Search Results (273)

Soybeans (Glycine max (L.) Merr.) are a multifunctional crop that contributes significantly to global food security, economic development, and agricultural sustainability. Genomic selection (GS) is widely used in plant breeding, which can effectively reduce breeding costs and shorten the breeding cycle compared to traditional breeding methods. In this study, Hyper-seq technology was used to gather data on 104,728 single nucleotide polymorphism (SNP) sites from 420 natural populations of soybean that were chosen as experimental materials. Furthermore, three years’ worth of phenotypic data on the population’s main stem node count were gathered for this investigation. Comparative analysis was used to assess the validity and accuracy of a number of GS models, including Ridge Regression Best Linear Unbiased Prediction (RRBLUP), Genomic Best Linear Unbiased Prediction (GBLUP), and various Bayesian techniques (Bayesian_A, Bayesian_B, Bayesian_C, Bayesian_RR, Bayesian_LOOS, and Bayesian_RKHS). Each model’s performance was compared using fivefold cross-validation. The research findings indicate that the data obtained by Hyper-seq technology is particularly useful for breeding experiments, including genome-wide selection. The most accurate of them is Bayesian_A, whereas the one with the quickest computational efficiency is GBLUP. Using Hyper-seq technology requires integrating at least 15,000 SNPs to guarantee the model’s stability. It is also important to note that, even if 153 Hyper-seq datasets are 50% less expensive than 153 Whole Genome Sequencing datasets, the difference in prediction accuracy between the two datasets is less than 4%. This discovery further validates the reliability and efficacy of Hyper-seq technology within the domain of genome-wide selection breeding. Full article

Genomic selection (GS) is a predictive methodology that is revolutionizing plant and animal breeding. However, the practical application of the GS methodology is challenging since a successful implementation requires a good identification of the best lines. For this reason, some approaches have been proposed to be able to select the top (or bottom) lines with more Precision. Despite the varying popularity of methods, with some being notably more efficient than others, this paper delves into the fundamentals of these techniques. We used five models/methods: (1) RC, known as the Bayesian Best Linear Unbiased Predictor (GBLUP); (2) R, which is like RC but uses a threshold; (3) RO, Regression Optimum, that leverages the RC model in its training process to fine-tune the threshold; (4) B, Threshold Bayesian Probit Binary model (TGBLUP) with a threshold of 0.5 to classify the cultivars as top or non-top; (5) BO is the TGBLUP but the threshold used is an optimal probability threshold that guarantees similar Sensitivity and Specificity. We also present a benchmark comparison of existing approaches for selecting the top (or bottom) performers, utilizing five real datasets for comprehensive analysis. For methods that necessitate a rigorous tuning process, we suggest a streamlined tuning approach that significantly decreases implementation time without notably compromising performance. Our analysis revealed that the regression optimal (RO) method outperformed other models across the five real datasets, achieving superior results in terms of the F1 score. Specifically, RO was more effective than models R, B, RC, and BO by 60.87, 42.37, 17.63, and 9.62%, respectively. When looking at the Kappa coefficient, the RO model was better than models B, BO, R, and RC by 37.46, 36.21, 52.18, and 3.95%, respectively. In terms of Sensitivity, the RO model outperformed models B, R, and RC by 145.74, 250.41, and 86.20, respectively. The second-best model was the model BO. It is important to point out that in the first stage, the BO and RO approaches train a classification and regression model, respectively, to classify the lines as the top (bottom) or not the top (not the bottom). However, both the BO and RO approaches optimize a threshold in the second stage to perform the classification of the lines that minimize the difference between the Sensitivity and Specificity. The BO and RO methods are superior for the selection of the top (or bottom) lines. For this reason, we encourage breeders to adopt these approaches to increase genetic gain in plant breeding programs. Full article

The predictive capabilities of artificial intelligence for predicting protein yield from larval biomass present valuable advancements for sustainable insect farming, an increasingly relevant alternative protein source. This study develops a neural network model to predict protein conversion efficiency based on the nutritional composition of larval feed. The model utilizes a structured two-layer neural network with four neurons in each hidden layer and one output neuron, employing logistic sigmoid functions in the hidden layers and a linear function in the output layer. Training is performed via Bayesian regularization backpropagation to minimize mean squared error, resulting in a high regression coefficient (R = 0.9973) and a low mean-squared error (MSE = 0.0072401), confirming the precision of the model in estimating protein yields. This AI-driven approach serves as a robust tool for predicting larval protein yields, enhancing resource efficiency and promoting sustainability in insect-based protein production. Full article

