Purpose Law enforcement agencies in the United States are relying on state fusion centers for intelligence to develop actionable, data-driven reports that increase efficiency and improve investigations in crime prevention and homeland security. This study assesses the extent to which artificial intelligence and machine learning (AI/ML) are increasingly shaping intelligence operations in law enforcement and the functions of state fusion centers in supporting intelligence-led policing (ILP). The reliance and integration of AI/ML is improving analytic accuracy, situational awareness and information and data sharing and collaboration among law enforcement and homeland security agencies. This study examines the state of contemporary academic literature, assesses AI/ML applications used in law enforcement and builds a conceptual and theoretical framework centered on ILP policing. It also relies on empirical data, case study applications, and DHS assessments to explore the degree to which AI-driven processes and analytics enhance criminal intelligence, investigative efficiencies, situational awareness and predictive policing. The analysis, while focusing on the opportunities and challenges of using AI/ML tools in law enforcement, also highlights the need for ethical governance, transparency and accountability when relying on advanced technologies for crime prevention and policing. Design/methodology/approach This study utilizes qualitative methods, including a thematic content analysis of government and think tank/practitioner reports as well as academic literature on the benefits, costs and ethical factors regarding variations in the implementation of AI/ML tools for law enforcement intelligence products and resource allocation. For cross-validation of operational outcomes, it examines publicly available information in the DHS Fusion Center Annual Assessment, Bureau of Justice Statistics, LEMAS and RAND Corporation assessments of intelligence-led policing. Findings Qualitative Results Federal and state sources report fusion centers and law enforcement agencies integrating advanced analytic and ML-enabled tools into each step in the criminal intelligence lifecycle process. However, ethical and structural challenges limit and constrain technology-driven narratives in fusion centers. Given these challenges, there is a consistent qualitative and thematic pattern: state fusion centers now function as criminal intelligence analytic hubs or resources that leverage the most contemporary analytic and data-driven tools for criminal intelligence and law enforcement investigations. Interrelated themes describe AI/ML technologies in terms of shaping, constraining and complicating the intelligence lifecycle in fusion centers and law enforcement operations. Seven specific themes emerged from latent coding are illustrated in the chart. Research limitations/implications There are limitations on the collection of quantitative data since DHS, leading think tanks and NGOs do not disclose specific figures on the proportion of AI/ML tools. The DHS Fusion Center Annual Assessment process monitors technology adoption and the growth of analytic capabilities throughout the national network of fusion centers; however, the specific quantitative statistics are not disclosed in public summaries (DHS, 2024). Second, publicly available data and information constitute the bulk of empirical sources. Consequently, this study relies primarily on qualitative narrative reporting, not quantitative performance metrics. Third, publication bias is likely present in industry and government sources as these reports may provide overly optimistic observations and conclusions while overlooking ethical dilemmas, failures and challenges. Moreover, qualitative thematic analysis could reflect broader structural narratives as opposed to empirical outcomes. Finally, since AI/ML adoption varies across fusion centers and according to technology levels, qualitative themes identified in this study must be read as representative patterns and not as universally generalizable. Originality/value Fusion center utilization of AI/ML technologies is as much an operational tool as it is a policy, governance and ethical challenge. Successful and professional use in support of law enforcement is about placing technological innovations firmly within institutional accountability and constitutional guardrails. On the one hand, AI/ML tools are enhancing analytical intelligence production by accelerating analytic workflows, predictive modeling and expanding data/information integration capabilities. AI/ML are extending ILP concepts by offering improvements in situational awareness and threat identification and operational efficiencies. On the other, substantial constraints hinder responsible use of these technologies. In the absence of standardized oversight frameworks, data-quality issues, algorithmic bias and the lack of professional development, workforce capacity and critical skills on the part of fusion center analysts will cancel the benefits of these tools.

This study develops a provincial carbon accounting and forecasting framework for Sichuan Province covering 2005–2022 under a consumption-based boundary. Direct fossil fuel emissions and indirect electricity-related emissions are clearly distinguished to ensure accounting consistency and additive closure. On this basis, a Transformer-based machine learning model integrated with SHAP is constructed to predict carbon emissions and identify peak characteristics. The results show high historical fitting accuracy and project that Sichuan’s carbon emissions will reach a plateau-type peak around 2031, followed by a gradual decline. SHAP-based interpretation indicates that total energy consumption and the carbon emission factor are the dominant drivers, while economic scale and energy intensity exert secondary but significant effects. Robustness tests confirm the stability of the explanatory structure. The proposed framework integrates accounting consistency, predictive modeling, and interpretability analysis, providing empirical support for regional peak management and low-carbon transition planning.

