Partial Regression Research Articles

Child maltreatment and behavioral health outcomes in child welfare: Exploring the roles of severity and polyvictimization

BackgroundChild maltreatment and polyvictimization are known risk factors for long-term detrimental health and development outcomes, including behavioral health challenges. However, effects from specific types and combinations of maltreatments are unclear. This study examined the association between maltreatment or polyvictimization and behavioral health in a child welfare sample. Participants and settingMedical records of children with child welfare involvement with at least one behavioral health condition (i.e., mental, behavioral or neurodevelopmental disorder, ICD-10 F01-F99) between 1/1/2018–12/31/2021 were extracted from a large, academic hospital system. MethodsBehavioral health complexity was categorized as non-chronic, non-complex chronic, or complex chronic using the Pediatric Medical Complexity Algorithm. Partial proportional logistic regression models adjusted for age, sex, race/ethnicity, caregiver type, and physical health complexity generated odds of behavioral health complexity by maltreatment type (physical abuse, sexual abuse, neglect) and maltreatment combinations. ResultsThe analytic sample included 3992 participants (mean age 7.6 (Standard Deviation, 5.0) 44 % female, 29 % white, 32 % black, 22 % Hispanic). Participants who experienced physical abuse (Odds Ratio [OR]: 1.79, 95 % Confidence Interval [CI]: 1.10–2.91), or neglect (OR: 1.69, 95 % CI: 1.38–2.07) were more likely to have increasing behavioral health complexity versus those without maltreatment. Participants with both physical abuse and neglect were over twice as likely (OR: 2.44, 95 % CI: 1.88–3.16) to have increasing behavioral health complexity versus those who did not experience maltreatment. ConclusionResults emphasize the differential impacts of maltreatment and polyvictimization exposures on behavioral health complexity among children with child welfare involvement that can guide risk assessment and clinical care.

Rapid and low-cost detection of saffron (Crocus sativus L.) adulteration using smartphone videos and spectral data fusion strategy

Saffron (Crocus sativus L.) is the most expensive spice in the world and is highly susceptible to economically motivated adulteration. Hyperspectral imaging (HSI) and near-infrared (NIR) spectroscopy are recently popular techniques for rapid, non-destructive detection of saffron adulteration. However, the high cost and measurement complexity of these techniques make them less suitable for consumer-level applications. In this work, a smartphone video-based system combined with chemometrics is used to detect saffron adulteration. A smartphone is utilised to capture short videos of pure and adulterated saffron powder samples illuminated by its colour-changing screen. The video frames are decomposed into RGB colour images and converted into spectral-like data. Partial least squares regression is used to model the relationship between data and saffron purity. The smartphone video-based system obtains a coefficient of determination of 0.9774 for prediction, which is comparable to reference techniques such as NIR spectroscopy and HSI. Moreover, it is efficient in presenting distribution maps related to saffron purity. In addition, when used in conjunction with the smartphone video-based system, HSI and NIR spectroscopy achieve higher performance without significantly increasing measurement cost and complexity. Such results suggest that the smartphone video-based system has the potential to be a viable primary screening and auxiliary tool for detecting saffron adulteration.

On function-on-function linear quantile regression

We present two innovative functional partial quantile regression algorithms designed to accurately and efficiently estimate the regression coefficient function within the function-on-function linear quantile regression model. Our algorithms utilize functional partial quantile regression decomposition to effectively project the infinite-dimensional response and predictor variables onto a finite-dimensional space. Within this framework, the partial quantile regression components are approximated using a basis expansion approach. Consequently, we approximate the infinite-dimensional function-on-function linear quantile regression model using a multivariate quantile regression model constructed from these partial quantile regression components. To evaluate the efficacy of our proposed techniques, we conduct a series of Monte Carlo experiments and analyze an empirical dataset, demonstrating superior performance compared to existing methods in finite-sample scenarios. Our techniques have been implemented in the ffpqr package in .

