Search

Background: Depression is one of the most common mental illnesses among middle-aged and older adults in China. It is of great importance to find the crucial factors that lead to depression and to effectively control and reduce the risk of depression. Currently, there are limited methods available to accurately predict the risk of depression and identify the crucial factors that influence it. Methods: We collected data from 25,586 samples from the harmonized China Health and Retirement Longitudinal Study (CHARLS), and the latest records from 2018 were included in the current cross-sectional analysis. Ninety-three input variables in the survey were considered as potential influential features. Five machine learning (ML) models were utilized, including CatBoost and eXtreme Gradient Boosting (XGBoost), Gradient Boosting decision tree (GBDT), Random Forest (RF), Light Gradient Boosting Machine (LightGBM). The models were compared to the traditional multivariable Linear Regression (LR) model. Simultaneously, SHapley Additive exPlanations (SHAP) were used to identify key influencing factors at the global level and explain individual heterogeneity through instance-level analysis. To explore how different factors are nonlinearly associated with the risk of depression, we employed the Accumulated Local Effects (ALE) approach to analyze the identified critical variables while controlling other covariates. Results: CatBoost outperformed other machine learning models in terms of MAE, MSE, MedAE, and R2metrics. The top three crucial factors identified by the SHAP were r4satlife, r4slfmem, and r4shlta, representing life satisfaction, selfreported memory, and health status levels, respectively. Conclusion: This study demonstrates that the CatBoost model is an appropriate choice for predicting depression among middle-aged and older adults in Harmonized CHARLS. The SHAP and ALE interpretable methods have identified crucial factors and the nonlinear relationship with depression, which require the attention of domain experts. [ABSTRACT FROM AUTHOR]

The quick Sequential Organ Failure Assessment (qSOFA) system identifies an individual's risk to progress to poor sepsis-related outcomes using minimal variables. We used Support Vector Machine, Learning Using Concave and Convex Kernels, and Random Forest to predict an increase in qSOFA score using electronic health record (EHR) data, electrocardiograms (ECG), and arterial line signals. We structured physiological signals data in a tensor format and used Canonical Polyadic/Parallel Factors (CP) decomposition for feature reduction. Random Forests trained on ECG data show improved performance after tensor decomposition for predictions in a 6-h time frame (AUROC 0.67 ± 0.06 compared to 0.57 ± 0.08, p = 0.01 ). Adding arterial line features can also improve performance (AUROC 0.69 ± 0.07, p < 0.01 ), and benefit from tensor decomposition (AUROC 0.71 ± 0.07, p = 0.01 ). Adding EHR data features to a tensor-reduced signal model further improves performance (AUROC 0.77 ± 0.06, p < 0.01 ). Despite reduction in performance going from an EHR data-informed model to a tensor-reduced waveform data model, the signals-informed model offers distinct advantages. The first is that predictions can be made on a continuous basis in real-time, and second is that these predictions are not limited by the availability of EHR data. Additionally, structuring the waveform features as a tensor conserves structural and temporal information that would otherwise be lost if the data were presented as flat vectors. [ABSTRACT FROM AUTHOR]

Background: Nosocomial infections (NIs) frequently occur and adversely impact prognosis for hospitalized patients with cirrhosis. This study aims to develop and validate two machine learning models for NIs and in-hospital mortality risk prediction. Methods: The Prediction of Nosocomial Infection and Prognosis in Cirrhotic patients (PIPC) study included hospitalized patients with cirrhosis at the Qingchun Campus of the First Affiliated Hospital of Zhejiang University. We then assessed several machine learning algorithms to construct predictive models for NIs and prognosis. We validated the best-performing models with bootstrapping techniques and an external validation dataset. The accuracy of the predictions was evaluated through sensitivity, specificity, predictive values, and likelihood ratios, while predictive robustness was examined through subgroup analyses and comparisons between models. Results: We enrolled 1,297 patients into derivation cohort and 496 patients into external validation cohort. Among the six algorithms assessed, the Random Forest algorithm performed best. For NIs, the PIPC-NI model achieved an area under the curve (AUC) of 0.784 (95% confidence interval [CI] 0.741–0.826), a sensitivity of 0.712, and a specificity of 0.702. For in-hospital mortality, the PIPC- mortality model achieved an AUC of 0.793 (95% CI 0.749–0.836), a sensitivity of 0.769, and a specificity of 0.701. Moreover, our PIPC models demonstrated superior predictive performance compared to the existing MELD, MELD-Na, and Child-Pugh scores. Conclusions: The PIPC models showed good predictive power and may facilitate healthcare providers in easily assessing the risk of NIs and prognosis among hospitalized patients with cirrhosis. [ABSTRACT FROM AUTHOR]

As lake and reservoir ecosystems transition across major environmental regimes (e.g., mixing regime) resulting from anthropogenic change, setting predictive expectations is imperative. We tested the hypothesis that (dissolved) oxygen is more predictable in monomictic reservoirs that thermally stratify throughout the summer (warm) season compared to polymictic reservoirs that stratify intermittently. Using two‐hourly vertical profiles of oxygen, we compared daily‐aggregated errors of oxygen predictions from random forests across and within two monomictic and two polymictic reservoirs in the south‐central (subtropical) USA. Although one monomictic reservoir was typically more predictable than the polymictic reservoirs, the hypereutrophic, small monomictic reservoir had less predictable oxygen patterns potentially related to rapid oxygen cycling and intrusions of oxygenated waters in the hypolimnion without mixing. Daily mixing did not relate strongly to model errors. Water temperature, depth, and wind were the most important predictors, but were not clearly related to season or mixing. Lastly, we compared multiple model types (regression, neural network, and process‐based) in one polymictic reservoir to test how our interpretations of oxygen predictability were sensitive to model type, finding that the models generally agreed; however, the process‐based model poorly predicted oxygen in the middle of the vertical profiles (5 m) where most models performed poorly due to a temporally unstable, vacillating metalimnion. Our results suggest predicting reservoir oxygen dynamics may be easier in stratified reservoirs, but eutrophication and complex hydrodynamics may cause forecasting surprises especially for those who use or manage water resources in mono‐ or dimictic reservoirs. [ABSTRACT FROM AUTHOR]

Background: Advance care planning (ACP) can contribute to individuals making decisions about their healthcare preferences in advance of serious illness. Up to now, the acceptance level and associated factors of ACP among the public in China remain unclear. This study aims to investigate the acceptance level of ACP in China and identify factors associated with it based on the socioecological model. Methods: A total of 19,738 participants were included in this survey. We employed a random forest regression analysis to select factors derived from the socioecological model. Multivariate generalized linear model analysis was then conducted to explore the factors that were associated with the acceptance level of ACP. Results: On a scale ranging from 0 to 100, the median score for acceptance level of ACP was 64.00 (IQR: 48.00–83.00) points. The results of the multivariate generalized linear model analysis revealed that participants who scored higher on measures of openness and neuroticism personality traits, as well as those who had greater perceptions of social support, higher levels of health literacy, better neighborly relationships, family health, and family social status, were more likely to accept ACP. Conversely, participants who reported higher levels of subjective well-being and greater family communication levels demonstrated a lower likelihood of accepting ACP. Conclusions: This study identified multiple factors associated with the acceptance level of ACP. The findings offer valuable insights that can inform the design and implementation of targeted interventions aimed at facilitating a good death and may have significant implications for the formulation of end-of-life care policies and practices in other countries facing similar challenges. [ABSTRACT FROM AUTHOR]

Low muscle mass is associated with numerous adverse outcomes independent of other associated comorbid diseases. We aimed to predict and understand an individual's risk for developing low muscle mass using proteomics and machine learning. We identified eight biomarkers associated with low pectoralis muscle area (PMA). We built three random forest classification models that used either clinical measures, feature selected biomarkers, or both to predict development of low PMA. The area under the receiver operating characteristic curve for each model was: clinical-only = 0.646, biomarker-only = 0.740, and combined = 0.744. We displayed the heterogenetic nature of an individual's risk for developing low PMA and identified two distinct subtypes of participants who developed low PMA. While additional validation is required, our methods for identifying and understanding individual and group risk for low muscle mass could be used to enable developments in the personalized prevention of low muscle mass. [ABSTRACT FROM AUTHOR]

With childhood hypertension emerging as a global public health concern, understanding its associated factors is crucial. This study investigated the prevalence and associated factors of hypertension among Chinese children. This cross-sectional investigation was conducted in Pinghu, Zhejiang province, involving 2,373 children aged 8–14 years from 12 schools. Anthropometric measurements were taken by trained staff. Blood pressure (BP) was measured in three separate occasions, with an interval of at least two weeks. Childhood hypertension was defined as systolic blood pressure (SBP) and/or diastolic blood pressure (DBP) ≥ age-, sex-, and height-specific 95th percentile, across all three visits. A self-administered questionnaire was utilized to collect demographic, socioeconomic, health behavioral, and parental information at the first visit of BP measurement. Random forest (RF) and multivariable logistic regression model were used collectively to identify associated factors. Additionally, population attributable fractions (PAFs) were calculated. The prevalence of childhood hypertension was 5.0% (95% confidence interval [CI]: 4.1–5.9%). Children with body mass index (BMI) ≥ 85th percentile were grouped into abnormal weight, and those with waist circumference (WC) > 90th percentile were sorted into central obesity. Normal weight with central obesity (NWCO, adjusted odds ratio [aOR] = 5.04, 95% CI: 1.96–12.98), abnormal weight with no central obesity (AWNCO, aOR = 4.60, 95% CI: 2.57–8.21), and abnormal weight with central obesity (AWCO, aOR = 9.94, 95% CI: 6.06–16.32) were associated with an increased risk of childhood hypertension. Childhood hypertension was attributable to AWCO mostly (PAF: 0.64, 95% CI: 0.50–0.75), followed by AWNCO (PAF: 0.34, 95% CI: 0.19–0.51), and NWCO (PAF: 0.13, 95% CI: 0.03–0.30). Our results indicated that obesity phenotype is associated with childhood hypertension, and the role of weight management could serve as potential target for intervention. [ABSTRACT FROM AUTHOR]

