检索结果-南通市图书馆

predictive modeling for postoperative delirium in elderly patients with abdominal malignancies using synthetic minority oversampling technique

引用

World Journal of Gastrointestinal Oncology 2024年第4期16卷 1227-1235页

作者： Wen-Jing Hu Gang Bai Yan Wang Dong-Mei Hong Jin-Hua Jiang Jia-Xun Li Yin Hua Xin-Yu Wang Ying Chen Intensive Care Unit Shanghai Fourth People’s Hospital Affiliated to Tongji University School of MedicineShanghai 200434China Department of Anesthesia and Perioperative Medicine Shanghai Fourth People’s Hospital Affiliated to Tongji University School of MedicineShanghai 200434China Department of Nursing Shanghai Fourth People’s Hospital Affiliated to Tongji University School of MedicineShanghai 200434China Department of Thyroid Breast and Vascular SurgeryShanghai Fourth People’s Hospital Affiliated to Tongji University School of MedicineShanghai 200434China

BACKGROUND Postoperative delirium,particularly prevalent in elderly patients after abdominal cancer surgery,presents significant challenges in clinical *** To develop a synthetic minority oversampling technique(SMOTE)-based model for predicting postoperative delirium in elderly abdominal cancer *** In this retrospective cohort study,we analyzed data from 611 elderly patients who underwent abdominal malignant tumor surgery at our hospital between September 2020 and October *** incidence of postoperative delirium was recorded for 7 d *** were divided into delirium and non-delirium groups based on the occurrence of postoperative delirium or not.A multivariate logistic regression model was used to identify risk factors and develop a predictive model for postoperative *** SMOTE technique was applied to enhance the model by oversampling the delirium *** model’s predictive accuracy was then *** In our study involving 611 elderly patients with abdominal malignant tumors,multivariate logistic regression analysis identified significant risk factors for postoperative *** included the Charlson comorbidity index,American Society of Anesthesiologists classification,history of cerebrovascular disease,surgical duration,perioperative blood transfusion,and postoperative pain *** incidence rate of postoperative delirium in our study was 22.91%.The original predictive model(P1)exhibited an area under the receiver operating characteristic curve of *** comparison,the SMOTE-based logistic early warning model(P2),which utilized the SMOTE oversampling algorithm,showed a slightly lower but comparable area under the curve of 0.856,suggesting no significant difference in performance between the two predictive *** This study confirms that the SMOTE-enhanced predictive model for postoperative delirium in elderly abdominal tumor patients shows performance equivalent to that of tradi

关键词： Elderly patients Abdominal cancer Postoperative delirium Synthetic minority oversampling technique predictive modeling Surgical outcomes

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Geological Controls and Prospectivity Mapping for Manganese Ore Deposits Using predictive modeling Comparison:An Integration of Outcrop and Remote Sensing Data,Sinai Microplate,Egypt

引用

Journal of Earth Science 2023年第2期34卷 588-608页

作者： Sara Zamzam Geology Department Faculty of ScienceZagazig UniversityZagazig 44519Egypt

One of the most controversial minerals in their origin and occurrence around the world is manganese *** Abu Zenima area is rated one of the most economically important places where manganese ore deposits(Mn ODs)are located in the southwest Sinai microplate,*** deposits are confined with the Um Bogma Formation(UBF)and the reserves of this region are relatively *** this study,optical and radar data are used in a new challenge as an attempt to reach the closest controls and setting of Mn ***,Frequency Ratio(FR)and Logistic Regression(LogR)predictive models are applied to integrate different geospatial thematic maps,to predict new potential resource zones for increasing the ranges of mining ***8 OLI,Sentinel-2A Multi Spectral Instrument and Radar(Sentinel-1B)data are combined for mapping Mn ODs locations and their relationship with geological structures and the surrounding *** ratio,Principal and Independent Component Analysis techniques and four classification algorithms were implemented to the optical’VNIR and SWIR ***,the interferometric processing steps for Sentinel-1 data were made for understanding the tectonic features in the *** FR and LogR models are validated during fieldwork with known Mn ODs *** indicate that processed images are capable of differentiation of UBF which broadly distributed in the central and southern parts of the *** ODs possibly formed by thermal events that attributed to paleo-volcanic events before the rift *** high accuracy of LogR model(0.902)suggests that high Mn ODs potential zones are identified within the intersected fault zones near granitic *** integration is recommended for discriminating hydrothermally Mn ODs in other arid geographic regions.

