Regression Model For Prediction Research Articles

Semi-parametric single-index predictive regression models with cointegrated regressors

This paper considers the estimation of a semi-parametric single-index regression model that allows for nonlinear predictive relationships. This model is useful for predicting financial asset returns, whose observed behaviour resembles a stationary process, if the multiple nonstationary predictors are cointegrated. The presence of cointegrated regressors imposes a single-index structure in the model, and this structure not only balances the nonstationarity properties of the multiple predictors with the stationarity properties of asset returns but also avoids the curse of dimensionality associated with nonparametric regression function estimation. An orthogonal series expansion is used to approximate the unknown link function for the single-index component. We consider the constrained nonlinear least squares estimator of the single-index (or the cointegrating) parameters and the plug-in estimator of the link function, and derive their asymptotic properties. In an empirical application, we find some evidence of in-sample nonlinear predictability of U.S. stock returns using cointegrated predictors. We also find that the single-index model in general produces better out-of-sample forecasts than both the historical average benchmark and the linear predictive regression model.

Prediction of Early Antidepressant Efficacy in Patients with Major Depressive Disorder Based on Multidimensional Features of rs-fMRI and P11 Gene DNA Methylation: Prédiction de l'efficacité précoce d'un antidépresseur chez des patients souffrant du trouble dépressif majeur d'après les caractéristiques multidimensionnelles de la méthylation de l'ADN du gène P11 et de la IRMf-rs.

This study established a machine learning model based on the multidimensional data of resting-state functional activity of the brain and P11 gene DNA methylation to predict the early efficacy of antidepressant treatment in patients with major depressive disorder (MDD). A total of 98 Han Chinese MDD were analysed in this study. Patients were divided into 51 responders and 47 nonresponders according to whether the Hamilton Depression Rating Scale-17 items (HAMD-17) reduction rate was ≥50% after 2 weeks of antidepressant treatment. At baseline, the Illumina HiSeq Platform was used to detect the methylation of 74 CpG sites of the P11 gene in peripheral blood samples. Resting-state functional magnetic resonance imaging (rs-fMRI) scan detected the amplitude of low-frequency fluctuations (ALFF), regional homogeneity (ReHo), and functional connectivity (FC) in 116 brain regions. The least absolute shrinkage and selection operator analysis method was used to perform feature reduction and feature selection. Four typical machine learning methods were used to establish support vector machine (SVM), random forest (RF), Naïve Bayes (NB), and logistic regression (LR) prediction models based on different combinations of functional activity of the brain, P11 gene DNA methylation and clinical/demographic features after screening. The SVM model based on ALFF, ReHo, FC, P11 methylation, and clinical/demographic features showed the best performance, with 95.92% predictive accuracy and 0.9967 area under the receiver operating characteristic curve, which was better than RF, NB, and LR models. The multidimensional data features combining rs-fMRI, DNA methylation, and clinical/demographic features can predict the early antidepressant efficacy in MDD.

Can we more precisely classify exposure to antenatal depression and anxiety in multivariable prediction models of pregnancy and birth outcomes: a population-based cohort study

BackgroundDepression and anxiety are highly prevalent within the perinatal period and have been associated with myriad adverse pregnancy and birth outcomes. In this study, we sought to investigate whether population-based data can be used to build complex, longitudinal mental health histories that improve our ability to predict adverse pregnancy and birth outcomes.MethodsUsing population-based, administrative datasets, we examined individual-level mental health services use of all birth parents who delivered a live infant in British Columbia, Canada between April 1, 2000, and December 31, 2013, and who were registered with the provincial Medical Services Plan for over 100 days per year from 10-years preconception to 1-year postpartum. We operationalized variables to proxy severity, persistence, and frequency of depression/anxiety from preconception through pregnancy, then constructed predictive regression models for postpartum depression/anxiety and preterm birth.ResultsPredictive modeling of postpartum depression/anxiety and preterm birth revealed better predictions and stronger performance with inclusion of a more detailed preconception mental health history. Incorporating dichotomous indicators for depression/anxiety across preconception markedly improved predictive power and model fit. Our detailed measures of mental health service use predicted postpartum depression/anxiety much better than preterm birth. Variables characterizing use of outpatient psychiatry care and outpatient visit frequency within the first five years preconception were most useful in predicting postpartum depression/anxiety and preterm birth, respectively.ConclusionWe report a feasible method for developing and applying more nuanced definitions of depression/anxiety within population-based data. By accounting for differing profiles of mental health treatment, mental health history, and current mental health, we can better control for severity of underlying conditions and thus better understand more complex associations between antenatal mental health and adverse outcomes.