Background: This study evaluates the efficacy of integrating MRI deep transfer learning, radiomic signatures, and clinical variables to accurately preoperatively differentiate between stage T2 and T3 rectal cancer. Methods: We included 361 patients with pathologically confirmed stage T2 or T3 rectal cancer, divided into a training set (252 patients) and a test set (109 patients) at a 7:3 ratio. The study utilized features derived from deep transfer learning and radiomics, with Spearman rank correlation and the Least Absolute Shrinkage and Selection Operator (LASSO) regression techniques to reduce feature redundancy. Predictive models were developed using Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM), selecting the best-performing model for a comprehensive predictive framework incorporating clinical data. Results: After removing redundant features, 24 key features were identified. In the training set, the area under the curve (AUC)values for LR, RF, DT, and SVM were 0.867, 0.834, 0.900, and 0.944, respectively; in the test set, they were 0.847, 0.803, 0.842, and 0.910, respectively. The combined model, using SVM and clinical variables, achieved AUCs of 0.946 in the trainingset and 0.920 in the test set. Conclusion: The study confirms the utility of a combined model of MRI deep transfer learning, radiomic features, and clinical factors for preoperative classification of stage T2 vs. T3 rectal cancer, offering significant technological support for precise diagnosis and potential clinical application. [ABSTRACT FROM AUTHOR]

Objective: By utilizing machine learning, we can identify genes that are associated with recurrence, invasion, and tumor stemness, thus uncovering new therapeutic targets. Methods: To begin, we obtained a gene set related to recurrence and invasion from the GEO database, a comprehensive gene expression database. We then employed the Weighted Gene Co-expression Network Analysis (WGCNA) to identify core gene modules and perform functional enrichment analysis on them. Next, we utilized the random forest and random survival forest algorithms to calculate the genes within the key modules, resulting in the identification of three crucial genes. Subsequently, one of these key genes was selected for prognosis analysis and potential drug screening using the Kaplan-Meier tool. Finally, in order to examine the role of CDC20 in lung adenocarcinoma (LUAD), we conducted a variety of in vitro and in vivo experiments, including wound healing assay, colony formation assays, Transwell migration assays, flow cytometric cell cycle analysis, western blotting, and a mouse tumor model experiment. Results: First, we collected a total of 279 samples from two datasets, GSE166722 and GSE31210, to identify 91 differentially expressed genes associated with recurrence, invasion, and stemness in lung adenocarcinoma. Functional enrichment analysis revealed that these key gene clusters were primarily involved in microtubule binding, spindle, chromosomal region, organelle fission, and nuclear division. Next, using machine learning, we identified and validated three hub genes (CDC45, CDC20, TPX2), with CDC20 showing the highest correlation with tumor stemness and limited previous research. Furthermore, we found a close association between CDC20 and clinical pathological features, poor overall survival (OS), progression-free interval (PFI), progression-free survival (PFS), and adverse prognosis in lung adenocarcinoma patients. Lastly, our functional research demonstrated that knocking down CDC20 could inhibit cancer cell migration, invasion, proliferation, cell cycle progression, and tumor growth possibly through the MAPK signaling pathway. Conclusion: CDC20 has emerged as a novel biomarker for monitoring treatment response, recurrence, and disease progression in patients with lung adenocarcinoma. Due to its significance, further research studying CDC20 as a potential therapeutic target is warranted. Investigating the role of CDC20 could lead to valuable insights for developing new treatments and improving patient outcomes. [ABSTRACT FROM AUTHOR]

Objective: To investigate the diagnostic efficacy of the clinical ultrasound imaging model, ultrasonographic radiomics model, and comprehensive model based on ultrasonographic radiomics for the differentiation of small clear cell Renal Cell Carcinoma (ccRCC) and Renal Angiomyolipoma (RAML). Methods: The clinical, ultrasound, and contrast-enhanced CT(CECT) imaging data of 302 small renal tumors (maximum diameter ≤ 4cm) patients in Tianjin Medical University Cancer Institute and Hospital from June 2018 to June 2022 were retrospectively analyzed, with 182 patients of ccRCC and 120 patients of RAML. The ultrasound images of the largest diameter of renal tumors were manually segmented by ITK-SNAP software, and Pyradiomics (v3.0.1) module in Python 3.8.7 was applied to extract ultrasonographic radiomics features from ROI segmented images. The patients were randomly divided into training and internal validation cohorts in the ratio of 7:3. The Random Forest algorithm of the Sklearn module was applied to construct the clinical ultrasound imaging model, ultrasonographic radiomics model, and comprehensive model. The efficacy of the prediction models was verified in an independent external validation cohort consisting of 69 patients, from 230 small renal tumor patients in two different institutions. The Delong test compared the predictive ability of three models and CECT. Calibration Curve and clinical Decision Curve Analysis were applied to evaluate the model and determine the net benefit to patients. Results: 491 ultrasonographic radiomics features were extracted from 302 small renal tumor patients, and 9 ultrasonographic radiomics features were finally retained for modeling after regression and dimensionality reduction. In the internal validation cohort, the area under the curve (AUC), sensitivity, specificity, and accuracy of the clinical ultrasound imaging model, ultrasonographic radiomics model, comprehensive model, and CECT were 0.75, 76.7%, 60.0%, 70.0%; 0.80, 85.6%, 61.7%, 76.0%; 0.88, 90.6%, 76.7%, 85.0%and 0.90, 92.6%, 88.9%, 91.1%, respectively. In the external validation cohort, AUC, sensitivity, specificity, and accuracy of the three models and CECT were 0.73, 67.5%, 69.1%, 68.3%; 0.89, 86.7%, 80.0%, 83.5%; 0.90, 85.0%, 85.5%, 85.2% and 0.91, 94.6%, 88.3%, 91.3%, respectively. The DeLong test showed no significant difference between the clinical ultrasound imagingmodel and the ultrasonographic radiomics model (Z=-1.287, P=0.198). The comprehensive model showed superior diagnostic performance than the ultrasonographic radiomics model (Z=4. 394, P<0.001) and the clinical ultrasound imaging model (Z=4. 732, P<0.001). Moreover, there was no significant difference in AUC between the comprehensive model and CECT (Z=-0.252, P=0.801). Both in the internal and external validation cohort, the Calibration Curve and Decision Curve Analysis showed a better performance of the comprehensive model. Conclusion: It is feasible to construct an ultrasonographic radiomics model for distinguishing small ccRCC and RAML based on ultrasound images, and the diagnostic performance of the comprehensive model is superior to the clinical ultrasound imaging model and ultrasonographic radiomics model, similar to that of CECT. [ABSTRACT FROM AUTHOR]

In order to increase the likelihood of obtaining treatment and achieving a complete recovery, early illness identification and diagnosis are crucial. Artificial intelligence is helpful with this process by allowing us to rapidly start the necessary protocol for treatment in the early stages of disease development. Artificial intelligence is a major contributor to the improvement of medical treatment for patients. In order to prevent and foresee this problem on the individual, family, and generational levels, Monitoring the patient's therapy and recovery is crucial. This study's objective is to outline a non-invasive method for using mammograms to detect breast abnormalities, classify breast disorders, and identify cancerous or benign tumor tissue in the breast. We used classification models on a dataset that has been pre-processed so that the number of samples is balanced, unlike previous work on the same dataset. Identifying cancerous or benign breast tissue requires the use of supervised learning techniques and algorithms, such as random forest (RF) and decision tree (DT) classifiers, to examine up to thirty features, such as breast size, mass, diameter, circumference, and the nature of the tumor (solid or cystic). To ascertain if the tissue is malignant or benign, the examination's findings are employed. These features are mostly what determines how effectively anything may be categorized. The DT classifier was able to get a score of 95.32%, while the RF satisfied a far higher 98.83 percent. [ABSTRACT FROM AUTHOR]

Background: The clinical presentation of Community-acquired pneumonia (CAP) in hospitalized patients exhibits heterogeneity. Inflammation and immune responses play significant roles in CAP development. However, research on immunophenotypes in CAP patients is limited, with few machine learning (ML) models analyzing immune indicators. Methods: A retrospective cohort study was conducted at Xinhua Hospital, affiliated with Shanghai Jiaotong University. Patients meeting predefined criteria were included and unsupervised clustering was used to identify phenotypes. Patients with distinct phenotypes were also compared in different outcomes. By machine learning methods, we comprehensively assess the disease severity of CAP patients. Results: A total of 1156 CAP patients were included in this research. In the training cohort (n=809), we identified three immune phenotypes among patients: Phenotype A (42.0%), Phenotype B (40.2%), and Phenotype C (17.8%), with Phenotype C corresponding to more severe disease. Similar results can be observed in the validation cohort. The optimal prognostic model, SuperPC, achieved the highest average C-index of 0.859. For predicting CAP severity, the random forest model was highly accurate, with C-index of 0.998 and 0.794 in training and validation cohorts, respectively. Conclusion: CAP patients can be categorized into three distinct immune phenotypes, each with prognostic relevance. Machine learning exhibits potential in predicting mortality and disease severity in CAP patients by leveraging clinical immunological data. Further external validation studies are crucial to confirm applicability. [ABSTRACT FROM AUTHOR]

