1 University of Pittsburgh, Pittsburgh, PA,USA; 2 University of Manchester, Manchester,UK

Size: px
Start display at page:

Download "1 University of Pittsburgh, Pittsburgh, PA,USA; 2 University of Manchester, Manchester,UK"

Transcription

1 Towards Computational Extraction of Potential Drug-Drug Interaction Information from Drug Product Labeling Tables Steven T. DeMarco 1, Nikola Milošević, MSc 2, Joshua Le 1, Jodi Schneider, PhD 1, Richard D. Boyce, PhD 1 1 University of Pittsburgh, Pittsburgh, PA,USA; 2 University of Manchester, Manchester,UK Abstract Structured Product Labels (SPLs) are mandated to provide information about potential drug-drug interactions (PDDIs). A major limitation of SPLs is that the information is provided as unstructured text and tables. Extracting, storing, processing, and annotating this information into an indexed knowledge base will allow increased accessibility to important prescribing information. In this paper we report on an analysis of the feasibility of automatically extracting PDDI information from tables found within the Drug Interactions section of SPLs. 1,161 SPLs (3.9% of prescription labeling) had a total 1,530 tables. These tables had 340 headers that we grouped into 8 categories. Both functional and structural analyses, and MetaMap annotation, was completed for 50% of the 1,530 tables. We observed that most tables were diversely structured, and that the most frequent semantic types aligned well with the 8 table header categories. The results provide a starting point for developing heuristics to extract PDDIs. Introduction Many thousands of people are harmed each year by exposure to two or more drugs for which there exists a known potential interaction 1. Unfortunately, there is currently no single complete source of information for these potential drug-drug interactions (PDDIs) 2. In the United States, one important information source is drug product labeling, which is required by law to contain information regarding clinically significant interactions (c.f., CFR (c)) 3. All drug product labels in the United States are freely available through the National Library of Medicine s DailyMed website 4 in a standard format called Structured Product Labeling (SPL) 5. While easy to access, a major limitation of SPLs is that information regarding PDDIs is provided as unstructured text and diversely formatted tables. Providing a solution to computationally extract PDDI information from the label into an indexed knowledge base would enable more convenient access to this information. Moreover, PDDI information extracted from the SPL could be more easily linked to other sources of information to provide a more complete picture of the mechanisms, risk factors, clinical implications, and management options of each PDDI. In this paper we report on an analysis of the feasibility of automatically extracting PDDI information from tables found within the Drug Interactions section of SPLs. In the remainder of this paper, we introduce background on text mining of tables and drug-related information, describe the methods for our analysis of SPL tables, and present the analysis results and conclusions. Background Text mining information within published tables is an active area of computer science research. Hurst was among the first to propose a text mining model of tables containing five elements: graphical, physical, functional, structural and semantic 6. Research has focused on detecting tables in various types of documents and assigning functional areas (or conducting functional analysis) of tables Functional analysis aims to classify table cells by their function and can be carried out using heuristic rules or machine learning algorithms After the functional areas are found, the relationships between cells can be resolved during structural analysis, which is usually done by applying heuristic rules 6,13,15. Applying text mining to biomedical tables is an emerging area. To extract gene mutation names, Wong et al. scraped PubMed s stand-alone HTML table documents (avoiding the need for table detection) and used heuristics to detect and classify table headers 16. Then they used the Mismatch Repair Database as a gold standard with a machinelearning based Named Entity Recognition system, to identify which table vector contained at least one mutation mention. The BioTextSearch project indexed tables from PubMedCentral, storing complete tables and images in an Apache Lucene-based search engine; their table search heavily weighted captions and headers to improve table retrieval compared to text search 17,18. Within the drug informatics domain, the SPLICER system 19 was successfully applied to extracting adverse drug events from tables and text written in the Adverse Reactions section of SPLs. Other efforts focused on side effects

2 and drug indications For example, the SIDER database uses named entity recognition to extract side effects and indications from product labeling, including SPLs 23. More recently, starting with full-text papers from the Journal of Oncology, Xu & Wang extracted drug-side effect relationships, which they compare to the SIDER database. They used Support Vector Machines to classify tables as side-effect-related or not, and then used a dictionary-based approach to extract drugs and side effects based on manually curated lexicons 24. Methods Descriptive Analysis of Table Content In order to develop a thorough understanding of the distribution of rows, columns and table headers within SPL tables, we first conducted a descriptive analysis. We wrote a Python script 25 to automatically download the Drug Interaction section for all US SPLs from the LinkedSPLs 26 resource, and to separate HTML tables from unstructured text content. All extracted HTML tables were merged into a single HTML page that we could view in a web browser to get an overall sense of the kinds of information provided by the tables. Also, a Python script was used to extract all table headers which we then manually organized into distinct categories. These categories were then used to describe the distribution of categorical assignment given to unique table headers. Table Content Extraction and Storage for Convenient Access The descriptive analysis made it apparent that tables with similar table headers contained similar information. This information regularly included drug mentions, clinical recommendations, and dosing instructions or adjustments. The next step was to enable computational access to data provided in the individual cells of each table. Doing so would enable semantic annotation of the table content which could then be used to extract PDDI information. We modified an existing software tool called Table Annotator 27 to extract the contents of each SPL table into its relational schema which is designed to store each table, cell, and semantic annotation. The schema also supports storing the results of the functional and structural analyses over the table data. After modifying Table Annotator, SPLs for all prescription drug products as of January 1, 2016 were downloaded from DailyMed. The full set of SPLs was reduced to a subset of SPLs that our descriptive analysis identified as having table content in the Drug Interaction section. These SPLs were used as input into Table Annotator which parsed and analyzed the table content, assigned functional roles and structural relationships to individual cells and annotated the contents of each cell. Functional Analysis A functional analysis determines each cell s function within each table. Cells are identified as a table header, row header, super-row, or data cell. Table Annotator implements an algorithm that determines these cellular functions based on a set of heuristic rules 27. Briefly, table headers are typically found within the first row of the table and are identified by the <thead> tag. These table headers provide insight into the data contained within the corresponding column. Similarly, each row heading classifies the information contained in the corresponding row. Some row headers are further classified as super-rows, which grouped related rows together. Each data cell corresponds to an individual data item that has a relationship with other functional groups, such as table headers and row headers. An example of the output of a typical functional analysis can be seen in Figure 1.

3 Figure 1. Functional analysis on the table Efficacy by Disease Site 28. Structural Analysis A structural analysis determines the relationships between cells. Table types can fall into four types based on their dimensionality and structure, and each table type requires different parsing strategies. The four table types are list tables, matrix tables, super-row tables and multi-tables. List tables are identified as one-dimensional tables that present a simple list of data cells. These data cells are involved in a relationship only with the header above them. Matrix tables are identified as simple two-dimensional tables that contain data cells within a matrix. These data cells are involved in relationships with their corresponding table header and row header. Super-row tables are identified as multi-dimensional tables, where dimensions are defined by the number of table headers, row headers and superrows. Data cells within this matrix are involved in relationships with the table headers above the corresponding cells, as well as the corresponding row headers and super-row headers. Multi-tables are comprised of multiple tables merged together. These tables can be a challenge during computational analysis because only table headers within the first row are formally labeled with a <thead> tag, while the rest of the headers are recognized as cells between rows containing a horizontal line. An example of a table containing problematic headers can be seen in Figure 2.

