Prediction of Abdominal Visceral Obesity From Body Mass Index,Waist Circumference and Waist-hip Ratio in Chinese Adults:Receiver Operating Characteristic Curves Analysis

Objective To evaluate the sensitivity and specificity of body mass index (BMI), waist circumference (WC) and waist-to-hip ratio (WHR) measurements in diagnosing abdominal visceral obesity. Methods BMI, WC, and WHR were assessed in 690 Chinese adults (305 men and 385 women) and compared with magnetic resonance imaging (MRI) measurements of abdominal visceral adipose tissue (VA). Receiver operating characteristic (ROC) curves were generated and used to determine the threshold point for each anthropometric parameter. Results 1) MRI showed that 61.7% of overweight/obese individuals (BMI≥25 kg/m2) and 14.2% of normal weight (BMI<25 kg/m2) individuals had abdominal visceral obesity (VA≥100 cm2). 2) VA was positively correlated with each anthropometric variable, of which WC showed the highest correlation (r=0.73-0.77, P<0.001). 3) The best cut-off points for assessing abdominal visceral obesity were as followed: BMI of 26 kg/m2, WC of 90 cm, and WHR of 0.93, with WC being the most sensitive and specific factor. 4) Among subjects with BMI≥28 kg/m2 or WC≥95 cm, 95% of men and 90% of women appeared to have abdominal visceral obesity. Conclusion Measurements of BMI, WC, and WHR can be used in the prediction of abdominal visceral obesity, of which WC was the one with better accuracy.

A method of line spectrum extraction based on target radiated spectrum feature and its post-processing

To improve the ability of detecting underwater targets under strong wideband interference environment,an efficient method of line spectrum extraction is proposed,which fully utilizes the feature of the target spectrum that the high intense and stable line spectrum is superimposed on the wide continuous spectrum.This method modifies the traditional beam forming algorithm by calculating and fusing the beam forming results at multi-frequency band and multi-azimuth interval,showing an excellent way to extract the line spectrum when the interference and the target are not in the same azimuth interval simultaneously.Statistical efficiency of the estimated azimuth variance and corresponding power of the line spectrum band depends on the line spectra ratio(LSR)of the line spectrum.The change laws of the output signal to noise ratio(SNR)with the LSR,the input SNR,the integration time and the filtering bandwidth of different algorithms bring the selection principle of the critical LSR.As the basis,the detection gain of wideband energy integration and the narrowband line spectrum algorithm are theoretically analyzed.The simulation detection gain demonstrates a good match with the theoretical model.The application conditions of all methods are verified by the receiver operating characteristic(ROC)curve and experimental data from Qiandao Lake.In fact,combining the two methods for target detection reduces the missed detection rate.The proposed post-processing method in2-dimension with the Kalman filter in the time dimension and the background equalization algorithm in the azimuth dimension makes use of the strong correlation between adjacent frames,could further remove background fluctuation and improve the display effect.

ROC analysis of CT hemodynamic in the diagnosis of breast cancer

Objective:The aim of this study was evaluate the diagnostic value of computed tomography(CT) perfusion in breast cancer by the method of receiver operator characteristic curve(ROC) analysis.Methods:Eighty-one cases with breast masses found by health examination or mammography were scanned by multi-slice spiral CT(MSCT) perfusion and hemodynamic parameters of blood flow(BF), mean transit time(MTT) and blood volume(BV) were calculated by deconvolution arithmetic.According to the pathologic results, two groups, benign and malignant were classified and statistical analysis were performed between them.The ROC characteristics of BF, MTT, BV were compared for each and the diagnostic value of the hemodynamic parameters were confirmed.Results:In the malignant group, BF was(0.735 ± 0.440) mL/min/mL, MTT was(22.771 ± 7.647) s and BV was 0.234 ± 0.082.In the benign group, BF was(0.466 ± 0.527) mL/min/mL, MTT was(26.712 ± 12.934) s and BV was 0.179 ± 0.117.There was a significant difference for BF and BV between the benign and malignant groups.When the hemodynamic parameters were used to discriminate the breast lesions, the area under the ROC curve(AUCROC) of BF was 0.832 ± 0.086, the maximum, while AUCROC of BV was 0.695 ± 0.092.There was no significant statistical difference between BF and BV.AUCROC of MTT was 0.473 ± 0.102, which was minimal.Since the threshold of BF was 0.381 mL/min/mL, the sensitivity was 82.3%, the specificity was 73.2%, the positive likelihood ratio(LR) was 3.071 and the negative LR was 0.242.The threshold of BV was 0.190 with sensitivity 73.3%, specificity 56.5%, positive likelihood ratio 1.685 and negative LR 0.473.Conclusion:BF and BV among CT hemodynamic parameters have certain diagnostic value in breast cancer, but BF or BV can not yet be single index to confirm or deny the diagnosis.

