Modeling of polygalacturonase enzyme activity and biomass production by <Emphasis Type="Italic">Aspergillus sojae</Emphasis> ATCC 20235

Aspergillus sojae, which is used in the making of koji, a characteristic Japanese food, is a potential candidate for the production of polygalacturonase (PG) enzyme, which of a major industrial significance. In this study, fermentation data of an A. sojae system were modeled by multiple linear regression (MLR) and artificial neural network (ANN) approaches to estimate PG activity and biomass. Nutrient concentrations, agitation speed, inoculum ratio and final pH of the fermentation medium were used as the inputs of the system. In addition to nutrient conditions, the final pH of the fermentation medium was also shown to be an effective parameter in the estimation of biomass concentration. The ANN parameters, such as number of hidden neurons, epochs and learning rate, were determined using a statistical approach. In the determination of network architecture, a cross-validation technique was used to test the ANN models. Goodness-of-fit of the regression and ANN models was measured by the R ² of cross-validated data and squared error of prediction. The PG activity and biomass were modeled with a 5-2-1 and 5-9-1 network topology, respectively. The models predicted enzyme activity with an R ² of 0.84 and biomass with an R ² value of 0.83, whereas the regression models predicted enzyme activity with an R ² of 0.84 and biomass with an R ² of 0.69.     

Construction of Predictive Models to Describe Apparent and Complex Viscosity Values of O/W Model System Meat Emulsions Using Adaptive Neuro – Fuzzy Inference System (ANFIS) and Artificial Neural Networks (ANN)

This paper introduces an adaptive neuro ?C fuzzy inference system (ANFIS) and artificial neural networks (ANN) models to predict the apparent and complex viscosity values of model system meat emulsions. Constructed models were compared with multiple linear regression (MLR) modeling based on their estimation performance. The root mean square error (RMSE), mean absolute error (MAE) and determination coefficient (R ²) statistics were performed to evaluate the accuracy of the models tested. Comparison of the models showed that the ANFIS model performed better than the ANN and MLR models to estimate the apparent and complex viscosity values of the model system meat emulsions. Coefficients of determination (R ²) calculated for estimation performance of ANFIS modeling to predict apparent and complex viscosity of the emulsions were 0.996 and 0.992, respectively. Similar R ² values (0.991 and 0.985) were obtained when estimating the performance of the ANN model. In the present study, use of the constructed ANFIS models can be suggested to effectively predict the apparent and complex viscosity values of model system meat emulsions.     

The application of Artificial Neural Network (ANN) model to the simulation of denitrification rates in mesocosm-scale wetlands

Denitrification and its regulating factors are of great importance to aquatic ecosystems, as denitrification is a critical process to nitrogen removal. Additionally, a by-product of denitrification, nitrous oxide, is a much more potent greenhouse gas than carbon dioxide. However, the estimation of denitrification rates is usually clouded with uncertainty, mainly due to high spatial and temporal variations, as well as complex regulating factors within wetlands. This hampers the development of general mechanistic models for denitrification as well, as most previously developed models were empirical or exhibited low predictability with numerous assumptions. In this study, we tested Artificial Neural Network (ANN) as an alternative to classic empirical models for simulating denitrification rates in wetlands. ANN, multiple linear regression (MLR) with two different methods, and simplified mechanistic models were applied to estimate the denitrification rates of 2-year observations in a mesocosm-scale constructed wetland system. MLR and simplified mechanistic models resulted in lower prediction power and higher residuals compared to ANN. Although the stepwise linear regression model estimated similar average values of denitrification rates, it could not capture the fluctuation patterns accurately. In contrast, ANN model achieved a fairly high predictability, with an R² of 0.78 for model validation, 0.93 for model calibration (training), and a low root mean square error (RMSE) together with low bias, indicating a high capacity to simulate the dynamics of denitrification. According to a sensitivity analysis of the ANN, non-linear relationships between input variables and denitrification rates were well explained. In addition, we found that water temperature, denitrifying enzyme activity (DEA), and DO accounted for 70% of denitrification rates. Our results suggest that the ANN developed in this study has a greater performance in simulating variations in denitrification rates than multivariate linear regressions or simplified nonlinear mechanistic model.     