Multi-faceted analysis and prediction for the outbreak of pediatric respiratory syncytial virus.

Respiratory syncytial virus (RSV) is a significant cause of pediatric hospitalizations. This article aims to utilize multisource data and leverage the tensor methods to uncover distinct RSV geographic clusters and develop an accurate RSV prediction model for future seasons. This study utilizes 5-year RSV data from sources, including medical claims, CDC surveillance data, and Google search trends. We conduct spatiotemporal tensor analysis and prediction for pediatric RSV in the United States by designing (i) a nonnegative tensor factorization model for pediatric RSV diseases and location clustering; (ii) and a recurrent neural network tensor regression model for county-level trend prediction using the disease and location features. We identify a clustering hierarchy of pediatric diseases: Three common geographic clusters of RSV outbreaks were identified from independent sources, showing an annual RSV trend shifting across different US regions, from the South and Southeast regions to the Central and Northeast regions and then to the West and Northwest regions, while precipitation and temperature were found as correlative factors with the coefficient of determination R2≈0.5, respectively. Our regression model accurately predicted the 2022-2023 RSV season at the county level, achieving R2≈0.3 mean absolute error MAE < 0.4 and a Pearson correlation greater than 0.75, which significantly outperforms the baselines with P-values <.05. Our proposed framework provides a thorough analysis of RSV disease in the United States, which enables healthcare providers to better prepare for potential outbreaks, anticipate increased demand for services and supplies, and save more lives with timely interventions.

Forming characteristics analysis of variable-process alternated overlapping strategy based on contour description for laser melting deposition

To predict the geometric characteristics and improve the forming quality and macro-micro defects of multi-track overlapping cladding layer effectively, the experimental research of laser melting deposition single-track Co-based alloy on 42CrMo substrate was carried out. The influence trends of laser process parameters on the single-track cladding height and cladding width were analyzed, and the regression prediction models were established. A variable-process alternated overlapping strategy was proposed using the geometric functions to fit the single-track profile. The surface forming quality and macro-micro defect of different overlapping cladding layers were compared and evaluated. The results showed that the cladding height and cladding width regression models established by an improved optimization algorithm had an excellent prediction effect. The variable-process alternated overlapping cladding layer prepared by the parabolic function had a flat surface, and the fluctuation distance was 81.56 μm, which was significantly improved compared with other overlapping strategies. The surface flatness of the continuous overlapping cladding layer was the worst and the spheroidization defect was the most unsatisfied. The internal defects of the constant-process alternated overlapping cladding layer were the most terrible, with more non-fusion and cracks caused by oxides. The variable-process alternated overlapping strategy proposed in this study can effectively prepare a multi-track cladding layer with a smooth surface and dense interior, which provides essential theoretical guidance for the near-net forming of component surface deposition and repair.

Development of experimental error-Driven model for prediction of corrosion rates of amines based on their chemical structures

This work investigated the relationships between amine corrosion rates and their chemical structural properties for application in the development of a Gaussian Process Regression (GPR) model for chemical structure-based prediction of corrosion rate of any amine. The GPR model accounted for experimental errors, which widened its scope to accurately predict the true corrosion rates, being restricted only to error associated with the trained model. The Average Absolute Deviation (AAD) between experimental corrosion rates and model predicted rates was 4.26 % for the test data, and 5.32 % for two test data unknown to the model. This showed that the model is generalizable and its predictions are accurate. This work also developed a user-friendly Graphical-User Interface, which allows a user to define any amine's structure to provide needed information to calculate its surface tension and steric effects for use as input variables to the model in predicting the corrosion rate of the amine.

