of information on the sexual dimorphism in the crania. For comparable data, computed tomography scans of modern Black, Coloured and White South Africans were included in addition to Indian South Africans. Four cranial morphoscopic traits, were assessed on 408 modern South Africans (equal sex and population distribution). Frequencies, Chi-squared tests, binary logistic regression and random forest modelling were used to assess the data. Males were more robust than females for all populations, while White South African males were the most robust, and Black South African females were the most gracile. Population differences were noted among most groups for at least two variables, necessitating the creation of populations-specific binary logistic regression equations. Only White and Coloured South Africans were not significantly different. Indian South Africans obtained the highest correct classifications for binary logistic regression (94.1%) and random forest modelling (95.7%) and Coloured South Africans had the lowest correct classifications (88.8% and 88.0%, respectively). This study provides a description of the patterns of sexual dimorphism in four cranial morphoscopic traits in the current South African population, as well as binary logistic regression functions for sex estimation of Black, Coloured, Indian and White South Africans.

Clustering analysis for classifying fake real estate listings.

With the rapid growth of online property rental and sale platforms, the prevalence of fake real estate listings has become a significant concern. These deceptive listings waste time and effort for buyers and sellers and pose potential risks. Therefore, developing effective methods to distinguish genuine from fake listings is crucial. Accurately identifying fake real estate listings is a critical challenge, and clustering analysis can significantly improve this process. While clustering has been widely used to detect fraud in various fields, its application in the real estate domain has been somewhat limited, primarily focused on auctions and property appraisals. This study aims to fill this gap by using clustering to classify properties into fake and genuine listings based on datasets curated by industry experts. This study developed a K-means model to group properties into clusters, clearly distinguishing between fake and genuine listings. To assure the quality of the training data, data pre-processing procedures were performed on the raw dataset. Several techniques were used to determine the optimal value for each parameter of the K-means model. The clusters are determined using the Silhouette coefficient, the Calinski-Harabasz index, and the Davies-Bouldin index. It was found that the value of cluster 2 is the best and the Camberra technique is the best method when compared to overlapping similarity and Jaccard for distance. The clustering results are assessed using two machine learning algorithms: Random Forest and Decision Tree. The observational results have shown that the optimized K-means significantly improves the accuracy of the Random Forest classification model, boosting it by an impressive 96%. Furthermore, this research demonstrates that clustering helps create a balanced dataset containing fake and genuine clusters. This balanced dataset holds promise for future investigations, particularly for deep learning models that require balanced data to perform optimally. This study presents a practical and effective way to identify fake real estate listings by harnessing the power of clustering analysis, ultimately contributing to a more trustworthy and secure real estate market.

Construction and validation of risk prediction models for pulmonary embolism in hospitalized patients based on different machine learning methods.

Objective: This study aims to apply different machine learning (ML) methods to construct risk prediction models for pulmonary embolism (PE) in hospitalized patients, and to evaluate and compare the predictive efficacy and clinical benefit of each model. Methods: We conducted a retrospective study involving 332 participants (172 PE positive cases and 160 PE negative cases) recruited from Guangdong Medical University. Participants were randomly divided into a training group (70%) and a validation group (30%). Baseline data were analyzed using univariate analysis, and potential independent risk factors associated with PE were further identified through univariate and multivariate logistic regression analysis. Six ML models, namely Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), Naive Bayes (NB), Support Vector Machine (SVM), and AdaBoost were developed. The predictive efficacy of each model was compared using the receiver operating characteristic (ROC) curve analysis and the area under the curve (AUC). Clinical benefit was assessed using decision curve analysis (DCA). Results: Logistic regression analysis identified lower extremity deep venous thrombosis, elevated D-dimer, shortened activated partial prothrombin time, and increased red blood cell distribution width as potential independent risk factors for PE. Among the six ML models, the RF model achieved the highest AUC of 0.778. Additionally, DCA consistently indicated that the RF model offered the greatest clinical benefit. Conclusion: This study developed six ML models, with the RF model exhibiting the highest predictive efficacy and clinical benefit in the identification and prediction of PE occurrence in hospitalized patients.