The cultivation of abalone, a species with high economic value, faces significant challenges due to its slow growth rate and sensitivity to environmental conditions, resulting in prolonged cultivation periods and increased mortality risks. To address these challenges, we propose a novel probabilistic machine learning approach based on a Bayesian framework to predict abalone growth by modeling key environmental factors, including water temperature, pH, salinity, nutrient supply, and dissolved oxygen levels. The proposed method employs a weighted Bayesian kernel machine regression model, integrating Gaussian processes with a spike-and-slab prior to identify influential variables. This approach accommodates heteroscedasticity, capturing varying levels of variance across observations, and models complex, non-linear relationships between environmental factors and abalone growth. Our analysis reveals that time, dissolved oxygen, salinity, and nutrient supply are the most critical factors influencing growth, while water temperature and pH play relatively minor roles under controlled indoor farming conditions. Interaction analysis highlights the non-linear dependencies among factors, such as the combined effects of salinity and nutrient supply. The proposed model not only improves prediction accuracy compared to baseline methods, but also provides actionable insights into the environmental dynamics that optimize abalone growth. These findings underscore the potential of advanced machine learning techniques in enhancing aquaculture practices and offer a robust framework for managing complex, multi-variable systems in sustainable farming. Full article

This work aims to improve the characterization of petrophysical properties by accurately estimating subsurface porosity using seismic and well data. The study includes Bayesian Linearized Inversion to obtain elastic parameters (e.g., compressional e shear wave velocities and densities). This reduces processing uncertainty and provides a reliable substitute for the standard Amplitude versus Offset inversion method. Furthermore, incorporating sparse spike wavelets with Bayesian Linearized Inversion refines the inversion output, facilitating the extraction of petrophysical properties. Combined with log data from seventeen wells, these inverted parameters serve as inputs for two porosity prediction models: the empirical Han’s equation and a more adaptable Support Vector Regression model, the latter demonstrating superior precision in most cases due to its flexible fitting and calibration capabilities. Results from the Norne field in the North Sea confirm the approach’s viability, with the Support Vector Regression model achieving a significant Pearson correlation coefficient of 90% in porosity prediction, underscoring the potential of machine learning techniques in improving subsurface exploration results. Full article

Volatile organic compounds (VOCs) are associated with obesity health risks, while the association of mixed VOCs with visceral adiposity indicators remains unclear. In this study, a total of 2015 adults from the National Health and Nutrition Examination Survey (NHANES) were included. Weighted generalized linear models, restricted cubic spline (RCS), weighted quantile sum (WQS), and Bayesian kernel machine regression (BKMR) were adopted to assess the association of VOC metabolites (mVOCs) with the visceral adiposity index (VAI) and lipid accumulation product (LAP). Multiple mVOCs were positively associated with the VAI and LAP in the single-exposure model, especially N-acetyl-S-(2-carboxyethyl)-L-cysteine (CEMA) and N-acetyl-S-(N-methylcarbamoyl)-L-cysteine (AMCC). The associations of mVOCs with VAI and LAP were more significant in <60-year-old and non-obese individuals, with interactions of CEMA with age and AMCC with obesity status. Nonlinear relationships between certain mVOCs and the VAI or the LAP were also observed. In the WQS model, co-exposure to mVOCs was positively correlated with the VAI [β (95%CI): 0.084 (0.022, 0.147)]; CEMA (25.24%) was the major contributor. The result of the BKMR revealed a positive trend of the association between mixed mVOCs and the VAI. Our findings suggest that VOC exposure is strongly associated with visceral obesity indicators. Further large prospective investigations are necessary to support our findings. Full article