Evaluation of the diagnostic value of tumor markers with ROC and logistic regression in gastrocolic tumors

Objective: The aim of the study was to evaluate the clinical significance of multiple tumor markers (CEA, AFP, CA72-4 and CA19-9) in patients with gastrocolic tumors by receiver operating characteristic (ROC) curve and stepwise logistic regression (LR) analysis. Methods: The serum concentrations of CEA, AFP, CA72-4 and CA19-9 were measured with electrochemiluminescence immunoassay in 126 patients with gastrocolic tumors, 137 patients with benign gastrocolic disorders and 109 healthy controls. The area under the ROC curve (AUC) of CEA, AFP, CA72-4 and CA19-9 and stepwise LR results were compared by sensitivity, specificity, Youden's index and positive likelihood ratio/negative likelihood ratio. Results: The levels of four tested tumor markers in patients with gastrocolic tumors were significantly higher than those in benign gastrocolic group and normal controls. In the benign gastrocolic group, the AUC from stepwise logistic regression was larger than the AUC of four tumor markers respectively. Sensitivity, Youden's index and positive likelihood ratio/negative likelihood ratio were the highest in the combination assay of CA72-4, CEA, and CA19-9, as compared with one of the tumor markers alone. Conclusion: The use of ROC established by LR analysis model improved the diagnostic accuracy of gastrocolic tumors. For the screening of gastrocolic tumors, the AUC value of the combination probability index (sensitivity and specificity) was significantly higher than the values of the different tumour markers.

BOOTSTRAP TECHNIQUE FOR ROC ANALYSIS: A STABLE EVALUATION OF FISHER CLASSIFIER PERFORMANCE

This paper presents a novel bootstrap based method for Receiver Operating Characteristic (ROC) analysis of Fisher classifier. By defining Fisher classifier’s output as a statistic, the bootstrap technique is used to obtain the sampling distributions of the outputs for the positive class and the negative class respectively. As a result, the ROC curve is a plot of all the (False Positive Rate (FPR), True Positive Rate (TPR)) pairs by varying the decision threshold over the whole range of the boot- strap sampling distributions. The advantage of this method is, the bootstrap based ROC curves are much stable than those of the holdout or cross-validation, indicating a more stable ROC analysis of Fisher classifier. Experiments on five data sets publicly available demonstrate the effectiveness of the proposed method.

Support vector machine for prediction of siRNA silencing efficacy

In order to assist the design of short interfering ribonucleic acids （siRNA）, 573 non-redundant siRNAs were collected from published literatures and the relationship between siRNAs sequences and RNA interference （RNAi） effect is analyzed by a support vector machine （SVM） based algorithm relied on a basebase correlation （BBC） feature. The results show that the proposed algorithm has the highest area under curve （AUC） value （0. 73） of the receive operating characteristic （ROC） curve and the greatest r value （0. 43） of the Pearson＇s correlation coefficient. This indicates that the proposed algorithm is better than the published algorithms on the collected datasets and that more attention should be paid to the base-base correlation information in future siRNA design.

