检索结果-内蒙古大学图书馆

Validation of a Major and Clinically Relevant Nonmajor Bleeding Phenotyping algorithm on Electronic Health Records

PHARMACOEPIDEMIOLOGY AND DRUG SAFETY 2024年第8期33卷 e5875-e5875页

作者： Yap, Aaron Jun Yi Teo, Desmond Chun Hwee Ang, Pei San Yap, Eng Soo Tan, Siew Har Loke, Celine Wei Ping Dorajoo, Sreemanee Raaj Hlth Sci Author Vigilance & Compliance Branch Hlth Prod Regulat Grp Singapore Singapore Natl Univ Singapore Hosp Dept Lab Med Singapore Singapore

Purpose: Bleeding is an important health outcome of interest in epidemiological studies. We aimed to develop and validate rule-based algorithms to identify (1) major bleeding and (2) all clinically relevant bleeding (CRB) (composite of major and all clinically relevant nonmajor bleeding) within real-world electronic healthcare data. Methods: We took a random sample (n = 1630) of inpatient admissions to Singapore public healthcare institutions in 2019 and 2020, stratifying by hospital and year. We included patients of all age groups, sex, and ethnicities. Presence of major bleeding and CRB were ascertained by two annotators through chart review. A total of 630 and 1000 records were used for algorithm development and validation, respectively. We formulated two algorithms: sensitivity- and positive predictive value (PPV)-optimized algorithms. A combination of hemoglobin test patterns and diagnosis codes were used in the final algorithms. Results: During validation, diagnosis codes alone yielded low sensitivities for major bleeding (0.16) and CRB (0.24), although specificities and PPV were high (>0.97). For major bleeding, the sensitivity-optimized algorithm had much higher sensitivity and negative predictive values (NPVs) (sensitivity = 0.94, NPV = 1.00), however false positive rates were also relatively high (specificity = 0.90, PPV = 0.34). PPV-optimized algorithm had improved specificity and PPV (specificity = 0.96, PPV = 0.52), with little reduction in sensitivity and NPV (sensitivity = 0.88, NPV = 0.99). For CRB events, our algorithms had lower sensitivities (0.50-0.56). Conclusions: The use of diagnosis codes alone misses many genuine major bleeding events. We have developed major bleeding algorithms with high sensitivities, which can ascertain events within populations of interest.

关键词： clinically relevant nonmajor bleeding electronic health records major bleeding pharmacovigilance phenotyping rule-based algorithm validation

来源：评论

学校读者我要写书评

暂无评论

Realization of rule-based automated design for HVAC duct layout

引用

JOURNAL OF BUILDING ENGINEERING 2023年 80卷

作者： Liang, Ruobing Wang, Changxiao Wang, Peng Yoon, Sungmin Dalian Univ Technol Fac Infrastruct Engn Dalian Peoples R China Sungkyunkwan Univ Dept Global Smart City Suwon 16419 South Korea Sungkyunkwan Univ Sch Civil Architectural Engn & Landscape Architect Suwon 16419 South Korea

In the traditional process of pipeline design, a designer typically creates a general layout of pipeline based on their experience, and then calculates whether the hydraulic calculation of pipeline meets the requirements. This method of design is both time-consuming and laborintensive. Furthermore, the results are often suboptimal and prone to errors, which creates a lot of waste of human and material resources. The objective of this paper is to propose a computer-aided method for completely automating the heating, ventilation and air conditioning (HVAC) duct system design process. This method incorporates all the necessary design processes, such as duct selection and hydraulic calculation, and introduces a rule-based divide-and-conquer method to the pipe routing design (PRD). The research assesses the practical effect of this piping design algorithm in a BIM environment using varied building scenarios. The findings show that the proposed method is capable of meeting the design requirements of actual projects. The automatic piping design technique presented in this paper can significantly reduce labor costs associated with HVAC design while eliminating calculation errors and compressing the design timeline for most of the complex projects to within 5 min.

关键词： HVAC PRD Automated design rule-based algorithm BIM

来源：评论

学校读者我要写书评

暂无评论

Consistent regression using data-dependent coverings

引用

ELECTRONIC JOURNAL OF STATISTICS 2021年第1期15卷 1743-1782页

作者： Margot, Vincent Baudry, Jean-Patrick Guilloux, Frederic Wintenberger, Olivier Sorbonne Univ Lab Probabilites Stat & Modelisat Campus Pierre & Marie CurieTour 16-261er Etage F-75005 Paris France

We introduce a procedure to generate an estimator of the regression function based on a data-dependent quasi-covering of the feature space. A quasi-partition is generated from the quasi-covering and the estimator predicts the conditional empirical expectation over the cells of the quasi-partition. We provide sufficient conditions to ensure the consistency of the estimator. Each element of the quasi-covering is labeled as significant or insignificant. We avoid the condition of cell shrinkage commonly found in the literature for data-dependent partitioning estimators. This reduces the number of elements in the quasi-covering. An important feature of our estimator is that it is interpretable. The proof of the consistency is based on a control of the convergence rate of the empirical estimation of conditional expectations, which is interesting in itself.

