检索结果-内蒙古大学图书馆

Implementation and evaluation of a negation tagger in a pipeline-based system for information extraction from pathology reports

引用

Studies in Health Technology and informatics 2004年第PT 1期107卷 663-667页

作者： Mitchell, Kevin J. Becich, Michael J. Berman, Jules J. Chapman, Wendy W. Gilbertson, John Gupta, Dilip Harrison, James Legowski, Elizabeth Crowley, Rebecca S. Centers for Pathology and Oncology Informatics UPMC Shadyside 5230 Centre Avenue Pittsburgh PA 15232 United States Center for Biomedical Informatics University of Pittsburgh United States National Cancer Institute Bethesda MD United States Intelligent Systems Program University of Pittsburgh United States

We have developed a pipeline-based system for automated annotation of Surgical Pathology Reports with UMLS terms that builds on GATE-an open-source architecture for language engineering. The system includes a module for detecting and annotating negated concepts, which implements the NegEx algorithm-an algorithm originally described for use in discharge summaries and radiology reports. We describe the implementation of the system, and early evaluation of the Negation Tagger. Our results are encouraging. In the key Final Diagnosis section, with almost no modification of the algorithm or phrase lists, the system performs with precision of 0.84 and recall of 0.80 against a gold-standard corpus of negation annotations, created by modified Delphi technique by a panel of pathologists. Further work will focus on refining the Negation Tagger and UMLS Tagger and adding additional processing resources for annotating free-text pathology reports. © 2004 IMIA. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Causal discovery using a Bayesian local causal discovery algorithm

引用

Studies in Health Technology and informatics 2004年第PT 1期107卷 731-735页

作者： Mani, Subramani Cooper, Gregory F. Center for Biomedical Informatics Intelligent Systems Program University of Pittsburgh PA 15213 United States Department of Computer Science University of Wisconsin Milwaukee Milwaukee WI 53201 United States

This study focused on the development and application of an efficient algorithm to induce causal relationships from observational data. The algorithm, called BLCD, is based on a causal Bayesian network framework. BLCD initially uses heuristic greedy search to derive the Markov Blanket (MB) of a node that serves as the 'locality' for the identification of pair-wise causal relationships. BLCD takes as input a dataset and outputs potential causes of the form variable X causally influences variable Y. Identification of the causal factors of diseases and outcomes, can help formulate better management, prevention and control strategies for the improvement of health care. In this study we focused on investigating factors that may contribute causally to infant mortality in the United States. We used the U.S. Linked Birth/Infant Death dataset for 1991 with more than four million records and about 200 variables for each record. Our sample consisted of 41,155 records randomly selected from the whole dataset. Each record had maternal, paternal and child factors and the outcome at the end of the first year-whether the infant survived or not. Using the infant birth and death dataset as input, BLCD output six purported causal relationships. Three out of the six relationships seem plausible. Even though we have not yet discovered a clinically novel causal link, we plan to look for novel causal pathways using the full sample. © 2004 IMIA. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Characteristics of outpatient clinical decision support systems: A taxonomic description

引用

Studies in Health Technology and informatics 2004年第PT 1期107卷 578-581页

作者： Berlin, Amy Sorani, Marco Sim, Ida Department of Psychiatry University of California San Francisco San Francisco CA United States Program in Biological and Medical Informatics University of California San Francisco San Francisco CA United States

Computer-based clinical decision support systems (CDSSs) have been championed for their potential to improve healthcare quality. However, there has been no systematic study of the types of CDSSs that have been developed. In previous work, we developed the CDSS Taxonomy for comprehensively describing the technical, workflow, and contextual characteristics of CDSSs. We now use the CDSS Taxonomy to describe outpatient CDSSs evaluated in randomized controlled trials published between 1998 and 2002. 31 studies comprising 42 CDSS systems were included in our analysis. The majority of systems used rule-based reasoning engines to 'push' explicit, individualized recommendations concerning non-urgent decisions to clinicians or patients, but not both. 71% of the systems required someone to manually enter data into the system or to process the system output for use by the target decision maker. The average kappa for coding agreement was > 0.6. Our findings demonstrate that outpatient CDSSs vary greatly in design and function. Many impose a data entry or output processing burden on clinic staff. More complete reporting of CDSS characteristics is needed in the literature. © 2004 IMIA. All rights reserved.

