检索结果-内蒙古大学图书馆

The Compensatory Reserve Index Responds to Acute Hemodynamic Changes in Patients with Congenital Heart Disease: A Proof of Concept Study

引用

PEDIATRIC CARDIOLOGY 2020年第6期41卷 1190-1198页

作者： Ehrmann, Daniel E. Leopold, David K. Phillips, Ryan Shahi, Niti Campbell, Kristen Ross, Michael Zablah, Jenny E. Moulton, Steven L. Morgan, Gareth Kim, John S. Univ Colorado Div Cardiol Dept Pediat Childrens Hosp ColoradoSch Med 13123 East 16th AveB100 Aurora CO 80045 USA Univ Colorado Sch Med Dept Anesthesia Aurora CO USA Univ Colorado Dept Surg Div Pediat Surg Sch Med Aurora CO USA Univ Colorado Dept Pediat Sch Med Aurora CO USA Univ N Carolina Div Pediat Cardiol Chapel Hill NC 27515 USA

Patients with congenital heart disease (CHD) who undergo cardiac procedures may become hemodynamically unstable. predictive algorithms that utilize dense physiologic data may be useful. The compensatory reserve index (CRI) trends beat-to-beat progression from normovolemia (CRI = 1) to decompensation (CRI = 0) in hemorrhagic shock by continuously analyzing unique sets of features in the changing pulse photoplethysmogram (PPG) waveform. We sought to understand if the CRI accurately reflects changing hemodynamics during and after a cardiac procedure for patients with CHD. A transcatheter pulmonary valve replacement (TcPVR) model was used because left ventricular stroke volume decreases upon sizing balloon occlusion of the right ventricular outflow tract (RVOT) and increases after successful valve placement. A single-center, prospective cohort study was performed. The CRI was continuously measured to determine the change in CRI before and after RVOT occlusion and successful TcPVR. Twenty-six subjects were enrolled with a median age of 19 (interquartile range (IQR) 13-29) years. The mean (+/- standard deviation) CRI decreased from 0.66 +/- 0.15 1-min before balloon inflation to 0.53 +/- 0.16 (p = 0.03) 1-min after balloon deflation. The mean CRI increased from a pre-valve mean CRI of 0.63 [95% confidence interval (CI) 0.56-0.70] to 0.77 (95% CI 0.71-0.83) after successful TcPVR. In this study, the CRI accurately reflected acute hemodynamic changes associated with TcPVR. Further research is justified to determine if the CRI can be useful as an early warning tool in patients with CHD at risk for decompensation during and after cardiac procedures.

关键词： Compensatory reserve index predictive algorithm Transcatheter pulmonary valve replacement Congenital heart disease

来源：评论

学校读者我要写书评

暂无评论

Predicting first-trimester outcome of embryos with cardiac activity in women with recurrent spontaneous abortion

引用

JOURNAL OF INTERNATIONAL MEDICAL RESEARCH 2020年第6期48卷 300060520911829-300060520911829页

作者： Li, Huixian Qin, Shuang Xiao, Fanfan Li, Yuhong Gao, Yunhe Zhang, Jiexin Xiao, Qing Sun Yat Sen Univ Affiliated Hosp 8 3025 ShenNan Rd Shenzhen 518033 Guangdong Peoples R China Guangzhou Med Univ Inst Pediat Guangzhou Women & Childrens Med Ctr Guangzhou Guangdong Peoples R China Guangzhou Med Univ Guangzhou Women & Childrens Med Ctr Dept Reprod & Immunol Gynecol Guangzhou Guangdong Peoples R China Guangzhou Med Univ Dept Gynecol Outpatient Guangzhou Women & Childrens Med Ctr Guangzhou Guangdong Peoples R China

Objective This study was performed to evaluate the capability of routine clinical indicators to predict the early outcome of embryos with cardiac activity in women with recurrent spontaneous abortion (RSA). Methods A retrospective cohort study of pregnant women with a history of RSA in a Chinese tertiary hospital was performed using unadjusted and multivariable logistic regression. Results Of 789 pregnant women with RSA, 625 (79.21%) had ongoing pregnancy, whereas 164 (20.79%) developed abortion before 20 full weeks of gestational age even after embryonic heart motion was detected. The final model had an area under the curve of 0.81 (95% confidence interval, 0.78-0.84) with a sensitivity of 74.39%, a specificity of 76.00%, and a false-positive rate of 52.32% at a fixed detection rate of 90%. Conclusions The combination of multiple routine clinical indicators was valuable in predicting the early outcome of embryos with cardiac activity in viable pregnancies with RSA. However, this model might result in a high false-positive rate with a fixed detection rate of 90%;other markers must be investigated to identify first-trimester RSA once positive embryonic heart motion is established.