A 44-year balanced fertilizer application affected rill erosion resistance by changing humus, aggregates, and polyvalent cation

Fertilizer application can affect the physicochemical properties of soil, such as the contents of large aggregates, humus, and exchangeable cations, thereby influencing soil erosion resistance. However, the rill erosion resistance and its key influencing factors of soil following long-term balanced fertilizer application remains unclear. This study aimed to analyze the change in rill erosion resistance following 44 years of balanced fertilizer application (No changes in the type of fertilizer) to non-calcareous soils and establish a Partial Least Squares Regression (PLSR) model of rill erodibility (kd) and soil critical shear stress (τc) to changes in the physical and chemical properties of the soil. Five treatments were designed: (1) CK (no fertilizer applied), (2) N (nitrogen), (3) NP (nitrogen plus phosphorus), (4) NK (nitrogen plus potassium), and (5) NPK (nitrogen, phosphorus, and potassium). Compared to CK, the N, NP, NK, and NPK application significantly increased τc by 49.6, 96.7, 73.6, and 36.2 %, respectively. Whereas, kd increased significantly only in the NPK treatment group. The optimal partial least squares regression model showed that mean weight diameter (MWD) had the greatest positive influence on soil critical shear stress, followed by fulvic acid (FA) content, whereas water-dissolved substances had a negative influence. Long-term balanced fertilizer application can increase MWD and τc by combining micro-aggregates and humus into large aggregates. Ca2+ content had the greatest positive effect on kd. Compared with that of CK, exchangeable Ca2+ content increased significantly with NP and NPK application (7.9 and 34.3 %, respectively). Ca2+ can increase kd by binding to the polar functional groups in FA to promote the shedding of hydration shells in large aggregates. Among all treatments, the NP treatment showed the best performance for reducing kd and increasing τc. This study could contribute to the understanding of the rill erosion process and modeling in non-calcareous soils and offer a reference for agricultural erosion control treatments.

Characterization of Key Aroma Compounds of Soy Sauce-like Aroma Produced in Ferment of Soybeans by Bacillus subtilis BJ3-2.

Fermented soybeans are popular among many for their rich soy sauce-like aroma. However, the precise composition of this aroma remains elusive, with key aroma compounds unidentified. In this study, we screened the candidate genes ilvA and serA in BJ3-2 based on previous multi-omics data, and we constructed three mutant strains, BJ3-2-ΔserA, BJ3-2-ΔilvA, and BJ3-2-ΔserAΔilvA, using homologous recombination to fermented soybeans with varying intensities of soy sauce-like aroma. Our objective was to analyze samples that exhibited different aroma intensities resulting from the fermented soybeans of BJ3-2 and its mutant strains, thereby exploring the key flavor compounds influencing soy sauce-like aroma as well analyzing the effects of ilvA and serA on soy sauce-like aroma. We employed quantitative descriptive sensory analysis (QDA), gas chromatography-olfactometry-mass spectrometry (GC-O-MS), relative odor activity value analysis (rOAV), principal component analysis (PCA), orthogonal partial least squares-discriminant analysis (OPLS-DA), and partial least squares regression analysis (PLSR). QDA revealed the predominant soy sauce-like aroma profile of roasted and smoky aromas. GC-MS detected 99 volatile components, predominantly pyrazines and ketones, across the four samples, each showing varying concentrations. Based on rOAV (>1) and GC-O, 12 compounds emerged as primary contributors to soy sauce-like aroma. PCA and OPLS-DA were instrumental in discerning aroma differences among the samples, identifying five compounds with VIP > 1 as key marker compounds influencing soy sauce-like aroma intensity levels. Differential analyses of key aroma compounds indicated that the mutant strains of ilvA and serA affected soy sauce-like aroma mainly by affecting pyrazines. PLSR analysis indicated that roasted and smoky aromas were the two most important sensory attributes of soy sauce-like aroma, with pyrazines associated with roasted aroma and guaiacol associated with smoky aroma. In addition, substances positively correlated with the intensity of soy sauce-like aroma were verified by additional experiments. This study enhances our understanding of the characteristic flavor compounds in soy sauce-like aroma ferments, provides new perspectives for analyzing the molecular mechanisms of soy sauce-like aroma formation, and provides a theoretical framework for the targeted enhancement of soy sauce-like aroma in various foods.