4 Figure 2. Drug-Thyroidal Axis Interactions is an example of a table that would be classified as a multi-table 29. Annotation of Cell Content After Table Annotator performed a functional and structural analysis of the input SPLs, the system was used to annotate the cell content of each loaded table. Internally, the Table Annotator uses Marvin, a semantic text annotation tool, to annotate cell content 30. We configured Marvin to use the Unified Medical Language System s (UMLS) MetaMap program to identify named entities within the table cells 31,32. Table Annotator stored the MetaMap annotations as Concept Unique Identifiers (CUIs) linked to data from specific tables cells 33. The UMLS Semantic Network provides a semantic type for each CUI, such as Pharmacologic Substance, Clinical Attribute or Therapeutic or Preventative Procedure. We queried the Table Annotator schema for the CUIs associated with each MetaMap annotation, and then queried our local implementation of the UMLS database (2014AB) to retrieve the corresponding semantic types and describe their distribution. Results Descriptive Analysis of Table Content Tables 1 and 2 summarize our descriptive analysis of table content. Out of 29,964 prescription drug SPLs, only 1,161 SPLs (3.9%) had tables present in the Drug Interaction section. These 1,161 SPLs included a total 1,530 tables. From these tables, we identified 340 unique table headers which we then grouped into 8 different categories. We computationally identified the most prominent categories as Drug Class or Drug Name, Effect on Drug and Recommendation or Comment. Table 1. Basic statistics for 1,530 HTML tables. Property Count Property Minimum Median Mean Maximum Number of Tables 1,530 Columns Number of Distinct Headers 340 Rows Number of Categories 8

5 Table 2. Number of Distinct Headers per Category for 1,530 HTML tables. Category Name Count Proportion of Unique Headers Drug Class or Drug Name % Effect on Drug % Interaction Properties % Interacting Substance % Interacting Substance Properties % Miscellaneous % Recommendation or Comment % Sample Size % Table Content Extraction and Storage for Convenient Access Due to technical difficulties (described below) that were not addressed due to time constraints, Table Annotator loaded and completed the functional, structural, and annotation tasks on only 772 (50%) of the 1,530 tables. The results below apply to that subset of the tables. Functional Analysis After completing the functional analysis, Table Annotator identified 35,407 cells which were classified into 43,179 cell types. The classifications were distributed as 7,558 table headers, 11,790 row headers, 20,256 data cells and 3,575 super-rows. Row headers can be further classified as super-rows (see Figure 1), which accounts for the offset in cell types. Structural Analysis After completing the structural analysis, Table Annotator identified 772 tables which were classified as 298 matrix tables and 474 super-row tables. Annotation of Cell Content The total number of distinct headers was 179, which fell into eight different categories. As with the full set of tables, the most prominent categories for these table headers were Drug Name or Drug Class, Effect on Drug and Recommendation or Comment. Figure 3 and Table 3 show example of MetaMap annotated content. In total, MetaMap identified 332,504 named entities which mapped to 107 semantic types. The two most frequent semantic types were Pharmacologic Substance and Organic Chemical. Tables 4 6 summarize the results of the Table Annotator processing for the tables for which MetaMap annotation was completed. Figure 3. An example of MetaMap annotated content (underlined). This row is an excerpt from Established and Other Potentially Significant Drug Interactions 34. Each of these annotations has a corresponding semantic type that is outlined in Table 3.

6 Table 3. The MetaMap annotations for the table excerpt shown in Figure 3. Each annotation can belong to multiple semantic types. Drugs or drug classes corresponded to Pharmacologic Substance and Organic Chemical semantic types, whereas content within the clinical recommendation corresponded to Functional, Quantitative or Qualitative Concept semantic types. MetaMap Annotation corticosteroid (C , C ) dexamethasone (C ) delavirdine (C ) use with caution (C ) rescriptor (C ) less (C , C ) effective (C , C ) due to (C ) decreased (C , C , C ) patients (C ) take (C ) agent (C , C , C ) concentrations plasma (C ) Corresponding Semantic Type(s) Pharmacologic Substance (T121), Hormone (T125), Organic Chemical (T109) Pharmacologic Substance (T121), Organic Chemical (T109) Pharmacologic Substance (T121), Organic Chemical (T109) Functional Concept (T169) Pharmacologic Substance (T121), Organic Chemical (T109) Quantitative Concept (T081), Qualitative Concept (T080) Quantitative Concept (T081), Qualitative Concept (T080) Functional Concept (T169) Quantitative Concept (T081), Qualitative Concept (T080) Patient or Disabled Group (T101) Health Care Activity (T058) Chemical Viewed Functionally (T120), Pharmacologic Substance (T121), Intellectual Product (T170) Quantitative Concept (T081) Table 4. Basic statistics for the 722 tables processed by MetaMap named entity recognition with Table Annotator. Property Count Property Minimum Median Mean Maximum Number of Tables 772 Columns Number of Distinct Headers Number of Categories Rows MetaMap Annotations

7 Table 5. Number of distinct headers per category for the 772 tables processed by MetaMap named entity recognition with Table Annotator. Category Name Count Proportion of Unique Headers Drug Class or Drug Name % Effect on Drug % Interaction Properties % Interacting Substance % Interacting Substance Properties % Miscellaneous % Recommendation or Comment % Sample Size % Table 6. Distribution of most frequent semantic types processed by MetaMap named entity recognition with Table Annotator. Conclusion Semantic Type Total Count Proportion of Total Annotations Pharmacologic Substance (T121) 60, % Organic Chemical (T109) 38, % Qualitative Concept (T080) 35, % Quantitative Concept (T081) 34, % Functional Concept (T169) 32, % Spatial Concept (T082) 15, % Intellectual Product (T170) 11, % Clinical Attribute (T201) 10, % Finding (T033) 9, % Therapeutic or Preventative Procedure (T061) 9, % To the best of our knowledge, no other project has attempted to extract PDDI information from tables in SPLs. We found that Table Annotator could load and conduct a functional and structural analysis of all Drug Interaction section tables. With respect to semantic annotations, while we ran into difficulties applying MetaMap to the cell content of many of the tables, we think the problem will be addressable in future work. MetaMap has strict requirements for the strings that it receives for processing and the raw cell content of SPL tables would frequently break these requirements causing the MetaMap server to crash. Some additional pre-preprocessing of the data sent to MetaMap from Table Annotator should fix this issue. Moving forward, we plan to complete an in-depth analysis on the causes of the MetaMap server crashing, pre-process these problematic SPLs, and fully process the 1,530 tables with Table Annotator. The current analysis characterizes the current functional and structural characteristics for a significant subset of tables of all tables in the Drug Interactions section. It also identified patterns of semantic types within the table cells for that subset. As a result of the structural analysis, the majority of tables analyzed were super-row tables, confirming our initial observation that many of these tables contain diverse and difficult-to-process formatting. Our functional analysis found that data cells were the most frequent cell type, with row headers as the second most common cell type. We observed that the most frequent semantic types aligned well with our categorical assignments for table headers. The most frequent table header categories were Drug Class or Drug Name, Effect on Drug and Recommendation or Comment. The most frequent semantic types (Table 6) contain annotations that correspond to these categorical header assignments. For example, Pharmacologic Substance and Organic Chemical semantic types corre-