Comparison of Regression Methods for Modeling Intensive Care Length of Stay

Intensive care units (ICUs) are increasingly interested in assessing and improving their performance. ICU Length of Stay (LoS) could be seen as an indicator for efficiency of care. However, little consensus exists on which prognostic method should be used to adjust ICU LoS for case-mix factors. This study compared the performance of different regression models when predicting ICU LoS. We included data from 32,667 unplanned ICU admissions to ICUs participating in the Dutch National Intensive Care Evaluation (NICE) in the year 2011. We predicted ICU LoS using eight regression models: ordinary least squares regression on untransformed ICU LoS,LoS truncated at 30 days and log-transformed LoS; a generalized linear model with a Gaussian distribution and a logarithmic link function; Poisson regression; negative binomial regression; Gamma regression with a logarithmic link function; and the original and recalibrated APACHE IV model, for all patients together and for survivors and non-survivors separately. We assessed the predictive performance of the models using bootstrapping and the squared Pearson correlation coefficient (R²), root mean squared prediction error (RMSPE), mean absolute prediction error (MAPE) and bias. The distribution of ICU LoS was skewed to the right with a median of 1.7 days (interquartile range 0.8 to 4.0) and a mean of 4.2 days (standard deviation 7.9). The predictive performance of the models was between 0.09 and 0.20 for R², between 7.28 and 8.74 days for RMSPE, between 3.00 and 4.42 days for MAPE and between −2.99 and 1.64 days for bias. The predictive performance was slightly better for survivors than for non-survivors. We were disappointed in the predictive performance of the regression models and conclude that it is difficult to predict LoS of unplanned ICU admissions using patient characteristics at admission time only.     

Predictive modelling of Fe(III) precipitation in iron removal process for bioleaching circuits

In this study, the applicability of three modelling approaches was determined in an effort to describe complex relationships between process parameters and to predict the performance of an integrated process, which consisted of a fluidized bed bioreactor for Fe³⁺ regeneration and a gravity settler for precipitative iron removal. Self-organizing maps were used to visually evaluate the associations between variables prior to the comparison of two different modelling methods, the multiple regression modelling and artificial neural network (ANN) modelling, for predicting Fe(III) precipitation. With the ANN model, an excellent match between the predicted and measured data was obtained (R ² = 0.97). The best-fitting regression model also gave a good fit (R ² = 0.87). This study demonstrates that ANNs and regression models are robust tools for predicting iron precipitation in the integrated process and can thus be used in the management of such systems.     

Modeling daily chlorophyll a dynamics in a German lowland river using artificial neural networks and multiple linear regression approaches

Phytoplankton biomass is an important indicator for water quality, and predicting its dynamics is thus regarded as one of the important issues in the domain of river ecology and management. However, the vast majority of models in river systems have focused mostly on flow prediction and water quality with very few applications to biotic parameters such as chlorophyll a (Chl a). Based on a 1.5-year measured dataset of Chl a and environmental variables, we developed two modeling approaches [artificial neural networks (ANN) and multiple linear regression (MLR)] to simulate the daily Chl a dynamics in a German lowland river. In general, the developed ANN and MLR models achieved satisfactory accuracy in predicting daily dynamics of Chl a concentrations. Although some peaks and lows were not predicted, the predicted and the observed data matched closely by the MLR model with the coefficient of determination (R ²), Nash–Sutcliffe efficiency (NS), and the root mean square error (RMSE) of 0.53, 0.53, and 2.75 for the calibration period and 0.63, 0.62, and 1.94 for the validation period, respectively. Likewise, the results of the ANN model also illustrated a good agreement between observed and predicted data during calibration and validation periods, which was demonstrated by R ², NS, and RMSE values (0.68, 0.68, and 2.27 for the calibration period, 0.55, 0.66 and 2.12 for the validation period, respectively). According to the sensitivity analysis, Chl a concentration was highly sensitive to dissolved inorganic nitrogen, nitrate–nitrogen, autoregressive Chl a, chloride, sulfate, and total phosphorus. We concluded that it was possible to predict the daily Chl a dynamics in the German lowland river based on relevant environmental factors using either ANN or MLR models. The ANN model is well suited for solving non-linear and complex problems, while the MLR model can explicitly explore the coefficients between independent and dependent variables. Further studies are still needed to improve the accuracy of the developed models.     