A novel quantum genetic algorithm with the application in LS-SVR

The characteristics of LS-SVR are analyzed. LS-SVR is fitted for modeling small samples and high dimensional data, but the performance of LS-SVR is related to the specific data distribution, the kind of kernel function, its related kernel parameter, and the penalty coefficient. In this paper, the radial basis function is applied as the kernel function of LS-SVR, and the real double-chain coding target gradient quantum genetic algorithm (DCQGA) is applied to optimize the kernel parameter and penalty item coefficient of LS-SVR, then the regression prediction model DCQGALSSVR is proposed. It is of great significance to build an accurate and reliable fault prediction model for the health monitoring and fault diagnosis of liquid rocket engines. The thrust of a liquid rocket engine is an important factor in its health monitoring. By predicting the thrust change value and comparing the predicted value with the engine thrust threshold, it can be predicted whether the engine will fail at a certain time. In this paper, the proposed DCQGALSSVR model is used to model the thrust of a liquid rocket engine. The simulation results show that the average relative error is 0.37% using LSSVR for modeling on 12 test samples, and is 0.3186% using DCQGALSSVR on the same samples. It can be seen that DCQGALSSVR is effective for the health monitoring of liquid rocket engines, so it has a certain promotion significance.

Explainable boosted combining global and local feature multivariate regression model for deformation prediction during braced deep excavations

PurposeAn accurate prediction of the deformation of retaining structures is critical for ensuring the stability and safety of braced deep excavations, while the high nonlinear and complex nature of the deformation makes the prediction challenging. This paper proposes an explainable boosted combining global and local feature multivariate regression (EB-GLFMR) model with high accuracy, robustness and interpretability to predict the deformation of retaining structures during braced deep excavations.Design/methodology/approachDuring the model development, the time series of deformation data is decomposed using a locally weighted scatterplot smoothing technique into trend and residual terms. The trend terms are analyzed through multiple adaptive spline regressions. The residual terms are reconstructed in phase space to extract both global and local features, which are then fed into a gradient-boosting model for prediction.FindingsThe proposed model outperforms other established approaches in terms of accuracy and robustness, as demonstrated through analyzing two cases of braced deep excavations.Research limitations/implicationsThe model is designed for the prediction of the deformation of deep excavations with stepped, chaotic and fluctuating features. Further research needs to be conducted to expand the model applicability to other time series deformation data.Practical implicationsThe model provides an efficient, robust and transparent approach to predict deformation during braced deep excavations. It serves as an effective decision support tool for engineers to ensure the stability and safety of deep excavations.Originality/valueThe model captures the global and local features of time series deformation of retaining structures and provides explicit expressions and feature importance for deformation trends and residuals, making it an efficient and transparent approach for deformation prediction.

Machine learning regression algorithms to predict short-term efficacy after anti-VEGF treatment in diabetic macular edema based on real-world data

The objective of this retrospective study was to predict short-term efficacy of anti-vascular endothelial growth factor (VEGF) treatment in diabetic macular edema (DME) using machine learning regression models. Real-world data from 279 DME patients who received anti-VEGF treatment at Ineye Hospital of Chengdu University of TCM between April 2017 and November 2022 were analyzed. Eight machine learning regression models were established to predict four clinical efficacy indicators. The accuracy of the models was evaluated using mean absolute error (MAE), mean square error (MSE) and coefficient of determination score (R2). Multilayer perceptron had the highest R2 and lowest MAE among all models. Regression tree and lasso regression had similar R2, with lasso having lower MAE and MSE. Ridge regression, linear regression, support vector machines and polynomial regression had lower R2 and higher MAE. Support vector machine had the lowest MSE, while polynomial regression had the highest MSE. Stochastic gradient descent had the lowest R2 and high MAE and MSE. The results indicate that machine learning regression algorithms are valuable and effective in predicting short-term efficacy in DME patients through anti-VEGF treatment, and the lasso regression is the most effective ML algorithm for developing predictive regression models.