Environmental enrichment partially rescues neurodevelopmental milestone delays in the prenatal VPA rat model of autism spectrum disorders.

This study explored the role of cellular senescence in the progression of rheumatoid arthritis (RA) and evaluated the targeting of Cyclin E2 (CCNE2) in synovial fibroblasts as a potential therapeutic approach. A risk prediction model for RA was developed using LASSO regression analysis, which involved analyzing differential gene expression and performing Gene Set Enrichment Analysis (GSEA). The model was validated using the Receiver Operating Characteristic (ROC) curve. CCNE2 expression was examined via Western blotting. Knockdown of CCNE2 in RA synovial fibroblasts (RASFs) using shRNA resulted in reduced cell viability, increased apoptosis, and elevated levels of senescence markers such as p16, p21, and p53. Additionally, senescence-associated β-galactosidase (SA-β-Gal) activity and H3K9me3 fluorescence intensity were significantly increased. In vivo, Adeno-Associated Virus (AAV)-mediated intra-articular injection of shCCNE2 in a collagen-induced arthritis (CIA) mouse model significantly reduced the arthritis index, alleviated joint inflammation, and suppressed CCNE2 expression. Furthermore, the secretion of SASP factors such as MMP-3 and IL-8 was significantly enhanced. These findings suggest that targeting CCNE2 induces senescence in RASFs and may offer a novel strategy to mitigate RA progression and inflammation.

Inflammatory bowel disease (IBD) is a chronic, relapsing-remitting autoimmune disorder of the gastrointestinal tract. The management of IBD is complex and requires accurate assessment of disease extent and severity which guide therapeutic decisions. Endoscopic evaluation with biopsy remains the standard for diagnosing and assessing disease activity. Additionally, other modalities such as computed tomography enterography are used for suspected small bowel involvement. However, these processes are costly, time consuming, and often rely on subjective interpretation which is influenced by clinician experience. Artificial intelligence (AI) has been used to standardize and improve efficiency in many facets of healthcare. Similarly, in the past decade, there has been growing interest in the applications of AI in the management of IBD. The applications of AI in IBD to date include automated endoscopic and histologic assessment, analysis of non-invasive imaging, discovery of novel biomarkers for the development of disease prediction models and the use of chatbots. In this article, we will discuss recent advancements in the use of AI in IBD as well as some of the practical and ethical concerns with large scale implementation of AI into clinical practice.

First-principles molecular dynamics simulations systematically elucidate the influence of atomic structure on ionic conductivity in BeF2-NdF3 (FBeNd) molten salt, a key constituent salt in electrochemical pyroprocessing for the molten salt reactor. The increase in ionic conductivity with Nd concentration is explained by multilevel structural analyses encompassing phonon modes, ionic pair structures, network architectures, and electronic characteristics. Phonon dispersion analysis demonstrates that high- and low-frequency vibrational modes are governed by Be and Nd ions, respectively. Detailed structural analyses confirm that enhanced Nd diffusivity correlates with improved Nd-Nd interactions manifested through shortened Nd-Nd distances, distorted Nd-F-Nd angles, emergent edge/face-sharing clusters, and intensified electronic polarization. Conversely, Be-F tetrahedra retain structural integrity with increasing Nd concentrations, and network fragmentation accelerates Be and F diffusion. The dual enhancement effect of ionic self-diffusion coefficients and charge carrier concentration synergistically elevates the bulk ionic conductivity of molten FBeNd. Overall, a composition-structure-property framework spanning macroscale conductivity to atomistic features is established, offering foundational insights for the predictive modeling of fission product accumulation effects and the rational design of separation protocols in pyroprocessing.

