Shock index and its variants as predictors of mortality in severe traumatic brain injury

BACKGROUND The increase in severe traumatic brain injury(sTBI)incidence is a worldwide phenomenon,resulting in a heavy disease burden in the public health systems,specifically in emerging countries.The shock index(SI)is a physiological parameter that indicates cardiovascular status and has been used as a tool to assess the presence and severity of shock,which is increased in sTBI.Considering the high mortality of sTBI,scrutinizing the predictive potential of SI and its variants is vital.AIM To describe the predictive potential of SI and its variants in sTBI.METHODS This study included 71 patients(61 men and 10 women)divided into two groups:Survival(S;n=49)and Non-survival(NS;n=22).The responses of blood pressure and heart rate(HR)were collected at admission and 48 h after admission.The SI,reverse SI(rSI),rSI multiplied by the Glasgow Coma Score(rSIG),and Age multiplied SI(AgeSI)were calculated.Group comparisons included Shapiro-Wilk tests,and independent samples t-tests.For predictive analysis,logistic regression,receiver operator curves(ROC)curves,and area under the curve(AUC)measurements were performed.RESULTS No significant differences between groups were identified for SI,rSI,or rSIG.The AgeSI was significantly higher in NS patients at 48 h following admission(S:26.32±14.2,and NS:37.27±17.8;P=0.016).Both the logistic regression and the AUC following ROC curve analysis showed that only AgeSI at 48 h was capable of predicting sTBI outcomes.CONCLUSION Although an altered balance between HR and blood pressure can provide insights into the adequacy of oxygen delivery to tissues and the overall cardiac function,only the AgeSI was a viable outcome-predictive tool in sTBI,warranting future research in different cohorts.

Design and preliminary validation of a tool for the simulation of train braking performance

Train braking performance is important for the safety and reliability of railway systems. The availability of a tool that allows evaluating such performance on the basis of the main train features can be useful for train system designers to choose proper dimensions for and optimize train＇s subsystems. This paper presents a modular tool for the prediction of train braking performance, with a par- ticular attention to the accurate prediction of stopping distances. The tool takes into account different loading and operating conditions, in order to verify the safety require- ments prescribed by European technical specifications for interoperability of high-speed trains and the corresponding EN regulations. The numerical results given by the tool were verified and validated by comparison with experimental data, considering as benchmark case an Ansaldo EMU V250 train--a European high-speed train--currently developed for Belgium and Netherlands high-speed lines, on which technical information and experimental data directly recorded during the preliminary tests were available. An accurate identification of the influence of the braking pad friction factor on braking performances allowed obtaining reliable results.

Multi-Scale Convolutional Gated Recurrent Unit Networks for Tool Wear Prediction in Smart Manufacturing

As an integrated application of modern information technologies and artificial intelligence,Prognostic and Health Management(PHM)is important for machine health monitoring.Prediction of tool wear is one of the symbolic applications of PHM technology in modern manufacturing systems and industry.In this paper,a multi-scale Convolutional Gated Recurrent Unit network(MCGRU)is proposed to address raw sensory data for tool wear prediction.At the bottom of MCGRU,six parallel and independent branches with different kernel sizes are designed to form a multi-scale convolutional neural network,which augments the adaptability to features of different time scales.These features of different scales extracted from raw data are then fed into a Deep Gated Recurrent Unit network to capture long-term dependencies and learn significant representations.At the top of the MCGRU,a fully connected layer and a regression layer are built for cutting tool wear prediction.Two case studies are performed to verify the capability and effectiveness of the proposed MCGRU network and results show that MCGRU outperforms several state-of-the-art baseline models.

Applications of EPSE method for predicting crossflow instability in swept-wing boundary layers

The nth-order expansion of the parabolized stability equation （EPSEn） is obtained from the Taylor expansion of the linear parabolized stability equation （LPSE） in the streamwise direction. The EPSE together with the homogeneous boundary conditions forms a local eigenvalue problem, in which the streamwise variations of the mean flow and the disturbance shape function are considered. The first-order EPSE （EPSE1） and the second-order EPSE （EPSE2） are used to study the crossflow instability in the swept NLF（2）-0415 wing boundary layer. The non-parallelism degree of the boundary layer is strong. Compared with the growth rates predicted by the linear stability theory （LST）, the results given by the EPSE1 and EPSE2 agree well with those given by the LPSE. In particular, the results given by the EPSE2 are almost the same as those given by the LPSE. The prediction of the EPSE1 is more accurate than the prediction of the LST, and is more efficient than the predictions of the EPSE2 and LPSE. Therefore, the EPSE1 is an efficient ey prediction tool for the crossflow instability in swept-wing boundary-layer flows.