8 spond with the Drug Class or Drug Name table header category. The Clinical Attribute, Finding and Therapeutic or Preventative Procedure semantic types correspond with the Recommendation or Comment table header category. Based on the results, we are confident that is feasible to construct scalable rules for extracting PDDI information from tables found within the Drug Interactions section of SPLs. This can be done using table header categorical assignments and the semantic types of corresponding annotations. By grouping similar tables based upon the pattern of both the semantic types and the table headers, we can begin to extract the individual pieces of PDDI information. The first step would be to test if the header categories for a table align with the semantic types from each cell annotation. This will confirm the fact that the table header contains relevant information in the data cells beneath it. The second step would be to test for features that indicate specific kinds of information within each of the columns defined by the table header categories. For example, if the cells within a column with Drug Class or Drug Name header contain an entity tagged with the Pharmacologic Substance and Organic Chemical semantic type then, each entity is likely referring to a drug that interacts with that drug that the SPL is about. Similarly, if the cells within a column with the Effect on Drug header type include entities tagged with a Functional, Quantitative or Qualitative Concept semantic type then, the cell likely provides information on the clinical effect (e.g., effect direction, magnitude, or severity). Other heuristics can be imagined and, taken together, will serve as a starting point for developing extracting PDDIs from most of the diverse PDDI tables found in SPLs. Acknowledgements This work was partially supported by the National Library of Medicine grant Addressing gaps in clinically useful evidence on drug-drug interactions (1R01LM ) and a training grant 5T15LM from the National Library of Medicine and National Institute of Dental and Craniofacial Research. References 1. Magro L, Moretti U, Leone R. Epidemiology and characteristics of adverse drug reactions caused by drugdrug interactions. Expert Opin Drug Saf Jan;11(1): Ayvaz S, Horn J, Hassanzadeh O, Zhu Q, Stan J, Tatonetti NP, et al. Toward a complete dataset of drug drug interaction information from publicly available sources. J Biomed Inform Jun;55: CFR - Code of Federal Regulations Title 21 [Internet]. Apr 1, Available from: 4. DailyMed - About [Internet]. [cited 2016 Mar 7]. Available from: 5. FDA. Indexing Structured Product Labeling [Internet]. Rockville, MD: Federal Drug Administration; 2008 Jun. Report No.: ucm Available from: f 6. Hurst MF. The Interpretation of Tables in Texts [Internet] [PhD]. University of Edinburgh; 2000 [cited 2016 Mar 7]. Available from: 7. Thomas Kieninger AD. The T-Recs Table Recognition and Analysis System. In: Document Analysis Systems: Theory and Practice. Nagano, Japan: Springer; p Ng HT, Lim CY, Koo JLT. Learning to Recognize Tables in Free Text. In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics on Computational Linguistics [Internet]. Stroudsburg, PA, USA: Association for Computational Linguistics; 1999 [cited 2016 Mar 7]. p (ACL 99). Available from: 9. Son JW, Lee JA, Park SB, Song HJ, Lee SJ, Park SY. Discriminating Meaningful Web Tables from Decorative Tables Using a Composite Kernel. In: IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology, p Yildiz B, Kaiser K, Miksch S. pdf2table: A Method to Extract Table Information from PDF Files. In: Indian International Conference on Artificial Intelligence. Tumkur, Karnataka, India; p Hu J, Kashi RS, Lopresti DP, Wilfong G. Table structure recognition and its evaluation. In: Proc SPIE, Document Recognition and Retrieval VIII [Internet] [cited 2016 Mar 7]. p Available from: Chavan MM, Shirgave SK. A Methodology for Extracting Head Contents from Meaningful Tables in Web Pages. In: 2011 International Conference on Communication Systems and Network Technologies (CSNT) p Wei X, Croft B, Mccallum A. Table Extraction for Answer Retrieval. Inf Retr Nov;9(5):

9 14. Tengli A, Yang Y, Ma NL. Learning Table Extraction from Examples. In: COLING 04: Proceedings of the 20th International Conference on Computational Linguistics [Internet]. Stroudsburg, PA, USA: Association for Computational Linguistics; 2004 [cited 2016 Mar 7]. Available from: Milosevic N, Gregson C, Hernandez R, Nenadic G. Extracting patient data from tables in clinical literature: Case study on extraction of BMI, weight and number of patients. In: Proceedings of the 9th International Joint Conference on Biomedical Engineering Systems and Technologies [Internet]. Rome, Italy; 2016 [cited 2016 Mar 7]. p Available from: on_extraction_of_bmi_weight_and_number_of_patients 16. Wong W, Martinez D, Cavedon L. Extraction of named entities from tables in gene mutation literature. In: Proceedings of the Workshop on Current Trends in Biomedical Natural Language Processing [Internet]. Association for Computational Linguistics; 2009 [cited 2016 Mar 9]. p Available from: Hearst MA, Divoli A, Guturu H, Ksikes A, Nakov P, Wooldridge MA, et al. BioText Search Engine: beyond abstract search. Bioinformatics Aug 15;23(16): Divoli A, Wooldridge MA, Hearst MA. Full Text and Figure Display Improves Bioscience Literature Search. PLOS ONE Apr 14;5(4):e Duke J, Friedlin J, Li X. Consistency in the safety labeling of bioequivalent medications. Pharmacoepidemiol Drug Saf Mar 1;22(3): Fung KW, Jao CS, Demner-Fushman D. Extracting drug indication information from structured product labels using natural language processing. J Am Med Inform Assoc May 1;20(3): Khare R, Li J, Lu Z. LabeledIn: Cataloging labeled indications for human drugs. J Biomed Inform Dec;52: Boyce R, Gardner G, Harkema H. Using Natural Language Processing to Extract Drug-Drug Interaction Information from Package Inserts. In: BioNLP: Proceedings of the 2012 Workshop on Biomedical Natural Language Processing [Internet]. Montréal, Canada: Association for Computational Linguistics; p Available from: Kuhn M, Letunic I, Jensen LJ, Bork P. The SIDER database of drugs and side effects. Nucleic Acids Res Jan 4;44(Database issue):d Xu R, Wang Q. Large-scale automatic extraction of side effects associated with targeted anticancer drugs from full-text oncological articles. J Biomed Inform Jun;55: Python [Internet]. Python.org. [cited 2016 Mar 9]. Available from: dbmi-pitt/ner-pddi-table-parsing [Internet]. GitHub. [cited 2016 Mar 10]. Available from: TableAnnotator [Internet]. GitHub. [cited 2016 Mar 7]. Available from: DailyMed - LETROZOLE- letrozole tablet [Internet]. [cited 2016 Mar 7]. Available from: DailyMed - LEVOTHYROXINE SODIUM - levothyroxine sodium tablet [Internet]. [cited 2016 Mar 7]. Available from: Milosevic N. Marvin: Semantic annotation using multiple knowledge sources. ArXiv Cs [Internet] Feb 1 [cited 2016 Mar 7]; Available from: UMLS Quick Start Guide [Internet]. [cited 2016 Mar 7]. Available from: MetaMap - A Tool For Recognizing UMLS Concepts in Text [Internet]. [cited 2016 Mar 7]. Available from: McInnes BT, Pedersen T, Carlis J. Using UMLS Concept Unique Identifiers (CUIs) for Word Sense Disambiguation in the Biomedical Domain. AMIA Annu Symp Proc. 2007;2007: DailyMed - RESCRIPTOR- delavirdine mesylate tablet [Internet]. [cited 2016 Mar 7]. Available from:

Extracting patient data from tables in clinical literature Case study on extraction of BMI, weight and number of patients

Extracting patient data from tables in clinical literature Case study on extraction of BMI, weight and number of patients Extracting patient data from tables in clinical literature Case study on extraction of BMI, weight and number of patients Nikola Milosevic 1, Cassie Gregson 2, Robert Hernandez 2 and Goran Nenadic 1,3

More information

Precise Medication Extraction using Agile Text Mining

Precise Medication Extraction using Agile Text Mining Precise Medication Extraction using Agile Text Mining Chaitanya Shivade *, James Cormack, David Milward * The Ohio State University, Columbus, Ohio, USA Linguamatics Ltd, Cambridge, UK shivade@cse.ohio-state.edu,

More information

Exploring the Query Expansion Methods for Concept Based Representation

Exploring the Query Expansion Methods for Concept Based Representation Exploring the Query Expansion Methods for Concept Based Representation Yue Wang and Hui Fang Department of Electrical and Computer Engineering University of Delaware 140 Evans Hall, Newark, Delaware, 19716,

More information

HTML Extraction Algorithm Based on Property and Data Cell

HTML Extraction Algorithm Based on Property and Data Cell IOP Conference Series: Materials Science and Engineering OPEN ACCESS HTML Extraction Algorithm Based on Property and Data Cell To cite this article: Detty Purnamasari et al 2013 IOP Conf. Ser.: Mater.