Background: Chronic stress, characterized by sustained activation of physiological stress response systems, is a key risk factor for numerous health conditions. Allostatic load (AL), a biomarker of cumulative physiological stress, offers a quantitative measure of this burden. Lifestyle habits such as alcohol consumption and smoking, alongside environmental exposures to toxic metals like lead, cadmium, and mercury, were individually implicated in increasing AL. However, the combined impact of these lifestyle habits and environmental factors remains underexplored, particularly in populations facing co-occurring exposures. This study aims to investigate the joint effects of lifestyle habits and environmental factors on AL, using data from the NHANES 2017–2018 cycle. By employing linear regression and Bayesian Kernel Machine Regression (BKMR), we identify key predictors and explore interaction effects, providing new insights into how cumulative exposures contribute to chronic stress. Results from BKMR analysis underscore the importance of addressing combined exposures, particularly the synergistic effects of cadmium and alcohol consumption, in managing physiological stress. Methods: Descriptive statistics were calculated to summarize the dataset, and multivariate linear regression was performed to assess associations between exposures and AL. BKMR was employed to estimate exposure–response functions and posterior inclusion probabilities (PIPs), focusing on identifying key predictors of AL. Results: Descriptive analysis indicated that the mean levels of lead, cadmium, and mercury were 1.23 µg/dL, 0.49 µg/dL, and 1.37 µg/L, respectively. The mean allostatic load was 3.57. Linear regression indicated that alcohol consumption was significantly associated with increased AL (β = 0.0933; 95% CI [0.0369, 0.1497]; p = 0.001). Other exposures, including lead (β = −0.1056; 95% CI [−0.2518 to 0.0408]; p = 0.157), cadmium (β = −0.0001, 95% CI [−0.2037 to 0.2036], p = 0.999), mercury (β = −0.0149; 95% CI [−0.1175 to 0.0877]; p = 0.773), and smoking (β = 0.0129; 95% CI [−0.0086 to 0.0345]; p = 0.508), were not significant. BKMR analysis confirmed alcohol’s strong importance for AL, with a PIP of 0.9996, and highlighted a non-linear effect of cadmium (PIP = 0.7526). The interaction between alcohol and cadmium showed a stronger effect on AL at higher exposure levels. In contrast, lead, mercury, and smoking demonstrated minimal effects on AL. Conclusions: Alcohol consumption and cadmium exposure were identified as key contributors to increased allostatic load, while other exposures showed no significant associations. These findings emphasize the importance of addressing lifestyle habits and environmental factors in managing physiological stress. Full article

We conducted an in-depth exploration of the use of different machine learning (ML) for regression algorithms, including Linear, Ridge, LASSO, Bayesian Ridge, Decision Tree, and a variety of Deep Neural Network (DNN) architectures, to estimate the slope of the high-frequency feature (HFF), a prominent emergent feature found in the gravitational wave (GW) signals of core collapse supernovae (CCSN). We created a data set of CCSN GW signals generated by an analytical model that mimics the characteristics of the signals obtained from numerical simulations, particularly the HFF. This enabled us to simulate a wide range of HFF slope values and analyze their properties. We opted to employ ML for regression techniques, particularly a supervised learning approach, to analyze the data set due to the parameter chosen for estimating the slope of the HFF. This type of architecture is ideal for this purpose as it can detect the connections between input and output data. In addition, it is suitable for handling high-dimensional input data and produces efficient results with low computational cost. We evaluated the efficiency and performance of the ML algorithms using a set of metrics to measure their ability to accurately predict the HFF slope within the data set. The results showed that a DNN algorithm for regression exhibits the highest accuracy in estimating the slope of the HFF. Full article

For tropical rainforest regions with dense vegetation cover, the development of effective large-scale soil mapping methods is crucial to improve soil management practices to replace the time-consuming and laborious conventional approaches. While machine learning (ML) algorithms demonstrate superior predictability of soil properties over linear models, their practical and automated application for predicting soil properties using remote sensing data requires further assessment. Therefore, this study aims to integrate Unmanned Aerial Vehicles (UAVs)-based hyperspectral images and Light Detection and Ranging (LiDAR) points to predict the soil properties indirectly in two tropical rainforest mountains (Diaoluo and Limu) in Hainan Province, China. A total of 175 features, including texture features, vegetation indices, and forest parameters, were extracted from two study sites. Six ML models, Partial Least Squares Regression (PLSR), Random Forest (RF), Adaptive Boosting (AdaBoost), Gradient Boosting Decision Trees (GBDT), Extreme Gradient Boosting (XGBoost), and Multilayer Perceptron (MLP), were constructed to predict soil properties, including soil acidity (pH), total nitrogen (TN), soil organic carbon (SOC), and total phosphorus (TP). To enhance model performance, a Bayesian optimization algorithm (BOA) was introduced to obtain optimal model hyperparameters. The results showed that compared with the default parameter tuning method, BOA always improved models’ performances in predicting soil properties, achieving average R² improvements of 202.93%, 121.48%, 8.90%, and 38.41% for soil pH, SOC, TN, and TP, respectively. In general, BOA effectively determined the complex interactions between hyperparameters and prediction features, leading to an improved model performance of ML methods compared to default parameter tuning models. The GBDT model generally outperformed other ML methods in predicting the soil pH and TN, while the XGBoost model achieved the highest prediction accuracy for SOC and TP. The fusion of hyperspectral images and LiDAR data resulted in better prediction of soil properties compared to using each single data source. The models utilizing the integration of features derived from hyperspectral images and LiDAR data outperformed those relying on one single data source. In summary, this study highlights the promising combination of UAV-based hyperspectral images with LiDAR data points to advance digital soil property mapping in forested areas, achieving large-scale soil management and monitoring. Full article