Quantitative predictions of protein and total flavonoids content in Tartary and common buckwheat using near-infrared spectroscopy and chemometrics

A rapid method was developed for determining the total flavonoid and protein content in Tartary buckwheat by employing near-infrared spectroscopy (NIRS) and various machine learning algorithms, including partial least squares regression (PLSR), support vector regression (SVR), and backpropagation neural network (BPNN). The RAW-SPA-CV-SVR model exhibited superior predictive accuracy for both Tartary and common buckwheat, with a high coefficient of determination (R2p = 0.9811) and a root mean squared error of prediction (RMSEP = 0.1071) for flavonoids, outperforming both PLSR and BPNN models. Additionally, the MMN-SPA-PSO-SVR model demonstrated exceptional performance in predicting protein content (R2p = 0.9247, RMSEP = 0.3906), enhancing the effectiveness of the MMN preprocessing technique for preserving the original data distribution. These findings indicate that the proposed methodology could efficiently assess buckwheat adulteration analysis. It can also provide new insights for the development of a promising method for quantifying food adulteration and controlling food quality.

THE INFLUENCE OF BLOCKHOLDER OWNERSHIP , PROFITABILITY, AND FIRM SIZE ON TAX AGGRESSIVITY

In Indonesia, foreign direct investment is increasing, but in the field, companies with foreign capital say they are making losses to avoid paying taxes, so this is very counterproductive by opening up foreign investment, but the companies are actually losing money both fiscally and commercially. This research aims to analyze the influence of blockholder ownership , profitability, and firm size on tax aggressiveness. This research uses the data analysis method that will be used in this research, namely partial and multiple regression analysis, where the processing uses descriptive statistical analysis. This research uses computer program tools to manage data in the form of Eviews software version 10 . The research results show that the blockholder ownership variable has no effect on tax aggressiveness, but the profitability and firm size variables do tax aggressiveness. So that service companies are expected to pay more attention to the possibility of tax aggressiveness occurring both internally and externally to the company, and the government to tighten and clarify the contents of regulations regarding tax aggressiveness so that companies truly comply with the obligation to pay taxes

Using visible and near infrared spectroscopy and machine learning for estimating total petroleum hydrocarbons in contaminated soils

Petroleum pollution in soil is very damaging to the areas affected by the accidental release of petroleum hydrocarbons and has destructive impacts on natural resources and environmental health. Therefore, its monitoring and analysis are critical, however, due to the cost and time associated with chemical approaches, finding a quick and cost-effective analytical method is valuable. This study was conducted to evaluate the potential of using visible near infrared (Vis-NIR) spectroscopy to predict total petroleum hydrocarbons (TPH) in polluted soils around the Shadegan ponds, in southern Iran. One hundred soil samples showing various degrees of pollution were randomly collected from topsoil (0–10 cm). The soil samples were analyzed for TPH using Vis-NIR reflectance spectroscopy in the laboratory and then following application of preprocessing transformation, partial least squares PLS regression as well as two machine learning models including random forest (RF), and support vector machine (SVM) were examined. The results showed that the reflectance values at 1725 nm and 2311 nm, respectively, served as indicative TPH reflectance features, exhibiting weaker reflection with rising TPH. Among the preprocessing methods, the baseline correction method indicated the highest performance than the others. According to the evaluation model criteria in the validation dataset, the efficiency of the three selected models was observed in the following order SVM > RF > PLS regression. The SVM model provided the best performance in the validation dataset with r2 = 0.85, root mean of square (RMSEP = 1.59 %, and the ratio of prediction to deviation (RPD) = 2.6. Overall, this study provided strong evidence supporting the considerable potential of Visible-NIR spectroscopy as a rapid and cost-effective technique for estimating TPH levels in oil-contaminated soils, surpassing traditional chemical analytical methods. Applying the mid-infrared spectrum (MIR) in combination with Visible-NIR data is expected to provide more comprehensive and accurate results when assessing soils in polluted areas, thereby enhancing the accuracy and reliability of the results across a diverse range of soil types.

