Search

Purpose - This paper seeks to develop a specified typology of various levels of semantic interoperability, designed to provide semantically expressive and functional means to interconnect typologically different sub-systems in an international comprehensive knowledge organization system, supporting advanced information retrieval and exploration strategies. Design/methodology/approach - Taking the analysis of rudimentary forms of a functional interoperability based on simple pattern matching as a starting-point, more refined strategies to provide semantic interoperability, which is actually reaching the conceptual and even thematic level, are being developed. The paper also examines the potential benefits and perspectives of the selective transfer of modelling strategies from the field of semantic technologies for the refinement of relational structures of inter-system and inter-concept relations as a requirement for expressive and functional indexing languages supporting advanced types of semantic interoperability. Findings - As the principles and strategies of advanced information retrieval systems largely depend on semantic information, new concepts and strategies to achieve semantic interoperability have to be developed. Research limitations/implications - The approach has been developed in the functional and structural context of an international comprehensive system integrating several heterogeneous knowledge organization systems and indexing languages by interconnecting them to a central conceptual structure operating as a spine in an overall system designed to support retrieval and exploration of bibliographic records representing complex conceptual entities. Originality/value - Research and development aimed at providing technical and structural interoperability has to be complemented by a thorough and precise reflection and definition of various degrees and types of interoperability on the semantic level as well. The approach specifies these levels and reflects the implications and their potential for advanced strategies of retrieval and exploration. [ABSTRACT FROM AUTHOR]

Background: Healthcare providers generate a huge amount of biomedical data stored in either legacy system (paper-based) format or electronic medical records (EMR) around the world, which are collectively referred to as big biomedical data (BBD). To realize the promise of BBD for clinical use and research, it is an essential step to extract key data elements from unstructured medical records into patient-centered electronic health records with computable data elements. Our objective is to introduce a novel solution, known as a double-reading/entry system (DRESS), for extracting clinical data from unstructured medical records (MR) and creating a semi-structured electronic health record database, as well as to demonstrate its reproducibility empirically.Methods: Utilizing the modern cloud-based technologies, we have developed a comprehensive system that includes multiple subsystems, from capturing MRs in clinics, to securely transferring MRs, storing and managing cloud-based MRs, to facilitating both machine learning and manual reading, and to performing iterative quality control before committing the semi-structured data into the desired database. To evaluate the reproducibility of extracted medical data elements by DRESS, we conduct a blinded reproducibility study, with 100 MRs from patients who have undergone surgical treatment of lung cancer in China. The study uses Kappa statistic to measure concordance of discrete variables, and uses correlation coefficient to measure reproducibility of continuous variables.Results: Using the DRESS, we have demonstrated the feasibility of extracting clinical data from unstructured MRs to create semi-structured and patient-centered electronic health record database. The reproducibility study with 100 patient's MRs has shown an overall high reproducibility of 98 %, and varies across six modules (pathology, Radio/chemo therapy, clinical examination, surgery information, medical image and general patient information).Conclusions: DRESS uses a double-reading, double-entry, and an independent adjudication, to manually curate structured data elements from unstructured clinical data. Further, through distributed computing strategies, DRESS protects data privacy by dividing MR data into de-identified modules. Finally, through internet-based computing cloud, DRESS enables many data specialists to work in a virtual environment to achieve the necessary scale of processing thousands MRs within days. This hybrid system represents probably a workable solution to solve the big medical data challenge. [ABSTRACT FROM AUTHOR]

Most recent document standards like XML rely on structured representations. On the other hand, current information retrieval systems have been developed for flat document representations and cannot be easily extended to cope with more complex document types. The design of such systems is still an open problem. We present a new model for structured document retrieval which allows computing scores of document parts. This model is based on Bayesian networks whose conditional probabilities are learnt from a labelled collection of structured documents-which is composed of documents, queries and their associated assessments. Training these models is a complex machine learning task and is not standard. This is the focus of the paper: we propose here to train the structured Bayesian Network model using a cross-entropy training criterion. Results are presented on the INEX corpus of XML documents. [ABSTRACT FROM AUTHOR]

Background: With the development and application of medical information system, semantic interoperability is essential for accurate and advanced health-related computing and electronic health record (EHR) information sharing. The openEHR approach can improve semantic interoperability. One key improvement of openEHR is that it allows for the use of existing archetypes. The crucial problem is how to improve the precision and resolve ambiguity in the archetype retrieval.Method: Based on the query expansion technology and Word2Vec model in Nature Language Processing (NLP), we propose to find synonyms as substitutes for original search terms in archetype retrieval. Test sets in different medical professional level are used to verify the feasibility.Result: Applying the approach to each original search term (n = 120) in test sets, a total of 69,348 substitutes were constructed. Precision at 5 (P@5) was improved by 0.767, on average. For the best result, the P@5 was up to 0.975.Conclusions: We introduce a novel approach that using NLP technology and corpus to find synonyms as substitutes for original search terms. Compared to simply mapping the element contained in openEHR to an external dictionary, this approach could greatly improve precision and resolve ambiguity in retrieval tasks. This is helpful to promote the application of openEHR and advance EHR information sharing. [ABSTRACT FROM AUTHOR]

The article reports that Beijing, China has been designated as the new Global Information System Centers (GISC) of the World Meteorological Organization (WMO) in 2013. Services that will be provided by GISC Beijing include Global Telecommunication System (GTS) data transmission and exchange, Data Discovery, Access and Retrieve (DAR) and Data Subscription. Information on the three types of WMO Information System (WIS) centers is provided, as well as the objective of each GISC.

Purpose - The purpose of the study was to compare an internet search engine, Google, with appropriate library databases and systems, in order to assess the relative value, strengths and weaknesses of the two sorts of system. Design/methodology/approach - A case study approach was used, with detailed analysis and failure checking of results. The performance of the two systems was assessed in terms of coverage, unique records, precision, and quality and accessibility of results. A novel form of relevance assessment, based on the work of Saracevic and others was devised. Findings - Google is superior for coverage and accessibility. Library systems are superior for quality of results. Precision is similar for both systems. Good coverage requires use of both, as both have many unique items. Improving the skills of the searcher is likely to give better results from the library systems, but not from Google. Research limitations/implications - Only four case studies were included. These were limited to the kind of queries likely to be searched by university students. Library resources were limited to those in two UK academic libraries. Only the basic Google web search functionality was used, and only the top ten records examined. Practical implications - The results offer guidance for those providing support and training for use of these retrieval systems, and also provide evidence for debates on the "Google phenomenon". Originality/value - This is one of the few studies which provide evidence on the relative performance of internet search engines and library databases, and the only one to conduct such in-depth case studies. The method for the assessment of relevance is novel. [ABSTRACT FROM AUTHOR]