ABSTRACT This study investigated predictors of gifted identification among Syrian refugee students in Jordan, focusing on academic achievement, gender, and school context. A dataset comprising 13,598 students assessed using the Arabic version of the HOPE Teacher Rating Scale was analyzed. Logistic regression and random forest analyses examined the influence of GPA, gender, school stage (elementary, middle, secondary), and school location (in-camp and out-of-camp) on identification patterns. GPA emerged as a strong predictor, with higher GPA substantially increasing the likelihood of gifted identification. School location demonstrated a modest effect, as students in camp settings were less likely to be identified, reflecting structural inequities in educational provision. Middle school students were less likely to be identified compared to secondary students, while gender differences were not significant. Predictive modeling results should be interpreted with caution, as gifted identification was derived directly from the HOPE total score; models incorporating HOPE items closely mirrored the HOPE-based classification, whereas models using only demographic variables had limited discriminatory power. These findings underscore the importance of culturally validated, behaviorally anchored teacher rating tools in promoting equitable gifted identification in refugee education contexts and highlight the need for policies that reduce reliance on academic metrics alone.

Current enzyme thermostability prediction models are predominantly designed for cross-family generalization, with limited focus on hydroxylases, which restricts their accuracy and applicability in hydroxylase-specific thermostability design. In this study, we develop HyS-BST, a dedicated self-trained semisupervised framework for hydroxylase thermostability prediction. Leveraging a limited hydroxylase data set, HyS-BST integrates a self-training strategy with Bayesian dynamic tuning to achieve high-precision prediction of mutant thermostability in terms of ΔΔG. Experimental results demonstrate that after only ten training iterations, HyS-BST attains a coefficient of determination (R2) of 0.96, a Pearson correlation coefficient (PCC) of 0.98, and a root mean squared error (RMSE) as low as 0.06 on the test set. Compared with the optimal cross-family generalization model, HyS-BST improves PCC and RMSE by approximately 70%. Overall, this framework provides a specialized, efficient, and cost-effective solution for hydroxylase thermostability prediction, substantially reducing the candidate search space and experimental resources required for downstream validation.

Postoperative pulmonary complications (PPCs) are a major cause of morbidity and mortality in surgical patients, particularly among the critically ill. Several risk prediction models have been developed to stratify the risk of PPCs. However, comparative evidence on theirperformance in critically ill populations remain scarce. In the present retrospective cohort study, 495 critically ill surgical subjectswho were admitted to a tertiary hospital ICU in China were assessed for PPCs using 3 established risk models:Local Assessment of Ventilatory Management During General Anesthesia for Surgery (LAS VEGAS), Assess Respiratory risk in Surgical Patients in Catalonia (ARISCAT),and Chinese Brief Predictive Risk Index (CHI-BPRI). Inclusion required intra-operative mechanical ventilation and postoperative ICU care. Then, predictive performance was evaluated by receiver operating characteristic analysis, with discrimination quantified using the area under the receiver operating characteristic curve (AUC), sensitivity, specificity, and odds ratio. In the cohort, 20.4% developed PPCs. The LAS VEGAS score had the highest AUC (0.63, 95% CI 0.57-0.68), with 74% sensitivity and 47% specificity. However, the ARISCAT and CHI-BPRI scores had lower AUCs of 0.60 and 0.55, respectively. Despite the numerical differences, none of the scores achieved statistically superior discrimination (P = .44, .058, .16), and all AUCs fell below 0.70, indicating suboptimal predictive accuracy. The LAS VEGAS score had the strongest association with PPCs (OR 2.26, 95% CI 1.42-3.60). In critically ill Chinese surgical subjects, the LAS VEGAS, ARISCAT, and CHI-BPRI scores had limited predictive performance for PPCs, and none of the scores achieved strong discriminative power. Among these, the LAS VEGAS score performed best and may offer modest utility for early risk identification. These findings underscore the need for improved, population-specific prediction tools tailored to the unique risk profiles of critically ill surgical patients.