A machine learning algorithm-based model for predicting the risk of non-suicidal self-injury among adolescents in western China: A multicentre cross-sectional study

The prevalence of non-suicidal self-injurious (NSSI) in adolescents is high. However, few studies exist to predict NSSI in this population. This study employed a machine learning algorithm to develop a predictive model, aiming to more accurately assess the risk of NSSI in Chinese adolescents. Sociodemographic, psychological data were collected in 50 schools in western China. We constructed eXtreme Gradient Boosting (XGBoost) model and multivariate logistic regression model to predict the risk of NSSI and nomograms are plotted. Data from 13,304 adolescents were used for model development, with an average age of 13.00 ± 2.17 years; 617 individuals (4.6 %) reported non-suicidal self-injury (NSSI) behaviors. The results of the XGBoost model showed that depression and anxiety were the top two predictors of NSSI in adolescents. The results of the multivariate logistic regression model showed that the risk factors for adolescent NSSI behaviors include: gender (being female), Age, Living with whom (father), History of psychiatric consultation, Stress, Depression, Anxiety, Tolerance, Emotion abreaction. The XGBoost prediction and multivariate logistic regression model showed good predictive ability. Nomograms can serve as clinical tools to assist in intervention measures, helping adolescents reduce NSSI behaviors and improve their mental and physical well-being.

Diffuse interface method for solid composite propellant ignition and regression

Solid Composite Propellants (SCPs) are extensively used in the field of propulsion for their chemical and mechanical stability in long-term storage, and for having simple production and operation processes. Computational modeling enables cost reduction, increased efficiency, and greater coverage of the configuration space in the SCP design process. However, accurate and efficient SCP modeling presents a number of numerical challenges. A primary obstacle in modeling these systems is capturing the complex evolving interface. Recently, it has been shown that the phase-field method has a strong ability to model the combustion behavior of SCPs, implicitly capturing the topological evolution at a relatively low computational cost. Initial phase-field methods show promise in their ability to do predictive regression modeling but require a number of approximations and heuristic modeling methods. This work presents a new formulation for the phase field regression model that combines a thermal solver with an Arrhenius rate law to model interface regression using a comprehensive and physics-based approach. This improves the capability of previous methods by increasing the number of kinematic forces that are accounted for, and allowing the study of thermal diffusivity in the system. It also enables the integration of a fully coupled solid-fluid interface. To demonstrate the efficacy of the model, it is applied and calibrated to a homogeneous monopropellant (ammonium perchlorate). The model is validated for a range of temperatures, with a reasonable quantitative match to experimental data. It was also demonstrated that the model recovered the relationship between ignition time and heat flux, with no fitting required. Overall, the method showed great capability of reproducing experimental data by matching temperature, burn rate, and thermal diffusivity profiles. Statement of SignificanceA new diffuse interface method is developed for calculating ignition and regression rates in SCPs. While this builds on previous work in diffuse interface modeling of SCPs, it is novel in its coupling to thermal transport, as well as its development of (and coupling to) a approximation for gas phase heat flux. The model is shown to reproduce experimental regression rate data with reasonable accuracy. Moreover, it quantitatively captures ignition behavior with no additional modifications to the model. The model is implemented in a high performance computational framework that is able to resolve large, three-dimensional mesostuctures.

Comparison the effects of KNN and linear regression models in lung cancer prediction

Lung cancer has a range of major factors like smoking, yellow gingers, anxiety, etc. now, the problem of this research is that prediction for lung cancer. Prediction for lung cancer is a complex problem that is not suitable for human prediction. This research using a dataset was from Kaggle. There are 16 rows and 309 columns. To determine the k nearest neighbors (KNN) algorithm and linear regression algorithm, which one is better for prediction for lung cancer, and which coefficient will be best effective. This research uses mixed method research. In this work, when the K of the KNN algorithm equals 7 or 2, the effectiveness of the KNN model is best, when the alpha of the linear regression algorithm equals 20, the effectiveness of the linear regression model is best. The KNN model is better than the linear regression model, though the difference is negligible. In the future, more emphasis can be placed on using a wider range of algorithms or using more extensive and generalized dataset, as well as assessing the efficiency of the algorithm on larger datasets.