More information

Learning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li

Learning to Match. Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li Learning to Match Jun Xu, Zhengdong Lu, Tianqi Chen, Hang Li 1. Introduction The main tasks in many applications can be formalized as matching between heterogeneous objects, including search, recommendation,

More information

Medical Records Clustering Based on the Text Fetched from Records

Medical Records Clustering Based on the Text Fetched from Records Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology ISSN 2320 088X IMPACT FACTOR: 5.258 IJCSMC,

More information

A TEXT MINER ANALYSIS TO COMPARE INTERNET AND MEDLINE INFORMATION ABOUT ALLERGY MEDICATIONS Chakib Battioui, University of Louisville, Louisville, KY

A TEXT MINER ANALYSIS TO COMPARE INTERNET AND MEDLINE INFORMATION ABOUT ALLERGY MEDICATIONS Chakib Battioui, University of Louisville, Louisville, KY Paper # DM08 A TEXT MINER ANALYSIS TO COMPARE INTERNET AND MEDLINE INFORMATION ABOUT ALLERGY MEDICATIONS Chakib Battioui, University of Louisville, Louisville, KY ABSTRACT Recently, the internet has become

More information

The NLM Medical Text Indexer System for Indexing Biomedical Literature

The NLM Medical Text Indexer System for Indexing Biomedical Literature The NLM Medical Text Indexer System for Indexing Biomedical Literature James G. Mork 1, Antonio J. Jimeno Yepes 2,1, Alan R. Aronson 1 1 National Library of Medicine, Bethesda, MD, USA {mork,alan}@nlm.nih.gov

More information

Document Retrieval using Predication Similarity

Document Retrieval using Predication Similarity Document Retrieval using Predication Similarity Kalpa Gunaratna 1 Kno.e.sis Center, Wright State University, Dayton, OH 45435 USA kalpa@knoesis.org Abstract. Document retrieval has been an important research

More information

BioNav: An Ontology-Based Framework to Discover Semantic Links in the Cloud of Linked Data

BioNav: An Ontology-Based Framework to Discover Semantic Links in the Cloud of Linked Data BioNav: An Ontology-Based Framework to Discover Semantic Links in the Cloud of Linked Data María-Esther Vidal 1, Louiqa Raschid 2, Natalia Márquez 1, Jean Carlo Rivera 1, and Edna Ruckhaus 1 1 Universidad

More information

Text Mining. Munawar, PhD. Text Mining - Munawar, PhD

Text Mining. Munawar, PhD. Text Mining - Munawar, PhD 10 Text Mining Munawar, PhD Definition Text mining also is known as Text Data Mining (TDM) and Knowledge Discovery in Textual Database (KDT).[1] A process of identifying novel information from a collection

More information

Keywords Data alignment, Data annotation, Web database, Search Result Record

Keywords Data alignment, Data annotation, Web database, Search Result Record Volume 5, Issue 8, August 2015 ISSN: 2277 128X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: www.ijarcsse.com Annotating Web

More information

Graphical Methods for Reducing, Visualizing and Analyzing Large Data Sets Using Hierarchical Terminologies

Graphical Methods for Reducing, Visualizing and Analyzing Large Data Sets Using Hierarchical Terminologies Graphical Methods for Reducing, Visualizing and Analyzing Large Data Sets Using Hierarchical Terminologies Xia Jing, MB, PhD 1, James J. Cimino, MD 1, 2 1 National Library of Medicine, 2 Clinical Center,

More information

Framework for Sense Disambiguation of Mathematical Expressions

Framework for Sense Disambiguation of Mathematical Expressions Proc. 14th Int. Conf. on Global Research and Education, Inter-Academia 2015 JJAP Conf. Proc. 4 (2016) 011609 2016 The Japan Society of Applied Physics Framework for Sense Disambiguation of Mathematical

More information

Ontology-based Information Extraction from Technical Documents

Ontology-based Information Extraction from Technical Documents Ontology-based Information Extraction from Technical Documents Syed Tahseen Raza Rizvi 1,2, Dominique Mercier 2, Stefan Agne 1, Steffen Erkel 3, Andreas Dengel 1 and Sheraz Ahmed 1 1 German Research Center

More information

Guidance for the format and content of the final study report of non-interventional post-authorisation safety studies

Guidance for the format and content of the final study report of non-interventional post-authorisation safety studies 23 January 2013 EMA/48663/2013 Patient Health Protection Guidance for the format and content of the final study report of non-interventional post-authorisation safety studies Introduction From 10 January

More information

Information Extraction of Important International Conference Dates using Rules and Regular Expressions

Information Extraction of Important International Conference Dates using Rules and Regular Expressions ISBN 978-93-84422-80-6 17th IIE International Conference on Computer, Electrical, Electronics and Communication Engineering (CEECE-2017) Pattaya (Thailand) Dec. 28-29, 2017 Information Extraction of Important

More information

Data Mining of the E-Pelvis Simulator Database: A Quest for a Generalized Algorithm for Objectively Assessing Medical Skill

Data Mining of the E-Pelvis Simulator Database: A Quest for a Generalized Algorithm for Objectively Assessing Medical Skill 355 Data Mining of the E-Pelvis Simulator Database: A Quest for a Generalized Algorithm for Objectively Assessing Medical Skill Thomas MACKEL 1, Jacob ROSEN 1,2, Ph.D., Carla PUGH 3, M.D., Ph.D. 1 Department

More information

e-scider: A tool to retrieve, prioritize and analyze the articles from PubMed database Sujit R. Tangadpalliwar 1, Rakesh Nimbalkar 2, Prabha Garg* 3

e-scider: A tool to retrieve, prioritize and analyze the articles from PubMed database Sujit R. Tangadpalliwar 1, Rakesh Nimbalkar 2, Prabha Garg* 3 e-scider: A tool to retrieve, prioritize and analyze the articles from PubMed database Sujit R. Tangadpalliwar 1, Rakesh Nimbalkar 2, Prabha Garg* 3 1 National Institute of Pharmaceutical Education and

More information

Supporting Discovery in Medicine by Association Rule Mining in Medline and UMLS

Supporting Discovery in Medicine by Association Rule Mining in Medline and UMLS Supporting Discovery in Medicine by Association Rule Mining in Medline and UMLS Dimitar Hristovski a, Janez Stare a, Borut Peterlin b, Saso Dzeroski c a IBMI, Medical Faculty, University of Ljubljana,

More information

Multimodal Information Spaces for Content-based Image Retrieval

Multimodal Information Spaces for Content-based Image Retrieval Research Proposal Multimodal Information Spaces for Content-based Image Retrieval Abstract Currently, image retrieval by content is a research problem of great interest in academia and the industry, due

More information

Natural Language Processing Pipelines to Annotate BioC Collections with an Application to the NCBI Disease Corpus

Natural Language Processing Pipelines to Annotate BioC Collections with an Application to the NCBI Disease Corpus Natural Language Processing Pipelines to Annotate BioC Collections with an Application to the NCBI Disease Corpus Donald C. Comeau *, Haibin Liu, Rezarta Islamaj Doğan and W. John Wilbur National Center