Background/Objective: Environmental exposures, such as heavy metals, can significantly affect physical activity, an important determinant of health. This study explores the effect of physical activity on combined exposure to cadmium, lead, and mercury (metals), using data from the 2013–2014 National Health and Nutrition Examination Survey (NHANES). Methods: Physical activity was measured with ActiGraph GT3X+ devices worn continuously for 7 days, while blood samples were analyzed for metal content using inductively coupled plasma mass spectrometry. Descriptive statistics and multivariable linear regression were used to assess the impact of multi-metal exposure on physical activity. Additionally, Bayesian Kernel Machine Regression (BKMR) was applied to explore nonlinear and interactive effects of metal exposures on physical activity. Using a Gaussian process with a radial basis function kernel, BKMR estimates posterior distributions via Markov Chain Monte Carlo (MCMC) sampling, allowing for robust evaluation of individual and combined exposure-response relationships. Posterior Inclusion Probabilities (PIPs) were calculated to quantify the relative importance of each metal. Results: The linear regression analysis revealed positive associations between cadmium and lead exposure and physical activity. BKMR analysis, particularly the PIP, identified lead as the most influential metal in predicting physical activity, followed by cadmium and mercury. These PIP values provide a probabilistic measure of each metal’s importance, offering deeper insights into their relative contributions to the overall exposure effect. The study also uncovered complex relationships between metal exposures and physical activity. In univariate BKMR exposure-response analysis, lead and cadmium generally showed positive associations with physical activity, while mercury exhibited a slightly negative relationship. Bivariate exposure-response analysis further illustrated how the impact of one metal could be influenced by the presence and levels of another, confirming the trends observed in univariate analyses while also demonstrating the complexity varying doses of two metals can have on either increased or decreased physical activity. Additionally, the overall exposure effect analysis across different quantiles revealed that higher levels of combined metal exposures were associated with increased physical activity, though there was greater uncertainty at higher exposure levels as the 95% credible intervals were wider. Conclusions: Overall, this study fills a critical gap by investigating the interactive and combined effects of multiple metals on physical activity. The findings underscore the necessity of using advanced methods such as BKMR to capture the complex dynamics of environmental exposures and their impact on human behavior and health outcomes. Full article

This paper introduces a novel hyperparameter optimization framework for regression tasks called the Combined-Sampling Algorithm to Search the Optimized Hyperparameters (CASOH). Our approach enables hyperparameter tuning for deep learning models with two hidden layers and multiple types of hyperparameters, enhancing the model’s capacity to work with complex optimization problems. The primary goal is to improve hyperparameter tuning performance in deep learning models compared to conventional methods such as Bayesian Optimization and Random Search. Furthermore, CASOH is evaluated alongside the state-of-the-art hyperparameter reinforcement learning (Hyp-RL) framework to ensure a comprehensive assessment. The CASOH framework integrates the Metropolis-Hastings algorithm with a uniform random sampling approach, increasing the likelihood of identifying promising hyperparameter configurations. Specifically, we developed a correlation between the objective function and samples, allowing subsequent samples to be strongly correlated with the current sample by applying an acceptance probability in our sampling algorithm. The effectiveness of our proposed method was examined using regression datasets such as Boston Housing, Critical heat flux (CHF), Concrete compressive strength, Combined Cycle Power Plant, Gas Turbine CO, and NOx Emission, as well as an ‘in-house’ dataset of lattice-physics parameters generated from a Monte Carlo code for nuclear fuel assembly simulation. One of the primary goals of this study is to construct an optimized deep-learning model capable of accurately predicting lattice-physics parameters for future applications of machine learning in nuclear reactor analysis. Our results indicate that this framework achieves competitive accuracy compared to conventional random search and Bayesian optimization methods. The most significant enhancement was observed in the lattice-physics dataset, achieving a 56.6% improvement in prediction accuracy, compared to improvements of 53.2% by Hyp-RL, 44.9% by Bayesian optimization, and 38.8% by random search relative to the nominal prediction. While the results are promising, further empirical validation across a broader range of datasets would be helpful to better assess the framework’s suitability for optimizing hyperparameters in complex problems involving high-dimensional parameters, highly non-linear systems, and multi-objective optimization tasks. Full article