Cardiovascular metrics on CT pulmonary angiography in patients with pulmonary hypertension — re-evaluation under the updated guidelines of pulmonary hypertension

PurposeTo re-assess cardiovascular metrics on computed tomography pulmonary angiography (CTPA) in predicting pulmonary hypertension (PH) under the 2022 ESC/ERS guidelines.Materials and methodsThis observational study retrospectively included 272 patients (female 143, mean age = 54.9 ± 12.5 years old) with suspected PH. 218 patients were grouped to evaluate cardiovascular metrics on CTPA and develop a binary logistic regression model. The other 54 patients were grouped into the validation group to assess the performance of the prediction model under the updated criteria. Based on mean pulmonary artery pressure (mPAP), patients were divided into three groups: group A consisted of patients with mPAP ≤ 20 mmHg, group B included patients with 20 mmHg < mPAP < 25 mmHg, and group C comprised patients with mPAP ≥ 25 mmHg. Cardiovascular metrics among the three groups were compared, and receiver operating characteristic curves (ROCs) were used to evaluate the performance of cardiovascular metrics in predicting mPAP > 20 mmHg.ResultsThe main pulmonary arterial diameter (MPAd), MPAd/ascending aorta diameter ratio (MPAd/AAd ratio), and right ventricular free wall thickness (RVFWT) showed significant differences among the three groups (p < 0.05). The area under curve (AUC) of MPAd was larger than MPAd/AAd ratio and RVFWT. A MPAd cutoff value of 30.0 mm has a sensitivity of 83.1% and a specificity of 90.4%. The AUC of the binary logistic regression model (Z = − 12.98187 + 0.31053 MPAd + 1.04863 RVFWT) was 0.938 ± 0.018. In the validation group, the AUC, sensitivity, specificity, and accuracy of the prediction model were 0.878, 92.7%, 76.9%, and 88.9%, respectively.ConclusionUnder the updated criteria, MPAd with a threshold value of 30.0 mm has better sensitivity and specificity in predicting PH. The binary logistic regression model may improve the diagnostic accuracy.Critical relevance statementUnder the updated criteria, the main pulmonary arterial diameter with a threshold value of 30.0 mm has better sensitivity and specificity in predicting pulmonary hypertension. The binary logistic regression model may improve diagnostic accuracy.Key points• According to 2022 ESC/ERS guidelines, a MPAd cutoff value of 30.0 mm has better sensitivity and specificity in predicting mPAP > 20 mmHg• A binary logistic regression model (Z = − 12.98187 + 0.31053 MPAd + 1.04863 RVFWT) was developed and had a sensitivity, specificity, and accuracy of 92.7%, 76.9%, and 88.9% in predicting mPAP > 20 mmHg.• A binary logistic regression prediction model outperforms MPAd in predicting mPAP > 20 mmHg.Graphical

Multiphase flow rate prediction using chained multi-output regression models

Virtual flow meters (VFM) are emerging as an attractive and cost-effective alternative to traditional multiphase flow meters to meet monitoring demands, reduce operational costs, and improve oil recovery efficiency. However, no previous studies have accounted for the correlations between the oil, water, and gas flow rates when developing machine learning models. This study proposes a chained regression model for multiphase flow rate prediction to account for such relationships. Real-field data consists of 375 data points for sensory measurements, including pressure, temperature, and choke opening levels, and 42 data points for oil, water, and gas flow rates that were measured downstream of the wellhead, which was acquired over one month. Two robust algorithms, Support Vector Machine (SVM) and Gaussian Process (GP), were employed to develop the chained regression model. The evaluation metrics such as mean absolute percentage error (MAPE) for all the models were estimated using a repeated hold-out approach of cross-validation. The response variables, i.e., the three flow rates, were moderate to strongly correlated. The results showed that the GP-based chain regression model was significantly better than the direct model using the GP algorithm for oil (MAPE: 2.07% vs. 2.27%) and gas (MAPE: 2.5% vs. 2.65%) flow rate prediction (p < 0.01). Overall, the chained model is generally superior to the direct model for flow rate prediction, which was supported by the ranking scores, consistently outperforming the latter in both SVM (79 vs. 87) and GP (64 vs. 70) based approaches. The sensitivity analysis showed that the GP-based chained model accurately predicted oil, water, and gas flow rates within 39.45 m3/day, 14.69 m3/day, and 5.63 m3/day, respectively, of the actual values for approximately 92% of the data points. This study’s findings can be instrumental in designing and developing practical and accurate VFM for multiphase flow rate prediction.