High-precision estimation of plant alpha diversity in different ecosystems based on Sentinel-2 data

At present, the accuracy of remote sensing estimation models of plant alpha diversity is generally low, and high-precision estimation models in deciduous broadleaved forest (DBF), deciduous coniferous forest (DCF) and evergreen coniferous forest (ECF) are still lacking. The main purpose of this study is to construct high-precision remote sensing models for plant alpha diversity in multiple ecosystems at global scale. Normalized Difference Vegetation Index (NDVI) were derived from Sentinel-2 data. NDVI and NDVI based spectral diversity/heterogeneity indices were selected as predictive variables, and alpha diversity indices were selected as response variables. Simple linear regression (SLR), partial linear regression (PLSR), and random forest (RF) models were used to evaluate the predictive ability of the predictive variables against the response variables under six ecosystems (evergreen broadleaved forest (EBF), DBF, ECF, DCF, shrub, and grassland), and to compare the estimated robustness of various spectral diversity indices. In terms of prediction accuracy, the SLR models were the worst, and the PLSR model were average. RF performed best, outperforming most current models. Especially in DBF, ECF, shrub and grassland, the determination coefficient R2 of RF models can be as high as 0.9. In terms of the prediction of α-diversity, the prediction effect of species richness was better than that of Shannon index, Simpson index and Pielou index. The higher the vegetation complexity, the more accurate the assessment of vegetation α-diversity tends to be, especially in DBF, shrub and grassland. According to the importance of predictive variables and model stability evaluation results, NDVI, standard deviation of NDVI (SD), and NDVI derived Shannon’s diversity index (Sha), Cumulative Residual Entropy (CRE), Pielou’s evenness index (Pie), Hill’s numbers (Hill), Berger-Parker’s diversity index (Ber), Parametric Rao’s index of quadratic entropy(paRao) are all powerful indicators for predicting plant alpha diversity. Among them, the prediction performance of NDVI and SD is better. This study is not only an exploration of the practicability of R package “rasterdiv”, but also an attempt to construct high-precision remote sensing estimation models of plant alpha diversity at global scale.

A detection method of oil content for maize kernels based on CARS feature selection and deep sparse autoencoder feature extraction

To achieve accurate, rapid, and non-destructive oil content determination in maize, a neural fitting model that combines feature selection and feature extraction is proposed. Competitive adaptive re-weighted sampling (CARS) is used to choose features, while the deep sparse autoencoder (DSAE) network is utilized to extract features. The 160 spectral data from the near-infrared spectra public datasets of maize served as experimental samples. Several preprocessing approaches were tested, and the first-order derivatives fared the best. To capture the various degrees of abstract features in spectral data, SSAE networks with two or three hidden layers are developed. The number of nodes in the network's hidden layer (30, 50, 70, 100, 200, 300, respectively) and the network's sparsity parameter (0.001, 0.004, 0.007, 0.01, 0.04, 0.07, 0.1, 0.2, …, 1) are tuned to generate partial least squares regression (PLSR) models for testing the feature learning effect. The highest performance comes from a three-layer network with 200 hidden layer nodes and a sparsity parameter of 0.04. This network extracts three levels of features from the preprocessed spectral data: F1, F2, and F3. Full_cars, F1_cars, F2_cars, and F3_cars are obtained using the CARS algorithm for variable selection on the preprocessed spectral data, F1, F2, and F3, respectively. They are then integrated into a final feature set to build a neural-fitting network (FNN). After training and testing, the test set has a correlation coefficient of 0.964205 and an mean square error (MSE) of 0.00636809. Comparing this model to support vector machine regression (SVR), PLSR, and gaussian process regression (GPR), the findings demonstrate that the model described in this study outperforms the others in terms of fitting accuracy and generalization performance. To summarize, this paper introduces a new regression analysis method based on near-infrared spectra.