Accurately predicting grapevine yield and quality is critical for optimising vineyard management and ensuring economic viability. Numerous studies have reported the complexity in modelling grapevine yield and quality due to variability in the canopy structure, challenges in incorporating soil and microclimatic factors, and management practices throughout the growing season. The use of multimodal data and machine learning (ML) algorithms could overcome these challenges. Our study aimed to assess the potential of multimodal data (hyperspectral vegetation indices (VIs), thermal indices, and canopy state variables) and ML algorithms to predict grapevine yield components and berry composition parameters. The study was conducted during the 2019/20 and 2020/21 grapevine growing seasons in two South Australian vineyards. Hyperspectral and thermal data of the canopy were collected at several growth stages. Simultaneously, grapevine canopy state variables, including the fractional intercepted photosynthetically active radiation (fiPAR), stem water potential (Ψ_stem), leaf chlorophyll content (LCC), and leaf gas exchange, were collected. Yield components were recorded at harvest. Berry composition parameters, such as total soluble solids (TSSs), titratable acidity (TA), pH, and the maturation index (IMAD), were measured at harvest. A total of 24 hyperspectral VIs and 3 thermal indices were derived from the proximal hyperspectral and thermal data. These data, together with the canopy state variable data, were then used as inputs for the modelling. Both linear and non-linear regression models, such as ridge (RR), Bayesian ridge (BRR), random forest (RF), gradient boosting (GB), K-Nearest Neighbour (KNN), and decision trees (DTs), were employed to model grape yield components and berry composition parameters. The results indicated that the GB model consistently outperformed the other models. The GB model had the best performance for the total number of clusters per vine (R² = 0.77; RMSE = 0.56), average cluster weight (R² = 0.93; RMSE = 0.00), average berry weight (R² = 0.95; RMSE = 0.00), cluster weight (R² = 0.95; RMSE = 0.13), and average berries per bunch (R² = 0.93; RMSE = 0.83). For the yield, the RF model performed the best (R² = 0.97; RMSE = 0.55). The GB model performed the best for the TSSs (R² = 0.83; RMSE = 0.34), pH (R² = 0.93; RMSE = 0.02), and IMAD (R² = 0.88; RMSE = 0.19). However, the RF model performed best for the TA (R² = 0.83; RMSE = 0.33). Our results also revealed the top 10 predictor variables for grapevine yield components and quality parameters, namely, the canopy temperature depression, LCC, fiPAR, normalised difference infrared index, Ψ_stem, stomatal conductance (g_s), net photosynthesis (P_n), modified triangular vegetation index, modified red-edge simple ratio, and ANT_gitelson index. These predictors significantly influence the grapevine growth, berry quality, and yield. The identification of these predictors of the grapevine yield and fruit composition can assist growers in improving vineyard management decisions and ultimately increase profitability. Full article