Effect of nano-gypsum on mechanical properties cement admixed marginal silty soil

Even though the chemical stabilization is by far the most common ground improvement technique, very few studies have been conducted on the joint incorporation of two or more additives (cement-nanogypsum mix) to stabilise soft soil. This study investigates the effect on the mechanical properties of cement-stabilised silty soft soil (CSS) using nano-gypsum (NG). Unconfined compression strength (UCS) test trials were conducted to achieve soft soil conditions. The effect of NG and cement on soft soil was investigated by performing Atterberg limit, compaction, UCS, and Direct shear tests. The soil was treated with four percentages (10%, 15%, 20%, and 25%) of cement and with three percentages (1%, 1.5%, and 2%) of NG by its dry unit weight. The test results showed that the plasticity index of the soil was reduced significantly by the addition of stabilizers (Cement-NG mix) making the soil stiffer. The compaction tests suggested that optimum cement content was 20% for CSS and for cement-NG mix maximum strength was achieved at cement: NG proportion of 20:1. The unconfined compression strength (UCS) was increased by 9.11 times in comparison to untreated soft soil at cement: NG proportion of 20:1.5. The direct shear test (DST) suggested that there was an increase in cohesion by 4.44 times in comparison to the untreated sample at the soil–cement-NG combination of 78.5: 20: 1.5. However, the angle of internal friction remained almost unchanged. The development of cementitious substances was confirmed through XRD spectroscopy. Microstructural and chemical properties were observed using combined FESEM-EDAX analysis and Fourier transform infrared spectroscopy (FTIR). The multivariate linear regression (MLR) predictive model was developed for the unconfined compressive strength and failure strain as a function of various parameters considered in the study. The test results demonstrated that the combination of cement and NG can result in remarkable improvement in the geotechnical properties of soft soil. The use of NG may also reduce the demand for cement in deep cement mixing technique, which eventually reduces the carbon footprint and renders the ground improvement technique, ecologically beneficial.

The importance of patch shape at threshold occupancy: functional patch size within total habitat amount.

The habitat amount hypothesis (HAH) stresses the importance of total patch amount over the size of individual patches in determining species richness within a local landscape. However, the absence of some species from patches too small to contain a territory would be inconsistent with the HAH. Using the association of territory size with body size and the circle as optimal territory shape, we tested several HAH predictions of threshold patch occupancy and richness of 19 guilds of primarily insectivorous breeding birds. We characterized 16 guild-associated patch types at high spatial resolution and assigned one type to each guild. We measured functional patch size as the largest circle that fit within each patch type occurring in a local landscape. Functional patch size was the sole or primary predictor in regression models of species richness for 15 of the 19 guilds. Total patch amount was the sole or primary variable in only 2 models. Quantifying patch size at high resolution also demonstrated that breeding birds should be absent from patches that are too small to contain a territory and larger species should occur only in larger patches. Functional patch size is a readily interpretable metric that helps explain the habitat basis for differences in species composition and richness between areas. It provides a tool to assess the combined effects of patch size, shape and perforation on threshold habitat availability, and with total patch amount can inform design and/or evaluation of conservation, restoration or enhancement options for focal taxa or biodiversity in general.

In silico Prediction of Sodium-Glucose Co-Transporter-2 (SGLT2) Inhibition Activity by Allium Fistulosum Compound Based on SkelSpheres Molecular Descriptor

The Sodium-Glucose co-transporter-2 (SGLT2) inhibitor represents a novel agent for the treatment of type 2 diabetes. Drugs of this class function by inhibiting glucose reabsorption in the kidneys, thereby controlling blood glucose levels. It is known that SGLT2 inhibitors activate the AMPK signaling pathway by increasing the expression and activity of AMP-activated protein kinase (AMPK). In vivo tests have demonstrated that ethanolic and aqueous extracts of Welsh onion leaves (Allium fistulosum L) can reduce body weight, liver weight, adipocyte size, and enhance AMP-activated protein kinase (AMPK) expression. In this study, the inhibitory activity (IC50) of compounds within Allium fistulosum against SGLT2 was predicted using the Support Vector Regression (SVR) predictive model and the SkelSpheres descriptor. The results of the predicted IC50 measurements for compounds present in the 70% ethanol extract of Allium fistulosum in silico indicate that 4 tyramine derivatives and 1 decursidate compound exhibit Excellent or Potent inhibitor activity criteria (IC50 &lt; 1 µM). Among these, the four tyramine group compounds are the isomers N-trans-feruloyltyramine and N-cis-feruloyltyramine, as well as the isomers N-trans-feruloyl-3'-methoxytyramine and N-cis-feruloyl-3'-methoxytyramine. The findings of this study suggest that the ability of Allium fistulosum to enhance AMPK expression is possibly achieved through the inhibition of SGLT2.