More information

Powering Knowledge Discovery. Insights from big data with Linguamatics I2E

Powering Knowledge Discovery. Insights from big data with Linguamatics I2E Powering Knowledge Discovery Insights from big data with Linguamatics I2E Gain actionable insights from unstructured data The world now generates an overwhelming amount of data, most of it written in natural

More information

A Rough Set Approach for Generation and Validation of Rules for Missing Attribute Values of a Data Set

A Rough Set Approach for Generation and Validation of Rules for Missing Attribute Values of a Data Set A Rough Set Approach for Generation and Validation of Rules for Missing Attribute Values of a Data Set Renu Vashist School of Computer Science and Engineering Shri Mata Vaishno Devi University, Katra,

More information

Text mining tools for semantically enriching the scientific literature

Text mining tools for semantically enriching the scientific literature Text mining tools for semantically enriching the scientific literature Sophia Ananiadou Director National Centre for Text Mining School of Computer Science University of Manchester Need for enriching the

More information

Developing A Semantic Web-based Framework for Executing the Clinical Quality Language Using FHIR

Developing A Semantic Web-based Framework for Executing the Clinical Quality Language Using FHIR Developing A Semantic Web-based Framework for Executing the Clinical Quality Language Using FHIR Guoqian Jiang 1, Eric Prud Hommeax 2, and Harold R. Solbrig 1 1 Mayo Clinic, Rochester, MN, 55905, USA 2

More information

Projects Tools BLAH proposal Conclusion. OntoGene/BioMeXT

Projects Tools BLAH proposal Conclusion. OntoGene/BioMeXT OntoGene/BioMeXT The Bio Term Hub and OGER Lenz Furrer, Nico Colic, Fabio Rinaldi University of Zurich and Swiss Institute of Bioinformatics January 10, 2018 Outline Projects Tools BLAH proposal Conclusion

More information

Prof. Ahmet Süerdem Istanbul Bilgi University London School of Economics

Prof. Ahmet Süerdem Istanbul Bilgi University London School of Economics Prof. Ahmet Süerdem Istanbul Bilgi University London School of Economics Media Intelligence Business intelligence (BI) Uses data mining techniques and tools for the transformation of raw data into meaningful

More information

Dr. SubraMANI Paramasivam. Think & Work like a Data Scientist with SQL 2016 & R

Dr. SubraMANI Paramasivam. Think & Work like a Data Scientist with SQL 2016 & R Dr. SubraMANI Paramasivam Think & Work like a Data Scientist with SQL 2016 & R About the Speaker Group Leader Dr. SubraMANI Paramasivam PhD., MVP, MCT, MCSE (x2), MCITP (x2), MCP, MCTS (x3), MCSA CEO,

More information

SELF-SERVICE SEMANTIC DATA FEDERATION

SELF-SERVICE SEMANTIC DATA FEDERATION SELF-SERVICE SEMANTIC DATA FEDERATION WE LL MAKE YOU A DATA SCIENTIST Contact: IPSNP Computing Inc. Chris Baker, CEO Chris.Baker@ipsnp.com (506) 721 8241 BIG VISION: SELF-SERVICE DATA FEDERATION Biomedical

More information

TERM BASED WEIGHT MEASURE FOR INFORMATION FILTERING IN SEARCH ENGINES

TERM BASED WEIGHT MEASURE FOR INFORMATION FILTERING IN SEARCH ENGINES TERM BASED WEIGHT MEASURE FOR INFORMATION FILTERING IN SEARCH ENGINES Mu. Annalakshmi Research Scholar, Department of Computer Science, Alagappa University, Karaikudi. annalakshmi_mu@yahoo.co.in Dr. A.

More information

A Semantic Multi-Field Clinical Search for Patient Medical Records

A Semantic Multi-Field Clinical Search for Patient Medical Records BULGARIAN ACADEMY OF SCIENCES CYBERNETICS AND INFORMATION TECHNOLOGIES Volume 18, No 1 Sofia 2018 Print ISSN: 1311-9702; Online ISSN: 1314-4081 DOI: 10.2478/cait-2018-0014 A Semantic Multi-Field Clinical

More information

Improving Interoperability of Text Mining Tools with BioC

Improving Interoperability of Text Mining Tools with BioC Improving Interoperability of Text Mining Tools with BioC Ritu Khare, Chih-Hsuan Wei, Yuqing Mao, Robert Leaman, Zhiyong Lu * National Center for Biotechnology Information, 8600 Rockville Pike, Bethesda,

More information

Maximizing the Value of STM Content through Semantic Enrichment. Frank Stumpf December 1, 2009

Maximizing the Value of STM Content through Semantic Enrichment. Frank Stumpf December 1, 2009 Maximizing the Value of STM Content through Semantic Enrichment Frank Stumpf December 1, 2009 What is Semantics and Semantic Processing? Content Knowledge Framework Technology Framework Search Text Images

More information

Welcome to the Louis Calder Memorial Library NW 10 Ave., Miami, FL 33136

Welcome to the Louis Calder Memorial Library NW 10 Ave., Miami, FL 33136 Welcome to the Louis Calder Memorial Library 1601 NW 10 Ave., Miami, FL 33136 Calder Library Website http://calder.med.miami.edu Forms Quick links: e-books e-db s e-journals Resource Guides usearch Featured

More information

Ontology and Hyper Graph Based Dashboards in Data Warehousing Systems

Ontology and Hyper Graph Based Dashboards in Data Warehousing Systems Ontology and Hyper Graph Based Dashboards in Data Warehousing Systems Gitanjali.J #1, C Ranichandra #2, Meera Kuriakose #3, Revathi Kuruba #4 # School of Information Technology and Engineering, VIT University

More information

Latest development in image feature representation and extraction

Latest development in image feature representation and extraction International Journal of Advanced Research and Development ISSN: 2455-4030, Impact Factor: RJIF 5.24 www.advancedjournal.com Volume 2; Issue 1; January 2017; Page No. 05-09 Latest development in image

More information

Developing A Semantic Web-based Framework for Executing the Clinical Quality Language Using FHIR

Developing A Semantic Web-based Framework for Executing the Clinical Quality Language Using FHIR Developing A Semantic Web-based Framework for Executing the Clinical Quality Language Using FHIR Guoqian Jiang 1, Eric Prud Hommeaux 2, Guohui Xiao 3, and Harold R. Solbrig 1 1 Mayo Clinic, Rochester,

More information

AAUITEC at ImageCLEF 2015: Compound Figure Separation

AAUITEC at ImageCLEF 2015: Compound Figure Separation AAUITEC at ImageCLEF 2015: Compound Figure Separation Mario Taschwer 1 and Oge Marques 2 1 ITEC, Klagenfurt University (AAU), Austria, mario.taschwer@aau.at 2 Florida Atlantic University (FAU), Boca Raton,

More information

Nancy Baker 1, Thomas Knudsen 2, Antony Williams 2

Nancy Baker 1, Thomas Knudsen 2, Antony Williams 2 SOFTWARE TOOL ARTICLE Abstract Sifter: a comprehensive front-end system to PubMed [version 1; referees: 2 approved] Nancy Baker 1, Thomas Knudsen 2, Antony Williams 2 1Leidos, Research Triangle Park, NC,

More information

A Generalized Method to Solve Text-Based CAPTCHAs

A Generalized Method to Solve Text-Based CAPTCHAs A Generalized Method to Solve Text-Based CAPTCHAs Jason Ma, Bilal Badaoui, Emile Chamoun December 11, 2009 1 Abstract We present work in progress on the automated solving of text-based CAPTCHAs. Our method

More information

In the previous lecture we went over the process of building a search. We identified the major concepts of a topic. We used Boolean to define the

In the previous lecture we went over the process of building a search. We identified the major concepts of a topic. We used Boolean to define the In the previous lecture we went over the process of building a search. We identified the major concepts of a topic. We used Boolean to define the relationships between concepts. And we discussed common

More information

Deduplication of Hospital Data using Genetic Programming

Deduplication of Hospital Data using Genetic Programming Deduplication of Hospital Data using Genetic Programming P. Gujar Department of computer engineering Thakur college of engineering and Technology, Kandiwali, Maharashtra, India Priyanka Desai Department

More information

Text Mining: A Burgeoning technology for knowledge extraction

Text Mining: A Burgeoning technology for knowledge extraction Text Mining: A Burgeoning technology for knowledge extraction 1 Anshika Singh, 2 Dr. Udayan Ghosh 1 HCL Technologies Ltd., Noida, 2 University School of Information &Communication Technology, Dwarka, Delhi.