Spatial and Temporal Dynamics in Vegetation Greenness and Its Response to Climate Change in the Tarim River Basin, China

Vegetation in ecologically sensitive regions has experienced significant alterations due to global climate change. The underlying mechanisms remain somewhat obscure owing to the spatial heterogeneity of influencing factors, particularly in the Tarim River Basin (TRB) in China. Therefore, this study targets the TRB, analyzing the spatial and temporal dynamics of vegetation greenness and its climatic determinants across multiple spatial scales. Utilizing Normalized Difference Vegetation Index (NDVI) data, vegetation greenness trends over the past 23 years were assessed, with future projections based on the Hurst exponent. Partial correlation and multiple linear regression analyses were employed to correlate NDVI with temperature (TMP), precipitation (PRE), and potential evapotranspiration (PET), elucidating NDVI’s response to climatic variations. Results revealed that from 2000 to 2022, 90.1% of the TRB exhibited an increase in NDVI, with a significant overall trend of 0.032/decade (p < 0.01). The difference in NDVI change across sub-basins and vegetation types highlighted the spatial disparity in greening. Notable greening predominantly occurred near rivers at lower elevations and in extensive cropland areas, with projections indicating continued greening in some regions. Conversely, future trends mainly suggested a shift towards browning, particularly in higher-elevation areas with minimal human influence. From 2000 to 2022, the TRB experienced a gradual increase in TMP, PRE, and PET. The latter two factors were significantly correlated with NDVI, indicating their substantial role in greening. However, vegetation sensitivity to climate change varied across sub-basins, vegetation types, and elevations, likely due to differences in plant characteristics, hydrothermal conditions, and human disturbances. Despite climate change influencing vegetation dynamics in 51.5% of the TRB, its impact accounted for only 25% of the total NDVI trend. These findings enhance the understanding of vegetation ecosystems in arid regions and provide a scientific basis for developing ecological protection strategies in the TRB.

Quantitative and qualitative evaluation of maltodextrin products in the industry using near‐infrared spectroscopy

SummaryMaltodextrin is a crucial ingredient in food and pharmaceutical sectors. Traditional quality assessment methods for maltodextrin are destructive and time consuming. This study aimed to employ near‐infrared (NIR) spectroscopy and chemometrics to differentiate maltodextrin variants and measure their quality parameters efficiently. NIR spectra were recorded in the range of 12 000–4000 cm−1 using the transflectance mode. The classification model effectively distinguished maltodextrin types based on their dextrose equivalent (DE) values using techniques such as partial least squares‐discriminant analysis and supervised self‐organising map (SSOM). Moreover, quality parameters including moisture content, DE value, maltose, maltotriose, pH, and SO2 were quantitatively assessed using partial least squares regression (PLSR) and SSOM models. Particularly, PLSR provided better results, with residual predictive deviation values exceeding 2.5 for moisture content, DE values, maltose, and maltotriose. These models can be applied for use in both laboratory settings and industrial monitoring.

Combination model for freshness prediction of pork using VIS/NIR hyperspectral imaging with chemometrics.

This study aimed to develop an enhanced model for predicting pork freshness by integrating hyperspectral imaging and chemometric analysis. A total of 30 Longissimus thoracis samples from three sows were stored under vacuum conditions at 4 ± 2℃ for 27 days to acquire data. The freshness prediction model for pork loin employed partial least squares regression (PLSR) with Monte Carlo data augmentation. Total bacterial count (TBC) and volatile basic nitrogen (VBN), which exhibited increases correlating with metabolite changes during storage, were designated as freshness indicators. Metabolic contents of the sample were quantified using NMR. A total of 64 metabolites were identified, with 34 and 35 showing high correlations with TBC and VBN, respectively. Lysine and malate for TBC (R2 = 0.886) and methionine and niacinamide for VBN (R2 = 0.909) were identified as the main metabolites in each indicator by Model 1. Model 2 predicted main metabolites using HSI spectral data. Model 3, which predicted freshness indicators with HSI spectral data, demonstrated high prediction coefficients; TBC R2p = 0.7220 and VBN R2p = 0.8392. Furthermore, the combination model (Model 4), utilizing HSI spectral data and predicted metabolites from Model 2 to predict freshness indicators, improved the prediction coefficients compared to Model 3; TBC R2p = 0.7583 and VBN R2p = 0.8441. Combining HSI spectral data with metabolites correlated to the meat freshness may elucidate why certain HSI spectra indicate meat freshness and prove to be more effective in predicting the freshness state of pork loin compared to using only HSI spectral data.