关键词： First-trimester recurrent spontaneous abortion fetal ultrasound biomarker embryonic heart motion predictive value predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

101 predictive Model for Aiding in Early Common Variable Immunodeficiency Diagnosis

引用

Clinical Immunology 2024年 262卷 110043-110043页

作者： Alsaati, Nouf Penney, Chris Helbig, Ingo Sullivan, Kathleen Allergy and Immunology Fellow/Children’s Hospital of Philadelphia Data Scientist/Children’s Hospital of Philadelphia Assistant Professor of Neurology and Pediatrics/Children’s Hospital of Philadelphia Chief of Allergy Immunology Professor of Pediatrics Wallace Chair of Pediatrics/Children’s Hospital of Philadelphia

来源：评论

学校读者我要写书评

暂无评论

An efficient strategy for predicting river dissolved oxygen concentration: application of deep recurrent neural network model

引用

ENVIRONMENTAL MONITORING AND ASSESSMENT 2021年第12期193卷 798-798页

作者： Moghadam, Salar Valizadeh Sharafati, Ahmad Feizi, Hajar Marjaie, Seyed Mohammad Saeid Asadollah, Seyed Babak Haji Seyed Motta, Davide Islamic Azad Univ Dept Civil Engn Sci & Res Branch Tehran Iran Tabriz Univ Fac Agr Dept Water Engn Tabriz Iran Northumbria Univ Dept Mech & Construct Engn Wynne Jones Bldg Newcastle Upon Tyne NE1 8ST Tyne & Wear England

Dissolved oxygen (DO) concentration in water is one of the key parameters for assessing river water quality. Artificial intelligence (AI) methods have previously proved to be accurate tools for DO concentration prediction. This study presents the implementation of a deep learning approach applied to a recurrent neural network (RNN) algorithm. The proposed deep recurrent neural network (DRNN) model is compared with support vector machine (SVM) and artificial neural network (ANN) models, formerly shown to be robust AI algorithms. The Fanno Creek in Oregon (USA) is selected as a case study and daily values of water temperature, specific conductance, streamflow discharge, pH, and DO concentration are used as input variables to predict DO concentration for three different lead times ("t + 1," "t + 3," and "t + 7"). Based on Pearson's correlation coefficient, several input variable combinations are formed and used for prediction. The model prediction performance is evaluated using various indices such as correlation coefficient, Nash-Sutcliffe efficiency, root mean square error, and mean absolute error. The results identify the DRNN model (CCTesting = 0.97, NSETesting = 0.948, RMSETesting = 0.43 and MAE(Testing) = 0.25) as the most accurate among the three models considered, highlighting the potential of deep learning approaches for water quality parameter prediction.

关键词： River water quality Dissolved oxygen concentration predictive algorithm Deep recurrent neural network Artificial neural network Support vector machine

来源：评论

学校读者我要写书评

暂无评论

Climatology of nutrient distributions in the South China Sea based on a large data set derived from a new algorithm

引用

PROGRESS IN OCEANOGRAPHY 2021年 195卷 102586-102586页

作者： Du, Chuanjun He, Ruoying Liu, Zhiyu Huang, Tao Wang, Lifang Yuan, Zhongwei Xu, Yanping Wang, Zhe Dai, Minhan Xiamen Univ Coll Ocean & Earth Sci State Key Lab Marine Environm Sci Xiamen Peoples R China North Carolina State Univ Dept Marine Earth & Atmospher Sci Raleigh NC USA

Nutrients are typically the most important determinant of the productivity of marine ecosystems. Hence, nutrients have been an essential variable of ocean observations in the modern oceanography era. Understanding of marine ecosystems and biogeochemistry, however, is largely limited by the spatiotemporal coverage of nutrient data. Herein, we developed a novel algorithm based on a large observational dataset of nutrients and their relationship with water masses indexed by temperature and salinity in the South China Sea (SCS). The algorithm yielded errors of <= 1.3, <= 0.10 and <= 3.5 mu mol L (-1) for NO3 (-) + NO2 (-) (N + N), phosphate and silicate, respectively. It is then applied to reconstruct nutrient concentrations primarily using temperature and salinity data archived in the World Ocean Database and Argo database during 1940-2018. It increases the nutrient data to similar to 5 million, by ca. three orders of magnitude compared to direct measurements in the SCS. This allows for a full examination of the seasonal climatology of nutrients in the SCS. In summer, in the upper 200 m, nutrient concentrations in the northwest and southernmost SCS are higher than in the rest of the SCS. An overall reversed pattern is revealed in winter, when higher nutrient concentrations are found in the central basin rather than basin margins. The Kuroshio intrusion and the vertical displacement of the nutricline, driven by upwelling/downwelling induced by horizontal convergences/divergences at both meso- and basin scales, determine the spatial and seasonal variation of nutrients. Seasonally, the Kuroshio intrusion and vertical displacements of the nutricline tend to offset the spatial variation of nutrient concentrations in spring, while they show an additive effect in the fall.