老年乳腺癌治疗前量化评估工具简述

乳腺癌是女性最常见的癌症之一,中国的人口结构老龄化进程导致了癌症负担的增加,其中乳腺癌的发病率随着年龄的增长而增加,老年乳腺癌患者因为身体机能下降和基础疾病的原因,在治疗上的选择有限。在治疗前评估患者的身体情况并预测疗效,才能在安全范围内进行最有效的治疗。本文主要总结了近几年来临床上较常使用的几种治疗前评估工具,并探讨其优劣,简述如何根据评估工具对老年乳腺癌患者进行治疗前评估。

Novel intelligent reasoning system for tool wear prediction and parameter optimization in intelligent milling

Accurate intelligent reasoning systems are vital for intelligent manufacturing.In this study,a new intelligent reasoning system was developed for milling processes to accurately predict tool wear and dynamically optimize machining parameters.The developed system consists of a self-learning algorithm with an improved particle swarm optimization(IPSO)learning algorithm,prediction model determined by an improved case-based reasoning(ICBR)method,and optimization model containing an improved adaptive neural fuzzy inference system(IANFIS)and IPSO.Experimental results showed that the IPSO algorithm exhibited the best global convergence performance.The ICBR method was observed to have a better performance in predicting tool wear than standard CBR methods.The IANFIS model,in combination with IPSO,enabled the optimization of multiple objectives,thus generating optimal milling parameters.This paper offers a practical approach to developing accurate intelligent reasoning systems for sustainable and intelligent manufacturing.

Fingerprint Patterns in Students with Learning Disability:Evidence of Sexual Dimorphism and Potential for Diagnosis in a Nigerian Population

This study assessed the sex-based relationship and prediction pattern between fingerprint patterns,ridge counts,and learning disability(LD).This cross-sectional study recruited 300 students(150 LD and 150 non-LD)aged between 3 and 29 years.The fingerprint patterns(arch,whorl,ulnar loop,and radial loop)and the ridge count:total finger ridge count(TFRC),absolute ridge count(ARC),ulnar ridge count(URC),and radial ridge count(RRC)were accessed.Students with LD showed a significantly higher whorl and a significantly lower ulnar loop than students without LD.There is a significant association of whorl pattern in the first right finger of subjects with LD compared to non-LD counterparts.TFRC,ARC,and URC were significantly higher in females with LD than non-LD females(P=0.01,0.03,and 0.001).Males with LD showed significantly lower TFRC,RRC,and URC counts than the non-LD males(P=0.02,0.01,and 0.001).TFRC can predict LD in males(odds ratio[OR]=1.010,P=0.032)and females(OR=0.993,P=0.012).Fingerprint pattern and ridge counts are sexually dimorphic in subjects with or without LD.TFRC and whorl fingerprint patterns may be vital predictive and screening tools for LD in males and females.

Prediction of diabetes and hypertension using multi-layer perceptron neural networks

Background:Diabetes and hypertension are two of the commonest diseases in the world.As they unfavorably affect people of different age groups,they have become a cause of concern and must be predicted and diagnosed well in advance.Objective:This research aims to determine the effectiveness of artificial neural networks(ANNs)in predicting diabetes and blood pressure diseases and to point out the factors which have a high impact on these diseases.Sample:This work used two online datasets which consist of data collected from 768 individuals.We applied neural network algorithms to predict if the individuals have those two diseases based on some factors.Diabetes prediction is based on five factors:age,weight,fat-ratio,glucose,and insulin,while blood pressure prediction is based on six factors:age,weight,fat-ratio,blood pressure,alcohol,and smoking.Method:A model based on the Multi-Layer Perceptron Neural Network(MLP)was implemented.The inputs of the network were the factors for each disease,while the output was the prediction of the disease’s occurrence.The model performance was compared with other classifiers such as Support Vector Machine(SVM)and K-Nearest Neighbors(KNN).We used performance metrics measures to assess the accuracy and performance of MLP.Also,a tool was implemented to help diagnose the diseases and to understand the results.Result:The model predicted the two diseases with correct classification rate(CCR)of 77.6%for diabetes and 68.7%for hypertension.The results indicate that MLP correctly predicts the probability of being diseased or not,and the performance can be significantly increased compared with both SVM and KNN.This shows MLPs effectiveness in early disease prediction.