Inversion of Cotton Soil and Plant Analytical Development Based on Unmanned Aerial Vehicle Multispectral Imagery and Mixed Pixel Decomposition

In order to improve the accuracy of multispectral image inversion of soil and plant analytical development (SPAD) of the cotton canopy, image segmentation methods were utilized to remove the background interference, such as soil and shadow in UAV multispectral images. UAV multispectral images of cotton bud stage canopies at three different heights (30 m, 50 m, and 80 m) were acquired. Four methods, namely vegetation index thresholding (VIT), supervised classification by support vector machine (SVM), spectral mixture analysis (SMA), and multiple endmember spectral mixture analysis (MESMA), were used to segment cotton, soil, and shadows in the multispectral images of cotton. The segmented UAV multispectral images were used to extract the spectral information of the cotton canopy, and eight vegetation indices were calculated to construct the dataset. Partial least squares regression (PLSR), Random forest (FR), and support vector regression (SVR) algorithms were used to construct the inversion model of cotton SPAD. This study analyzed the effects of different image segmentation methods on the extraction accuracy of spectral information and the accuracy of SPAD modeling in the cotton canopy. The results showed that (1) The accuracy of spectral information extraction can be improved by removing background interference such as soil and shadows using four image segmentation methods. The correlation between the vegetation indices calculated from MESMA segmented images and the SPAD of the cotton canopy was improved the most; (2) At three different flight altitudes, the vegetation indices calculated by the MESMA segmentation method were used as the input variable, and the SVR model had the best accuracy in the inversion of cotton SPAD, with R2 of 0.810, 0.778, and 0.697, respectively; (3) At a flight altitude of 80 m, the R2 of the SVR models constructed using vegetation indices calculated from images segmented by VIT, SVM, SMA, and MESMA methods were improved by 2.2%, 5.8%, 13.7%, and 17.9%, respectively, compared to the original images. Therefore, the MESMA mixed pixel decomposition method can effectively remove soil and shadows in multispectral images, especially to provide a reference for improving the inversion accuracy of crop physiological parameters in low-resolution images with more mixed pixels.

Interpretation of high dimensional definitive screening designs assisted by bootstrapped partial least squares regression

Definitive screening design (DSD) has become a widely used type of Design of Experiments for chemical, pharmaceutical and biopharmaceutical processes and product development due to its optimization properties with an estimation of main, interaction, and squared variable effects with a minimum number of experiments. These high dimensional DOEs with more variables than samples, and with partly correlated variables, make the statistical interpretation frequently challenging. The purpose of the study was to test bootstrap PLSR using a heredity procedure to select the variable subset to be finally evaluated by MLR. The heredity selection was used on bootstrap T values given by original PLSR coefficients (B) divided on the bootstrap estimated standard deviation. The investigated fractional weighted and non-parametric bootstrap PLSR resulted in same variable selection outcome and final models in this study.A simulation study with 7 main variables and 12 tested literature real data DSDs with 4, 5, 7 and 8 main variables showed improved model performance for small and particularly for large DSDs for the bootstrap PLSR MLR methods compared to two common DSD reference methods; DSD fit definitive screening and AICc forward stepwise regression (AICc FSR). Variable selection accuracy and predictive ability were significantly improved by the investigated method in 6 out of 13 DSDs compared to the best model from either of the two reference methods. The remaining 7 DSDs gave the same model as best reference model. Strong heredity was found to provide the best models for all real data in this study. The use of the heredity procedure on the percent non-zero SVEM FSR variable effects followed by MLR showed promising results. AICc Lasso regression was among other methods partially tested and was found to set almost all variables to zero effect when tested on three large minimum DSDs. While the DSD fit definitive screening method may often be the first choice for DSD, the heredity bootstrap PLSR MLR and heredity SVEM FSR MLR may be alternative methods to improve the variable selection and model precision.