More information

UML-Based Conceptual Modeling of Pattern-Bases

UML-Based Conceptual Modeling of Pattern-Bases UML-Based Conceptual Modeling of Pattern-Bases Stefano Rizzi DEIS - University of Bologna Viale Risorgimento, 2 40136 Bologna - Italy srizzi@deis.unibo.it Abstract. The concept of pattern, meant as an

More information

A Survey Of Different Text Mining Techniques Varsha C. Pande 1 and Dr. A.S. Khandelwal 2

A Survey Of Different Text Mining Techniques Varsha C. Pande 1 and Dr. A.S. Khandelwal 2 A Survey Of Different Text Mining Techniques Varsha C. Pande 1 and Dr. A.S. Khandelwal 2 1 Department of Electronics & Comp. Sc, RTMNU, Nagpur, India 2 Department of Computer Science, Hislop College, Nagpur,

More information

CIRGDISCO at RepLab2012 Filtering Task: A Two-Pass Approach for Company Name Disambiguation in Tweets

CIRGDISCO at RepLab2012 Filtering Task: A Two-Pass Approach for Company Name Disambiguation in Tweets CIRGDISCO at RepLab2012 Filtering Task: A Two-Pass Approach for Company Name Disambiguation in Tweets Arjumand Younus 1,2, Colm O Riordan 1, and Gabriella Pasi 2 1 Computational Intelligence Research Group,

More information

The National Medical Device Information Sharing & Analysis Organization (MD-ISAO) Initiative Session 2, February 19, 2017 Moderator: Suzanne

The National Medical Device Information Sharing & Analysis Organization (MD-ISAO) Initiative Session 2, February 19, 2017 Moderator: Suzanne The National Medical Device Information Sharing & Analysis Organization (MD-ISAO) Initiative Session 2, February 19, 2017 Moderator: Suzanne Schwartz, Assoc. Dir., CDRH, FDA Denise Anderson, MBA, President,

More information

Text Document Clustering Using DPM with Concept and Feature Analysis

Text Document Clustering Using DPM with Concept and Feature Analysis Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 2, Issue. 10, October 2013,

More information

Dynamic Programming User Manual v1.0 Anton E. Weisstein, Truman State University Aug. 19, 2014

Dynamic Programming User Manual v1.0 Anton E. Weisstein, Truman State University Aug. 19, 2014 Dynamic Programming User Manual v1.0 Anton E. Weisstein, Truman State University Aug. 19, 2014 Dynamic programming is a group of mathematical methods used to sequentially split a complicated problem into

More information

How to Apply Basic Principles of Evidence-

How to Apply Basic Principles of Evidence- CSHP 2015 TOOLKIT FROM PAPER TO PR ACTI CE: INCORPORATING EV IDENCE INTO YOUR PAGE 1 PHARMACY PR ACTICE (O BJECTIVE 3.1) How to Apply Basic Principles of Evidence- Based Practice May 2011 How to Do a Basic

More information

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach

Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Automatic Linguistic Indexing of Pictures by a Statistical Modeling Approach Abstract Automatic linguistic indexing of pictures is an important but highly challenging problem for researchers in content-based

More information

Usability: An Introduction

Usability: An Introduction Usability: An Introduction Joseph Kannry, MD Lead Technical Informaticist Mount Sinai Health System Professor Medicine Icahn School of Medicine at Mount Sinai Defining Usability Usability has been studied

More information

VISO: A Shared, Formal Knowledge Base as a Foundation for Semi-automatic InfoVis Systems

VISO: A Shared, Formal Knowledge Base as a Foundation for Semi-automatic InfoVis Systems VISO: A Shared, Formal Knowledge Base as a Foundation for Semi-automatic InfoVis Systems Jan Polowinski Martin Voigt Technische Universität DresdenTechnische Universität Dresden 01062 Dresden, Germany

More information

Classification and retrieval of biomedical literatures: SNUMedinfo at CLEF QA track BioASQ 2014

Classification and retrieval of biomedical literatures: SNUMedinfo at CLEF QA track BioASQ 2014 Classification and retrieval of biomedical literatures: SNUMedinfo at CLEF QA track BioASQ 2014 Sungbin Choi, Jinwook Choi Medical Informatics Laboratory, Seoul National University, Seoul, Republic of

More information

MAGE-ML: MicroArray Gene Expression Markup Language

MAGE-ML: MicroArray Gene Expression Markup Language MAGE-ML: MicroArray Gene Expression Markup Language Links: - Full MAGE specification: http://cgi.omg.org/cgi-bin/doc?lifesci/01-10-01 - MAGE-ML Document Type Definition (DTD): http://cgi.omg.org/cgibin/doc?lifesci/01-11-02

More information

efip online Help Document

efip online Help Document efip online Help Document University of Delaware Computer and Information Sciences & Center for Bioinformatics and Computational Biology Newark, DE, USA December 2013 K K S I K K Table of Contents INTRODUCTION...

More information

CIS UDEL Working Notes on ImageCLEF 2015: Compound figure detection task

CIS UDEL Working Notes on ImageCLEF 2015: Compound figure detection task CIS UDEL Working Notes on ImageCLEF 2015: Compound figure detection task Xiaolong Wang, Xiangying Jiang, Abhishek Kolagunda, Hagit Shatkay and Chandra Kambhamettu Department of Computer and Information

More information

Functional Modeling with Data Flow Diagrams

Functional Modeling with Data Flow Diagrams Functional Modeling with Data Flow Diagrams Amasi Elbakush 5771668 Teaching Assistant : Daniel Alami Utrecht University 1 Introduction Data Flow Diagrams (DFDs) are a visual representation of the flow

More information

NUS-I2R: Learning a Combined System for Entity Linking

NUS-I2R: Learning a Combined System for Entity Linking NUS-I2R: Learning a Combined System for Entity Linking Wei Zhang Yan Chuan Sim Jian Su Chew Lim Tan School of Computing National University of Singapore {z-wei, tancl} @comp.nus.edu.sg Institute for Infocomm

More information

Recent Developments in FDA s Review of Proprietary Names for Drugs

Recent Developments in FDA s Review of Proprietary Names for Drugs Recent Developments in FDA s Review of Proprietary Names for Drugs Kellie Taylor, PharmD, MPH Deputy Director Office of Medication Error Prevention and Risk Management, CDER Division Director (acting)

More information

A Multiple-stage Approach to Re-ranking Clinical Documents

A Multiple-stage Approach to Re-ranking Clinical Documents A Multiple-stage Approach to Re-ranking Clinical Documents Heung-Seon Oh and Yuchul Jung Information Service Center Korea Institute of Science and Technology Information {ohs, jyc77}@kisti.re.kr Abstract.