Coastal and marine systems are governed by fragile water-quality dynamics, where disturbances can trigger harmful algal blooms with significant ecological and societal consequences. These pressures have intensified interest in forecasting systems that can anticipate bloom development and support environmental management. This study presents a systematic review of simulation-based and predictive environmental modeling approaches used for marine forecasting of water quality and harmful algal bloom phenomena. Following PRISMA guidelines, 11,185 records were identified, 127 articles were screened in full text for eligibility, and 40 peer-reviewed studies published between 2015 and 2025 were included and synthesized using a structured extraction framework capturing modeling paradigms, forecast targets, data inputs, spatial and temporal scope, validation practices, operational context, and reported limitations. The reviewed literature indicates the dominance of predictive and hybrid modeling approaches, with forecasting efforts primarily focused on coastal systems and short-term applications. Harmful algal blooms and chlorophyll-a emerge as dominant forecast targets, commonly supported by satellite observations, in situ measurements, and environmental forcing variables. Despite substantial methodological advances, persistent challenges related to data availability and quality, validation rigor, system integration, and operational deployment remain evident across modeling paradigms. Overall, the findings suggest that while marine forecasting models have become increasingly sophisticated, their translation into reliable and operational systems remains uneven, highlighting the need for closer alignment.

Neglected infectious diseases (NIDs) remain a major public health challenge in the Amazon, particularly among quilombola populations living in rural and riverside territories marked by historical inequalities and structural limitations. This study examined the occurrence of NIDs in eight quilombola communities in the Lower Amazon, identified socioenvironmental factors associated with these conditions, and evaluated the performance of machine learning models in predicting individual risk of illness. This analytical cross-sectional study included 518 participants, with data collected through a structured questionnaire. Descriptive and bivariate analyses were conducted, followed by multivariable logistic regression, Poisson regression, cluster analysis, and predictive modeling using Random Forest, XGBoost, and Logistic Regression. Spatial analysis was performed in Google Colab. The overall prevalence of at least one NID was 34.7%. Lack of sanitation facilities, use of river or well water, precarious housing, inadequate waste disposal, low income, and residence in rural areas were significantly associated with both the occurrence and number of NIDs per individual. XGBoost and Random Forest achieved the best predictive performance (AUC-ROC 0.87 and 0.85, respectively). Cluster analysis revealed distinct vulnerability profiles, with the highest burden observed among groups characterized by multidimensional poverty and limited sanitation. The findings highlight the overlapping social and environmental determinants that sustain the persistence of NIDs in these territories, underscoring the need for structural, territorialized policies tailored to the specific realities of quilombola communities in the Amazon. The cross-sectional design and reliance on self-reported disease history should be considered when interpreting the findings.

The quality of wind power output data directly impacts the assessment of wind farm operational status and the accuracy of power forecasting models. However, due to factors such as sensor precision, communication interference, and the complex harbor environment, raw data collected from port-area wind turbines often contain noise, outliers, and missing values. Without effective cleaning, the resulting power curves can be distorted, reducing the generalization capability of predictive models. To overcome the limitations of traditional outlier detection methods in terms of adaptability and robustness, this study proposes a two-stage port-area wind power data cleaning approach based on dynamic interquartile range and an improved Sigmoid function fitting. In the first stage, an adaptive binning and density-weighting mechanism dynamically expands the interquartile range to identify and remove local outliers across different wind speed intervals. In the second stage, the cleaned wind speed–power data are subjected to secondary fitting and residual analysis using an improved Sigmoid model to detect hidden anomalies and boundary-type outliers. Using measured data from the #1 WT in the Chuanshan Port area as a case study, the experimental results demonstrate that the proposed method achieves high data retention while outperforming the conventional interquartile range, density-based spatial clustering of applications with noise and isolation forest algorithms in terms of the Pearson correlation coefficient (r = 0.93) and the coefficient of determination (R2 = 0.89), with mean squared error and root mean squared error reduced to 446.39 kW and 545.58 kW, respectively. The findings verify the efficiency, stability, and practical feasibility of the method for port-area wind power data cleaning, providing a reliable data foundation for wind power forecasting and operational optimization in port environments.