Statistical optimization of the phytoremediation of arsenic by Ludwigia octovalvis- in a pilot reed bed using response surface methodology (RSM) versus an artificial neural network (ANN)

In this study, the removal of arsenic (As) by plant, Ludwigia octovalvis, in a pilot reed bed was optimized. A Box-Behnken design was employed including a comparative analysis of both Response Surface Methodology (RSM) and an Artificial Neural Network (ANN) for the prediction of maximum arsenic removal. The predicted optimum condition using the desirability function of both models was 39 mg kg^?1 for the arsenic concentration in soil, an elapsed time of 42 days (the sampling day) and an aeration rate of 0.22 L/min, with the predicted values of arsenic removal by RSM and ANN being 72.6% and 71.4%, respectively. The validation of the predicted optimum point showed an actual arsenic removal of 70.6%. This was achieved with the deviation between the validation value and the predicted values being within 3.49% (RSM) and 1.87% (ANN). The performance evaluation of the RSM and ANN models showed that ANN performs better than RSM with a higher R² (0.97) close to 1.0 and very small Average Absolute Deviation (AAD) (0.02) and Root Mean Square Error (RMSE) (0.004) values close to zero. Both models were appropriate for the optimization of arsenic removal with ANN demonstrating significantly higher predictive and fitting ability than RSM.     

Foraging and predator avoidance: a test of a patch choice model with juvenile bluegill sunfish

Summary In situations where foraging sites vary both in food reward and predation risk, conventional optimal foraging models based on the criterion of maximizing net rate of energy intake commonly fail to predict patch choice by foragers. Recently, an alternative model based on the simple rule when foraging, minimize the ratio of mortality rate (u) to foraging rate (f) was successful in predicting patch preference under such conditions (Gilliam and Fraser 1987). In the present study, I compare the predictive ability of these two models under conditions where available patches vary both in predation hazard and foraging returns. Juvenile bluegill sunfish (Lepomis macrochirus) were presented with a choice between two patches of artificial vegetation differing in stem density (i.e. 100, 250, and 500 stems/m²) in which to forage. Each combination (100:250, 250:500, or 100:500) was presented in the absence, presence, and after exposure to a bass predator (Micropterus salmoides). Which patch of vegetation bluegills chose to forage in, and foraging rate within each patch were recorded. Independent measurements of bluegill foraging rate and risk of mortality in the three stem densities provided the data for predicting patch choice by the two models. With no predator, preference between plots was consistent with the maximize energy intake per unit time rule of conventional optimality models. However, with a predator present, patch preference switched to match a minimize u/f criterion. Finally, when tested shortly after exposure to a predator (i.e. 15 min), bluegill preference appeared to be in a transitional phase between these two rules. Results are discussed with respect to factors determining the distribution of organisms within beds of aquatic vegetation.     