关键词： Consistency nonparametric regression rule-based algorithm data-dependent covering interpretable learning

来源：评论

学校读者我要写书评

暂无评论

BIM-based Framework for Formwork Planning Considering Potential Reuse

引用

JOURNAL OF MANAGEMENT IN ENGINEERING 2022年第2期38卷 04021090-04021090页

作者： Mei, Zhongya Xu, Maozeng Wu, Peng Luo, Siyu Wang, Jun Tan, Yi Chongqing Jiaotong Univ Sch Econ & Management Chongqing 400074 Peoples R China Curtin Univ Sch Design & Built Environm Perth WA 6845 Australia Western Sydney Univ Sch Engn Design & Built Environm Kingswood NSW 2747 Australia Shenzhen Univ Sino Australia Joint Res Ctr BIM & Smart Construc Shenzhen 518060 Peoples R China

Concrete formwork is frequently required with the increasing demands of building and infrastructure construction and has a significant impact on the costs of concrete works. Onsite formwork planning is often conducted via site managers' individual experience, resulting in low efficiency and waste production. The potential reuse and material waste reduction of concrete formwork should be focused on, and an automated and accurate planning approach is required. Therefore, this study proposes a building information modeling (BIM)-based framework to assist site managers in automatically obtaining accurate demands of concrete formwork to reduce waste and costs. The developed framework is introduced to provide an approach to information extraction, potential reuse, and waste reduction of concrete formwork and consists of three major parts: component information extraction, panel use planning, and concrete form planning. Geometry and quantity information of building concrete components is automatically extracted from a BIM model to provide more accurate quantity take-offs compared with the conventional two-dimensional (2D) drawings. Demands of reused formwork panels are then calculated by a designed rule-based algorithm and rules based on trades' know-how. Finally, quantities of concrete forms are minimized using a 2D cutting stock problem optimization model based on the genetic algorithm. An illustrative example of a reinforced concrete building for formwork planning is analyzed using the developed framework. Results show that the developed BIM-based framework can automatically generate an accurate plan and assist to save 28% of the formwork purchase cost compared with expert-based planning methods. Furthermore, the framework has great potential for more accurate decisions making in formwork layout planning, processing, and onsite storage.

关键词： Building information modeling (BIM) Concrete formwork Potential reuse Material waste reduction rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

Multi-label annotation of text reports from computed tomography of the chest, abdomen, and pelvis using deep learning

引用

BMC MEDICAL INFORMATICS AND DECISION MAKING 2022年第1期22卷 102-102页

作者： D'Anniballe, Vincent M. Tushar, Fakrul Islam Faryna, Khrystyna Han, Songyue Mazurowski, Maciej A. Rubin, Geoffrey D. Lo, Joseph Y. Duke Univ Ctr Virtual Imaging Trials Dept Radiol Carl E Ravin Adv Imaging LabsSch Med 2424 Erwin Rd Ste 302 Durham NC 27705 USA Duke Univ Pratt Sch Engn Dept Elect & Comp Engn Durham NC 27705 USA Univ Girona Erasmus Joint Master Med Imaging & Applicat Girona Spain South China Univ Technol Sch Software Engn Guangzhou Guangdong Peoples R China Univ Arizona Dept Med Imaging Coll Med Tucson AZ USA

Background There is progress to be made in building artificially intelligent systems to detect abnormalities that are not only accurate but can handle the true breadth of findings that radiologists encounter in body (chest, abdomen, and pelvis) computed tomography (CT). Currently, the major bottleneck for developing multi-disease classifiers is a lack of manually annotated data. The purpose of this work was to develop high throughput multi-label annotators for body CT reports that can be applied across a variety of abnormalities, organs, and disease states thereby mitigating the need for human annotation. Methods We used a dictionary approach to develop rule-based algorithms (RBA) for extraction of disease labels from radiology text reports. We targeted three organ systems (lungs/pleura, liver/gallbladder, kidneys/ureters) with four diseases per system based on their prevalence in our dataset. To expand the algorithms beyond pre-defined keywords, attention-guided recurrent neural networks (RNN) were trained using the RBA-extracted labels to classify reports as being positive for one or more diseases or normal for each organ system. Alternative effects on disease classification performance were evaluated using random initialization or pre-trained embedding as well as different sizes of training datasets. The RBA was tested on a subset of 2158 manually labeled reports and performance was reported as accuracy and F-score. The RNN was tested against a test set of 48,758 reports labeled by RBA and performance was reported as area under the receiver operating characteristic curve (AUC), with 95% CIs calculated using the DeLong method. Results Manual validation of the RBA confirmed 91-99% accuracy across the 15 different labels. Our models extracted disease labels from 261,229 radiology reports of 112,501 unique subjects. Pre-trained models outperformed random initialization across all diseases. As the training dataset size was reduced, performance was robust except for a