Grapevine (Vitis vinifera L.) is an economically important fruit crop, but its production is severely affected by anthracnose caused by Colletotrichum gloeosporioides, commonly known as bird’s eye spot. The present investigation was conducted at the Horticultural Farm, University of Agricultural Sciences, Raichur, during the Kharif seasons of 2024 and 2025 to study disease progression and to develop a prediction model for grape anthracnose in the susceptible cultivar Thompson Seedless. Disease severity was recorded at weekly intervals using a 0-4 rating scale and expressed as Per cent Disease Index (PDI). Simultaneously, weekly weather data were collected from the Main Agricultural Research Station, Raichur. Anthracnose appeared during the 27th and 24th standard meteorological weeks in 2024 and 2025, respectively, and gradually increased to 100 per cent severity by the end of the season. Observed PDI ranged from 8.50 to 100.00 per cent in 2024 and from 7.13 to 100.00 per cent in 2025. A first-order autoregressive model was developed to predict disease progression, which showed close agreement between observed and predicted PDI values, particularly during the mid-season period. The developed models exhibited high autocorrelation coefficients (R = 0.953 in 2024 and R = 0.891 in 2025), indicating a strong temporal relationship in disease development. The study demonstrates that an autoregressive approach can effectively describe the progression pattern of grape anthracnose under field conditions.

Objectives It is well established that calcified plaques are highly likely to lead to residual stenosis after stenting; however, the specific characteristics responsible for this effect remain unknown. This study aimed to identify both qualitative and quantitative imaging risk factors for residual stenosis using computed tomography angiography. Methods We retrospectively enrolled 233 patients with carotid artery stenosis. Patients were categorized into two groups based on the presence or absence of postoperative residual stenosis. Carotid computed tomography angiography evaluated plaque characteristics both qualitatively and quantitatively. Logistic regression analysis identified independent risk factors for residual stenosis. We evaluated the predictive model’s discriminative ability by calculating the area under the receiver operating characteristic (ROC) curve. Results Univariate analysis indicated a statistical difference in age, creatinine, total plaque volume, percentage of total calcified plaque, percentage of total soft plaque, maximum slice attenuation value, maximum thickness, total length, and a circumferential calcification score ≥2 points ( p < 0.05). Multivariable logistic regression identified creatinine (OR = 1. 020; 95%CI: 1.005–1.035; p = 0.010), maximum slice attenuation value(Z-score; OR = 1.627; 95%CI: 1.024–2.585; p = 0.039), percentage of calcified plaque volume(Z-score; OR = 1.872; 95%CI: 1.137–3.082; p = 0.014) and circumferential calcification score ≥2 (OR = 3.257; 95%CI: 1.620–6.548; p < 0.001) as independent factors associated with residual stenosis. Furthermore, receiver operating characteristic curve analysis revealed that the area under the curve for the combined model in diagnosing residual stenosis was 0.784. Conclusion In conclusion, preoperative CTA-based assessment of specific plaque characteristics, such as calcified plaque volume percentage, circumferential calcium score, and the maximum slice attenuation value of calcification are related to residual stenosis.

Venovenous extracorporeal membrane oxygenation (ECMO) is essential for patients with severe respiratory failure who do not respond to conventional mechanical ventilation. Adequate ECMO flow and safe circuit pressure are critical; however, cannula selection, which has a great impact on these factors, is often based on empirical judgment. This study aimed to develop a simple predictive method based on fluid dynamics for estimating ECMO flow rate and circuit pressures (P1: pre-pump, P2: pre-oxygenator, and P3: post-oxygenator). This experimental predictive model study compared the calculated and measured ECMO parameters across 36 combinations of cannula sizes, pump speeds, and bed heights. A laboratory-based ECMO circuit model was assembled with various drainage and return cannulas, an oxygenator, tubing, and a centrifugal pump. The circuit was primed with a 33% glycerin solution and tested across the 36 combinations. A four-step prediction method was applied: (1) modeling the pressure-flow relationships of ECMO components and the pump using manufacturer data; (2) identifying the expected flow rate by locating the intersection of the total circuit resistance and pump output curves; (3) sequentially calculating pressure drops across the circuit; and (4) adjusting pressures based on bed height. The predicted flow rate and circuit pressure values were compared to experimental measurements across the 36 combinations. The calculated and measured values showed strong agreement (R2 = 0.96-0.97), and predictions were significant. Notably, bed height alterations were confirmed to affect circuit pressure but not flow rate. Our newly developed method reliably predicts the ECMO flow rate and circuit pressure. Hence, it can be considered a valuable tool for preemptively selecting the optimal cannula size for ECMO, thus improving patient safety and circuit management. Furthermore, it may be a valuable educational tool, making complex hemodynamic concepts more intuitive for trainees.