Background: Neuropathic pain (NP) is a debilitating and refractory chronic pain with a higher prevalence especially in elderly patients. Cell senescence considered a key pathogenic factor in NP. The objective of this research is to discover genes associated with aging in peripheral blood of individuals with NP using bioinformatics techniques. Methods: Two cohorts (GSE124272 and GSE150408) containing peripheral blood samples of NP were downloaded from the GEO database. By merging the two cohorts, differentially expressed aging-related genes (DE-ARGs) were obtained by intersection with aging-related genes. The potential biological mechanisms of DE-ARGs were further analyzed through GO and KEGG. Three machine learning methods, namely, LASSO, SVM-RFE, and Random Forest, were utilized to identify diagnostic biomarkers. A Nomogram model was developed to assess their diagnostic accuracy. The validation of biomarker expression and diagnostic effectiveness was conducted in three distinct pain cohorts. The CIBERSORT algorithm was employed to evaluate the immune cell composition in the peripheral blood of patients with NP and investigate its association with the expression of diagnostic biomarkers. Results: This study identified a total of 24 DE-ARGs, mainly enriched in “Chemokine signaling pathway,” “Inflammatory mediator regulation of TRP channels,” “HIF-1 signaling pathway” and “FOXO signaling pathway”. Three machine learning algorithms identified a total of four diagnostic biomarkers (CEBPA, CEACAM1, BTG3 and IL-1R1) with good diagnostic performance and the similar expression difference trend in different types of pain cohorts. The expression levels of CEACAM1 and IL-1R1 exhibit a positive correlation with the percentage of neutrophils. Conclusion: Using machine learning techniques, our research identified four diagnostic biomarkers related to aging in peripheral blood, providing innovative approaches for the diagnosis and treatment of NP. [ABSTRACT FROM AUTHOR]

Introduction: Transient receptor potential (TRP) channels function as cellular sensors with a broad impact, and their dysregulation is linked to numerous cancers. The influence of TRP channel-related long noncoding RNAs (TCRLs) on uveal melanoma (UM) remains poorly understood. Methods: We employed bioinformatics to examine the RNA-seq data and relevant clinical information of UM in the TCGA databases. By implementing coexpression analysis, we identified differentially expressed TCRLs. Using univariate Cox regression analysis, selection operator (LASSO) algorithm and stepwise regression, five key prognostic biomarkers were chosen. The high- and low-risk groups were divided based on the risk scores. Afterwards, the prediction performance of the signature was evaluated by receiver operating characteristic (ROC) curve and Kaplan-Meier (K-M) survival analysis. The functional enrichment analysis of TCRLs was also investigated. Following that, we examined immune cell infiltration, immune checkpoint expression, and tumor immune microenvironment between patients in high and low risk groups. TCRLs were validated using Random forests and multifactor Cox analysis. Candidate biomarkers were identified and screened. Finally, the effects of the candidate biomarkers on the proliferation, migration and invasion of UM cells were detected by CCK-8 assay, migration assay and perforation invasion assay. Results: The risk score generated by five TCRLs demonstrated robust predictive power. The high-risk group exhibited a poorer prognosis, increased immune cell infiltration, and an active tumor immune microenvironment compared to the low-risk group. Furthermore, two TCRLs of risk score, AC092535.4 and LINC01637, were screened to multiplex modelling. The in vitro experiments demonstrated that UM cells were suppressed following AC092535.4 or LINC01637 knockdown. Discussion: Two TCRLs, AC092535.4 and LINC01637, serve as novel prognostic biomarkers for uveal melanoma and may present potential therapeutic targets. [ABSTRACT FROM AUTHOR]

Strengthening industrial pollution control in the Yangtze River is a fundamental national policy of China. There is a lack of detailed distribution of chemical industrial parks (CIPs). This Study utilized random forest (RF) and active learning to generate the distribution map of CIPs along the Yangtze River at 10-m resolution. Based on Sentinel-2 imagery, spectral and texture features are extracted. Combined with the Points of Interest (POI), a multidimensional feature space is constructed. By employing partitioned training, classification of CIPs map is achieved on Google Earth Engine (GEE). Technical validation along the entire Yangtze River demonstrates a model accuracy of 80%. Compared to traditional manual survey methods, this approach saves significant time and economic costs while also being timelier. As the first publicly available CIPs map within a 5-km range along the Yangtze River, this research will provide a scientific basis for the fine governance of chemical industries in the region. Additionally, it offers a model guide for the accurate identification of the chemical industry. [ABSTRACT FROM AUTHOR]

Introduction: Clinical reasoning in veterinary medicine is often based on clinicians' personal experience in combination with information derived from publications describing cohorts of patients. Studies on the use of scientific methods for patient individual decision making are largely lacking. This applies to the prediction of the individual underlying pathology in seizuring dogs as well. The aim of this study was to apply machine learning to the prediction of the risk of structural epilepsy in dogs with seizures. Materials and methods: Dogs with a history of seizures were retrospectively as well as prospectively included. Data about clinical history, neurological examination, diagnostic tests performed as well as the final diagnosis were collected. For data analysis, the Bayesian Network and Random Forest algorithms were used. A total of 33 features for Random Forest and 17 for Bayesian Network were available for analysis. The following four feature selection methods were applied to select features for further analysis: Permutation Importance, Forward Selection, Random Selection and Expert Opinion. The two algorithms Bayesian Network and Random Forest were trained to predict structural epilepsy using the selected features. Results: A total of 328 dogs of 119 different breeds were identified retrospectively between January 2017 and June 2021, of which 33.2% were diagnosed with structural epilepsy. An overall of 89,848 models were trained. The Bayesian Network in combination with the Random feature selection performed best. It was able to predict structural epilepsy with an accuracy of 0.969 (sensitivity: 0.857, specificity: 1.000) among all dogs with seizures using the following features: age at first seizure, cluster seizures, seizure in last 24 h, seizure in last 6 month, and seizure in last year. Conclusion: Machine learning algorithms such as Bayesian Networks and Random Forests identify dogs with structural epilepsy with a high sensitivity and specificity. This information could provide some guidance to clinicians and pet owners in their clinical decision-making process. [ABSTRACT FROM AUTHOR]

Mangroves are unique coastal blue carbon ecosystems in tropical and subtropical areas. However, the dynamic changes of their carbon storage are rarely reported. Based on ground sample points and WorldView-3 high-resolution remote sensing images obtained in 2017, we identified the canopy of dominant mangrove communities in Futian mangrove utilizing random forest algorithm and object-oriented classification methods, and inverted and calculated the area of each dominant community. We then calculated the carbon storage of each dominant community combining the field survey data in 2017, 2020 and 2023, and obtained the spatial distribution and interannual dynamic changes of carbon storage of mangrove communities. The results were as follows: (1) The overall accuracy of the random forest algorithm for canopy identification was 82.29%, with a Kappa coefficient of 0.77; Futian mangrove spaned an area of 93.84 hm², with Kandelia obovata having the largest distribution area of 49.96 hm², followed by Avicennia marina, Sonneratia caseolaris, S. apetala, and Bruguiera gymnorhiza, with respective areas of 26.23, 8.90, 6.52, and 0.50 hm². (2) The total carbon storage of Kandelia obovata community was the highest, followed by Avicennia marina, Sonneratia caseolaris, S. apetala, and Bruguiera gymnorhiza the lowest. The carbon density in Sonneratia apetala and S. caseolaris community showed an increasing trend, and S. apetala community revealed the highest among the five dominant communities. The carbon density of Kandelia obovata community increased first and then decreased, while Avicennia marina community showed a downward trend consistently, and carbon density in Bruguiera gymnorhiza community did not vary significantly. In summary, the carbon storage of mangrove dominant communities in Futian did not change much from 2017 to 2023. The carbon sequestration capacity of mangrove in Kandelia obovata, Sonneratia apetala and S. caseolaris communities was stronger. The carbon density of Avicennia marina community decreased year by year, while that of Bruguiera gymnorhiza community was relatively stable. These results provide foundational data for evaluating the carbon sequestration capacities of different dominant communities in Futian mangrove, in tandem with scientific support for subsequent mangrove restoration and management. [ABSTRACT FROM AUTHOR]