Artificial neural networking to estimate the leaf area for invasive plant Wedelia trilobata

Leaf area are very important parameter for the understanding of growth and physiological responses of invasive plant species under different environmental factors. This study was conducted to build non-destructive leaf area model of Wedelia trilobata that were grown in greenhouse. Regression analysis and artificial neural network (ANN) approaches were used for the development of leaf area model with the help of leaf length and width of 262 plants samples. In selection of best method under both techniques, the lower value of mean absolute error (MAE), root mean square error (RMSE), mean absolute percentage error (MAPE) and higher value of R² were considered. According to the results it was found that ANN have higher value of (R² = 0.96) and lower value of error (MAE = 0.023, RMSE = 0.379, MAPE = 0.001) than regression analysis (R² = 0.94, MAE = 0.111, RMSE = 1.798, MAPE = 0.0005). It was concluded that error between predicted and actual value was less under ANN. Therefore, ANN model approach can be used as an alternating method for the estimation of leaf area. Through estimation of leaf area, invasive plant growth can predict under different environment conditions.     

Predicting major complications in patients undergoing laparoscopic and open hysterectomy for benign indications

Background:Hysterectomy, the most common gynecological operation, requires surgeons to counsel women about their operative risks. We aimed to develop and validate multivariable logistic regression models to predict major complications of laparoscopic or abdominal hysterectomy for benign conditions.Methods:We obtained routinely collected health administrative data from the English National Health Service (NHS) from 2011 to 2018. We defined major complications based on core outcomes for postoperative complications including ureteric, gastrointestinal and vascular injury, and wound complications. We specified 11 predictors a priori. We used internal–external cross-validation to evaluate discrimination and calibration across 7 NHS regions in the development cohort. We validated the final models using data from an additional NHS region.Results:We found that major complications occurred in 4.4% (3037/68 599) of laparoscopic and 4.9% (6201/125 971) of abdominal hysterectomies. Our models showed consistent discrimination in the development cohort (laparoscopic, C-statistic 0.61, 95% confidence interval [CI] 0.60 to 0.62; abdominal, C-statistic 0.67, 95% CI 0.64 to 0.70) and similar or better discrimination in the validation cohort (laparoscopic, C-statistic 0.67, 95% CI 0.65 to 0.69; abdominal, C-statistic 0.67, 95% CI 0.65 to 0.69). Adhesions were most predictive of complications in both models (laparoscopic, odds ratio [OR] 1.92, 95% CI 1.73 to 2.13; abdominal, OR 2.46, 95% CI 2.27 to 2.66). Other factors predictive of complications included adenomyosis in the laparoscopic model, and Asian ethnicity and diabetes in the abdominal model. Protective factors included age and diagnoses of menstrual disorders or benign adnexal mass in both models and diagnosis of fibroids in the abdominal model.Interpretation:Personalized risk estimates from these models, which showed moderate discrimination, can inform clinical decision-making for people with benign conditions who may require hysterectomy.

Hysterectomy is one of the most frequently performed surgical procedures. Canada has one of the highest rates of hysterectomy globally, with one-third of women undergoing this procedure before 60 years of age.¹ Minimal access approaches are favoured by both clinicians and patients,² and the proportion of hysterectomies being undertaken by a laparoscopic approach has increased substantially in many countries over the last 10 years.^3–7 The evidence-based medicine paradigm for surgical approaches to hysterectomy for benign disease advocates that the chosen surgical approach should be discussed with the patient by their surgeon and decided in light of the relative benefits and risks.² This advice is echoed by national guidelines.^8,9Most clinicians undertaking hysterectomy will intuitively identify patient characteristics that have the potential to increase the complexity and complications of surgery. A 2016 systematic review of studies that reported significant associations between patient characteristics and surgical outcomes for laparoscopic hysterectomy and a 2020 population-based prospective cohort study using data from the Danish hysterectomy database have suggested that older age, race, raised body mass index (BMI), diabetes mellitus, increased uterine weight, fibroids, endometriosis and adhesions are predictors of complications in patients undergoing hysterectomy for benign indications.^10,11 However, assimilating this information to individualize and anticipate the precise risk for each patient if there are multiple factors present can be challenging. A 2020 systematic review reported that surgeons in other specialties were outperformed by risk prediction models in estimating postoperative risk and outcomes; their discriminatory ability showed greater variation (C-statistic 0.51–0.75) than other risk prediction tools.¹²Patients should be given information about potential risks before surgery to manage expectations.¹³ This is especially important when surgery is considered for benign disease because nonsurgical options are often available.Our aim was to generate prediction models that can be used in conjunction with a surgeon’s intuition to enhance preoperative patient counselling and match the advances made in the technical aspects of surgery. We sought to quantify the proportion of patients who underwent hysterectomy for benign disease and will have a major complication, and to develop and validate prognostic models to individualize this risk, using a national data set.     

