Text Documents Research Articles

Using natural language processing of clinical text to enhance identification of opioid-related overdoses in electronic health records data.

PurposeTo enhance automated methods for accurately identifying opioid‐related overdoses and classifying types of overdose using electronic health record (EHR) databases.MethodsWe developed a natural language processing (NLP) software application to code clinical text documentation of overdose, including identification of intention for self‐harm, substances involved, substance abuse, and error in medication usage. Using datasets balanced with cases of suspected overdose and records of individuals at elevated risk for overdose, we developed and validated the application using Kaiser Permanente Northwest data, then tested portability of the application using Kaiser Permanente Washington data. Datasets were chart‐reviewed to provide a gold standard for comparison and evaluation of the automated method.ResultsThe method performed well in identifying overdose (sensitivity = 0.80, specificity = 0.93), intentional overdose (sensitivity = 0.81, specificity = 0.98), and involvement of opioids (excluding heroin, sensitivity = 0.72, specificity = 0.96) and heroin (sensitivity = 0.84, specificity = 1.0). The method performed poorly at identifying adverse drug reactions and overdose due to patient error and fairly at identifying substance abuse in opioid‐related unintentional overdose (sensitivity = 0.67, specificity = 0.96). Evaluation using validation datasets yielded significant reductions, in specificity and negative predictive values only, for many classifications mentioned above. However, these measures remained above 0.80, thus, performance observed during development was largely maintained during validation. Similar results were obtained when evaluating portability, although there was a significant reduction in sensitivity for unintentional overdose that was attributed to missing text clinical notes in the database.ConclusionsMethods that process text clinical notes show promise for improving accuracy and fidelity at identifying and classifying overdoses according to type using EHR data.

Southeast Asia-China Economic Interactions in the Late First to Mid-Second Millennium C.E.

This essay provides an overview of the economic interactions between China and Southeast Asia during the late first and early second millennia C.E.. It positions the development of this relationship within the context of the Old World, and looks at how the interactions manifested in the ports that grew as a result of the economic exchanges that took place, the transportation networks that were developed to facilitate the exchanges, the growth in the demand and production of products from both regions, the migration of traders, and the development of economic codependency between both economies. The essay also provided sub-topics and online sources with which this topic could be approached in a classroom, including art materials, archaeological information, and textual documentation.

Variance-based Features for Keyword Extraction in Persian and English Text Documents

This paper address automatic keyword extraction in Persian and English text documents. Generally, for keyword extraction in a text, a weight is assigned to each token and words having higher weights are selected as the keywords. We have proposed four methods for weighting the words and have compared these methods with five previous weighting techniques. The previous methods used in this paper are term frequency (TF), term frequency inverse document frequency (TF-IDF), variance, discriminative feature selection (DFS), and document length normalization based on unit words (LNU). The proposed weighting methods are based on using variance features and include variance to TF-IDF ratio, variance to TF ratio, the intersection of TF and variance, and the intersection of variance and IDF. For evaluation, the documents are clustered using the extracted keywords as feature vectors, and K-means, expectation maximization (EM), and Ward hierarchical clustering methods. The entropy of the clusters and pre-defined classes of the documents are used as the evaluation metric. For the evaluations, we have collected and labelled Persian documents. Results show that our proposed weighting method, variance to TF ratio, has the best performance for Persian. Also, the best entropy is resulted by variance to TD-IDF ratio for English.

Retrieving Arabic Textual Documents Based on Queries Written in Bahraini Slang Language

Nowadays, the most used language is the colloquial language not the classical language. It is widely used in many nations. The kingdom of Bahrain had the largest share in the spread of the colloquial language, which becomes the trader's language and the language of the social communication too. It became so popular that its usage starts dominating the daily conversations. In this research, we will create algorithm to enhance the process of information retrieval in Arabic slang language of the Gulf. In this algorithm, we put some special Bahraini rules to convert queries from Slang Bahraini to a classical language. In addition, we will apply this algorithm on the Bahraini colloquial language. After making an evaluation for the system relying on the results of three main aspects recall, precision, and F-measure, we noticed that the results of precision about 0.64 for both researches slang and classical, which gives a great indication that the system supports searching in Bahraini slang language. The purpose of this research is to improve the Information Retrieval system field. In addition, it will save the time and the effort of the researchers of the Bahraini colloquial language.

Clustering Based Approach for Novelty Detection in Text Documents

As the information is overloaded over the internet accessing of information from the internet according to a given query provides redundant and irrelevant information. It is necessary to retrieve relevant and novel information from a given query by the user. With the result of this the user will require minimum effort to access the information need. In this work we proposed a clustering based approach for novelty detection which will provide the relevant and novel documents for the information need. Based on the user query the incoming stream of documents will be clustered using k-means algorithm. Then the cluster heads are selected from the various clusters with the minimum distance. These cluster heads are the novel documents from a collection of documents from different clusters having the large distance. The proposed technique can be further used in the field of information retrieval.