TWIN SUPPORT TENSOR MACHINES FOR MCS DETECTION

Tensor representation is useful to reduce the overfitting problem in vector-based learning algorithm in pattern recognition.This is mainly because the structure information of objects in pattern analysis is a reasonable constraint to reduce the number of unknown parameters used to model a classifier.In this paper, we generalize the vector-based learning algorithm TWin Support Vector Machine(TWSVM) to the tensor-based method TWin Support Tensor Machines(TWSTM), which accepts general tensors as input.To examine the effectiveness of TWSTM, we implement the TWSTM method for Microcalcification Clusters(MCs) detection.In the tensor subspace domain, the MCs detection procedure is formulated as a supervised learning and classification problem, and TWSTM is used as a classifier to make decision for the presence of MCs or not.A large number of experiments were carried out to evaluate and compare the performance of the proposed MCs detection algorithm.By comparison with TWSVM, the tensor version reduces the overfitting problem.

Support vector machine and ROC curves for modeling of aircraft fuel consumption

To estimate the fuel consumption of a civil aircraft,we propose to use the receiver operating characteristic(ROC)curve to optimize a support vector machine(SVM)model.The new method and procedure has been developed to build,train,validate,and apply an SVM model.A conceptual support vector network is proposed to model fuel consumption,and the flight data collected from routes are used as the inputs to train an SVM model.During the training phase,an ROC curve is defined to evaluate the performance of the model.To validate the applicability of the trained model,a case study is developed to compare the data from an aircraft performance manual and from the implemented simulation model.The investigated aircraft in the case study is a Boeing 737-800 powered by CFM-56 engines.The comparison has shown that the trained SVM model from the proposed procedure is capable of representing a complex fuel consumption function accurately for all phases during the flight.The proposed methodology is generic,and can be extended to reliably model the fuel consumption of other types of aircraft,such as piston engine aircraft or turboprop engine aircraft.

Fraud Identification of Chinese Listed Companies——an Improvement Based on M-Score

To evaluate the applicability of the M-score model in the Chinese capital market,this research observed 190 financial fraud samples punished by the China Securities Regulatory Commission(CSRC)in the years from 2014 to 2018.The test results indicate that two types of errors are high,which means that the applicability of the M-score is unacceptable.Therefore,in this paper,a 9-index model is constructed by Wald's backward stepwise regression method,and the optimal threshold is set by the Beneish expected cost method(ECM).The accuracy of the modified M-score is significantly improved,especially the Type I error rate of is reduced from 70.37%to 19.75%.The receiver operating characteristic(ROC)curve test also proves the superior identification effect of the modified M-score applied in the Chinese market.Finally,variables such as current ratio,fixed asset index,and equity concentration in the modified model could represent the fraud characteristics of Chinese listed companies.

Prediction of Flash Flood Susceptibility of Hilly Terrain Using Deep Neural Network:A Case Study of Vietnam

Flash floods are one of the most dangerous natural disasters,especially in hilly terrain,causing loss of life,property,and infrastructures and sudden disruption of traffic.These types of floods are mostly associated with landslides and erosion of roads within a short time.Most of Vietnamis hilly and mountainous;thus,the problem due to flash flood is severe and requires systematic studies to correctly identify flood susceptible areas for proper landuse planning and traffic management.In this study,three Machine Learning(ML)methods namely Deep Learning Neural Network(DL),Correlation-based FeatureWeighted Naive Bayes(CFWNB),and Adaboost(AB-CFWNB)were used for the development of flash flood susceptibility maps for hilly road section(115 km length)of National Highway(NH)-6 inHoa Binh province,Vietnam.In the proposedmodels,88 past flash flood events were used together with 14 flash floods affecting topographical and geo-environmental factors.The performance of themodels was evaluated using standard statisticalmeasures including Receiver Operating Characteristic(ROC)Curve,Area Under Curve(AUC)and Root Mean Square Error(RMSE).The results revealed that all the models performed well(AUC>0.80)in predicting flash flood susceptibility zones,but the performance of the DL model is the best(AUC:0.972,RMSE:0.352).Therefore,the DL model can be applied to develop an accurate flash flood susceptibility map of hilly terrain which can be used for proper planning and designing of the highways and other infrastructure facilities besides landuse management of the area.

