检索结果-内蒙古大学图书馆

Cardiovascular burden in systemic sclerosis: QRISK3 versus Framingham for risk estimation

MODERN RHEUMATOLOGY 2022年第3期32卷 584-588页

作者： Di Battista, Marco Barsotti, Simone Della Rossa, Alessandra Mosca, Marta Univ Pisa Rheumatol Unit Via Roma 67 I-56123 Pisa Toscana Italy

Objectives To compare two algorithms for cardiovascular (CV) risk estimation in systemic sclerosis (SSc) patients, investigating correlations with disease characteristics. Methods Traditional CV risk factors and SSc-specific characteristics were assessed in a cohort of SSc patients. Framingham and QRISK3 algorithms were used to estimate the risk of developing a CV disease over the next 10 years. Results Seventy-two SSc patients were enrolled. Among those 56 without previous CV events, Framingham reported a median risk score of 9.6%, classifying 24 (42.9%) subjects at high risk. QRISK3 showed a median risk score of 15.8%, with 36 (64.3%) patients considered at high risk. Both algorithms revealed a significant role of some traditional risk factors and a noteworthy potential protective role of endothelin receptor antagonists (p = .003). QRISK3 was also significantly influenced by some SSc-specific characteristics, such as limited cutaneous subset (p = .01), interstitial lung disease (p = .04), and non-ischemic heart involvement (p = .03), with the first two maintaining statistical significance in the multivariate analysis (p = .02). Conclusions QRISK3 classifies more SSc patients at high risk to develop CV diseases than Framingham, reflecting the influence of some SSc-specific characteristics. If its predictive accuracy were prospectively verified, the use of QRISK3 as a tool in the early detection of SSc patients at high CV risk should be recommended.

关键词： Cardiovascular risk systemic sclerosis risk factors algorithm performance cardiovascular diseases

来源：评论

学校读者我要写书评

暂无评论

Sequestration of imaging studies in MIDRC: stratified sampling to balance demographic characteristics of patients in a multi-institutional data commons

引用

JOURNAL OF MEDICAL IMAGING 2023年第6期10卷 064501页

作者： Baughan, Natalie Whitney, Heather M. Drukker, Karen Sahiner, Berkman Hu, Tingting Kim, Grace Hyun McNitt-Gray, Michael Myers, Kyle J. Giger, Maryellen L. Univ Chicago Dept Radiol Chicago IL 60637 USA US FDA Bethesda MD USA Univ Calif Los Angeles Los Angeles CA USA Puente Solut Phoenix AZ USA

Purpose: The Medical Imaging and Data Resource Center (MIDRC) is a multi-institutional effort to accelerate medical imaging machine intelligence research and create a publicly available image repository/commons as well as a sequestered commons for performance evaluation and benchmarking of algorithms. After de-identification, approximately 80% of the medical images and associated metadata become part of the open commons and 20% are sequestered from the open commons. To ensure that both commons are representative of the population available, we introduced a stratified sampling method to balance the demographic characteristics across the two ***: Our method uses multi-dimensional stratified sampling where several demographic variables of interest are sequentially used to separate the data into individual strata, each representing a unique combination of variables. Within each resulting stratum, patients are assigned to the open or sequestered commons. This algorithm was used on an example dataset containing 5000 patients using the variables of race, age, sex at birth, ethnicity, COVID-19 status, and image modality and compared resulting demographic distributions to naive random sampling of the dataset over 2000 independent ***: Resulting prevalence of each demographic variable matched the prevalence from the input dataset within one standard deviation. Mann-Whitney U test results supported the hypothesis that sequestration by stratified sampling provided more balanced subsets than naive randomization, except for demographic subcategories with very low ***: The developed multi-dimensional stratified sampling algorithm can partition a large dataset while maintaining balance across several variables, superior to the balance achieved from naive randomization.

关键词： machine learning stratified sampling sequestration COVID-19 image database algorithm performance Medical Imaging and Data Resource Center

来源：评论

学校读者我要写书评

暂无评论

Development and Evaluation of an Improved algorithm for Detection of Ventricular Fibrillation 10th

引用

World Congress on Medical Physics and Biomedical Engineering

作者： Park, Sung-Bin Yoon, Hyoung-Ro Yonsei Univ Wonju South Korea

ISBN: (纸本)9783540368397

Our study focuses on a development and evaluation of ventricular fibrillation detection algorithm included clinical considerations on electrocardiography(ECG) signals as real-time warning on ventricular fibrillation occurrence in patients, especially at ICU and CCU is most critical function of a patient monitoring system. To determine whether ECG signal contains features on ventricular fibrillation, first, band-pass filter was applied, then peaks and valleys were detected in recent 2 seconds by 0.5second interval. Finally, time-difference and amplitude variation on both peaks and valleys and mutual relation on time difference between peak and valley were computed. These computed values allow us to decide whether ventricular fibrillation occurs or not. Moreover, we separated cardiac pulsation state into heartbeat, asystole and ventricular fibrillation state respectively so as to transfer one state to another state if present state did not meet the requirements established for each state. We conducted an assessment of performance of our proposed algorithm. Test signals were taken from the AHA ECG Database Series I and MIT-BIH Arrhythmia Database. As a result, VF duration sensitivity and VF duration positive predictivity is 98.1% and 99.1% in AHA DB, 88.5% and 86.3% in MIT-BIH DB respectively.