Implementing mandatory early warning scoring impacts nurses' practice of documenting free text notes.

To evaluate whether implementing the Modified Early Warning Scoring system impacts nurses' free text notes related to Airway, Breathing, Circulation and Pain in general ward medical and surgical patients. The quality of nursing documentation in patient health records is important to secure patient safety, but faces multiple challenges whether being paper-based or electronic. Nurses' ability to draw a complete picture of the patient situation is thereby compromised. Structured use of the Modified Early Warning Score, found to reduce unexpected death, might affect nurses' free text documentation of clinical observations. A prospective, pre- and postinterventional, nonrandomised study adhering to the EQUATOR guideline TREND. Data on nurses' free text notes were obtained in 1,497 patient records during one preinterventional (March-June 2009) and two postinterventional study periods (September-December 2010 and March-June 2011) in a Danish university hospital. Data were organised by the Airway, Breathing and Circulation principles and by nurses' working shifts in the 56hr surrounding the first recording of deviating vital parameters or a Modified Early Warning Score≥2. Preinterventional free text notes were compared with notes from the two postinterventional periods, respectively. In the 8-hr working shift where deviations in vital parameters were recorded for the first time, nurses' free text notes related to patients' breathing (B) increased significantly, comparing 2009 with 2010 and 2011, respectively. In the 24hr following initial deviations in vital parameters, a significant increase in free text notes was identified concerning Airway, Breathing and Circulation-related symptoms or problems. Mandatory use of the Modified Early Warning Score and related implementation activities significantly impacts nursing documentation of free text notes. Nurses' practice of communicating observed clinical symptoms by documenting free text notes should be supported through measures to enhance situation awareness.

CNN-Bidirectional LSTM Based Optical Character Recognition of Sanskrit Manuscripts : A Comprehensive Systematic Literature Review

Optical character recognition (OCR) is a technology that allows you to convert different types of documents or images into searchable, editable, and analyzable data. The current work on Sanskrit Character Recognition from Images of Text Documents is one of the most difficult due to similarities in the forms of unique letters, script complexity, non-forte in the representation, and a vast number of symbols. The Devanagari script is used to write the Sanskrit language. There are a variety of approaches for recognizing characters in a scanned image. The present research initiatives highlight the importance and needs of efforts in recognition of printed and handwritten documents written in Sanskrit language. This paper is aims at reviewing the state of various scripts in use including those from medieval to present era and explores the prospective of digital recognition of printed texts and thereby pointing towards futuristic trends in developing restoration software for Sanskrit scripts. Challenge is due to the number of languages and their diverse scripts. The scarcity of digitized linguistic resources makes the task a tougher one. The paper also highlights on the characteristics and challenges of recognition of scripts of Sanskrit origin. Largely the digital recognition is limited to simple numerals and isolated characters. In addition, this review article serves the purpose an optical character recognition (OCR) system that enables to analyse the word recognition and translate various types of Sanskrit documents or images into text using deep learning architectures which include Convolutional Neural Network (CNN) and Bidirectional long-short term memory (Bidirectional LSTM).

A Similarity Function for Feature Pattern Clustering and High Dimensional Text Document Classification

Text document classification and clustering is an important learning task which fits to both data mining and machine learning areas. The learning task throws several challenges when it is required to process high dimensional text documents. Word distribution in text documents plays a very key role in learning process. Research related to high dimensional text document classification and clustering is usually limited to application of traditional distance functions and most of the research contributions in the existing literature did not consider the word distribution in documents. In this research, we propose a novel similarity function for feature pattern clustering and high dimensional text classification. The similarity function proposed is used to carry supervised learning based dimensionality reduction. The important feature of this work is that the word distribution before and after dimensionality reduction is the same. Experiment results prove the proposed approach achieves dimensionality reduction, retains the word distribution and obtained better classification accuracies compared to other measures.

Mining Sequential Pattern of Data in Textual Document Using Data Mining Classification Technique

Text document were transmitted over the internet for the text communication. So they were occurred many problems like repeated text occurred because of same data were provided in the internet. To characterize and extracting that is a most critical task for the researchers. Many researchers were characterized and applied in many fields like real-life scenarios, such as real-time monitoring on abnormal user behaviors, etc. In this case to detect and characterize the personalized behavior of the user were provide some drawbacks. To solve this problem, this paper analyzing the sequential data and characterize the user behavior with the help of the data mining sequential pattern matching algorithm.