关键词： Decision support systems

来源：评论

学校读者我要写书评

暂无评论

Implementation and initial evaluation of a web-based nurse order entry system for multidrug-resistant tuberculosis patients in Peru

引用

Studies in Health Technology and informatics 2004年第PT 1期107卷 202-206页

作者： Choi, Sharon S Jazayeri, Darius G Mitnick, Carole D Chalco, Katiuska Bayona, Jaime Fraser, Hamish S F Program in Infectious Disease and Social Change Dept. of Social Medicine Harvard Medical School Boston MA United States Children's Hospital Informatics Program Boston MA United States Partners in Health Boston MA United States Socios en Salud Lima Peru

Socios En Salud uses directly observed therapy to treat a majority of the multidrug-resistant tuberculosis in Peru. The nurses play an important role in this community-based model as the patients' primary care givers. Since nurses, rather than physicians, are involved in patients' daily care, we developed a nurse-order entry system to test whether such a system would improve the accuracy and quality of medication data. We compared regimen information from patient electronic medical records, paper charts and pharmacy records. After a two-month training period on the new system, we conducted the trial for 52 days in two of Lima's six geographic treatment areas, and re-reviewed the three sources of medication data. We measured the error rates after the trial period and found there was no significant difference in the control group's (Lima Este), error rate (8.6% vs. 6.9%, P=O.66) after the trial. The intervention group (Lima Callao), however, showed a significant drop in the error rate (17.4% vs. 3.1%, P=0.0074) after the same time interval. Additionally, the nurse expressed satisfaction with the order entry system and its ease of use. The decrease in error rates and user satisfaction regarding the system are promising measures of our order entry system's success. © 2004 IMIA. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

An information extraction and representation system for rapid review of the biomedical literature

引用

Studies in Health Technology and informatics 2004年第PT 2期107卷 788-792页

作者： Revere, Debra Fuller, Sherrilynne Bugni, Paul F. Martin, George M. Telemakus Research Program Division of Biomedical and Health Informatics University of Washington Seattle WA 98195-7155 United States Department of Pathology School of Medicine University of Washington Seattle WA United States

With the rapid expansion of scientific research, the ability to effectively find or integrate new domain knowledge in the sciences is proving increasingly difficult. The development of methods and tools for assisting researchers to effectively extract problem-oriented knowledge from heterogeneous and massive information sources, and for using this knowledge in problem-solving is one of the mostfundamental research directions for the information and computer sciences today. There is a need for new tools to support more precise identification of relevant research articles and provide visual clues regarding relationships among the document sets. We present the Telemakus system in which aggregated citation information and extracted research findings are displayed in a schema-based document surrogate and an interactive mapping tool provides graphical displays of research inter-relationships from documents across a domain. This system is an innovative approach to creating useful and precise document surrogates and may re-conceptualize the way we currently represent, retrieve, and assimilate research findings from the published literature. © 2004 IMIA. All rights reserved.

关键词： Information services

来源：评论

学校读者我要写书评

暂无评论

An edge detection method using 2-D autoregressive lattice prediction filters for remotely sensed images

An edge detection method using 2-D autoregressive lattice pr...

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： R. Gurcan I. Erer S. Kent Informatics Institute Advanced Technologies in Engineering Satellite Communication and Remote Sensing Program Istanbul Technical University Maslak Istanbul Turkey Istanbul Technical University Maslak Istanbul Turkey

Edges characterize boundaries and are therefore a problem of fundamental importance in image processing. Edge detecting an image significantly reduces the amount of data and filters out useless information, while preserving the important structural properties in an image. Edge detection is useful for segmentation, registration, and identification of objects in remote sensing images. Two dimensional lattice filters have been shown to be useful in many applications such as multidimensional spectral estimation, image data compression, high-resolution radar imaging, and removal of correlated clutter to enhance the detection ability of small objects in images. In this work, lattice filters are used for detecting the edges in remote sensing images. Lattice filter can be used to predict the correlated parts in an image and the resulting error (the output of the filter) will be edges. Edge detection results have been compared with other conventional edge detection methods as well as wavelet based methods. Results show that the proposed method is a good candidate for edge detection problem in remotely sensed images

关键词： Image edge detection Lattices Remote sensing Radar detection Image processing Information filtering Information filters Image segmentation Multidimensional systems Data compression

来源：评论

学校读者我要写书评

暂无评论

2-D orthogonal lattice filter based image segmentation

2-D orthogonal lattice filter based image segmentation

引用

IEEE International Symposium on Geoscience and Remote Sensing (IGARSS)

作者： S.Z. Aykut R. Gurcan I. Erer Istanbul Technical University Maslak Istanbul Turkey Informatics Institute Advanced Technologies in Engineering Satellite Communications and Remote Sensing Program Istanbul Technical University Maslak Istanbul Turkey

The purpose of image segmentation is to partition an image into homogeneous regions. Features are of major importance in image segmentation. In this work, a new method is proposed in which features used for segmentation are reflection coefficients of the two-dimensional (2D) orthogonal lattice filters. Principal component analysis (PCA) is applied to the features for reducing the complexity of the work. A minimum distance classifier is used in the classification algorithms. The proposed method is compared with the discrete wavelet transform which is a common segmentation algorithm. In our work, selected image is a monospectral optical image