关键词： Ventricular Fibrillation Pulsation State algorithm performance

来源：评论

学校读者我要写书评

暂无评论

引用

11th IEEE International Conference on Intelligent Computer Communication and Processing (ICCP)

作者： Oprisa, Ciprian Ignat, Nicolae Bitdefender Bucharest Romania Tech Univ Cluj Napoca Cluj Napoca Romania

ISBN: (纸本)9781467382007

Finding similar binary programs is a challenging task, as there is no best way to compute this kind of similarity. The approach in the current paper is based on the fact that some programs retain structural information from the source code, like the division into packages, classes and methods. Using such a hierarchical structure, comparison algorithms based on OpCode n-grams can be enriched in order to produce more meaningful results. The method was implemented in order to detect plagiarism cases in a collection of Android applications written in Java. By employing the new techniques, the plagiarism detector exceeded 95% in terms of both precision and recall. The algorithm performance is also better if we use the new information about the program hierarchy, as the proposed system managed to compare large applications of over 7000 methods in about 15 seconds. By automatically detecting plagiarism cases from an early stage, our framework can limit the loss in financial revenue for the legitimate developers.

关键词： Android (operating system) Java program compilers security of data source code (software) Android application OpCode n-gram algorithm performance binary program hierarchical structure legitimate developer plagiarism case plagiarism detector program hierarchy source code Androids Complexity theory Feature extraction Humanoid robots Plagiarism Yttrium Java Java programming language Plagiarism hierarchical structure Androids Androids Source code compilers Humanoid robots Data Security Complexity theory Rare earths yttrium Feature extraction similar measure

来源：评论

学校读者我要写书评

暂无评论

Assessment of the performance of Tonal-Broadband Decomposition algorithms for Propeller Noise

Assessment of the Performance of Tonal-Broadband Decompositi...

引用

AIAA Aviation Forum

作者： Bonomo, Lucas A. Cordioli, Julio A. Colaciti, Alysson K. Fonseca, Joao Victor N. Simoes, Leandro G. C. Univ Fed Santa Catarina Dept Mech Engn BR-88040900 Florianopolis SC Brazil EMBRAER SA Noise & Vibrat BR-12227901 Sao Jose Dos Campos SP Brazil

ISBN: (数字)9781624107047

ISBN: (纸本)9781624107047

The usage of propellers is increasingly as an alternative to traditional aircraft and have become the primary option for new urban mobility vehicles. However, noise emissions from rotating blades can be a challenge for the certification of these new vehicles. The acoustic sources from a propeller can be decomposed into deterministic and random components. Therefore, academic research has focused on developing methods to separate these components. This study compares the performance of several literature methods to decompose propeller noise signals into tonal and broadband components. Initially, the methods were applied to a synthetic data that represents the main characteristics of rotating blade noise. Later, the methods were tested on realistic acoustic data collected within an isolated propeller test rig. The results showed that methods based on phase-averaging the recorded signals satisfactorily detected harmonic components. The method based on cross-correlation between data blocks had good ability to extract the broadband spectra, while poor performance on harmonic detection was observed. Additionally, the wavelet transform and Proper Orthogonal Decomposition methods were capable of reconstructing the time series related to both deterministic and random parts. However, further investigation is required regarding the POD modes separation, as unexpected trends were observed with the wavelet-based method.

关键词： Propeller Noise Proper Orthogonal Decomposition Propellers Wavelet Transform Overall Sound Pressure Level Short Time Fourier Transform Gaussian White Noise Convergence Analysis algorithm performance Spectral Analysis

来源：评论

学校读者我要写书评

暂无评论

RETRACTED: Development and validation of algorithms to differentiate ductal carcinoma in situ from invasive breast cancer within administrative claims data (Retracted Article)