Comparison of artificial neural network and logistic regression models for predicting in-hospital mortality after primary liver cancer surgery

Background

Since most published articles comparing the performance of artificial neural network (ANN) models and logistic regression (LR) models for predicting hepatocellular carcinoma (HCC) outcomes used only a single dataset, the essential issue of internal validity (reproducibility) of the models has not been addressed. The study purposes to validate the use of ANN model for predicting in-hospital mortality in HCC surgery patients in Taiwan and to compare the predictive accuracy of ANN with that of LR model.

Methodology/Principal Findings

Patients who underwent a HCC surgery during the period from 1998 to 2009 were included in the study. This study retrospectively compared 1,000 pairs of LR and ANN models based on initial clinical data for 22,926 HCC surgery patients. For each pair of ANN and LR models, the area under the receiver operating characteristic (AUROC) curves, Hosmer-Lemeshow (H-L) statistics and accuracy rate were calculated and compared using paired T-tests. A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and the relative importance of variables. Compared to the LR models, the ANN models had a better accuracy rate in 97.28% of cases, a better H-L statistic in 41.18% of cases, and a better AUROC curve in 84.67% of cases. Surgeon volume was the most influential (sensitive) parameter affecting in-hospital mortality followed by age and lengths of stay.

Conclusions/Significance

In comparison with the conventional LR model, the ANN model in the study was more accurate in predicting in-hospital mortality and had higher overall performance indices. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.     

Comparisons of Prediction Models of Quality of Life after Laparoscopic Cholecystectomy: A Longitudinal Prospective Study

Background

Few studies of laparoscopic cholecystectomy (LC) outcome have used longitudinal data for more than two years. Moreover, no studies have considered group differences in factors other than outcome such as age and nonsurgical treatment. Additionally, almost all published articles agree that the essential issue of the internal validity (reproducibility) of the artificial neural network (ANN), support vector machine (SVM), Gaussian process regression (GPR) and multiple linear regression (MLR) models has not been adequately addressed. This study proposed to validate the use of these models for predicting quality of life (QOL) after LC and to compare the predictive capability of ANNs with that of SVM, GPR and MLR.

Methodology/Principal Findings

A total of 400 LC patients completed the SF-36 and the Gastrointestinal Quality of Life Index at baseline and at 2 years postoperatively. The criteria for evaluating the accuracy of the system models were mean square error (MSE) and mean absolute percentage error (MAPE). A global sensitivity analysis was also performed to assess the relative significance of input parameters in the system model and to rank the variables in order of importance. Compared to SVM, GPR and MLR models, the ANN model generally had smaller MSE and MAPE values in the training data set and test data set. Most ANN models had MAPE values ranging from 4.20% to 8.60%, and most had high prediction accuracy. The global sensitivity analysis also showed that preoperative functional status was the best parameter for predicting QOL after LC.

Conclusions/Significance

Compared with SVM, GPR and MLR models, the ANN model in this study was more accurate in predicting patient-reported QOL and had higher overall performance indices. Further studies of this model may consider the effect of a more detailed database that includes complications and clinical examination findings as well as more detailed outcome data.     