BACKGROUND: The field of toxicology has witnessed substantial advancements in recent years, particularly with the adoption of new approach methodologies (NAMs) to understand and predict chemical toxicity. Class-based methods such as clustering and classification are key to NAMs development and application, aiding the understanding of hazard and risk concerns associated with groups of chemicals without additional laboratory work. Advances in computational chemistry, data generation and availability, and machine learning algorithms represent important opportunities for continued improvement of these techniques to optimize their utility for specific regulatory and research purposes. However, due to their intricacy, deep understanding and careful selection are imperative to align the adequate methods with their intended applications. OBJECTIVES: This commentary aims to deepen the understanding of class-based approaches by elucidating the pivotal role of chemical similarity (structural and biological) in clustering and classification approaches (CCAs). It addresses the dichotomy between general end point–agnostic similarity, often entailing unsupervised analysis, and end point–specific similarity necessitating supervised learning. The goal is to highlight the nuances of these approaches, their applications, and common misuses. DISCUSSION: Understanding similarity is pivotal in toxicological research involving CCAs. The effectiveness of these approaches depends on the right definition and measure of similarity, which varies based on context and objectives of the study. This choice is influenced by how chemical structures are represented and the respective labels indicating biological activity, if applicable. The distinction between unsupervised clustering and supervised classification methods is vital, requiring the use of end point–agnostic vs. end point–specific similarity definition. Separate use or combination of these methods requires careful consideration to prevent bias and ensure relevance for the goal of the study. Unsupervised methods use end point– agnostic similarity measures to uncover general structural patterns and relationships, aiding hypothesis generation and facilitating exploration of datasets without the need for predefined labels or explicit guidance. Conversely, supervised techniques demand end point–specific similarity to group chemicals into predefined classes or to train classification models, allowing accurate predictions for new chemicals. Misuse can arise when unsupervised methods are applied to end point–specific contexts, like analog selection in read-across, leading to erroneous conclusions. This commentary provides insights into the significance of similarity and its role in supervised classification and unsupervised clustering approaches. [ABSTRACT FROM AUTHOR]

Pineapple is one of the most important tropical fruit species, widely cultivated and economically important in Benin. This study aimed to identify potentially favorable areas for the cultivation of pineapple under current and future environmental conditions in Benin. The two cultivars of pineapple grown in Benin were separately considered: Sugarloaf and Smooth Cayenne. Five (05) modeling algorithms such as Maxent, Random Forest (RF), Support-Vector Machines (SVM), Boosted Regression Trees (BRT) and Generalized Linear Model (GLM) were compared using the criteria: area under the curve (AUC), sensitivity, specificity, Cohen’s Kappa, deviance and True Skill Statistic (TSS). The future climate models available for Africa at horizon 2055 were used under the “Representative Concentration Pathways” scenario 4.5 and 8.5. Results suggested that pineapple suitable areas were governed by a combination of effects of climate (temperature and precipitation) and soils characteristics. Indeed, soil pH, temperature seasonality and precipitation of driest quarter were the main variables driving pineapple production in Benin. Results also indicated that RF was the most suitable technique to model the distribution of pineapples regardless of the variety. The current potential range of favorable areas for the two varieties was mainly found in the central and southern parts of the country. In the future, following the RCP4.5 scenario, there will be an increase in the area favorable for the cultivation of Smooth Cayenne variety by 5.28% compared to the current situation whereas, the area favorable for the cultivation of the Sugarloaf variety will be increased by 7.7%. However, suitable areas for cultivation of Smooth Cayenne and Sugarloaf following the RCP8.5 scenario will be increased, respectively by 21.82% and 31.64%. The low and medium suitability areas for the cultivation of smooth cayenne will decrease by 15.57% and 2.93%, respectively at the horizon 2055 with future conditions under RCP4.5, and 15.48% and 4.97%, respectively at the horizon 2055 with future conditions under RCP8.5. For sugarloaf, the low and medium suitable cultivation areas will decrease by 1.59% and 14.24, respectively at the horizon 2055 with future conditions under RCP4.5. According to RCP8.5, the low suitable areas will decrease by 5.08%. This study constitutes an initial step towards a sustainable scheme for planning exploration of the possibility of extending pineapple cultivation in Benin. [ABSTRACT FROM AUTHOR]

Purpose: Discrete choice experiment (DCE) and profile case (case 2) best-worst scaling (BWS) present uncertainties regarding the acceptability of quantifying individual healthcare preferences, which may adversely affect the validity of responses and impede the reflection of true healthcare preferences. This study aimed to assess the acceptability of these two methods from the perspective of patients with type 2 diabetes mellitus (T2DM) and examine their association with specific characteristics of the target population. Patients and Methods: This cross-sectional study was based on a nationally representative survey; data were collected using a multistage stratified cluster-sampling procedure between September 2021 and January 2022. Eligible adults with confirmed T2DM voluntarily participated in this study. Participants completed both the DCE and case 2 BWS (BWS-2) choice tasks in random order and provided self-reported assessments of acceptability, including task completion difficulty, comprehension of task complexity, and response preference. Logistic regression and random forest models were used to identify variables associated with acceptability. Results: In total, 3286 patients with T2DM were included in the study. Respondents indicated there was no statistically significant difference in completion difficulty between the DCE and BWS-2, although the DCE scores were slightly higher (3.07 ± 0.68 vs 3.03 ± 0.67, P = 0.06). However, 1979 (60.2%) respondents found the DCE easier to comprehend. No significant preferences were observed between the two methods (1638 (49.8%) vs 1648 (50.2%)). Sociodemographic factors, such as residence, monthly out-of-pocket costs, and illness duration were significantly associated with comprehension complexity and response preference. Conclusion: This study yielded contrasting results to most of previous studies, suggesting that DCE may be less cognitively demanding and more suitable for patients with T2DM from the perspective of self-reported acceptability of DCE and BWS. This study promotes a focus on patient acceptability in quantifying individual healthcare preferences to inform tailored optimal stated-preference method for a target population. Plain Language Summary: Stated preference methodologies such as the discrete choice experiment (DCE) and case 2 best-worst scaling (BWS-2) are gaining popularity as methods for quantifying individual preferences in healthcare. However, the acceptability of the two methods to participants must be considered in practice to reduce cognitive burden and ensure the validity of preference elicitation.DCE was perceived to be less cognitively burdensome than BWS-2. In contrast to patients who thought that DCE was more acceptable, BWS-2 was more accepted by rural patients, patients who lived with the disease for a longer period, and those who had lower monthly out-of-pocket costs.These findings demonstrate potential differences in the acceptability of DCE and BWS-2 for patients with type 2 diabetes mellitus. To improve efficiency, it would be useful for researchers to consider the optimal stated preference method for identifying target populations according to sociodemographic and disease-related characteristics. [ABSTRACT FROM AUTHOR]

This research addresses the presence of substances of very high concern (SVHCs) confronting the drinking water sector. Responding adequately to the potential hazards by SVHCs, knowledge of emission pathways, toxicity, presence in drinking water sources, and removability during water production is crucial. As this information cannot be received for each compound individually, we employed a detailed clustering approach based on chemical properties and structures of SVHCs from lists with over 1,000 compounds. Through this process, 915 substances were divided into 51 clusters. We tested this clustering in risk assessment. To assess the risks, we developed toxicity prediction models utilizing random forests and multiple linear regression. These models were applied to make toxicity predictions for the list of compounds. This study shows that clustering is a viable approach to reducing sample size. In addition, the toxicity models provide insights into the potential human health risks. This research contributes to more informed decision-making and improved risk assessment in the drinking water sector, aiding in the protection of human health and the environment. This principle is generally applicable. If in a group a suitable representative is found, data from experiments with this compound can be used to gauge the behaviour of chemicals in this group. [ABSTRACT FROM AUTHOR]

Objective To analyze risk factors for occupational blood-borne exposures among healthcare workers, providing a basis for timely and targeted interventions to prevent occupational blood-borne exposure. Methods The study included 103 healthcare workers who reported occupational blood-borne exposures from January 2016 to June 2023 at a tertiary hospital in Hulunbuir as the exposure group and 625 healthcare workers from the same shifts who did not experience occupational exposures as the control group. Relevant information was collected for all subjects. Random Forest algorithms and multivariate logistic regression analysis were used to construct predictive models for occupational blood-borne exposure among healthcare workers. Results Among the 103 blood-borne exposure cases, the main exposure site was the hand in 89 cases (86.41%); the main mode of exposure was sharp force injury in 83 cases (80.58%); and the predominant exposure source was hepatitis B virus (HBV) in 65 cases (63.11%). Sixty-five cases (63.11%) were reported immediately after exposure, while 24 cases (23.30%) were reported within 12 hours. Logistic regression analysis revealed that compared to healthcare workers aged 30 years or more, likelihood of occupational blood-borne exposure increased to 4.142 times for those under 30 years (P < 0.05) ; compared with 5 or more years, the likelihood of occupational blood-borne exposure increased to 1.696 times for healthcare workers with less than 5 years of service (P < 0.05) the likelihood of occupational blood-borne exposure increased to 5.989 times for junior-title healthcare workers compared to intermediate and higher- level titles (P < 0.05); healthcare workers who attended occupational protection training only once per year were up to 1.864 times more likely to have occupational blood-borne exposure compared to those who participated multiple times annually (P < 0.05); the likelihood of occupational blood-borne exposure increased to 2.205 times for healthcare workers in the departmental categories of emergency, critical care, and operating room compared to those in other departments (P < 0.05). The Random Forest algorithm identified the top 6 influential factors in order of importance as professional title, age, years of work experience, annual training frequency of occupational protection, occupation type, and education level. The Random Forest predictive model demonstrated higher accuracy, precision, recall, and FI score (the reconciled mean of precision and recall) compared to the logistic regression model. The area under the receiver operating characteristic curve (AUC) for the Random Forest model was 0.829 (P < 0.001) which was also higher than that of the logistic regression model of 0.818 (P < 0.001). Conclusions The Random Forest model showed superior predictive performance for occupational blood-borne exposures, while the logistic regression model provided more intuitive analytical results. The combined use of both models can further enhance prediction accuracy. Enhanced training should be provided for high-risk groups, including younger healthcare workers, those with less work experience, and those with lower professional titles. Standardized measures should be implemented to prevent blood-borne exposure among healthcare workers. [ABSTRACT FROM AUTHOR]