关键词： manganese deposits Abu Zenima Landsat8 oli sentinel data fault zones predictive modeling remote sensing

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

predictive modeling in neurocritical care using causal artificial intelligence

引用

World Journal of Critical Care Medicine 2021年第4期10卷 112-119页

作者： Johnny Dang Amos Lal Laure Flurin Amy James Ognjen Gajic Alejandro A Rabinstein Mayo Clinic Alix School of Medicine Mayo ClinicRochesterMN 55905United States Department of Medicine Division of Pulmonary and Critical Care MedicineMultidisciplinary Epidemiology and Translational Research in Intensive CareMayo ClinicRochesterMN 55905United States Division of Clinical Microbiology Mayo ClinicRochesterMN 55905United States Department of Medicine Mayo ClinicRochesterMN 55905United States Department of Medicine Department of NeurologyMayo Clinic College of MedicineRochesterMN 55905United States

Artificial intelligence(AI)and digital twin models of various systems have long been used in industry to test products quickly and *** of digital twins in clinical medicine caught attention with the development of Archimedes,an AI model of diabetes,in *** recently,AI models have been applied to the fields of cardiology,endocrinology,and undergraduate medical *** use of digital twins and AI thus far has focused mainly on chronic disease management,their application in the field of critical care medicine remains much less *** neurocritical care,current AI technology focuses on interpreting electroencephalography,monitoring intracranial pressure,and prognosticating *** models have been developed to interpret electroencephalograms by helping to annotate the tracings,detecting seizures,and identifying brain activation in unresponsive *** this mini-review we describe the challenges and opportunities in building an actionable AI model pertinent to neurocritical care that can be used to educate the newer generation of clinicians and augment clinical decision making.

关键词： Artificial intelligence Digital twin Critical care Neurology Causal artificial intelligence predictive modeling

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

predictive modeling in Reproductive Medicine

引用

Reproductive and Developmental Medicine 2018年第4期2卷 224-229页

作者： Jing Lin Xiao-Xi Sun Shanghai Ji Ai Genetics and IVF Institute Obstetrics and Gynecology Hospital of Fudan UniversityShanghai 200011China Laboratory of Female Reproductive Endocrine-Related Diseases Shanghai 200011China

The accurate prediction of fertility outcomes is an extremely interesting and challenging task in reproductive medicine. Efforts in this area focus on classic statistical models and newer technologies, including machine learning. The modeling process has three steps, namely, data preparation, model selection and data fitting, and model validation. Here, we present a review of studies on these methods of fertility prediction. Various databases were searched using relevant keywords. Original studies with full-text available on this topic were included for review. Earlier studies explored prediction models for spontaneous pregnancy prognosis, reproductive outcomes after intrauterine insemination and in vitro fertilization, and implantation potential based on embryo morphology and morphokinetic data. Future directions for predictive modeling in reproductive medicine include solving problems presented by big data, identifying novel informative features, balancing predictive power and result interpretability, and validating models with gold-standard study designs.

关键词： Machine Learning Prediction Model predictive modeling Regression Model Reproductive Medicine

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

MultiDMet: Designing a Hybrid Multidimensional Metrics Framework to predictive modeling for Performance Evaluation and Feature Selection

引用

Intelligent Information Management 2023年第6期15卷 391-425页

作者： Tesfay Gidey Hailu Taye Abdulkadir Edris Department of Information and Communication Engineering Addis Ababa Science and Technology University Addis Ababa Ethiopia Department of Computer Science HILCOE School of Computer Science and Technology Addis Ababa Ethiopia