Predicting the invasion of a southern African savannah by the black wattle (Acacia mearnsii)

Understanding the drivers of biological invasions in landscapes is a major goal in invasion ecology.The control of biological invasions has increasingly become critical in the past few decades because invasive species are thought to be a major threat to endemism.In this study,by examining the key variables that influence Acacia mearnsii,we sought to understand its potential invasion in eastern Zimbabwe.We used the maximum entropy(MaxEnt)method against a set of environmental variables to predict the potential invasion front of A.mearnsii.Our study showed that the predictor variables,i.e.,aspect,elevation,distance from streams,soil type and distance from the nearest A.mearnsii plantation adequately explained(training AUC=0.96 and test AUC=0.93)variability in the spatial distribution of invading A.mearnsii.The front of invasion by A.mearnsii seemed also to occur next to existing A.mearnsii plantations.Results from our study could be useful in identifying priority areas that could be targeted for controlling the spread of A.mearnsii in Zimbabwe and other areas under threat from A.mearnsii invasion.We recommend that the plantation owners pay for the control of A.mearnsii invasion about their plantations.

Mineral Potential Mapping for Tungsten Polymetallic Deposits in the Nanling Metallogenic Belt, South China

The Nanling belt in South China has considerable resources of tungsten polymetallic commodities and is one of the most important metallogenic belts in the world. Data-driven weights-of-evidence （WofE） and fuzzy logic models are used to evaluate the tungsten polymetallic potential of the Nanling belt. Initially, seven ore-controlling factors derived from multi-source geospatial datasets （e.g., geological, geochemical, and geophysical） are used for data integration in the two models. Two mineral potential maps are generated that efficiently predicate the locations of the deposits. The WofE map predicate 81% of the deposits within 13.6% of the study area, whereas the fuzzy logic map predicate 81.5% of the deposits within 13% of the area. The predictive maps are syntheses of spatial association rules, which provide better understanding of those factors that control the distribution of mineralization and trigger eventual exploration work in new areas. Subsequently, in order to evaluate the success rate accuracy, the receiver operating characteristic curves and area under the curves （AUCs） for the two potential maps are constructed. The results show that the AUCs for the WofE and fuzzy logic models are 0.775 7 and 0.840 6, respectively. The higher AUC value for the fuzzy logic model implies that it delineate a greater number of favorable areas compared with the WorE model. Overall, the capabilities of both models for correctly classifying areas with existing mineral deposits are satisfactory.

Salivary microbiota may predict the presence of esophageal squamous cell carcinoma

The aim is to explore the predictive value of salivary bacteria for the presence of esophageal squamous cell carcinoma (ESCC). Saliva samples were obtained from 178 patients with ESCC and 101 healthy controls, and allocated to screening and verification cohorts, respectively. In the screening phase, after saliva DNA was extracted, 16S rRNA V4 regions of salivary bacteria were amplified by polymerase chain reaction (PCR) with high-throughput sequencing. Highly expressed target bacteria were screened by Operational Taxonomic Units clustering, species annotation and microbial diversity assessment. In the verification phase, the expression levels of target bacteria identified in the screening phase were verified by absolute quantitative PCR (Q-PCR). Receiver operating characteristic (ROC) curves were plotted to investigate the predictive value of target salivary bacteria. LEfSe analysis revealed higher proportions of Fusobacterium, Streptococcus and Porphyromonas, and Q-PCR assay showed significantly higher numbers of Streptococcus salivarius, Fusobacterium nucleatum and Porphyromonas gingivalis in patients with ESCC, when compared with healthy controls (all P < 0.05). The areas under the ROC curves for Streptococcus salivarius, Fusobacterium nucleatum, Porphyromonas gingivalis and the combination of the three bacteria for predicting patients with ESCC were 69%, 56.5%, 61.8% and 76.4%, respectively. The sensitivities corresponding to cutoff value were 69.3%, 22.7%, 35.2% and 86.4%, respectively, and the matched specificity were 78.4%, 96.1%, 90.2% and 58.8%, respectively. These highly expressed Streptococcus salivarius, Fusobacterium nucleatum and Porphyromonas gingivalis in the saliva, alone or in combination, indicate their predictive value for ESCC.