China has undergone rapid urbanization and internal migration in the past few years, and its up-to-date gridded population datasets are essential for various applications. Existing datasets for China, however, suffer from either outdatedness or failure to incorporate data from the latest Seventh National Population Census of China, conducted in 2020. In this study, we develop a novel population downscaling approach that leverages stacking ensemble learning and big geospatial data to produce up-to-date population grids at a 100 m resolution for China using seventh census data at both county and town levels. The proposed approach employs stacking ensemble learning to integrate the strengths of random forest, XGBoost, and LightGBM through fusing their predictions in a training mechanism, and it delineates the inhabited areas from big geospatial data to enhance the gridded population estimation. Experimental results demonstrate that the proposed approach exhibits the best-fit performance compared to individual base models. Meanwhile, the out-of-sample town-level test set indicates that the estimated gridded population dataset (R2=0.8936) is more accurate than existing WorldPop (R2=0.7427) and LandScan (R2=0.7165) products for China in 2020. Furthermore, with the inhabited area enhancement, the spatial distribution of population grids is intuitively more reasonable than the two existing products. Hence, the proposed population downscaling approach provides a valuable option for producing gridded population datasets. The estimated 100 m gridded population dataset of China holds great significance for future applications, and it is publicly available at https://doi.org/10.6084/m9.figshare.24916140.v1 (Chen et al., 2024b). [ABSTRACT FROM AUTHOR]

Coastal wetland ecosystems in the Gulf of Mexico provide a variety of services including high rates of carbon sequestration and storage, making their assessment and conservation essential. This study aimed to determine the spatial distribution of carbon stocks in protected and non-protected coastal wetland ecosystems along the Gulf of Mexico in Mexico. Aboveground carbon (AGC) and belowground carbon (BGC) stocks were quantified using predictive random forest models. The study analyzed carbon estimates in AGC and BGC across different coastal wetland ecosystems and assessed the carbon storage of protected areas (PAs) and non-protected areas (non-PAs) for carbon conservation. Field surveys provided biomass and soil carbon data for modeling training, incorporating environmental features such as canopy height, vegetation indices, and soil characteristics. The results reveal differences in carbon stocks quantities among various vegetation types, with mixed mangroves exhibiting the highest AGC stock (93.7 ± 8.4 Mg C ha−1) and herbaceous wetlands displaying the smallest range (3.9 ± 1.3 Mg C ha−1) across sites. Notably, cattail marshes showed the highest average BGC stocks (505.6 ± 86.8 Mg C ha−1), influenced by factors such as soil characteristics and land cover. Spatial distribution maps of AGC and BGC provided insights into areas of high and low carbon storage. Interestingly, non-PAs showed higher carbon stocks than certain PAs, emphasizing the importance of including both protected and non-protected areas in conservation efforts. These findings highlight the significance of carbon storage across coastal wetland ecosystems, and the need for comprehensive conservation strategies to preserve their valuable ecosystem services. [ABSTRACT FROM AUTHOR]

Objective: Compared to Mimas pigeons, Shiqi pigeons exhibit greater tolerance to coarse feeding because of their abundant gut microbiota. Here, to investigate the potential of utilizing intestinal flora derived from Shiqi pigeons, the intestinal flora and body indices of Mimas squabs were evaluated after fecal microbiota transplantation (FMT) from donors. Methods: A total of 90 one-day-old squabs were randomly divided into the control group (CON), the low-concentration group (LC) and the high-concentration group (HC): gavaged with 200 μL of bacterial solution at concentrations of 0, 0.1, and 0.2 g/15 mL, respectively. Results: The results suggested that FMT improved the body weight of Mimas squabs in the HC and LC groups (p<0.01), and 0.1 g/15 mL was the optimal dose during FMT. After 16S rRNA sequencing was performed, compared to those in the CON group, the abundance levels of microflora, especially Lactobacillus, Muribaculaceae, and Megasphaera (p<0.05), in the FMT-treated groups were markedly greater. Random forest analysis indicated that the main functions of key microbes involve pathways associated with metabolism, further illustrating their important role in the host body. Conclusion: FMT has been determined to be a viable method for augmenting the weight and intestinal microbiota of squabs, representing a unique avenue for enhancing the economic feasibility of squab breeding. [ABSTRACT FROM AUTHOR]

In vivo assessments of influenza A virus (IAV) pathogenicity and transmissibility in ferrets represent a crucial component of many pandemic risk assessment rubrics, but few systematic efforts to identify which data from in vivo experimentation are most useful for predicting pathogenesis and transmission outcomes have been conducted. To this aim, we aggregated viral and molecular data from 125 contemporary IAV (H1, H2, H3, H5, H7, and H9 subtypes) evaluated in ferrets under a consistent protocol. Three overarching predictive classification outcomes (lethality, morbidity, transmissibility) were constructed using machine learning (ML) techniques, employing datasets emphasizing virological and clinical parameters from inoculated ferrets, limited to viral sequence-based information, or combining both data types. Among 11 different ML algorithms tested and assessed, gradient boosting machines and random forest algorithms yielded the highest performance, with models for lethality and transmission consistently better performing than models predicting morbidity. Comparisons of feature selection among models was performed, and highest performing models were validated with results from external risk assessment studies. Our findings show that ML algorithms can be used to summarize complex in vivo experimental work into succinct summaries that inform and enhance risk assessment criteria for pandemic preparedness that take in vivo data into account. Use of machine learning to summarize complex in vivo data and provide predictive utility for Influenza A virus ferret lethality, morbidity, and transmission models. [ABSTRACT FROM AUTHOR]

Simple Summary: Fetal macrosomia is when a baby's weight at birth is equal to or greater than 4000 g or 4500 g. The rising incidence of macrosomia poses a significant challenge in obstetrics, as it can have serious health consequences for both mothers and babies. The maternal gut microbiome can influence the health of pregnant women and their babies, with potential effects on birth weight. However, research on the link between the microbiome and birth weight, especially macrosomia, is limited; further investigation is needed. Here, we discovered a connection between the maternal gut microbiome and macrosomia. Our findings present novel opportunities for preventing macrosomia by manipulating the composition of the intestinal microbiota. Early prediction models using gut microbiota and clinical indicators can predict macrosomia. Fetal macrosomia is defined as a birthweight ≥4000 g and causes harm to pregnant women and fetuses. Studies reported that the maternal intestinal microbiome plays a key role in the establishment, growth, and development of the fetal intestinal microbiome. However, whether there is a relationship between maternal gut microbiota and macrosomia remains unclear. Our study aimed to identify gut microbiota that may be related to the occurrence of macrosomia, explore the possible mechanisms by which it causes macrosomia, and establish a prediction model to determine the feasibility of predicting macrosomia by early maternal gut microbiota. We conducted a nested case-control study based on an early pregnancy cohort (ChiCTR1900020652) in the Maternity and Child Health Hospital of Hunan Province on fecal samples of 93 women (31 delivered macrosomia as the case group and 62 delivered normal birth weight newborns as the control group) collected and included in this study. We performed metagenomic analysis to compare the composition and function of the gut microbiome between cases and controls. Correlation analysis was used to explore the association of differential species and differential functional pathways. A random forest model was used to construct an early pregnancy prediction model for macrosomia. At the species level, there were more Bacteroides salyersiae, Bacteroides plebeius, Ruminococcus lactaris, and Bacteroides ovatus in the intestinal microbiome of macrosomias' mothers compared with mothers bearing fetuses that had normal birth weight. Functional pathways of the gut microbiome including gondoate biosynthesis, L-histidine degradation III, cis-vaccenate biosynthesis, L-arginine biosynthesis III, tRNA processing, and mannitol cycle, which were more abundant in the macrosomia group. Significant correlations were found between species and functional pathways. Bacteroides plebeius was significantly associated with the pathway of cis-vaccenate biosynthesis (r = 0.28, p = 0.005) and gondoate biosynthesis (r = 0.28, p < 0.001) and Bacteroides ovatus was positively associated with the pathway of cis-vaccenate biosynthesis (r = 0.29, p = 0.005) and gondoate biosynthesis (r = 0.32, p = 0.002). Bacteroides salyersiae was significantly associated with the pathway of cis-vaccenate biosynthesis (r = 0.24, p = 0.018), gondoate biosynthesis (r = 0.31, p = 0.003), and L–histidine degradation III (r = 0.22, p = 0.291). Finally, four differential species and four clinical indicators were included in the random forest model for predicting macrosomia. The areas under the working characteristic curves of the training and validation sets were 0.935 (95% CI: 0.851~0.979) and 0.909 (95% CI: 0.679~0.992), respectively. Maternal gut microbiota in early pregnancy may play an important role in the development of macrosomia and can be used as potential predictors to prevent macrosomia. [ABSTRACT FROM AUTHOR]

As global climate change intensifies, nations around the world are implementing policies aimed at reducing emissions, with carbon-trading mechanisms emerging as a key market-based tool. China has launched carbon-trading markets in several cities, achieving significant trading volumes. Carbon-trading mechanisms encompass cap-and-trade markets and voluntary markets, influenced by various factors, including policy changes, economic conditions, energy prices, and climate fluctuations. The complexity of these factors, coupled with the nonlinear and non-stationary nature of carbon prices, makes forecasting a substantial challenge. This paper proposes a dynamic weight hybrid forecasting model based on a dual sliding window approach, effectively integrating multiple forecasting models such as LSTM, Random Forests, and LASSO. This model facilitates a thorough analysis of the influences of policy, market dynamics, technological advancements, and climatic conditions on carbon pricing. It serves as a potent tool for predicting carbon market price fluctuations and offers valuable decision support to stakeholders in the carbon market, ultimately aiding in the global efforts towards emission reduction and achieving sustainable development goals. [ABSTRACT FROM AUTHOR]