In a competitive digital age where data volumes are increasing with time, the ability to extract meaningful knowledge from high-dimensional data using machine learning (ML) and data mining (DM) techniques and making decisions based on the extracted knowledge is becoming increasingly important in all business domains. Nevertheless, high-dimensional data remains a major challenge for classification algorithms due to its high computational cost and storage requirements. The 2016 Demographic and Health Survey of Ethiopia (EDHS 2016) used as the data source for this study which is publicly available contains several features that may not be relevant to the prediction task. In this paper, we developed a hybrid multidimensional metrics framework for predictive modeling for both model performance evaluation and feature selection to overcome the feature selection challenges and select the best model among the available models in DM and ML. The proposed hybrid metrics were used to measure the efficiency of the predictive models. Experimental results show that the decision tree algorithm is the most efficient model. The higher score of HMM (m, r) = 0.47 illustrates the overall significant model that encompasses almost all the user’s requirements, unlike the classical metrics that use a criterion to select the most appropriate model. On the other hand, the ANNs were found to be the most computationally intensive for our prediction task. Moreover, the type of data and the class size of the dataset (unbalanced data) have a significant impact on the efficiency of the model, especially on the computational cost, and the interpretability of the parameters of the model would be hampered. And the efficiency of the predictive model could be improved with other feature selection algorithms (especially hybrid metrics) considering the experts of the knowledge domain, as the understanding of the business domain has a significant impact.

关键词： predictive modeling Hybrid Metrics Feature Selection Model Selection Algorithm Analysis Machine Learning

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Analysis of the Resolution of Crime Using predictive modeling

引用

Open Journal of Statistics 2020年第3期10卷 600-610页

作者： Keshab R. Dahal Jiba N. Dahal Kenneth R. Goward Oluremi Abayami Department of Statistics Truman State University Kirksville MO USA Department of Physics Truman State University Kirksville MO USA Department of Mathematics SUNY Cortland Cortland NY USA Department of Mathematics Northwood University Midland MI USA

There has been evidence of crime in the US since colonization. In this article, we analyze the crime statistics of San Francisco and its resolution of crime recorded from January to September of the year 2018. We define resolution of crime as a target variable and study its relationship with other variables. We make several classification models to predict resolution of crime using several data mining techniques and suggest the best model for predicting resolution.

关键词： Machine Learning Classification Model Comparison predictive modeling Resolution of Crime

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Big data in computational toxicology:predictive animal toxicity modeling using data-driven profiling and mechanism-driven read-across

Big data in computational toxicology:predictive animal toxic...

引用

第十次全国分析毒理学大会暨第六届分析毒理专业委员会会议

作者： Daniel P.Russo Hao Zhu Center for Computational and Integrative Biology Rutgers University

Generating animal toxicity data for all untested chemicals under the current toxicity testing paradigm is not *** methods,as promising alternatives,are to estimate a new chemical’s toxicity based on its most similar compounds（***-across）.Traditional read-across studies were based on chemical structure similarity searching,which is not applicable to predict unknown compounds with new chemical *** low cost biological data（*** vitro assay data） in read-across has shown potential to address this issue[1].However,previous read-across studies based on biological data required highly curated data with known relevance to toxicity,which are not suitable to deal with unstructured public data[2].We aimed to develop an automated method to extract useful biological data from a public repository（***） as bioprofiles for target compounds and incorporate both chemical structure information and bioprofiles into a read-across study to assess chemical toxicity[3].To achieve this goal,we used a database containing 7,385 compounds with diverse animal acute toxicity results（*** oral acute toxicity） to search against PubChem for their *** a novel subspace clustering algorithm,we identified several groups of PubChem assays which may reflect similar biological *** used these assay groups to perform read-across for acute *** relevant to toxicity predictions were identified by a cross-validation procedure within the modeling ***,a set of over 600 new compounds obtained from a new resource was used to validate the predictivity of the resulted *** assay clusters showed high predictivity for chemical toxicants（positive prediction rates range from 62.19% to 100.00%） through a cross validation *** individual clusters into a consensus model,we were able to prioritize chemical toxicants in the validation set（positive prediction rate as 76%）.Additionally,we show that imputing data

关键词： Computational Toxicology Big Data predictive modeling Animal Toxicity

来源： cnki会议评论

在线全文

cnki会议

学校读者我要写书评

暂无评论

An ANN-Based Short-Term Temperature Forecast Model for Mass Concrete Cooling Control