引用

CANCER 2018年第13期124卷 2815-2823页

作者： Hirth, Jacqueline M. Hatch, Sandra S. Lin, Yu-Li Giordano, Sharon H. Silva, H. Colleen Kuo, Yong-Fang Univ Texas Med Branch Ctr Interdisciplinary Res Womens Hlth Dept Obstet & Gynecol 301 Univ BlvdRte 0587 Galveston TX 77555 USA Univ Texas Med Branch Dept Radiat Oncol Galveston TX 77555 USA Univ Texas Med Branch Dept Prevent Med & Community Hlth Off Biostat Galveston TX 77555 USA Univ Texas MD Anderson Canc Ctr Dept Hlth Serv Res Houston TX 77030 USA Univ Texas MD Anderson Canc Ctr Dept Breast Med Oncol Houston TX 77030 USA Univ Texas Med Branch Dept Oncol Surg Galveston TX 77555 USA

BACKGROUND: Overtreatment is a common concern for patients with ductal carcinoma in situ (DCIS), but this entity is difficult to distinguish from invasive breast cancers in administrative claims data sets because DCIS often is coded as invasive breast cancer. Therefore, the authors developed and validated algorithms to select DCIS cases from administrative claims data to enable outcomes research in this type of data. METHODS: This retrospective cohort using invasive breast cancer and DCIS cases included women aged 66 to 70 years in the 2004 through 2011 Texas Cancer Registry (TCR) data linked to Medicare administrative claims data. TCR records were used as "gold" standards to evaluate the sensitivity, specificity, and positive predictive value (PPV) of 2 algorithms. Women with a biopsy enrolled in Medicare parts A and B at 12 months before and 6 months after their first biopsy without a second incident diagnosis of DCIS or invasive breast cancer within 12 months in the TCR were included. Women in 2010 Medicare data were selected to test the algorithms in a general sample. RESULTS: In the TCR data set, a total of 6907 cases met inclusion criteria, with 1244 DCIS cases. The first algorithm had a sensitivity of 79%, a specificity of 89%, and a PPV of 62%. The second algorithm had a sensitivity of 50%, a specificity of 97%. and a PPV of 77%. Among women in the general sample, the specificity was high and the sensitivity was similar for both algorithms. However, the PPV was approximately 6% to 7% lower. CONCLUSIONS: DCIS frequently is miscoded as invasive breast cancer, and thus the proposed algorithms are useful to examine DCIS outcomes using data sets not linked to cancer registries. (C) 2018 American Cancer Society

关键词： administrative claims data algorithm performance breast cancer ductal carcinoma in situ (DCIS) validation

来源：评论

学校读者我要写书评

暂无评论

Sequestration methodology in practice through evaluation of joint demographic distributions of 54,185 patients in the Medical Imaging and Data Resource Center (MIDRC) data commons

Sequestration methodology in practice through evaluation of ...

引用

Conference on Medical Imaging - Imaging Informatics for Healthcare, Research, and Applications

作者： Baughan, Natalie Whitney, Heather M. Drukker, Karen Sahiner, Berkman Hu, Tingting Kim, Grace Hyun McNitt-Gray, Michael Myers, Kyle J. Giger, Maryellen L. Univ Chicago Dept Radiol Chicago IL 60637 USA US FDA Silver Spring MD USA Univ Calif Los Angeles Los Angeles CA USA Puente Solut LLC Sacramento CA USA MIDRC Org Med Imaging & Data Resource Ctr Chicago IL 60637 USA

ISBN: (纸本)9781510660434;9781510660441

The Medical Imaging and Data Resource Center (MIDRC) is a multi-institutional effort to accelerate medical imaging machine intelligence research and create a publicly available data commons as well as a sequestered commons for performance evaluation of algorithms. This work sought to evaluate the currently implemented methodology for apportioning data to the public and sequestered data commons by investigating the resulting distributions of joint demographic characteristics between the public and sequestered commons. 54,185 patients whose de-identified imaging studies and metadata had been submitted to MIDRC were previously separated into public and sequestered commons using a multi-dimensional stratified sampling method, resulting in 41,556 patients (77%) in the public commons and 12,629 patients (23%) in the sequestered commons. To compare the balance obtained in the joint distributions of patient characteristics from use of the developed sequestration method, patients from each commons were separated into bins, representing a unique combination of the demographic variables of COVID-19 status, age, race, and sex assigned at birth. The joint distributions of patients were visualized, and the absolute and percent difference in each bin from an exact 77:23 split of the data were calculated. Results indicated 75.9% of bins obtained differences of less than 15 patients, with a median difference of 3.6 from the total data for both public and sequestered commons. Joint distributions of patient characteristics in both the public and sequestered commons closely matched each other as well as that of the total data, indicating the sequestration by stratified sampling method has operated as intended.

关键词： Machine learning image database algorithm performance MIDRC AI sequestration COVID-19

来源：评论

学校读者我要写书评

暂无评论

Optimal Placement algorithm for Multiple Heterogeneous Stereo Vision Systems

Optimal Placement Algorithm for Multiple Heterogeneous Stere...