关键词： Lattices Image segmentation Discrete wavelet transforms Optical filters Feature extraction Principal component analysis Remote sensing Optical reflection Filtering theory Predictive models

来源：评论

学校读者我要写书评

暂无评论

A Log Likelihood Predictor for Genomic Classification of Oral Cancer using Principle Component Analysis for Feature Selection

引用

11th World Congress on Medical informatics, MEDINFO 2004

作者： Whipple, Mark E. Mendez, Eduardo Farwell, D. Gregory Agoff, S. Nicholas Chen, Chu Department of Otolaryngology-Head and Neck Surgery University of Washington SeattleWA United States Division of Biomedical and Health Informatics University of Washington SeattleWA United States Department of Pathology University of Washington SeattleWA United States Program in Epidemiology Fred Hutchinson Cancer Research Center SeattleWA United States

ISBN: (纸本)1586034448

DNA microarrays are powerful tools for exploring gene expression and predicting disease state. However, since the number of variables (genes) typically exceeds the number of samples (tissue specimens), many potentially spurious genes may be selected for a predictor function. Principle component analysis (PCA) can greatly reduce the high-dimensional microarray data space while retaining most of the inherent variability. We propose a methodology that uses PCA to identify a predictor vector between two mutually exclusive and collectively exhaustive classes. By projecting the training set upon this vector a distribution of projections can be computed for each class. A log-likelihood ratio is then calculated for class membership. We used this methodology to classify 48 biopsy specimens as either oral squamous cell carcinoma or normal oral mucosa using oligonucleotide microarrays. The system was trained using a set of half the samples, and correctly predicted the membership of the other half The three most highly positively and three most highly negative predictive genes were all keratins that are known markers of squamous cell carcinoma. © 2004 IMIA. All rights reserved.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Classifying perinatal advanced practice data with the Omaha System

引用

Home Health Care Management and Practice 2004年第3期16卷 214-221页

作者： Marek, Karen Dorman Jenkins, Melinda L. Stringer, Marilyn Brooten, Dorothy Alexander, Gregory L. University of Missouri Sinclair School of Nursing Columbia MO United States Center for Evidence-Based Practice in the Underserved Columbia University School of Nursing New York NY United States Standing Faculty-Clinician Educator Program School of Nursing University of Pennsylvania Philadelphia PA United States Florida International University School of Nursing North Miami FL United States National Library of Medicine Informatics Sinclair School of Nursinguri

This pilot study analyzed perinatal advanced practice registered nurse (APRN) diagnoses/client problems and interventions across sites using standardized terminology. APRN verbatim encounter logs from 8 patients in a previous study were coded by both the Omaha System and Current Procedural Terminology (CPT) codes. Previous outcomes were reduced preterm births, hospitalizations, and costs (Brooten et al., 2001). In 597 encounters (63% by telephone), 27 diagnoses and 8,077 interventions were recorded. Health Teaching, Guidance, and Counseling were 42%;Surveillance, 38%;Treatments and Procedures, 11%;and Case Management, 9%. Health Teaching, Guidance, and Counseling were most frequent in clinic (51%) and phone encounters (45%). Surveillance was 30% to 35% at each site. Treatments and Procedures occurred most frequently in home and clinic visits, whereas Case Management occurred most in clinic and phone visits. When coded with CPT, more than 80% of interventions were unlisted. Documentation using standardized terminology would facilitate the study of effective nursing interventions. © 2004 Sage Publications.

关键词： Controlled vocabulary Nurse practitioners Nursing care Perinatal care

来源：评论

学校读者我要写书评

暂无评论

A framework for assessing HMIS in developing countries: Latvia as a case study

A framework for assessing HMIS in developing countries: Latv...

引用

Annual Hawaii International Conference on System Sciences (HICSS)

作者： D.S. Haazen D.J. Streveler Senior Health Specialist Health Program Team Leader World Bank Europe and Central Asia Region Riga Latvia Medical Informatics Department of Information and Computer Science University of Hawai Honolulu HI USA

The health systems in many developing countries lag seriously behind the developed world in the use of health management information systems (HMIS). The World Bank, like other international donor organizations, is increasingly called upon to provide technical and financial assistance in this area, but success stories remain rare. Because HMIS are critical to developing and improving health systems delivery and finance, the bank must find ways to increase effectiveness of the interventions it supports. This paper attempts to contribute to this process by proposing a new conceptual framework for the assessment of HMIS interventions, and then demonstrating the framework by applying it to an existing project to support national health insurance in Latvia. The paper documents the key characteristics of the HMIS project, discusses successes and failures to date, and presents lessons learned that may be applicable to other HMIS projects in developing countries. The case study focuses on a functional classification of the HMIS implementation, and critical success factors that have emerged with regard to systems implementation in developed countries.

关键词： Computer aided software engineering Management information systems Europe Asia Insurance Environmental management Project management Biomedical informatics Computer science Finance

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：