Faecal indices predict organic matter digestibility, short chain fatty acid production and metabolizable energy content of browse-containing sheep diets

The ability of faecal composition to accurately predict nutritional characteristics of browse-containing sheep diets was investigated. Predictive regression models were developed using data derived from three feeding experiments conducted with Acacia saligna (i.e., Avena sativa control and five inclusion levels of A. saligna), Chamaecytisus palmensis (i.e., A. sativa control and five inclusion levels) and Atriplex amnicola (i.e., A. sativa control and five inclusion levels). The fourth experiment conducted to validate the predictive models included six levels of A. saligna and five levels of C. palmensis. Feed and faecal samples collected from six replicate sheep were analysed for neutral detergent fiber (NDFom), acid detergent fiber (ADFom), lignin(sa), ash and crude protein (CP) contents. Total phenolics (TP) and tannin (TT) contents and in vitro gas production of the feed samples were also measured. Organic matter digestibility (OMD), short chain fatty acid production (SCFA) and metabolizable energy (ME) content of diets were determined. Feed and faecal data of experiments 1, 2 and 3 were pooled. Correlation coefficients among feed and faecal variables were estimated. The predictive regression models of dietary characteristics were developed from faecal composition by a stepwise regression procedure. The significant (i.e., P<0.05) predictive model with the highest R² and lowest residual standard deviation (RSD) was selected (i.e., best-fit predictive model). The model was used to predict nutritional characteristics of diets in the validation experiment from respective faecal indices. The predicted nutritional characteristics were then regressed against measured nutritional characteristics. The best-fit predictive regression model for dietary CP had a very low R² (0.21). The best-fit regression models predicting dietary TP, TT, OMD, SCFA and ME from faecal N, ash and lignin(sa)/NDFom had R² greater than 0.78 and low RSD. In the validation experiment, regressions between measured and predicted TP and TT had positive intercepts (P<0.05) and low R². Slopes of these regressions were much lower than 1.0. Intercepts of the regressions between measured and predicted OMD, SCFA and ME did not different from zero. The R² of these regressions were very high and slopes were close to 1. Dietary CP content of browse-containing diets cannot be predicted from faecal fiber, lignin(sa) and ash contents. However, these faecal indices collectively can predict the OMD, SCFA production and ME contents of browse-containing diets, and these predictive models have broad application. Further research is necessary to understand the poor validity of the predictive models of TP and TT.     

Estimating excess post-exercise oxygen consumption using multiple linear regression in healthy Korean adults: a pilot study

[Purpose]This pilot study aimed to develop a regression model to estimate the excess post-exercise oxygen consumption (EPOC) of Korean adults using various easy-to-measure dependent variables.[Methods]The EPOC and dependent variables for its estimation (e.g., sex, age, height, weight, body mass index, fat-free mass [FFM], fat mass, % body fat, and heart rate_sum [HR_sum]) were measured in 75 healthy adults ( 31 males, 44 females). Statistical analysis was performed to develop an EPOC estimation regression model using the stepwise regression method.[Results]We confirmed that FFM and HR_sum were important variables in the EPOC regression models of various exercise types. The explanatory power and standard errors of estimates (SEE) for EPOC of each exercise type were as follows: the continuous exercise (CEx) regression model was 86.3% (R²) and 85.9% (adjusted R²), and the mean SEE was 11.73 kcal, interval exercise (IEx) regression model was 83.1% (R²) and 82.6% (adjusted R²), while the mean SEE was 13.68 kcal, and the accumulation of short-duration exercise (AEx) regression models was 91.3% (R²) and 91.0% (adjusted R²), while the mean SEE was 27.71 kcal. There was no significant difference between the measured EPOC using a metabolic gas analyzer and the predicted EPOC for each exercise type.[Conclusion]This pilot study developed a regression model to estimate EPOC in healthy Korean adults. The regression model was as follows: CEx = -37.128 + 1.003 × (FFM) + 0.016 × (HR_sum), IEx = -49.265 + 1.442 × (FFM) + 0.013 × (HR_sum), and AEx = -100.942 + 2.209 × (FFM) + 0.020 × (HR_sum).     