Given the complex powertrain of fuel cell electric vehicles (FCEVs) and diversified vehicle platooning synergy constraints, a control strategy that simultaneously considers inter-vehicle synergy control and energy economy is one of the key technologies to improve transportation efficiency and release the energy-saving potential of platooning vehicles. In this paper, an energy-oriented hybrid cooperative adaptive cruise control (eHCACC) strategy is proposed for an FCEV platoon, aiming to enhance energy-saving potential while ensuring stable car-following performance. The eHCACC employs a hybrid cooperative control architecture, consisting of a top-level centralized controller (TCC) and bottom-level distributed controllers (BDCs). The TCC integrates an eco-driving CACC (eCACC) strategy based on the minimum principle and random forest, which generates optimal reference velocity datasets by aligning the comprehensive control objectives of the platoon and addressing the car-following performance and economic efficiency of the platoon. Concurrently, to further unleash energy-saving potential, the BDCs utilize the equivalent consumption minimization strategy (ECMS) to determine optimal powertrain control inputs by combining the reference datasets with detailed optimization information and system states of the powertrain components. A series of simulation evaluations highlight the improved car-following stability and energy efficiency of the FCEV platoon. [ABSTRACT FROM AUTHOR]

Functional mobility tests, such as the L test of functional mobility, are recommended to provide clinicians with information regarding the mobility progress of lower-limb amputees. Smartphone inertial sensors have been used to perform subtask segmentation on functional mobility tests, providing further clinically useful measures such as fall risk. However, L test subtask segmentation rule-based algorithms developed for able-bodied individuals have not produced sufficiently acceptable results when tested with lower-limb amputee data. In this paper, a random forest machine learning model was trained to segment subtasks of the L test for application to lower-limb amputees. The model was trained with 105 trials completed by able-bodied participants and 25 trials completed by lower-limb amputee participants and tested using a leave-one-out method with lower-limb amputees. This algorithm successfully classified subtasks within a one-foot strike for most lower-limb amputee participants. The algorithm produced acceptable results to enhance clinician understanding of a person's mobility status (>85% accuracy, >75% sensitivity, >95% specificity). [ABSTRACT FROM AUTHOR]

A deep-seated landslide could release numerous microseismic signals from creep-slip movement, which includes a rock-soil slip from the slope surface and a rock-soil shear rupture in the subsurface. Machine learning can effectively enhance the classification of microseismic signals in landslide seismic monitoring and interpret the mechanical processes of landslide motion. In this paper, eight sets of triaxial seismic sensors were deployed inside the deep-seated landslide, Jiuxianping, China, and a large number of microseismic signals related to the slope movement were obtained through 1-year-long continuous monitoring. All the data were passed through the seismic event identification mode, the ratio of the long-time average and short-time average. We selected 11 days of data, manually classified 4131 data into eight categories, and created a microseismic event database. Classical machine learning algorithms and ensemble learning algorithms were tested in this paper. In order to evaluate the seismic event classification performance of each algorithmic model, we evaluated the proposed algorithms through the dimensions of the accuracy, precision, and recall of each model. The validation results demonstrated that the best performing decision tree algorithm among the classical machine learning algorithms had an accuracy of 88.75%, while the ensemble algorithms, including random forest, Gradient Boosting Trees, Extreme Gradient Boosting, and Light Gradient Boosting Machine, had an accuracy range from 93.5% to 94.2% and also achieved better results in the combined evaluation of the precision, recall, and F1 score. The specific classification tests for each microseismic event category showed the same results. The results suggested that the ensemble learning algorithms show better results compared to the classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

Cyber-security challenges are growing globally and are specifically targeting critical infrastructure. Conventional countermeasure practices are insufficient to provide proactive threat hunting. In this study, random forest (RF), support vector machine (SVM), multi-layer perceptron (MLP), AdaBoost, and hybrid models were applied for proactive threat hunting. By automating detection, the hybrid machine learning-based method improves threat hunting and frees up time to concentrate on high-risk warnings. These models are implemented on approach devices, access, and principal servers. The efficacy of several models, including hybrid approaches, is assessed. The findings of these studies are that the AdaBoost model provides the highest efficiency, with a 0.98 ROC area and 95.7% accuracy, detecting 146 threats with 29 false positives. Similarly, the random forest model achieved a 0.98 area under the ROC curve and a 95% overall accuracy, accurately identifying 132 threats and reducing false positives to 31. The hybrid model exhibited promise with a 0.89 ROC area and 94.9% accuracy, though it requires further refinement to lower its false positive rate. This research emphasizes the role of machine learning in improving cyber-security, particularly for critical infrastructure. Advanced ML techniques enhance threat detection and response times, and their continuous learning ability ensures adaptability to new threats. [ABSTRACT FROM AUTHOR]

The detection performance of radar is significantly impaired by active jamming and mutual interference from other radars. This paper proposes a radio signal modulation recognition method to accurately recognize these signals, which helps in the jamming cancellation decisions. Based on the ensemble learning stacking algorithm improved by meta-feature enhancement, the proposed method adopts random forests, K-nearest neighbors, and Gaussian naive Bayes as the base-learners, with logistic regression serving as the meta-learner. It takes the multi-domain features of signals as input, which include time-domain features including fuzzy entropy, slope entropy, and Hjorth parameters; frequency-domain features, including spectral entropy; and fractal-domain features, including fractal dimension. The simulation experiment, including seven common signal types of radar and active jamming, was performed for the effectiveness validation and performance evaluation. Results proved the proposed method's performance superiority to other classification methods, as well as its ability to meet the requirements of low signal-to-noise ratio and few-shot learning. [ABSTRACT FROM AUTHOR]

With the ongoing challenge of air pollution posing serious health and environmental threats, particularly in rapidly industrializing regions, accurate forecasting and effective pollutant identification are crucial for enhancing public health and ecological stability. This study aimed to optimize air quality management through the prediction of the Air Quality Index (AQI) and identification of air pollutants. Our study spans nine representative cities (Hohhot, Yinchuan, Lanzhou, Beijing, Taiyuan, Xi'an, Shanghai, Nanjing, Wuhan) in China, with data collected from January 1, 2015, to November 30, 2021. We proposed a new model for daily AQI prediction, termed VMD-CSA-CNN-LSTM, which employed advanced machine learning techniques, including convolutional neural networks (CNN) and long short-term memory (LSTM) networks, and leveraged the chameleon swarm algorithm (CSA) for hyperparameter optimization, integrated through a variational mode decomposition approach. The model was developed using data from Lanzhou, with a split ratio of 8:1:1 into training, validation, and test sets, achieving an RMSE of 2.25, MAPE of 0.02, adjusted R-squared of 98.91%, and training efficiency of 5.31%. The model was further externally validated in the other eight cities, yielding comparable results, with an adjusted R-squared above 96%, MAPE below 0.1, and RMSE below 7.5. Additionally, we employed a random forest algorithm to identify the primary pollutants contributing to AQI levels. Our results indicated that PM2.5 was the most significant pollutant in Beijing, Taiyuan, and Xi'an, while PM10 was dominant in Hohhot, Yinchuan, and Lanzhou. In Shanghai, Nanjing, and Wuhan, both PM2.5 and PM10 were critical, with ozone also identified as a major air pollutant. This study not only advances the predictive accuracy of AQI models but also aids policymakers by providing a reliable tool for air quality management and strategic planning aimed at pollution reduction. The integration of these advanced computational techniques into environmental monitoring practices offers a promising avenue for enhancing air quality and mitigating pollution-related risks. [ABSTRACT FROM AUTHOR]

The navigational accuracy of sea animals and trans-ocean birds provides inspiration in using geo-magnetic field (GMF) for realizing strategic truly autonomous underwater vehicles (AUV) capable of determining their absolute position on earth, without the aid of ship-referenced acoustic baseline systems. Supervised Machine Learning algorithms are applied on the GMF intensity data obtained from NOAA World Magnetic Model for a 900 km2 within the Indian mineral exploratory area in the Central Indian Ocean, with a resolution of 50 m, considering the sensitivity of commercially available magnetometers. It is identified that, for AUVs equipped with magnetometers with a detection sensitivity of 0.1 nT, the supervisory random forest regression and decision tree algorithm trained with priori GMF data, could provide trajectory guidance to AUVs with an absolute mean position accuracy in 2D plane, with reference to the last known position from Integrated Navigation system aided initially with GPS and with acoustic positioning in underwater. Circular Error Probable (CEP 50) of 53 m and 56 m, respectively. The scalar GMF anomaly navigation demonstrated to be a viable GPS-alternative navigation system could be extended to larger areas with inclination and declination vectors, as unique identifiers. [ABSTRACT FROM AUTHOR]