A Hybrid Synthetic Minority Oversampling Technique and Deep Neural Network Framework for Improving Rice Yield Estimation in an Open Environment

Quick and accurate prediction of crop yields is beneficial for guiding crop field management and genetic breeding. This paper utilizes the fast and non-destructive advantages of an unmanned aerial vehicle equipped with a multispectral camera to acquire spatial characteristics of rice and conducts research on yield estimation in an open environment. The study proposes a yield estimation framework that hybrids synthetic minority oversampling technique (SMOTE) and deep neural network (DNN). Firstly, the framework used the Pearson correlation coefficient to select 10 key vegetation indices and determine the optimal feature combination. Secondly, it created a dataset for data augmentation through SMOTE, addressing the challenge of long data collection cycles and small sample sizes caused by long growth cycles. Then, based on this dataset, a yield estimation model was trained using DNN and compared with partial least squares regression (PLSR), support vector regression (SVR), and random forest (RF). The experimental results indicate that the hybrid framework proposed in this study performs the best (R2 = 0.810, RMSE = 0.69 t/ha), significantly improving the accuracy of yield estimation compared to other methods, with an R2 improvement of at least 0.191. It demonstrates that the framework proposed in this study can be used for rice yield estimation. Additionally, it provides a new approach for future yield estimation with small sample sizes for other crops or for predicting numerical crop indicators.

Establishment of a metabolite diagnostic model for the risk of diabetic nephropathy in type 2 diabetic population: Based on a cross-sectional study in China

IntroductionThis study aimed to investigate the correlation between various plasma metabolites and the likelihood of developing diabetic nephropathy (DN) and construct a diagnostic model for DN in Chinese patients with type 2 diabetes mellitus (T2DM). MethodsA cross-sectional investigation was conducted in a hospital setting. Based on medical data, a total of 743 patients from a tertiary hospital were selected and categorized into two groups: the diabetic nephropathy group (DN group) and the non-diabetic nephropathy group (non-DN group). Plasma levels of metabolites, including amino acids and acylcarnitines, were determined using a laser counter measurement system (LC-MS). Subsequently, partial least-squares regression was used to assess the significance of these metabolites. Receiver operating characteristic (ROC) curves were generated for factors that ranked highest in terms of relevance. Model performance was assessed using the curve (AUC). ResultsOf the 743 patients with T2DM admitted to the hospital, 145 had DN. Compared with the non-DN group, the DN group exhibited elevated systolic blood pressure (P ​= ​0.001), high-density lipoprotein cholesterol (P ​= ​0.01), and low-density lipoprotein cholesterol (P ​= ​0.042). Additionally, the DN group had a higher prevalence of stroke patients (P ​< ​0.001) and diabetic retinopathy patients (P ​< ​0.001). Finally, a risk model that included citrulline, leucine, tyrosine, valine, propionylcarnitine (C3), and palmitoylcarnitine (C16) was developed. This model achieved an AUC of 0.709, with a 95% confidence interval (CI) ranging from 0.626 to 0.793. ConclusionsA diagnostic model consisting of six plasma metabolites to assess the risk of DN in Chinese patients with T2DM may provide clues for future research.

A hyperspectral metal concentration inversion method using attention mechanism and graph neural network

Soil heavy metal contamination has emerged as a global environmental concern, posing significant risks to human health and ecosystem integrity. Hyperspectral technology, with its non-invasive, non-destructive, large-scale, and high spectral resolution capabilities, shows promising applications in monitoring soil heavy metal pollution. Traditional monitoring methods are often time-consuming, labor-intensive, and expensive, limiting their effectiveness for rapid, large-scale assessments. This study introduces a novel deep learning method, SpecMet, for estimating heavy metal concentrations in naturally contaminated agricultural soils using hyperspectral data. The SpecMet model extracts features from hyperspectral data using convolutional neural networks (CNNs) and achieves end-to-end prediction of soil heavy metal concentrations by integrating attention mechanisms and graph neural networks. Results demonstrate that the OR-SpecMet model, which utilizes raw spectral data, achieves optimal prediction performance, significantly surpassing traditional machine learning methods such as multiple linear regression, partial least squares regression, and support vector machine regression in estimating concentrations of lead (Pb), copper (Cu), cadmium (Cd), and mercury (Hg). Moreover, training specialized OR-SpecMet models for individual heavy metals better accommodates their unique spectral-concentration relationships, enhancing overall estimation accuracy while achieving a 20.3 % improvement in predicting low-concentration mercury. The OR-SpecMet method showcases the superior performance and extensive application potential of deep learning techniques in precise soil heavy metal pollution monitoring, offering new insights and reliable technical support for soil pollution prevention and agricultural ecosystem protection. The code and datasets used in this study are publicly available at: https://github.com/zhang2lei/metal.git.