关键词： Weak supervision Report labeling Attention RNN rule-based algorithm Natural language processing Computed tomography

来源：评论

学校读者我要写书评

暂无评论

Health and wellness monitoring using ambient sensor networks

引用

JOURNAL OF AMBIENT INTELLIGENCE AND SMART ENVIRONMENTS 2020年第2期12卷 139-151页

作者： Yan Wang Ali Yalcin Univ S Florida Dept Ind & Management Syst Engn 4202 E Fowler AveENC 2400 Tampa FL 33620 USA

Smart homes equipped with ambient wireless sensor networks provide new opportunities to help older adults age-in-place, improve their quality of life and help better manage their health and wellness. In this paper, we present a methodology that estimates occupants' status as active, sedentary, in-bed, out-of-home and unobservable, their location in the house, and their daily activities related to overall health and wellness. The methodology is used to visualize and examine the daily patterns and activities of older adults living in their own homes and participating in a smart home research project. The proposed location and status estimation algorithm is highly accurate as validated by a mobile app that prompts participants with questions about the estimated time of their daily activities. A case study involving a significant health-related life event is presented where the participant's account of changes in her patterns and activities through bi-weekly interviews are shown to confirm inferences based on the results of the proposed methodology.

关键词： Health and wellness age-in-place rule-based algorithm smart homes wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Automated gait event detection for a variety of locomotion tasks using a novel gyroscope-based algorithm

引用

GAIT & POSTURE 2020年 81卷 102-108页

作者： Fadillioglu, Cagla Stetter, Bernd J. Ringhof, Steffen Krafft, Frieder C. Sell, Stefan Stein, Thorsten Karlsruhe Inst Technol Inst Sports & Sports Sci Engler Bunte Ring 15 D-76131 Karlsruhe Germany Univ Freiburg Dept Sport & Sport Sci Schwarzwaldstr 175 D-79117 Freiburg Germany Hosp Neuenbuerg Joint Ctr Black Forest D-75305 Neuenbuerg Germany

Background: The robust identification of initial contact (IC) and toe-off (TO) events is a vital task in mobile sensor-based gait analysis. Shank attached gyroscopes in combination with suitable algorithms for data processing can robustly and accurately complete this task for gait event detection. However, little research has considered gait detection algorithms that are applicable to different locomotion tasks. Research question: Does a gait event detection algorithm for various locomotion tasks provide comparable estimation accuracies as existing task-specific algorithms? Methods: Thirteen males, equipped with a gyroscope attached to the right shank, volunteered to perform nine different locomotion tasks consisting of linear movements and movements with a change of direction. A rule based algorithm for IC and TO events was developed based on the shank sagittal plane angular velocity. The algorithm was evaluated against events determined by vertical ground reaction force. Absolute mean error (AME), relative absolute mean error (RAME) and Bland-Altman analysis was used to assess its accuracy. Results: The average AME and RAME were 11 +/- 3 ms and 3.07 +/- 1.33 %, respectively, for IC and 29 +/- 11 ms and 7.27 +/- 2.92 %, respectively, for TO. Alterations of the walking movement, such as turns and types of running, slightly reduced the accuracy of IC and TO detection. In comparison to previous methods, increased or comparable accuracies for both IC and TO detection are shown. Significance: The study shows that the proposed algorithm is capable of detecting gait events for a variety of locomotion tasks by means of a single gyroscope located on the shank. In consequence, the algorithm can be applied to activities, which consist of various movements (e.g., soccer). Ultimately, this extends the use of mobile sensor-based gait analysis.