Introduction. Patients with coronary artery disease (CAD) have a residual risk of adverse vascular events. The multifactorial and heterogeneous nature of this risk requires an integrative approach to assessment, which is a pressing issue in cardiology. The role of lipoprotein (a) (Lp(a)) as a marker of residual risk has been demonstrated. In this article the role of advanced glycation end products (AGEs) is being investigated in the progression of residual risk in patients with CAD. Aim: To evaluate the relationship between the autofluorescence index of advanced glycation end products and lipoprotein (a) levels to determine residual risk in patients with stable coronary artery disease and dyslipidemia receiving intensive lipid-lowering therapy. Materials and Methods: A single-center prospective study was conducted involving 87 men aged 55 to 75 years with CAD and comorbidities. Standard laboratory tests, including Lp(a) levels, and instrumental methods in accordance with clinical guidelines were used. AGEs accumulation was also determined by calculating the autofluorescence index using the portable AGE Reader device. Dyslipidemia was corrected with a fixed combination of rosuvastatin and ezetimibe; alirocumab when indicated. The median follow-up was 12 weeks. Statistical processing was performed using StatTech 4.9.4 (StatTech LLC, Russia). Results. Study participants were divided into subgroups based on Lp(a) levels >0.5 g/L ( n = 41) and <0.5 g/L ( n = 46) assessing residual risk. Lipid profile target parameters were achieved in 78.2% of patients ( n = 68) with the fixed-dose combination of rosuvastatin and ezetimibe and in 21,8% ( n = 19) with triple therapy, of which 17.2% ( n = 15) belonged to subgroup 1 and 4.6% ( n = 4) to subgroup 2. Autofluorescence index at baseline: 2.8 [2.20; 4.07]. After 6 weeks of intensive lipid-lowering therapy and adequate treatment of comorbid pathology, the autofluorescence index was 2.79 [2.12; 4.00]; after 12 weeks – 2.75 [2.02; 3.88]. According to the color identification of the device, the red autofluorescence index (very high risk) was observed in 54% of patients at the start of the study ( n = 47), and after 12 weeks – in 35.6% ( n = 31). The study showed a strong direct correlation with the level of AGEs at the start and after 12 weeks for the group with the Lp(a)>0.5 g/l. ROC analysis demonstrated that an increase in the autofluorescence index is a statistically significant predictor of increased residual risk (AUC = 0.976; 95% CI: 0.918–1.000, p < 0.001). The sensitivity and specificity of the predictive model were estimated at 93.3%. Conclusions: The AGEs autofluorescence index may be used for comprehensive noninvasive assessment of residual risk in patients with stable coronary artery disease and hyperlipoproteinemia (a).

This study aimed to develop and validate a machine learning (ML) model to predict the need for mechanical ventilation (MV) in elderly patients diagnosed with acute pulmonary embolism (APE). The study included a cohort of 321 patients from two centers. Center A contributed 261 patients for the development of four ML models: Random Forest, XGBoost, Logistic Regression (LR), and Support Vector Classifier (SVC). The remaining 60 patients from Center B were used for external testing. Feature selection incorporated CT histogram features related to muscular density and area of the pectoralis muscles on CT images at the level of the fourth thoracic vertebra, common geriatric comorbidities, and routine laboratory tests for APE. The area under the curve (AUC) was used to evaluate the predictive performance of the models; calibration curves were employed to assess calibration performance, and the sPESI score served as a baseline comparator. Shapley Additive exPlanations (SHAP) plots were utilized to visualize the importance of each feature. The final set of features included low oxygen saturation, smoke status, CT_PMA_10th, CT_PMA_90th, CT_PMI_75th, CT_PMA_Fat_ratio, chest pain, syncope, diabetes, gender, chronic heart failure, NT-proBNP/BNP positive, and D-dimer. In the internal validation set, the four models performed well and exhibited similar performance, with AUC values exceeding 0.80. Among the models evaluated, the LR model demonstrated the best performance on the external test set, with an AUC of 0.837, an accuracy of 0.817, a recall of 0.750, a specificity of 0.833, a precision of 0.529, and an F1-score of 0.621. The SHAP plot revealed that low oxygen saturation, CT_PMA_10th, and CT_PMI_75th were highly important features. Loss of pectoral muscle may be associated with the need for MV in elderly patients with APE. The prediction model developed in this study, which includes this factor, could aid in identifying high-risk individuals and may inform future efforts to improve early risk stratification and personalized management in this population.