Sensory optimization of an instant brown rice cereal containing tigernut and soybean

The aim of this study was to determine the optimum ingredient formulation for an instant rice-based cereal enriched with tigernut and soybean flours. An extreme vertices design involving three (3) components (brown rice flour, tigernut flour and soybean flour) was used. A slurry of the three (3) was dried on a single drum dryer at 120 °C and 5 rpm. Mixture regression modeling was used to assess the impact of each component on the functional quality and sensory attributes properties of the drum dried product. Graphical optimization of the formulation was performed by superimposing contour plots of individual sensory attributes examined. Predicted regression models showed that tigernut flour, followed closely by rice flour, had the largest effect on overall acceptance of the product. The optimum formulation for an acceptable drum dried product was determined to be rice flour – 46.6 %, tigernut flour – 39.1 % and soybean flour – 14.3 %. The product was stable during storage, as only marginal increment was recorded in the quality attributes assessed. This study provides an avenue for enhancing the utilization potential of both brown rice and tigernut.

An exploration of the association between family functioning and nonsuicidal self-injury among Chinese adolescents with mood disorders

Background and objectivesThis study explored the correlation between nonsuicidal self-injury (NSSI) and family functioning among adolescents aged 12 to 17 years with mood disorders. MethodsA total of 142 participants were clinically assessed for NSSI, with 85 in the NSSI group and 57 in the non-NSSI group. The correlation between NSSI and family functioning was compared and a regression prediction model was constructed to determine the risk probability of NSSI. ResultsA significant association was found between family functioning and NSSI (P = 0.017). The correlation between adolescents with NSSI and gender, communication, affective responsiveness, and behaviour control was statistically significant. A nomogram graph and ROC curve were constructed, with an AUC of 0.772. ConclusionThe findings support the notion that family functioning is associated with a higher risk for NSSI among adolescents with mood disorders. Furthermore, gender, communication, affective responsiveness, and behaviour control may be contributing factors.

18F-FDG PET/CT-based radiomics model for predicting the degree of pathological differentiation in non-small cell lung cancer: a multicentre study

To explore the value of 2-[18F]-fluoro-2-deoxy-d-glucose (FDG) positron-emission tomography (PET)/computed tomography (CT)-based radiomics model for predicting the degree of pathological differentiation in non-small-cell lung cancer (NSCLC). Clinical characteristics of 182 NSCLC patients from four centres were collected, and radiomics features were extracted from 18F-FDG PET/CT images. Three logistic regression prediction models were established: clinical model; radiomics model; and nomogram combining radiomics signatures and clinical features. The predictive ability of the models was assessed using receiver operating characteristics curve analysis. Patients from centre 1 were assigned randomly to the training and internal validation cohorts (7:3 ratio); patients from centres 2-4 served as the external validation cohort. The area under the curve (AUC) values for the clinical model in the training, internal validation, and external validation cohort were 0.74 (95% confidence interval [CI]=0.64-0.84), 0.64 (95% CI=0.46-0.81), and 0.74 (95% CI=0.60-0.88), respectively. In the training (AUC: 0.84 [95% CI=0.77-0.92]), internal validation (AUC: 0.81 [95% CI=0.67-0.95]), and external validation cohorts (AUC: 0.74 [95% CI=0.58-0.89]), the radiomics model showed good predictive ability for differentiation. Compared to the clinical and radiomics models, the nomogram has relatively better diagnostic performance, and the AUC values for nomogram in the training, internal validation, and external validation cohort were 0.86 (95% CI=0.78-0.93), 0.83 (95% CI=0.70-0.96), and 0.77 (95% CI=0.62-0.92), respectively. The 18F-FDG PET/CT-based radiomics model showed good ability for predicting the degree of differentiation of NSCLC. The nomogram combining the radiomics signature and clinical features has relatively better diagnostic performance.