To optimize growth and management, precision agriculture relies on a deep understanding of agricultural dynamics, particularly crop water status analysis. Leveraging unmanned aerial vehicles, we can efficiently acquire high-resolution spatiotemporal samples by utilizing remote sensors. However, non-linear relationships among data features, localized within specific subgroups, frequently emerge in agricultural data. Interpreting these complex patterns requires sophisticated analysis due to the presence of noise, high variability, and non-stationarity behavior in the collected samples. Here, we introduce Local Biplot, a methodological framework tailored for discerning meaningful data patterns in non-stationary contexts for precision agriculture. Local Biplot relies on the well-known uniform manifold approximation and projection method, such as UMAP, and local affine transformations to codify non-stationary and non-linear data patterns while maintaining interpretability. This lets us find important clusters for transformation and projection within a single global axis pair. Hence, our framework encompasses variable and observational contributions within individual clusters. At the same time, we provide a relevance analysis strategy to help explain why those clusters exist, facilitating the understanding of data dynamics while favoring interpretability. We demonstrated our method's capabilities through experiments on both synthetic and real-world datasets, covering scenarios involving grass and rice crops. Moreover, we use random forest and linear regression models to predict water status variables from our Local Biplot-based feature ranking and clusters. Our findings revealed enhanced clustering and prediction capability while emphasizing the importance of input features in precision agriculture. As a result, Local Biplot is a useful tool to visualize, analyze, and compare the intricate underlying patterns and internal structures of complex agricultural datasets. [ABSTRACT FROM AUTHOR]

Wildfire susceptibility maps play a crucial role in preemptively identifying regions at risk of future fires and informing decisions related to wildfire management, thereby aiding in mitigating the risks and potential damage posed by wildfires. This study employs eXplainable Artificial Intelligence (XAI) techniques, particularly SHapley Additive exPlanations (SHAP), to map wildfire susceptibility in Izmir Province, Türkiye. Incorporating fifteen conditioning factors spanning topography, climate, anthropogenic influences, and vegetation characteristics, machine learning (ML) models (Random Forest, XGBoost, LightGBM) were used to predict wildfire-prone areas using freely available active fire pixel data (MODIS Active Fire Collection 6 MCD14ML product). The evaluation of the trained ML models showed that the Random Forest (RF) model outperformed XGBoost and LightGBM, achieving the highest test accuracy (95.6%). All of the classifiers demonstrated a strong predictive performance, but RF excelled in sensitivity, specificity, precision, and F-1 score, making it the preferred model for generating a wildfire susceptibility map and conducting a SHAP analysis. Unlike prevailing approaches focusing solely on global feature importance, this study fills a critical gap by employing a SHAP summary and dependence plots to comprehensively assess each factor's contribution, enhancing the explainability and reliability of the results. The analysis reveals clear associations between factors such as wind speed, temperature, NDVI, slope, and distance to villages with increased fire susceptibility, while rainfall and distance to streams exhibit nuanced effects. The spatial distribution of the wildfire susceptibility classes highlights critical areas, particularly in flat and coastal regions near settlements and agricultural lands, emphasizing the need for enhanced awareness and preventive measures. These insights inform targeted fire management strategies, highlighting the importance of tailored interventions like firebreaks and vegetation management. However, challenges remain, including ensuring the selected factors' adequacy across diverse regions, addressing potential biases from resampling spatially varied data, and refining the model for broader applicability. [ABSTRACT FROM AUTHOR]

Site-specific weed management employs image data to generate maps through various methodologies that classify pixels corresponding to crop, soil, and weed. Further, many studies have focused on identifying specific weed species using spectral data. Nonetheless, the availability of open-access weed datasets remains limited. Remarkably, despite the extensive research employing hyperspectral imaging data to classify species under varying conditions, to the best of our knowledge, there are no open-access hyperspectral weed datasets. Consequently, accessible spectral weed datasets are primarily RGB or multispectral and mostly lack the temporal aspect, i.e., they contain a single measurement day. This paper introduces an open dataset for training and evaluating machine-learning methods and spectral features to classify weeds based on various biological traits. The dataset comprises 30 hyperspectral images, each containing thousands of pixels with 204 unique visible and near-infrared bands captured in a controlled environment. In addition, each scene includes a corresponding RGB image with a higher spatial resolution. We included three weed species in this dataset, representing different botanical groups and photosynthetic mechanisms. In addition, the dataset contains meticulously sampled labeled data for training and testing. The images represent a time series of the weed's growth along its early stages, critical for precise herbicide application. We conducted an experimental evaluation to test the performance of a machine-learning approach, a deep-learning approach, and Spectral Mixture Analysis (SMA) to identify the different weed traits. In addition, we analyzed the importance of features using the random forest algorithm and evaluated the performance of the selected algorithms while using different sets of features. [ABSTRACT FROM AUTHOR]

The goal of this study was to develop a model describing the relationship between the ground-displacement-caused tremors induced by underground mining, and mining and geological factors using the Random Forest Regression machine learning method. The Rudna mine (Poland) was selected as the research area, which is one of the largest deep copper ore mines in the world. The SAR Interferometry methods, Differential Interferometric Synthetic Aperture Radar (DInSAR) and Small Baseline Subset (SBAS), were used in the first case to detect line-of-sight (LOS) displacements, and in the second case to detect cumulative LOS displacements caused by mining tremors. The best-prediction LOS displacement model was characterized by R2 = 0.93 and RMSE = 5 mm, which proved the high effectiveness and a high degree of explanation of the variation of the dependent variable. The identified statistically significant driving variables included duration of exploitation, the area of the exploitation field, energy, goaf area, and the average depth of field exploitation. The results of the research indicate the great potential of the proposed solutions due to the availability of data (found in the resources of each mine), and the effectiveness of the methods used. [ABSTRACT FROM AUTHOR]

The eastern coastline of James Bay is known to have been home to sizeable eelgrass beds (Zostera marina L.) which thrived in the bay's shallow, subarctic waters. The region was subjected to substantial hydroelectric dams, large fires, and other human activities in the past half-century. To assess the impact of these factors on eelgrass beds, a historical reconstruction of eelgrass bed distribution was performed from images acquired by Landsat-5 Thematic Mapper (TM) in 1988, 1991, and 1996 and images of the Landsat-8 Operational Land Imager (OLI) in 2019. All the images were classified using the Random Forests classifier (RF) and assessed for accuracy each year on a bay-wide scale using an independent field validation dataset. The validation data were extracted from an eelgrass bed map established using aerial photos and field surveys in 1986, 1991, and 1995 and from a field survey in 2019. The overall validation accuracy of the classified images (between 72% and 85%) showed good agreement with the other datasets for most locations, providing reassurance about the reliability of the research. This makes it possible to use satellite imagery to detect past changes to eelgrass distribution within a bay. The classified images of 1988 and 1996 were also compared to aerial photos taken in years close to each other at ten sites to determine their ability to assess small eelgrass beds' shape and presence. Such a comparison revealed that the classified images accurately portrayed eelgrass distribution even at finer scales. [ABSTRACT FROM AUTHOR]

On a global scale, wetlands are suffering from a steady decline in surface area and environmental quality. Protecting them is essential and requires a careful spatialisation of their natural habitats. Traditionally, in our study area, species discrimination for floristic mapping has been achieved through on-site field inventories, but this approach is very time-consuming in these difficult-to-access environments. Usually, the resulting maps are also not spatially exhaustive and are not frequently updated. In this paper, we propose to establish a complete map of the study area using remote sensors and set up a long-term and regular observatory of environmental changes to monitor the evolution of a major French wetland. This methodology combines three dataset acquisition technologies, airborne hyperspectral and WorldView-3 multispectral images, supplemented by LiDAR images, which we compared to evaluate the difference in performances. To do so, we applied the Random Forest supervised classification methods using ground reference areas and compared the out-of-bag score (OOB score) as well as the matrix of confusion resulting from each dataset. Thirteen habitats were discriminated at level 4 of the European Nature Information System (EUNIS) typology, at a spatial resolution of around 1.2 m. We first show that a multispectral image with 19 variables produces results which are almost as good as those produced by a hyperspectral image with 58 variables. The experiment with different features also demonstrates that the use of four bands derived from LiDAR datasets can improve the quality of the classification. Invasive alien species Ludwigia grandiflora and Crassula helmsii were also detected without error which is very interesting when applied to these endangered environments. Therefore, since WV-3 images provide very good results and are easier to acquire than airborne hyperspectral data, we propose to use them going forward for the regular observation of the Brière marshes habitat we initiated. [ABSTRACT FROM AUTHOR]

Effective planning and management strategies for restoring and conserving tropical peat swamp ecosystems require accurate and timely estimates of aboveground biomass (AGB), especially when monitoring the impacts of restoration interventions. The aim of this research is to assess changes in AGB and evaluate the effectiveness of restoration efforts in the North Selangor Peat Swamp Forest (NSPSF), one of the largest remaining peat swamp forests in Peninsular Malaysia, using advanced remote sensing techniques. A Random Forest machine learning method was employed to upscale AGB estimates, derived from a 'LiDAR AGB model', to larger landscape-scale areas with Sentinel-2 spectral and textural variables. The time period under investigation (2015–2018) marked a concentrated phase of restoration and regeneration efforts in NSPSF. The results demonstrate an overall increase in tropical peat swamp AGB during these years, where the total amount of estimated AGB stored in NSPSF increased from 19.3 Tg in 2015 to an estimated 19.8 Tg in 2018. The research found that a tailored variable selection approach improved predictions of AGB, with optimised input variables (n = 62) and parameter adjustments producing a good plausible result (R2 = 0.80; RMSE = 55.2 Mg/ha). This paper concludes by emphasizing the importance of long-term studies (>5 years) for analyzing the success of tropical peat swamp restoration methods, with a potential for integrating remote sensing technology. [ABSTRACT FROM AUTHOR]