关键词： Wearable sensors rule-based algorithm Initial contact Toe-off Linear movements Turning conditions

来源：评论

学校读者我要写书评

暂无评论

Real-time energy storage management system of a nanogrid integrating photovoltaics and V2G operation

引用

JOURNAL OF ENGINEERING-JOE 2020年第1期2020卷 32-40页

作者： Bampoulas, Adamantios Karlis, Athanasios Democritus Univ Thrace Dept Elect & Comp Engn Univ Campus Kimmeria Xanthi Greece

The widespread penetration of electric vehicles (EVs) in the automotive market will create not only concerns about additional energy burden on power grids but also incentives to further encourage vehicle to grid (V2G) functionalities. The integration of EVs with intermittent renewables requires complex control systems due to the need to predict and manage data related to user behaviour and climate. In this study, a real-time energy storage management system was developed to accommodate V2G technology integration in a residential nanogrid considering no prior knowledge about the future system's state. The rule-based algorithm developed maximises the direct use of solar energy, ensures a user-determined driving range and provides ancillary services to the utility grid in real-time through an autonomous distributed control. The considered residential nanogrid set up was modelled via Matlab/Simulink and the corresponding results are demonstrated and discussed. From simulations, it is shown that the smart house designed integrates the V2G technology so that the nanogrid provides ancillary services to the bulk power system causing the least possible energy burden on the utility.

关键词： energy management systems power grids electric vehicles vehicle-to-grid solar power future system solar energy bulk power system real-time energy storage management system nanogrid integrating photovoltaics electric vehicles power grids grid functionalities complex control systems user behaviour V2G technology integration residential nanogrid rule-based algorithm

来源：评论

学校读者我要写书评

暂无评论

Demand response potential of district heating in a swimming hall in Finland

引用

ENERGY AND BUILDINGS 2021年 248卷 111149-111149页

作者： Yuan, Xiaolei Lindroos, Leo Jokisalo, Juha Kosonen, Risto Pan, Yiqun Jin, Hui Tongji Univ Sch Mech Engn Shanghai 201804 Peoples R China Aalto Univ Dept Mech Engn Espoo Finland TalTech Smart City Ctr Excellence Tallinn Estonia Nanjing Tech Univ Coll Urban Construct Nanjing Peoples R China Gezhouba Grp Real Estate Corp Nanjing Peoples R China

In this paper, the demand response of district heating for swimming pools and pool space air is proposed and applied in a swimming hall in Finland. Swimming halls have significant heat demands e.g., domestic hot water supply, space heating and pool water heating, and thus have much large heat storage capacity for the realization of district-heat based demand response. A dynamic building simulation tool IDA ICE was used to simulate whole swimming hall including pools and HVAC systems. In addition, a rule-based demand response algorithm which utilized dynamic district heat price was proposed and applied in the district heating control of the studied swimming hall. The results show that the large storing capacity of pool water promises the large amount of charged and discharged heat energy, and ensure the application of demand response of district heating in swimming hall. The application of demand response of district heating can increase the average pool water temperature from the normal setpoint of 26.5 degrees C to 27.3 degrees C. In addition, demand-response district heating control for the swimming pool water and pool space air decreases the total district heat costs of the swimming hall by 1.1%. During the repayment periods of 7 and 15 years, the energy cost savings and maximum cost of profitable investment for the demand response control are between 10 000 (sic) and 20 000 (sic). (C) 2021 Published by Elsevier B.V.

关键词： Swimming hall Demand response District heating rule-based algorithm Profitable investment cost

来源：评论

学校读者我要写书评

暂无评论

An Intelligent Triphase rule-based Wheel Slip Controller with Slip Estimation for Heavy Vehicles

An Intelligent Triphase Rule-Based Wheel Slip Controller wit...

引用

International Conference on COMmunication Systems and NETworkS (COMSNETS)

作者： Ramakrushnan, Karthik Challa, Akhil Patil, Harshal Subramanian, Shankar C. Vivekanandan, Gunasekaran Sivaram, Sriram Indian Inst Technol Madras Dept Engn Design Chennai Tamil Nadu India Madras Engn Ind Pvt Ltd Chennai Tamil Nadu India

ISBN: (纸本)9781728131870

Wheel slip regulation (WSR) is an approach to achieve anti-lock braking, where the parameter, wheel slip ratio, is made to operate around a reference value. WSR algorithms can be rule-based or model-based. Model-based solutions require real-time information on vehicle parameters including tire model parameters that increases the challenge in their real-world implementation. Hence, this work proposes a novel triphase rule-based WSR algorithm for Heavy Commercial Road Vehicles, that employ an electro-pneumatic brake system. Since the direct measurement of wheel slip is not feasible, estimates from an Extended Kalman Filter are used to monitor and regulate slip. A real-time reference adaptation scheme is proposed to detect low friction road surfaces. The proposed algorithm is evaluated in a Hardware-in-Loop experimental setup, and shown to adapt to the road surface, prevent wheel lock, and reduce braking distance up to 19 % compared to the case without control.

关键词： Wheel slip regulation rule-based algorithm Extended Kalman Filter Reference slip Vehicle 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：