Dietary factors may be associated with measures of ultrasound-derived skeletal muscle echo intensity.

Skeletal muscle echo intensity (EI) is affected by ageing and physical activity; however, the effects of nutrition are less understood. The aim of this study was to explore whether habitual nutrient intake may be associated with ultrasound-derived EI. Partial least squares regression (PLSR) models were trained on an initial sample (n=100, M=45; F=55; 38±15 years) to predict EI of two quadriceps muscles from 19 variables, using the "jack-knife" function within the "pls" package (RStudio), which was then tested in an additional dataset (n=30, M=13; F=17; 38±16 years). EI was determined using B-mode ultrasonography of the rectus femoris (RF) and vastus lateralis (VL) and nutritional intake determined via 3-day weighed food diaries. Mean daily intake of specific nutrients were included as predictor variables with age, sex, and self-reported physical activity. PLSR training model 1 explained ∼52% and model 2 ∼46% of the variance in RF and VL EI, respectively. Model 1 also explained ∼35% and model 2 ∼30% of the variance in RF and VL EI in the additional testing dataset. Age and biological sex were associated with EI in both models (P<0.025). Dietary protein (RF: β = -7.617, VL: β = -7.480), and selenium (RF: β = -7.144, VL: β = -4.775) were associated with EI in both muscles (P<0.05), whereas fibre intake (RF: β = -5.215) was associated with RF EI only and omega-3 fatty acids (n-3/ω-3 FAs, RF: β = 3.145) with VL EI only (P<0.05). Therefore, absolute protein, selenium, fibre, and n-3 FAs may be associated with skeletal muscle EI, although further mechanistic work is required before claiming causal inference.

Crucial textural properties of braised pork to evaluate the oral mastication behavior and its water distribution to influence tenderness.

The complex composition of braised pork, including lean meat, pigskin, and fat, makes it difficult for sensory evaluation of its texture properties. This study investigated the correlation between sensory texture attributes and physicochemical properties to achieve an objective and comprehensive evaluation of the texture of braised pork. Sensory analysis demonstrated that the overall texture acceptability of braised pork was significantly and negatively influenced by sensory texture attributes (including sensory hardness, chewiness, and toughness), while it was positively impacted by sensory adhesiveness, softness, and juiciness. Shear force and texture profile analysis (TPA) variables, reflecting mastication behavior, were used to characterize the textural properties of braised pork. They were closely related to water distribution, with a higher proportion of immobilized water (P21), indicating a higher water holding capacity and a more tender texture. Correlation analysis between sensory texture attributes and physicochemical properties through partial least squares regression further revealed significant associations between shear force, TPA variables, and sensory texture attributes. Moreover, the proportion of immobilized water (P21) significantly and negatively affected sensory hardness and chewiness, whereas the proportion of free water (P22) significantly influenced sensory toughness. Sensory texture attributes could be well predicted by the physicochemical properties by projecting test samples onto calibration models established by known samples. Therefore, a combination of sensory and instrumental measures can reliably reflect the texture properties of braised pork. PRACTICAL APPLICATION: The combination of sensory and instrumental methods is an effective strategy to accurately and objectively evaluate the texture properties of braised pork, which overcomes the limitations caused by the complexity of the composition and texture traits of braised pork. The accurate evaluation and standardization of texture properties is an important premise for the repeatable and stable cooking of traditional braised pork. Furthermore, this research method and findings can also be applied to guide the procedural optimization of smart appliances (e.g., induction cookers) for cooking braised pork.