Accurate and timely prediction of crop yields is crucial for ensuring food security and promoting sustainable agricultural practices. This study developed a winter wheat yield prediction model using machine learning techniques, incorporating remote sensing data and statistical yield records from Henan Province, China. The core of the model is an ensemble voting regressor, which integrates ridge regression, gradient boosting, and random forest algorithms. This study optimized the hyperparameters of the ensemble voting regressor and conducted an in-depth comparison of its yield prediction performance with that of other mainstream machine learning models, assessing the impact of key hyperparameters on model accuracy. This study also explored the potential of yield prediction at different growth stages and its application in yield spatialization. The results demonstrate that the ensemble voting regressor performed exceptionally well throughout the entire growth period, with an R2 of 0.90, an RMSE of 439.21 kg/ha, and an MAE of 351.28 kg/ha. Notably, during the heading stage, the model's prediction performance was particularly impressive, with an R2 of 0.81, an RMSE of 590.04 kg/ha, and an MAE of 478.38 kg/ha, surpassing models developed for other growth stages. Additionally, by establishing a yield spatialization model, this study mapped county-level yield predictions to the pixel level, visually illustrating the spatial differences in land productivity. These findings provide reliable technical support for winter wheat yield prediction and valuable references for crop yield estimation in precision agriculture. [ABSTRACT FROM AUTHOR]

Vegetation indices are widely used to assess vegetation dynamics. The Normalized Vegetation Index (NDVI) is the most widely used metric in agriculture, frequently as a proxy for different physiological and agronomical aspects, such as crop yield or biomass, crop density, or drought stress. Much effort has therefore been directed to NDVI forecasting, which is usually correlated with precipitation. However, in Mediterranean and arid climates, the relationship is more complex due to prolonged dry periods and sparse precipitation events. In this study, we forecast the NDVI 7 and 30 days ahead for Mediterranean permanent grasslands using a machine learning Random Forest (RF) model for the period from 2015 to 2022. The model compares two soil moisture products as predictors: simulated soil moisture values based on in situ soil moisture sensor observations and remote sensing-derived observations of Soil Water Index (SWI) values. We further analyzed the anomalies of the predicted NDVI using the z-score. The results show that both products can be used as reliable predictors for permanent grasslands in Mediterranean areas. Predictions at 7 days are more accurate and better forecast the negative effect of drought on vegetation dynamics than those at 30 days. This study shows the potential of using a simple methodology and readily available data to predict the grassland growth dynamics in the Mediterranean area. [ABSTRACT FROM AUTHOR]

Crop models are instrumental in simulating resource utilization in agriculture, yet their complexity necessitates extensive calibration, which can impact the accuracy of yield predictions. Machine learning shows promise for enhancing yield estimations but relies on vast amounts of training data. This study aims to improve the pakchoi yield prediction accuracy of simulation models. We developed a stacking ensemble learning model that integrates three base models—EU-Rotate_N, Random Forest Regression and Support Vector Regression—with a Multi-layer Perceptron as the meta-model for the pakchoi dry matter yield prediction. To enhance the training dataset and bolster machine learning performance, we employed the EU-Rotate_N model to simulate daily dry matter yields for unsampled data. The test results revealed that the stacking model outperformed each base model. The stacking model achieved an R² value of 0.834, which was approximately 0.1 higher than that of the EU-Rotate_N model. The RMSE and MAE were 0.283 t/ha and 0.196 t/ha, respectively, both approximately 0.6 t/ha lower than those of the EU-Rotate_N model. The performance of the stacking model, developed with the expanded dataset, showed a significant improvement over the model based on the original dataset. [ABSTRACT FROM AUTHOR]

Maize plays a crucial role in China's grain production, with a cultivation area reaching 44.22 million hectares and an annual yield of 289 million tons in 2023. However, the challenge remains on how to further increase maize yield and water use efficiency (WUE) without adding to the environmental burden. To systematically evaluate the impact of straw incorporation under varying production conditions on maize yield and WUE, this study collected experimental data from multiple locations across China. A meta-analysis was conducted to compare the effects of straw incorporation versus no incorporation, and the main influencing factors were identified using correlation analysis and a random forest model. The results indicate that straw incorporation significantly enhances both maize yield and WUE, with the most pronounced improvements observed under conditions of an average growing season temperature of 19–23 °C, soil pH of 6.5–7.5, low initial soil organic matter content, and deep plowing for straw incorporation. Additionally, moderate nitrogen application rates and straw incorporation amounts (9000–15,000 kg·ha−2) also significantly boost maize yield and WUE. Field management practices and meteorological conditions are identified as the primary factors affecting maize yield and WUE under straw incorporation conditions. Therefore, straw incorporation stands out as an effective agricultural practice for achieving high maize yields and efficient resource utilization. The findings of this study provide valuable insights for global food security and the sustainable development of agriculture. [ABSTRACT FROM AUTHOR]

Timely and accurate predictions of winter wheat yields are key to ensuring food security. In this research, winter wheat yield prediction models for six provinces were established using a random forest (RF) model. Two methods were employed to analyze feature variables. RF partial dependence plots were generated to demonstrate the nonlinear relationships between the feature variables and yield, and bivariate Moran's I was considered to identify the spatial associations between variables. Results showed that when environmental data from key growth periods were used for prediction model establishment, the root mean square error (RMSE) varied between 200 and 700 kg/ha, and the coefficient of determination (R2) exceeded 0.5. Feature variable analysis results indicated that the longitude, latitude, topography and normalized difference vegetation index (NDVI) were important variables. Below the threshold, the yield gradually increased with increasing NDVI. Bivariate Moran's I results showed that there was zonal distribution of meteorological elements. Within a large spatial range, the change in environmental variables due to the latitude and longitude should be accounted for in modeling, but the influence of collinearity between the feature variables should be eliminated via variable importance analysis. [ABSTRACT FROM AUTHOR]

[Objective] The aims of this study are to evaluate the spatiotemporal trends of soil erosion, to reveal the contributions of driving factors, to elucidate the impacts of ecological restoration policies, and to provide a scientific basis for the management of soil erosion on the Tibetan Plateau. [Methods] This study assessed the temporal and spatial characteristics of soil erosion by water on the Tibetan Plateau from 1990 to 2020, and identified the contribution of climatic, anthropogenic and topographic factors to soil erosion by Random Forest Regression. [Results] (1) The average soil erosion rate on the Tibetan Plateau was 305.78 t/km², and more than 80% of the area was slightly erosion during 1990-2020. Soil erosion decreased before 2010 and increased after 2010, showing a nonlinear variation. (2) Climate factors had a greater impact on soil erosion than anthropogenic factors in the Tibetan Plateau, and annual precipitation was the main factor on soil erosion. In addition, since 2010, the influence of anthropogenic factors on soil erosion gradually increased. [Conclusion] Climate factors are the primary driving force inducing soil erosion in the Tibetan Plateau. The ecological restoration policies implemented in the Tibetan Plateau have initially achieved results, but the impact of climate change on soil erosion is more significant. Additionally, Random Forest Regression is effective for exploring the driving factors on soil erosion. [ABSTRACT FROM AUTHOR]

(1) Background: Artificial intelligence using machine learning techniques may help us to predict and prevent obesity. The aim was to design an interpretable prediction algorithm for overweight/obesity risk based on a combination of different machine learning techniques. (2) Methods: 38 variables related to sociodemographic, lifestyle, and health aspects from 1179 residents in Madrid were collected and used to train predictive models. Accuracy, precision, and recall metrics were tested and compared between nine classical machine learning techniques and the predictive model based on a combination of those classical machine learning techniques. Statistical validation was performed. The shapely additive explanation technique was used to identify the variables with the greatest impact on weight gain. (3) Results: Cascade classifier model combining gradient boosting, random forest, and logistic regression models showed the best predictive results for overweight/obesity compared to all machine learning techniques tested, reaching an accuracy of 79%, precision of 84%, and recall of 89% for predictions for weight gain. Age, sex, academic level, profession, smoking habits, wine consumption, and Mediterranean diet adherence had the highest impact on predicting obesity. (4) Conclusions: A combination of machine learning techniques showed a significant improvement in accuracy to predict risk of overweight/obesity than machine learning techniques separately. [ABSTRACT FROM AUTHOR]

This study introduces an innovative scheme for classifying uncrewed aerial vehicle (UAV)-derived vehicle trajectory behaviors by employing machine learning (ML) techniques to transform original trajectories into various sequences: space–time, speed–time, and azimuth–time. These transformed sequences were subjected to normalization for uniform data analysis, facilitating the classification of trajectories into six distinct categories through the application of three ML classifiers: random forest, time series forest (TSF), and canonical time series characteristics. Testing was performed across three different intersections to reveal an accuracy exceeding 90%, underlining the superior performance of integrating azimuth–time and speed–time sequences over conventional space–time sequences for analyzing trajectory behaviors. This research highlights the TSF classifier's robustness when incorporating speed data, demonstrating its efficiency in feature extraction and reliability in intricate trajectory pattern handling. This study's results indicate that integrating direction and speed information significantly enhances predictive accuracy and model robustness. This comprehensive approach, which leverages UAV-derived trajectories and advanced ML techniques, represents a significant step forward in understanding vehicle trajectory behaviors, aligning with the goals of enhancing traffic control and management strategies for better urban mobility. [ABSTRACT FROM AUTHOR]