More information

A Novel method for Frequent Pattern Mining

A Novel method for Frequent Pattern Mining A Novel method for Frequent Pattern Mining K.Rajeswari #1, Dr.V.Vaithiyanathan *2 # Associate Professor, PCCOE & Ph.D Research Scholar SASTRA University, Tanjore, India 1 raji.pccoe@gmail.com * Associate

More information

Content Based Image Retrieval system with a combination of Rough Set and Support Vector Machine

Content Based Image Retrieval system with a combination of Rough Set and Support Vector Machine Shahabi Lotfabadi, M., Shiratuddin, M.F. and Wong, K.W. (2013) Content Based Image Retrieval system with a combination of rough set and support vector machine. In: 9th Annual International Joint Conferences

More information

Profiling Medical Journal Articles Using a Gene Ontology Semantic Tagger. Mahmoud El-Haj Paul Rayson Scott Piao Jo Knight

Profiling Medical Journal Articles Using a Gene Ontology Semantic Tagger. Mahmoud El-Haj Paul Rayson Scott Piao Jo Knight Profiling Medical Journal Articles Using a Gene Ontology Semantic Tagger Mahmoud El-Haj Paul Rayson Scott Piao Jo Knight Origin and Outcomes Currently funded through a Wellcome Trust Seed award Collaboration

More information

E-Agricultural Services and Business

E-Agricultural Services and Business E-Agricultural Services and Business A Conceptual Framework for Developing a Deep Web Service Nattapon Harnsamut, Naiyana Sahavechaphan nattapon.harnsamut@nectec.or.th, naiyana.sahavechaphan@nectec.or.th

More information

Alternative Tools for Mining The Biomedical Literature

Alternative Tools for Mining The Biomedical Literature Yale University From the SelectedWorks of Rolando Garcia-Milian May 14, 2014 Alternative Tools for Mining The Biomedical Literature Rolando Garcia-Milian, Yale University Available at: https://works.bepress.com/rolando_garciamilian/1/

More information

Knowledge Discovery and Data Mining 1 (VO) ( )

Knowledge Discovery and Data Mining 1 (VO) ( ) Knowledge Discovery and Data Mining 1 (VO) (707.003) Data Matrices and Vector Space Model Denis Helic KTI, TU Graz Nov 6, 2014 Denis Helic (KTI, TU Graz) KDDM1 Nov 6, 2014 1 / 55 Big picture: KDDM Probability

More information

Data Clustering Hierarchical Clustering, Density based clustering Grid based clustering

Data Clustering Hierarchical Clustering, Density based clustering Grid based clustering Data Clustering Hierarchical Clustering, Density based clustering Grid based clustering Team 2 Prof. Anita Wasilewska CSE 634 Data Mining All Sources Used for the Presentation Olson CF. Parallel algorithms

More information

Sheffield University and the TREC 2004 Genomics Track: Query Expansion Using Synonymous Terms

Sheffield University and the TREC 2004 Genomics Track: Query Expansion Using Synonymous Terms Sheffield University and the TREC 2004 Genomics Track: Query Expansion Using Synonymous Terms Yikun Guo, Henk Harkema, Rob Gaizauskas University of Sheffield, UK {guo, harkema, gaizauskas}@dcs.shef.ac.uk

More information

Data Mining. Introduction. Hamid Beigy. Sharif University of Technology. Fall 1395

Data Mining. Introduction. Hamid Beigy. Sharif University of Technology. Fall 1395 Data Mining Introduction Hamid Beigy Sharif University of Technology Fall 1395 Hamid Beigy (Sharif University of Technology) Data Mining Fall 1395 1 / 21 Table of contents 1 Introduction 2 Data mining

More information

What is this Song About?: Identification of Keywords in Bollywood Lyrics

What is this Song About?: Identification of Keywords in Bollywood Lyrics What is this Song About?: Identification of Keywords in Bollywood Lyrics by Drushti Apoorva G, Kritik Mathur, Priyansh Agrawal, Radhika Mamidi in 19th International Conference on Computational Linguistics

More information

Structure in On-line Documents

Structure in On-line Documents Structure in On-line Documents Anil K. Jain and Anoop M. Namboodiri Department of Comp. Sci. and Engg. Michigan State University East Lansing, MI 4884 fjain, anoopg@cse.msu.edu Jayashree Subrahmonia IBM

More information

Optimizing the Deblocking Algorithm for. H.264 Decoder Implementation

Optimizing the Deblocking Algorithm for. H.264 Decoder Implementation Optimizing the Deblocking Algorithm for H.264 Decoder Implementation Ken Kin-Hung Lam Abstract In the emerging H.264 video coding standard, a deblocking/loop filter is required for improving the visual

More information

MEDICAL IMAGE RETRIEVAL BY COMBINING LOW LEVEL FEATURES AND DICOM FEATURES

MEDICAL IMAGE RETRIEVAL BY COMBINING LOW LEVEL FEATURES AND DICOM FEATURES International Conference on Computational Intelligence and Multimedia Applications 2007 MEDICAL IMAGE RETRIEVAL BY COMBINING LOW LEVEL FEATURES AND DICOM FEATURES A. Grace Selvarani a and Dr. S. Annadurai

More information

American International Journal of Research in Science, Technology, Engineering & Mathematics

American International Journal of Research in Science, Technology, Engineering & Mathematics American International Journal of Research in Science, Technology, Engineering & Mathematics Available online at http://www.iasir.net ISSN (Print): 2328-3491, ISSN (Online): 2328-3580, ISSN (CD-ROM): 2328-3629

More information

Chapter 6 Evaluation Metrics and Evaluation

Chapter 6 Evaluation Metrics and Evaluation Chapter 6 Evaluation Metrics and Evaluation The area of evaluation of information retrieval and natural language processing systems is complex. It will only be touched on in this chapter. First the scientific

More information

!"# $ # # $ $ % $ &% $ '"# $ ()&*&)+(( )+(( )

!# $ # # $ $ % $ &% $ '# $ ()&*&)+(( )+(( ) !"# # # % &% '"# ) !#, ' "# " "# -. / # 0 0 0 0 0 "0 "# " # 1 #! " " 0 0 0 0 0 0 2# 0 # # 3 ' 4 56 7-56 87 9# 5 6 7 6 & 0 " : 9 ; 4 " #! 0 - '% # % "# " "# " < 4 "! % " % 4 % % 9# 4 56 87 = 4 > 0 " %!#

More information

An Interactive User Interface for Drug Labeling to Improve Readability and Decision-Making

An Interactive User Interface for Drug Labeling to Improve Readability and Decision-Making An Interactive User Interface for Drug Labeling to Improve Readability and Decision-Making Hamed Abedtash 1, PharmD, Jon D. Duke, MD, MSc 2 1 School of Informatics and Computing, Indiana University, Indianapolis,

More information

Efficient Indexing and Searching Framework for Unstructured Data

Efficient Indexing and Searching Framework for Unstructured Data Efficient Indexing and Searching Framework for Unstructured Data Kyar Nyo Aye, Ni Lar Thein University of Computer Studies, Yangon kyarnyoaye@gmail.com, nilarthein@gmail.com ABSTRACT The proliferation

More information

Genescene: Biomedical Text and Data Mining

Genescene: Biomedical Text and Data Mining Claremont Colleges Scholarship @ Claremont CGU Faculty Publications and Research CGU Faculty Scholarship 5-1-2003 Genescene: Biomedical Text and Data Mining Gondy Leroy Claremont Graduate University Hsinchun