引用

Tsinghua Science and Technology 2023年第3期28卷 511-524页

作者： Hide Author's Information Ming Li Peng Lin Daoxiang Chen Zichang Li Ke Liu Yaosheng Tan Department of Hydraulic Engineering Tsinghua UniversityBeijing 100084China Sichuan Energy Internet Research Institute Tsinghua UniversityChengdu 610213China China Three Gorges Construction Engineering Corporation Chengdu 610000China

Concrete temperature control during dam construction(e.g.,concrete placement and curing)is important for cracking *** this study,a short-term temperature forecast model for mass concrete cooling control is developed using artificial neural networks(ANN).The development workflow for the forecast model consists of data integration,data preprocessing,model construction,and model *** than 80000 monitoring samples are collected by the developed intelligent cooling control system in the Baihetan Arch Dam,which is the largest hydropower project in the world under *** learning algorithms,including ANN,support vector machines,long short-term memory networks,and decision tree structures,are compared in temperature prediction,and the ANN is determined to be the best for the forecast ***,an ANN framework with two hidden layers is determined to forecast concrete temperature at intervals of one *** root mean square error of the forecast precision is 0.15∘C on *** application on concrete blocks verifies that the developed ANN-based forecast model can be used for intelligent cooling control during mass concrete construction.

关键词： artificial neural networks(ANN) predictive modeling temperature forecast mass concrete cooling control

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Assessment and Enhancement of FRC of Power Systems Considering Thermal Power Dynamic Conditions

引用

CSEE Journal of Power and Energy Systems 2024年第4期10卷 1371-1383页

作者： Feng Hong Yalei Pang Weiming Ji Lu Liang Fang Fang Junhong Hao Jizhen Liu State Key Laboratory of Alternate Electric Power System with Renewable Energy Sources and School of Control and Computer Engineering North China Electric Power UniversityBeijing 102206China State Key Laboratory of Alternate Electric Power System with Renewable Energy Sources School of Energy Power and Mechanical EngineeringNorth China Electric Power UniversityBeijing 102206China

Frequency stability and security have been a vital challenge as large-scale renewable energy is integrated into power *** contrast,the proportion of traditional thermal power units decreases during the decarbonization transformation process,resulting in poor frequency *** paper aims to explore the potential of frequency regulation support,dynamic assessment,and capacity promotion of thermal power plants in the transition *** the dynamic characteristics of the main steam working fluid under different working conditions,a nonlinear observer is constructed by extracting the main steam pressure and valve opening degree *** real-time frequency modulation capacity of thermal power units can provide a dynamic state for the power grid.A dynamic adaptive modification for primary frequency control(PFC)of power systems,including wind power and thermal power,is proposed and *** power dynamic allocation factor is adaptively optimized by predicting the speed droop ratio,and the frequency modulation capability of the system is improved by more than 11%under extreme ***,through the Monte Carlo simulation of unit states of the system under various working conditions,the promotion of the frequency regulation capacity with high wind power penetration(WPP)is verified.

关键词： Dynamic evaluation frequency regulation power system predictive modeling wind penetration

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Efficiently Exploring FPGA Design Space Based on Semi-Supervised Learning

引用

Chinese Journal of Electronics 2016年第1期25卷 58-63页

作者： YANG Liqun YANG Haigang LI Wei LI Zhihua University of Chinese Academy of Sciences System on Programmable Chip Research Department Institute of Electronics Chinese Academy of Sciences

Design space exploration(DSE) is an important step before the physical level design of Field programmable gate arrays(FPGA). An optimum architecture is usually selected from the whole space. As the architecture parameters increase, the huge time cost to explore an exponentially increasing space makes this method unrealistic. We propose a novel predictive modeling approach called ECOMT to estimate the area and delay of a circuit which is mapped onto an FPGA with certain ***-supervised model tree is adopted to model the performance with respect to architecture parameters. Combined with nonlinear programming, the area and delay model obtained can be used to guide the DSE. Experimental results show that the model trained through ECOMT has Mean relative error(MRE) below 5% compared to *** the time used to attain the model is less than3 minutes, which reduces the time of DSE considerably.

关键词： FPGA design space exploration predictive modeling Semi-supervised learning Performance prediction

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：