关键词： South China Sea Nutrients Climatological distributions predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

A Methodology for Taxi Demand Prediction Using Stream Learning 27

A Methodology for Taxi Demand Prediction Using Stream Learni...

引用

27th International Conference on Systems, Signals and Image Processing (IWSSIP)

作者： Faial, David Bernardini, Flavia Meza, Edwin Mitacc Miranda, Leandro Viterbo, Jose Fluminense Fed Univ Inst Sci & Technol Rio Das Ostras RJ Brazil Fluminense Fed Univ Inst Comp Niteroi RJ Brazil

ISBN: (纸本)9781728175393

Intelligent transport support systems have had a major impact on people's urban mobility. In large urban centers, transportation services still need ways to optimize vehicle supply in certain areas, according to the demand in each of them. Optimized distribution of on-demand taxi services can be part of an intelligent urban mobility plan, causing direct impacts on urban traffic, improving transport accessibility, improving safety at taxi standpoints by reduced waiting times, reduce transportation fare etc. Many vehicle-mounted sensors currently generate real-time information that is not used for processing and generating information with value. This paper proposes a Taxi Demand Forecasting methodology using stream machine learning algorithms that tackle concept drift detection on taxi data stream. A real data source made available on the New York open platform feeds a stream learning model, constructed using the Massive Online Analysis (MOA) tool - a framework for data stream mining. The stream model shows promising results in forecasting taxi demand, reaching 78% accuracy. Despite using data from a specific city, the methodology and results of this work can contribute to a more proactive demand management in other cities.

关键词： urban mobility stream data mining big data predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

PhiΦBreast & theory of spiral cancer new diagnostic techniques for breast cancer detection

引用

Translational Medicine Communications 2021年第1期6卷 1-10页

作者： Trapanese, Ersilio Tarro, Giulio CMM Diagnostic Center Cava de’ Tirreni Italy Foundation Teresa & Luigi De Beaumont Bonelli for Cancer Research Naples Italy De Beaumont Bonelli Foundation Naples Italy

Today, breast cancer is one of the most aggressive cancers in women and new cases continue to increase worldwide. The incidence of this tumor is kept under control especially with surgery. In order to reduce mortality we need to detect this life threatening disease at an earlier stage. For two years, we have conducted a study for the identification and characterization of suspicious breast lesions using a new diagnostic technique applied to ultrasonography and mammography called “PhiΦBreast.” Identification and characterization of category C4-C5 lesions of the breast with high predictive Positive PPV value, with a new innovative method called “PhiΦBreast” using the Golden Ratio (Phi, or Φ 1.618...) Fibonacci sequence and a predictive algorithm, applied to the ultrasonography and mammography with subsequent deepening with cytological examination using fine needle aspiration (FNAC), according to evaluation criteria of the Breast Imaging Report Data System (BI-RADS) and the American College of Radiology (ACR). Usefulness of this research and the use of this new diagnostic tecnique is to detect the breast cancer in early stage. In addition to develop a classification model of the histological type identified in the section areas and the percentage of probability in relation between the golden spiral and Fibonacci sequence. This amazing intuition and research has given contribution to the new Theory of Spiral Cancer. With the use of Golden Ratio and Fibonacci sequence, applied to ultrasonography and mammography, we have experimented and developed a diagnostic map with characteristics of high probability of identifying suspicious lesions at an early stage. We examined 987 women, 55 lesions detected with PhiΦBreast pattern were classified according to BI-RADS descriptors for US-imaging, including morphologic features that had a high predictive value for the malignancy (p <0.001). This innovative diagnostic technique has shown a sensitivity of 95%, a specificity of 97%,

关键词： PhiΦBreast Theory of Spiral Cancer predictive algorithm Golden Ratio Fibonacci Sequence Gravity Phyllotaxis Breast Cancer

来源：评论

学校读者我要写书评

暂无评论

Statistical and machine learning analysis of non-clinical factors impacting emergency room delays