引用

AIAA Aviation Forum and Exposition

作者： Kang, Changkoo Woolsey, Craig A. Virginia Tech Dept Aerosp & Ocean Engn Blacksburg VA 24061 USA

ISBN: (数字)9781624106101

ISBN: (纸本)9781624106101

An unmanned aircraft system (UAS) can use a heterogeneous stereo vision system to detect and localize other aircraft which may pose a threat. The error in the triangulated location may be large, however, because of the short baseline between the two cameras mounted on the host aircraft. One way to address this issue is to use multiple host aircraft, each with a heterogeneous stereo vision system, in order to increase the stereo vision baseline. In this letter, we suggest a heterogeneous stereo vision optimal placement (HSOP) algorithm that solves a mixed-integer nonlinear programming problem to determine optimal positions for multiple airborne heterogeneous stereo vision systems in order to minimize the localization error for multiple threats. After introducing camera models for the "peripheral-central vision system," we formulate an optimization problem that supports counter-UAS applications. To assess the algorithm's performance, the simulated localization error of the HSOP algorithm is compared with that of another placement algorithm that considers only threat coverage. The results indicate that the HSOP algorithm effectively reduces the threat localization error.

关键词： Unmanned Aircraft System algorithm performance Nonlinear Programming MATLAB Energy Consumption Image Resolution Search algorithm Image Processing Computer Vision Motion Planning

来源：评论

学校读者我要写书评

暂无评论

APIS: Honeybee Foraging Task Assignment for Use in Uncertain and Unreliable Environments

APIS: Honeybee Foraging Task Assignment for Use in Uncertain...

引用

AIAA SciTech Forum

作者： Pye, John E. Alexandrov, Natalia M. NASA Langley Res Ctr Autonomous Integrated Syst Res Branch Hampton VA 23681 USA

ISBN: (数字)9781624107115

ISBN: (纸本)9781624107115

Multiagent Cyber-Physical-Human (CPH) systems in realistic environments operate under uncertain conditions. Communication among agents, aimed at reducing the uncertainty, is itself subject to uncertainty. We propose to manage uncertainties in autonomous, long-duration operations of multiagent systems via a modified Honeybee Foraging (HBF) behavioral scheme. The resulting system, Autonomous Persistent Intelligent Swarm (APIS), incorporates two new behaviors to ameliorate informational uncertainty. When "scouting", agents are tasked based on informational quality and reliability rather than solely on priorities. When "dancing", agents are tasked to rendezvous with other dancing agents to exchange information at close range, where successful communication is guaranteed. When coupled with uncertainty-aware modeling across agents, these behaviors improve situational awareness and resilience of the system, enabling it to function under more uncertain conditions arising during long-duration missions.

关键词： Ground Control Station Autonomous Systems Obstacle Avoidance Artificial Bee Colony algorithm performance Collision Avoidance Mathematical Models

来源：评论

学校读者我要写书评

暂无评论

Assessment of computerized algorithms by comparing with human observers in binary classification tasks: a simulation study

Assessment of computerized algorithms by comparing with huma...

引用

Conference on Medical Imaging - Image Perception, Observer performance, and Technology Assessment

作者： Yang, Yang Sahiner, Berkman Huang, Zhipeng Petrick, Nicholas Chen, Weijie US FDA Div Imaging Diagnost & Software Reliabil Off Sci & Engn Labs Ctr Devices & Radiol Hlth Rockville MD 20857 USA SUNY Buffalo Sch Publ Hlth & Hlth Profess Dept Biostat Buffalo NY USA

ISBN: (数字)9781510616448

ISBN: (纸本)9781510616448

It is generally recognized that recent advancements in computer vision, especially the development of deep convolutional neural networks, has substantially improved the performance of computerized algorithms in medical imaging for classification tasks such as cancer detection/*** advancements underscore the importance of the question of how the computer algorithm's stand-alone performance compares with the performance of physicians. Current literature often uses descriptive statistics or a visual check of plots for the comparison lacking quantitative and rigorous statistical inference. In this work, we developed a U-statistic based approach to estimate the variance of performance difference between an algorithm and a group of human observers in a binary classification task. The performance metric considered in this work is percent correct (PC), e.g., sensitivity or specificity. Our variance estimation treats both human observers and patient cases as random samples and accounts for both sources of variability, thereby allowing for the conclusion to be generalizable to both the patient and the physician populations. Moreover, we investigated a z-statistic method based on our variance estimator for hypothesis testing. Our simulation results show that our variance estimator for the PC performance difference is unbiased. The normal approximation method using our variance estimator for hypothesis testing appears useful for large sample sizes.

关键词： technology assessment algorithm performance variance estimation MRMC

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：