This study investigates the combined effects of environmental pollutants (lead, cadmium, total mercury) and behavioral factors (alcohol consumption, smoking) on depressive symptoms in women. Data from the National Health and Nutrition Examination Survey (NHANES) 2017–2018 cycle, specifically exposure levels of heavy metals in blood samples, were used in this study. The analysis of these data included the application of descriptive statistics, linear regression, and Bayesian Kernel Machine Regression (BKMR) to explore associations between environmental exposures, behavioral factors, and depression. The PHQ-9, a well-validated tool that assesses nine items for depressive symptoms, was used to evaluate depression severity over the prior two weeks on a 0–3 scale, with total scores ranging from 0 to 27. Exposure levels of heavy metals were measured in blood samples. BKMR was used to estimate the exposure–response relationship, while posterior inclusion probability (PIP) in BKMR was used to quantify the likelihood that a given exposure was included in the model, reflecting its relative importance in explaining the outcome (depression) within the context of other predictors in the mixture. A descriptive analysis showed mean total levels of lead, cadmium, and total mercury at 1.21 µg/dL, 1.47 µg/L, and 0.80 µg/L, respectively, with a mean PHQ-9 score of 5.94, which corresponds to mild depressive symptoms based on the PHQ-9 scoring. Linear regression indicated positive associations between depression and lead as well as cadmium, while total mercury had a negative association. Alcohol and smoking were also positively associated with depression. These findings were not significant, but limitations in linear regression prompted a BKMR analysis. BKMR posterior inclusion probability (PIP) analysis revealed alcohol and cadmium as significant contributors to depressive symptoms, with cadmium (PIP = 0.447) and alcohol (PIP = 0.565) showing notable effects. Univariate and bivariate analyses revealed lead and total mercury’s strong relationship with depression, with cadmium showing a complex pattern in the bivariate analysis. A cumulative exposure analysis of all metals and behavioral factors concurrently demonstrated that higher quantile levels of combined exposures were associated with an increased risk of depression. Finally, a single variable-effects analysis in BKMR revealed lead, cadmium, and alcohol had a stronger impact on depression. Overall, the study findings suggest that from exposure to lead, cadmium, mercury, alcohol, and smoking, cadmium and alcohol consumption emerge as key contributors to depressive symptoms. These results highlight the need to address both environmental and lifestyle choices in efforts to mitigate depression. Full article

Counterparty risk, which combines market and credit risks, gained prominence after the 2008 financial crisis due to its complexity and systemic implications. Traditional management methods, such as netting and collateralization, have become computationally demanding under frameworks like the Fundamental Review of the Trading Book (FRTB). This paper explores the combined application of Gaussian process regression (GPR) and Bayesian quadrature (BQ) to enhance the efficiency and accuracy of counterparty risk metrics, particularly credit valuation adjustment (CVA). This approach balances excellent precision with significant computational performance gains. Focusing on fixed-income derivatives portfolios, such as interest rate swaps and swaptions, within the One-Factor Linear Gaussian Markov (LGM-1F) model framework, we highlight three key contributions. First, we approximate swaption prices using Bachelier’s formula, showing that forward-starting swap rates can be modeled as Gaussian dynamics, enabling efficient CVA computations. Second, we demonstrate the practical relevance of an analytical approximation for the CVA of an interest rate swap portfolio. Finally, the combined use of Gaussian processes and Bayesian quadrature underscores a powerful synergy between precision and computational efficiency, making it a valuable tool for credit risk management. Full article

Background: Emerging studies demonstrate that exposure to brominated flame retardants (BFRs) can have harmful effects on human health. Our study focused on the relationship between exposure to various BFRs and markers of liver function. Methods: To further explore the association between BFR exposure and liver function impairment, we used data from the National Health and Nutrition Examination Surveys (NHANES) for three cycles from 2009 to 2014, leaving 4206 participants (≥20 years of age) after screening. Nine BFRs and eight liver function tests (LFTs) were measured in the participants’ serum to represent BFRs and liver function impairment in vivo. To investigate whether there is a relationship between BFRs and health outcome, statistical research methods such as the weighted linear regression model, restricted cubic spline (RCS), weighted quantile sum (WQS), quantile-based g computing (QGC), and the Bayesian Kernel Machine Regression (BKMR) were used to evaluate the correlation between serum BFRs and LFTs. Results: The studies reveals that exposure to BFRs is associated with liver function biomarkers. In a weighted linear regression model, we found that PBB153, PBDE99, PBDE154, PBDE209, PBDE85 exposure was positively correlated with AST, ALT, GGT, ALP, TP, and SL risk. In RCS model, the nonlinear relationships between PBB153 and AST, ALT, and GGT and PBDE209 and ALT and TP are the most significant. The exposure to combined BFRs was positively correlated with AST, ALT, and GGT in WQS and QGC models. BKMR analysis showed that BFR exposure was positively correlated with AST, ALT, ALP, and GGT. Conclusions: Exposure to BFRs is associated with liver function impairment, suggesting that BFR exposure is potentially toxic to the human liver, but more in-depth studies are needed to explore this correlation. Full article