Abstract This study integrates advanced statistical modeling approaches to investigate and forecast the human capital development of organizations that integrate AI into their processes. Structural equation modeling was used to estimate the total direct and indirect effects of AI integration into human capital development, testing employee openness to change as a moderator. The estimation of the parameters in SEM, the test for moderation, and the assessment of model fit were conducted using SPSS and AMOS, using maximum likelihood methods along with standard goodness-of-fit indices. In this respect, machine learning-based predictive models were implemented in Python to evaluate the predictive power of AI integration measures with respect to human capital development, considering cross-validation and relevant accuracy metrics for evaluating model performance. The results show statistically significant moderation effects along with adequate predictive performance, thus emphasizing the complementary use of explanatory statistical modeling and predictive statistical learning in understanding and forecasting human capital development.

Objective To mitigate current research limitations, this cross-sectional study aimed to systematically evaluate the associations between dietary amino acids and overweight/obesity and to identify critical biomarkers among Chinese children and adolescents. This was achieved by integrating multiple machine learning algorithms with traditional statistical models. Methods This study utilized data from the 2016–2019 China Children and Lactating Women Nutrition and Health Surveillance, a nationally representative survey. Participants included children and adolescents aged 6–18 years. Dietary intake was assessed using a validated food frequency questionnaire, and amino acid intakes were calculated. Four machine learning algorithms were applied to build prediction models. Model performance was evaluated via the area under the receiver operating characteristic curve (AUC). The SHapley Additive exPlanations (SHAP) method was used to interpret the optimal model and identify important features. Multivariable logistic regression models were additionally used to examine the relationship between amino acids and overweight/obesity risk. Results A total of 8,664 participants were included. The LightGBM model showed the best predictive effect (AUC = 0.805). Both SHAP analysis and logistic regression results consistently identified leucine (OR 1.13; 95% CI 1.01 ~ 1.27), threonine (OR 1.41; 95% CI 1.22 ~ 1.63), methionine (OR 1.30; 95% CI 1.07 ~ 1.57), and cysteine (OR 0.71; 95% CI 0.59 ~ 0.84) as key amino acids associated with overweight/obesity risk. After multivariable adjustment, the intake of leucine, threonine, and methionine was positively related to the risk of overweight/obesity, whereas cysteine intake was inversely related to the risk. Restricted cubic spline analyses suggested linear relationships for these associations. Conclusion Higher dietary intakes of leucine, threonine, and methionine are potential risk factors, while cysteine is a potential protective factor against overweight/obesity in Chinese children and adolescents.

This study develops a novel AI-based trading framework designed to consistently generate profits across cyclical bullish and bearish futures markets. Unlike conventional strategies that rely on static rules or a single predictive model, the proposed framework introduces a dual-agent deep reinforcement learning (DRL) architecture, where one agent specializes in bullish conditions and the other in bearish conditions, while a trading decision selector dynamically predicts market regimes and allocates execution accordingly. This design enables the system to adapt to regime shifts and mitigate risks arising from market volatility and extreme events. Using Mini Taiwan Stock Exchange Index Futures (MTX) as a case study, a four-year historical backtest is conducted covering multiple disruptive periods, including the tax adjustment and the Russia–Ukraine conflict. The empirical results show that, under a monthly capital reset and loss-compensation rule with a fixed investment of TWD 500,000 per month, the proposed framework achieves an average cumulative return of 2240%, an annualized return of 109%, and a Sharpe ratio of 0.31, with the cumulative ROI exceeding twice the MTX index growth over the same period. Although the Sharpe ratio remains moderate, this outcome reflects the framework’s emphasis on directional trading and absolute return maximization, where profitable trades outweigh intermittent losses despite higher short-term volatility. These findings suggest that adaptive, regime-aware DRL architectures are particularly effective for futures trading in markets characterized by frequent trend reversals, offering both methodological innovation and practical applicability under realistic market conditions, with strong returns achieved at a moderate risk-adjusted level.