引用

Informatics in Medicine Unlocked 2022年 33卷

作者： Aldhoayan, Mohammed D. Al Harbi, Afrah Samier Arajhi, Khalid Abduljawad, Joud King Saud Bin Abdulaziz University for Health Sciences Riyadh Saudi Arabia King Abdullah International Medical Research Center Saudi Arabia King Abdulaziz Medical City Ministry of National Guard – Health Affairs Riyadh Saudi Arabia Prince Mohammed Bin Abdulaziz Hospital MOH Riyadh Saudi Arabia

Introduction: Plenty is known about the clinical factors impacting the time patients spend in emergency departments (EDs), but less is known about associated non-clinical factors. Here we fill this knowledge gap through a statistical and machine learning (ML) analysis of the non-clinical factors impacting ED length of stay (LoS). Methods: Data from adult patients visiting the tertiary healthcare organization ED, Riyadh between January 2017 and October 2019 were subjected to logistic regression and multiple ML classification models to predict non-clinical factors associated with delayed ED LoS (>6 h). Results: There were 352,230 emergency visits by 135,185 patients. Most were under 6 h, with only 18% exceeding that benchmark. In logistic regression analysis, weekend visits, in the summer, by elderly male patients were associated with delayed ED LoS. The results of this study and the analysis of non-clinical factors in general can be used to aid in administrative decisions in EDs, such as deciding the number of staff per shift or provide the patients with the expected LoS to help them make decisions whether to stay or leave. Conclusion: Logistic regression revealed some associations between ER LoS and the included factors. However, ML models showed disappointing performance with the included non-clinical predictive variables. Further research to examine the impact of both clinical and non-clinical parameters on ED delay is now needed. © 2022 The Authors

关键词： Emergency department Length of stay Logistic regression Machine learning predictive algorithm

来源：评论

学校读者我要写书评

暂无评论

Testing and Validation of Mobile Air Quality Monitor for Sensing and Delineating VOC Emissions

Testing and Validation of Mobile Air Quality Monitor for Sen...

引用

作者： Thakor, Govind Singh University of Guelph

学位级别：硕士

The uRAD A3 air quality monitor uses a linear model to convert the output resistance value of the metal oxide sensor into air quality index in terms of VOC (AQIVOC). To improve this representation of AQIVOC a predictive algorithm was developed to convert the resistance to concentration values and then to AQIVOC. The A3 monitor was first validated through point source emissions and comparison with an analyzer. Then it was calibrated under controlled conditions for three different types of VOCs – acetone, ethanol and hexane. Experiments were performed for each solvent and in combination to observe how each solvent interacted with metal oxide sensor to understand the relationship between the resistance and concentration through analysis. Resistance range of each solvent (acetone - 15.24 to 8.5 Kohms, ethanol - 25.73 to 13.59 Kohms, hexane - 104.25 to 43.49 Kohms) and resistance-concentration relationship served as the basis for algorithm development for predicting total concentration of VOCs and their individual composition

关键词： Air Quality Index predictive algorithm Metal Oxide Sensor VOCs Resistance-Concentration Relationship Air Quality Monitor

来源：评论

学校读者我要写书评

暂无评论

Using Decision Trees to Predict Intent to Use PassiveOccupational Exoskeletons in Manufacturing Tasks

Using Decision Trees to Predict Intent to Use PassiveOccupat...

引用

作者： McNamara, Nathan Patrick Ohio University

学位级别：硕士

A nontraditional decision tree approach was used to predict worker intent to use passive occupational exoskeletons in various manufacturing tasks. A dataset adapted from a previous study containing 33 records of participant, exoskeleton, and task combinations was used to create multiple decision tree models. Worker intent to use the exoskeleton was used as the target variable for all decision tree models. Data were collected during two separate sessions with fifteen participants at five manufacturing facilities in Ohio. Participants wore exoskeletons for under 30 minutes in each session and answered questions pertaining to personal characteristics, task characteristics, and personal preferences. Response data were used to create practitioner and research decision tree models. The practitioner models classified worker intent to use exoskeletons using only task characteristics and personal characteristics. Research models used personal characteristics, task characteristics, and personal preferences features to predict intent to use with all collected data. Both practitioner and research models may be useful for practitioners and exoskeleton developers for better understanding factors related to intent to use exoskeletons. All models created in the study yielded findings consistent with previous exoskeleton literature. This study demonstrated the ability of classification trees to identify nonlinear relationships in datasets relating to intent to use assistive technologies.

关键词： Industrial Engineering Decision tree trees assistive device devices exoskeleton ergonomic intervention ergonomics machine learning human factors predictive algorithm intent to use safety

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：