Ensemble learning algorithms to elucidate the core microbiome's impact on carbon content and degradation properties at the soil aggregate level.

Soil aggregates are crucial for soil organic carbon (OC) accumulation. This study, utilizing a 32-year fertilization experiment, investigates whether the core microbiome can elucidate variations in carbon content and decomposition across different aggregate sizes more effectively than broader bacterial and fungal community analyses. Employing ensemble learning algorithms that integrate machine learning with network inference, we found that the core microbiome accounts for an average increase of 26 % and 20 % in the explained variance of PCoA and Adonis analyses, respectively, in response to fertilization. Compared to the control, inorganic and organic fertilizers decreased the decomposition index (DDI) by 31 % and 38 %, respectively. The fungal core microbiome predominantly influenced OC content and DDI in larger macroaggregates (>2000 µm), explaining over 35 % of the variance, while the bacterial core microbiome had a lesser impact, explaining <30 %. Conversely, in smaller aggregates (<2000 µm), the bacterial core microbiome significantly influenced DDI (R2 > 0.2), and the fungal core microbiome more strongly affected OC content (R2 > 0.3). Mantel tests showed that pH is the most significant environmental factor affecting core microbiome composition across all aggregate sizes (Mantel's r > 0.8, P < 0.01). Linear correlation analysis further confirmed that the core microbiome's community structure could accurately predict OC content and DDI in aggregates (R2 > 0.8, P < 0.05). Overall, our findings suggested that the core microbiome provides deeper insights into the variability of aggregate organic carbon content and decomposition, with the bacterial core microbiome playing a particularly pivotal role within the soil aggregates.

Nonlinear association between PD-L1 expression levels and the risk of postoperative recurrence in non-small cell lung cancer.

Accurate prediction of postoperative recurrence is important for optimizing the treatment strategies for non-small cell lung cancer (NSCLC). Previous studies identified the PD-L1 expression in NSCLC as a risk factor for postoperative recurrence. This study aimed to examine the contribution of PD-L1 expression to predicting postoperative recurrence using machine learning. The clinical data of 647 patients with NSCLC who underwent surgical resection were collected and stratified into training (80%), validation (10%), and testing (10%) datasets. Machine learning models were trained on the training data using clinical parameters including PD-L1 expression. The top-performing model was assessed on the test data using the SHAP analysis and partial dependence plots to quantify the contribution of the PD-L1 expression. Multivariate Cox proportional hazards model was used to validate the association between PD-L1 expression and postoperative recurrence. The random forest model demonstrated the highest predictive performance with the SHAP analysis, highlighting PD-L1 expression as an important feature, and the multivariate Cox analysis indicated a significant increase in the risk of postoperative recurrence with each increment in PD-L1 expression. These findings suggest that variations in PD-L1 expression may provide valuable information for clinical decision-making regarding lung cancer treatment strategies.

Prediction of flood sensitivity based on Logistic Regression, eXtreme Gradient Boosting, and Random Forest modeling methods.

Floods are one of the most destructive disasters that cause loss of life and property worldwide every year. In this study, the aim was to find the best-performing model in flood sensitivity assessment and analyze key characteristic factors, the spatial pattern of flood sensitivity was evaluated using three machine learning (ML) models: Logistic Regression (LR), eXtreme Gradient Boosting (XGBoost), and Random Forest (RF). Suqian City in Jiangsu Province was selected as the study area, and a random sample dataset of historical flood points was constructed. Fifteen different meteorological, hydrological, and geographical spatial variables were considered in the flood sensitivity assessment, 12 variables were selected based on the multi-collinearity study. Among the results of comparing the selected ML models, the RF method had the highest AUC value, accuracy, and comprehensive evaluation effect, and is a reliable and effective flood risk assessment model. As the main output of this study, the flood sensitivity map is divided into five categories, ranging from very low to very high sensitivity. Using the RF model (i.e., the highest accuracy of the model), the high-risk area covers about 44% of the study area, mainly concentrated in the central, eastern, and southern parts of the old city area.

Bioplastic derived from corn stover: Life cycle assessment and artificial intelligence-based analysis of uncertainty and variability.