Comparative Assessment of the Artificial Neural Network and Response Surface Modelling Efficiencies for Biohydrogen Production on Sugar Cane Molasses

This study comparatively evaluates the modelling efficiency of the Response Surface Methodology (RSM) and the Artificial Neural Network (ANN). Twenty-nine biohydrogen fermentation batches were carried out to generate the experimental data. The input parameters consisted of a concentration of molasses (50–150 g/l), pH (4–8), temperature (35–40 °C) and inoculum concentration (10–50 %). The obtained data were used to develop the RSM and ANN models. The ANN model was a committee of networks with a topology of 4-(6-10)-1 structured on multilayer perceptrons. RSM and ANN models gave R ² values of 0.75 and 0.91, respectively, with predicted optimum conditions of 150 g/l, 8 and 35 °C for molasses, pH and temperature, respectively, with differences in inoculum concentrations (10.11 and 15 %) for RSM and ANN, respectively. Upon validation, 15.12 and 119.08 % prediction errors on hydrogen volume were found for ANN and RSM, respectively. These findings suggest that ANN has greater accuracy in modelling the relationships between the considered process inputs for fermentative biohydrogen production and thus, is more reliable to navigate the optimization space.     

Feasibility of estimating isokinetic knee torque using a neural network model

Many studies have investigated the relationships between electromyography (EMG) and torque production. A few investigators have used adjusted learning algorithms and feed-forward artificial neural networks (ANNs) to estimate joint torque in the elbow. This study sought to estimate net isokinetic knee torque using ANN models. Isokinetic knee extensor and flexor torque data were measured simultaneously with agonist and antagonist EMG during concentric and eccentric contractions at joint velocities of 30 degrees /s and 60 degrees /s. Age, gender, height, body mass, agonist EMG, antagonist EMG, joint position and joint velocity were entered as predictive variables of net torque. A three-layer ANN model was developed and trained using an adjusted back-propagation algorithm. Accuracy results were compared against those of forward stepwise regression models. Stepwise regression models included body mass, body height and joint position as the most influential predictors, followed by agonist EMG for concentric and eccentric contractions. Estimation of eccentric torque included antagonist EMG following the agonist activation. ANN models resulted in more accurate torque estimation (R=0.96), compared to the stepwise regression models (R=0.71). ANN model accuracy increased greatly when the number of hidden units increased from 5 to 10, continuing to increase gradually with additional hidden units. The average number of training epochs necessary for solution convergence and the relative accuracy of the model indicate a strong ability for the ANN model to generalize these estimations to a broader sample. The ANN model appears to be a feasible technique for estimating joint torque in the knee.     

基于DNA变异在亚欧混合人群中预测男性型脱发

男性型脱发(male pattern baldness,MPB)是一种雄激素依赖性的遗传性脱发疾病,对个人形象、心理产生较大的消极影响.近期欧美人群中进行的大样本全基因组关联分析(genome wide association studies,GWAS)已报道大量与MPB相关的遗传易感性单核苷酸多态性(single nucleotide polymorphisms,SNPs)位点,但这些位点在东亚人群中的遗传效应尚不清楚.本研究基于我国684个亚欧混合人群(Eurasian)样本,对在英国生物样本库(UK Biobank) 205 327个欧洲男性GWAS分析发现的624个与MPB相关的SNPs进行人群异质性分析,基于多基因风险打分(polygenic risk scores,PRS)建立预测模型,并对预测因子数量与模型预测性能的关系进行了研究.通过质控的467个SNPs中6.9%与MPB显著相关(P<0.05).结合年龄、体质指数(body mass index,BMI)和25个SNPs建立的线性回归和逻辑回归模型,效果较好(R²=28.9%,AUC=0....