More information

MIRACLE at ImageCLEFmed 2008: Evaluating Strategies for Automatic Topic Expansion

MIRACLE at ImageCLEFmed 2008: Evaluating Strategies for Automatic Topic Expansion MIRACLE at ImageCLEFmed 2008: Evaluating Strategies for Automatic Topic Expansion Sara Lana-Serrano 1,3, Julio Villena-Román 2,3, José C. González-Cristóbal 1,3 1 Universidad Politécnica de Madrid 2 Universidad

More information

Integrated Access to Biological Data. A use case

Integrated Access to Biological Data. A use case Integrated Access to Biological Data. A use case Marta González Fundación ROBOTIKER, Parque Tecnológico Edif 202 48970 Zamudio, Vizcaya Spain marta@robotiker.es Abstract. This use case reflects the research

More information

Qualitative Data Analysis Software. A workshop for staff & students School of Psychology Makerere University

Qualitative Data Analysis Software. A workshop for staff & students School of Psychology Makerere University Qualitative Data Analysis Software A workshop for staff & students School of Psychology Makerere University (PhD) January 27, 2016 Outline for the workshop CAQDAS NVivo Overview Practice 2 CAQDAS Before

More information

Practical Considerations for Exploiting the World Wide Web to Create Infobuttons

Practical Considerations for Exploiting the World Wide Web to Create Infobuttons Practical Considerations for Exploiting the World Wide Web to Create Infobuttons James J. Cimino a, Jianhua Li a, Mureen Allen a, Leanne M. Currie b, Mark Graham a, Viktoria Janetzki a Nam-Ju Lee b, Suzanne

More information

String Vector based KNN for Text Categorization

String Vector based KNN for Text Categorization 458 String Vector based KNN for Text Categorization Taeho Jo Department of Computer and Information Communication Engineering Hongik University Sejong, South Korea tjo018@hongik.ac.kr Abstract This research

More information

Biomedical literature mining for knowledge discovery

Biomedical literature mining for knowledge discovery Biomedical literature mining for knowledge discovery REZARTA ISLAMAJ DOĞAN National Center for Biotechnology Information National Library of Medicine Outline Biomedical Literature Access Challenges in

More information

Data Mining. Introduction. Hamid Beigy. Sharif University of Technology. Fall 1394

Data Mining. Introduction. Hamid Beigy. Sharif University of Technology. Fall 1394 Data Mining Introduction Hamid Beigy Sharif University of Technology Fall 1394 Hamid Beigy (Sharif University of Technology) Data Mining Fall 1394 1 / 20 Table of contents 1 Introduction 2 Data mining

More information

Efficiently Mining Positive Correlation Rules

Efficiently Mining Positive Correlation Rules Applied Mathematics & Information Sciences An International Journal 2011 NSP 5 (2) (2011), 39S-44S Efficiently Mining Positive Correlation Rules Zhongmei Zhou Department of Computer Science & Engineering,

More information

Automatic Image Annotation by Classification Using Mpeg-7 Features

Automatic Image Annotation by Classification Using Mpeg-7 Features International Journal of Scientific and Research Publications, Volume 2, Issue 9, September 2012 1 Automatic Image Annotation by Classification Using Mpeg-7 Features Manjary P.Gangan *, Dr. R. Karthi **

More information

January 16, Re: Request for Comment: Data Access and Data Sharing Policy. Dear Dr. Selby:

January 16, Re: Request for Comment: Data Access and Data Sharing Policy. Dear Dr. Selby: Dr. Joe V. Selby, MD, MPH Executive Director Patient-Centered Outcomes Research Institute 1828 L Street, NW, Suite 900 Washington, DC 20036 Submitted electronically at: http://www.pcori.org/webform/data-access-and-data-sharing-policypublic-comment

More information

EFFICIENT ALGORITHM FOR MINING ON BIO MEDICAL DATA FOR RANKING THE WEB PAGES

EFFICIENT ALGORITHM FOR MINING ON BIO MEDICAL DATA FOR RANKING THE WEB PAGES International Journal of Mechanical Engineering and Technology (IJMET) Volume 8, Issue 8, August 2017, pp. 1424 1429, Article ID: IJMET_08_08_147 Available online at http://www.iaeme.com/ijmet/issues.asp?jtype=ijmet&vtype=8&itype=8

More information

An Approach for Privacy Preserving in Association Rule Mining Using Data Restriction

An Approach for Privacy Preserving in Association Rule Mining Using Data Restriction International Journal of Engineering Science Invention Volume 2 Issue 1 January. 2013 An Approach for Privacy Preserving in Association Rule Mining Using Data Restriction Janakiramaiah Bonam 1, Dr.RamaMohan

More information

International Journal of Computer Science Trends and Technology (IJCST) Volume 3 Issue 3, May-June 2015

International Journal of Computer Science Trends and Technology (IJCST) Volume 3 Issue 3, May-June 2015 RESEARCH ARTICLE OPEN ACCESS A Semantic Link Network Based Search Engine For Multimedia Files Anuj Kumar 1, Ravi Kumar Singh 2, Vikas Kumar 3, Vivek Patel 4, Priyanka Paygude 5 Student B.Tech (I.T) [1].

More information

Data Mining of Web Access Logs Using Classification Techniques

Data Mining of Web Access Logs Using Classification Techniques Data Mining of Web Logs Using Classification Techniques Md. Azam 1, Asst. Prof. Md. Tabrez Nafis 2 1 M.Tech Scholar, Department of Computer Science & Engineering, Al-Falah School of Engineering & Technology,

More information

Attribute Reduction using Forward Selection and Relative Reduct Algorithm

Attribute Reduction using Forward Selection and Relative Reduct Algorithm Attribute Reduction using Forward Selection and Relative Reduct Algorithm P.Kalyani Associate Professor in Computer Science, SNR Sons College, Coimbatore, India. ABSTRACT Attribute reduction of an information

More information

FIGURE 1. The updated PubMed format displays the Features bar as file tabs. A default Review limit is applied to all searches of PubMed. Select Englis

FIGURE 1. The updated PubMed format displays the Features bar as file tabs. A default Review limit is applied to all searches of PubMed. Select Englis CONCISE NEW TOOLS AND REVIEW FEATURES OF FOR PUBMED CLINICIANS Clinicians Guide to New Tools and Features of PubMed DENISE M. DUPRAS, MD, PHD, AND JON O. EBBERT, MD, MSC Practicing clinicians need to have

More information

SK International Journal of Multidisciplinary Research Hub Research Article / Survey Paper / Case Study Published By: SK Publisher

SK International Journal of Multidisciplinary Research Hub Research Article / Survey Paper / Case Study Published By: SK Publisher ISSN: 2394 3122 (Online) Volume 2, Issue 1, January 2015 Research Article / Survey Paper / Case Study Published By: SK Publisher P. Elamathi 1 M.Phil. Full Time Research Scholar Vivekanandha College of

More information

Combining Review Text Content and Reviewer-Item Rating Matrix to Predict Review Rating

Combining Review Text Content and Reviewer-Item Rating Matrix to Predict Review Rating Combining Review Text Content and Reviewer-Item Rating Matrix to Predict Review Rating Dipak J Kakade, Nilesh P Sable Department of Computer Engineering, JSPM S Imperial College of Engg. And Research,

More information

Toward Part-based Document Image Decoding

Toward Part-based Document Image Decoding 2012 10th IAPR International Workshop on Document Analysis Systems Toward Part-based Document Image Decoding Wang Song, Seiichi Uchida Kyushu University, Fukuoka, Japan wangsong@human.ait.kyushu-u.ac.jp,

More information