Exploring feasible and renewable alternatives to reduce dependency on traditional fossil-based plastics is critical for sustainable development. These alternatives can be produced from biomass, which may have large uncertainties and variabilities in the feedstock composition and system parameters. This study develops a modeling framework that integrates cradle-to-grave life cycle assessment (LCA) with a rigorous process model and artificial intelligence (AI) models to conduct uncertainty and variability analyses, which are highly time-consuming to conduct using only the process model. This modeling framework examines polylactic acid (PLA) produced from corn stover in the U.S. An analysis of uncertainty and variability was conducted by performing a Monte Carlo simulation to show the detailed result distributions. Our Monte Carlo simulation results show that the mean life-cycle Global Warming Potential (GWP) of 1 kg PLA is 4.3 kgCO2eq (P5-P95 4.1-4.4) for composting PLA with natural gas combusted for the biorefinery, 3.7 kgCO2eq (P5-P95 3.4-3.9) for incinerating PLA for electricity with natural gas combusted for the biorefinery, and 1.9 kgCO2eq (P5-P95 1.6-2.1) for incinerating PLA for electricity with wood pellets combusted for the biorefinery. Tradeoffs for different environmental impact categories were identified. Based on feedstock composition variations, two AI models were trained: random forest and artificial neural networks. Both AI models demonstrated high prediction accuracy; however, the random forest performed slightly better.

Recognition of small water bodies under complex terrain based on SAR and optical image fusion algorithm.

Understanding the spatial and temporal distribution of small water bodies is essential for managing water resources, crafting conservation policies, and preserving watershed ecosystems and biodiversity. However, existing studies often rely on a single remote sensing data source (optical or microwave), focusing on large-scale, flat areas and lacking comprehensive monitoring of small water bodies in complex terrain. Therefore, considering the complementary advantages of multisource remote sensing (multispectral and SAR), this paper proposes a multispectral and SAR fusion algorithm, named Multispectral and SAR Fusion algorithm (MASF), to better capture the remote sensing characteristics of small water bodies in complex areas. Based on this, a dataset containing spectral, texture, and geometric features is constructed, and multi-scale segmentation and random forest algorithms are applied for identification of small water bodies in complex terrain. The results demonstrate that the proposed fusion algorithm MASF exhibits minimal spectral distortion (SAM < 3.5, ERGAS <21, RMSE <0.01) and robust spatial feature enhancement (PSNR >40, SSIM >0.999, CC > 0.99). The Overall Accuracy (OA) and Kappa coefficients for both experimental areas surpassed 0.9. For rivers and reservoirs, both Producer's Accuracy (PA) and User's Accuracy (UA) exceeded 0.9. The UA for agricultural ponds exceeded 0.8. Comparative analysis with three other types of water-related data products shows that the freshwater identification results in this study have certain advantages in local small water bodies. Our research holds significant implications for the utilization of water resources in mountainous areas, prevention and control of floods and floods, as well as the development of aquaculture industry.

Prediction model for cardiovascular disease in patients with diabetes using machine learning derived and validated in two independent Korean cohorts.

This study aimed to develop and validate a machine learning (ML) model tailored to the Korean population with type 2 diabetes mellitus (T2DM) to provide a superior method for predicting the development of cardiovascular disease (CVD), a major chronic complication in these patients. We used data from two cohorts, namely the discovery (one hospital; n = 12,809) and validation (two hospitals; n = 2019) cohorts, recruited between 2008 and 2022. The outcome of interest was the presence or absence of CVD at 3 years. We selected various ML-based models with hyperparameter tuning in the discovery cohort and performed area under the receiver operating characteristic curve (AUROC) analysis in the validation cohort. CVD was observed in 1238 (10.2%) patients in the discovery cohort. The random forest (RF) model exhibited the best overall performance among the models, with an AUROC of 0.830 (95% confidence interval [CI] 0.818-0.842) in the discovery dataset and 0.722 (95% CI 0.660-0.783) in the validation dataset. Creatinine and glycated hemoglobin levels were the most influential factors in the RF model. This study introduces a pioneering ML-based model for predicting CVD in Korean patients with T2DM, outperforming existing prediction tools and providing a groundbreaking approach for early personalized preventive medicine.