Text Document Classification: An Approach Based on Indexing

Text Document Classification: An Approach Based on Indexing

Artistic features and typology of subject motifs and objects on the matsevahs of Eastern Galicia XVI - the first third of XX century

An important artistic element or symbolic text of ancient Jewish cemeteries are the tombstones - matsevi. The most commonly used motifs in decorative decoration of Galician matsevahs are zoomorphic, ornithological and vegetative motifs, which are often used in all other forms of Jewish art. The image of subject motifs and larger objects is just as original as the decorative adornment of facades of matsevahs of Eastern Galicia XVI - the first third of the XX century. and deserves a separate thorough study. The presentation of these motifs on the matsevahs' facades gives the viewer enough visual information about a particular person, even without translating and deciphering the very text of the epitaph, which, in the vast majority of cases, correlates and significantly supplements, interprets, informs, extends and clarifies the symbols of the carving of the upper part of the matsevahs. Sometimes the symbolic image was unrelated to the text, it was only decorative and contained traditional Jewish characters or symbols. One should note the desire of the authors, stone-cutters, for originality, artistic individuality, recognition of a particular object as a characteristic feature, of the use of substantive motifs for the decoration of the matsevahs, as well as the significant impact of family traditions with the provision of a peculiar author's decision to build a composition or property of the client with appropriate simplification or the complication of the carved decoration and the refinement of the composition. Very few monuments of stone-making art of the 16th-17th centuries have remained intact until now, which makes it impossible to give a full description of the artistic peculiarities of the memorial plastics; and, the vast majority of the preserved monuments were erected over burials at the end of the 18th and 19th centuries. and preserved until the first third of the XX century. The article is based on materials of field studies by the author of ancient Jewish cemeteries within Lviv, Ternopil, Ivano-Frankivsk regions, in particular: Belza, Brody, Bolechova, Burshtyn, Busk, Dobromil, Drohobych, Zabolotova, Kosova, Kremenets, Kutov, Nikolaev, Leshnava, Stary Razdol, Skole, Snyatin, Solotvyn, Stanislavchik, Old Sambir, Ternopil, Turks, Shchyrets, Yabluniv, Yazlivets and others. In the article, individual examples of carved decor are studied, the features of compositional techniques and the specifics of their artistic and plastic expression on the facades of ancient matsevahs of the studied region are analyzed and described. Subject motifs like zoomorphic, ornithomorphic, and vegetative, formed on the basis of the texts of the Torah and the Talmud, biblical metaphors and allegories, which became the symbols of the Twelve tribes of Israel, the people and the land of Israel in the traditional Jewish art of Eastern Galicia from the XVIII - the first third of the XX century. are the dominant motives in stone carving and the matsevah's memorial plastics. The article deals with the most common substantive motifs found on preserved matsevahs of Eastern Galicia of the period under consideration. To systematize and describe the subject motifs are presented in alphabetical order in the following sequence: Building. Vase. Zban (jug) and tray (bowl) for washing hands of levites. Tools, objects and technical equipment. Interior. Chalice. Klepsidra. Book. Ship. Crown. Well. Lamp. Menorah. Subjects and objects of the second plan: Candle holder, candle, platform for Tora, Decalogue tablets. Treasure chest. Arrow. Urn. Cabinet. Poison. Further field investigations and thorough scientific research in accordance with the methodology of scientific study of Jewish cemeteries, which includes: architectural measurements, photo fixation, graphic documentation, writing, reading, decoding and elaboration of texts of epitaphs and documentation of information will help to discover, understand and popularize the traditional art of numerous Jewish communities, which were an integral part of the polyethnic Galician city of the studied period. After all, most of the monuments of stone masonry art are in an extremely poor condition, some of them are on the verge of extinction and require a number of urgent professional measures for their further preservation and research

Aplicações da arqueometria no mobiliário de São Paulo do século XVIII: análises indiciárias e contextualização histórica

RESUMO Neste artigo, são apresentados os resultados dos exames arqueométricos de Física aplicada sobre duas peças de mobiliário do acervo do Museu Paulista, uma arca-cofre e uma cadeira de couro de sola feitas por volta do século XVIII. As técnicas de análise utilizadas foram o ED-XRF e o imageamento com fluorescência de luz ultravioleta. As análises interdisciplinares tiveram por objetivo identificar os materiais com os quais as peças foram compostas, evidenciando informações históricas sobre a produção moveleira na cidade de São Paulo no século XVIII e princípios do XIX. Os resultados obtidos permitiram identificar parte dos materiais usados na pintura da arca-cofre, como o branco de chumbo e o vermelhão (ou Cinabre), no couro curtido da cadeira e nas partes metálicas de ferro e latão de ambas as peças, ainda que outros procedimentos ainda necessitem ser aplicados para a obtenção de resultados sobre outros materiais. As informações obtidas com as fontes materiais foram confrontadas com dados de documentação textual mais abrangente, como listas de compras de tintas, relatos de viagem e manuais artísticos da época, de maneira a permitir a contextualização da vida material e econômica da cidade, revelando sua dinamicidade e as intrincadas redes comerciais em que estava imbricada.

Ensemble-based method of answers retrieval for domain specific questions from text-based documentation

Many companies want or prefer to use chatbot systems to provide smart assistants for accompanying human specialists especially newbies with automatic consulting. Implementation of a really useful smart assistant for a specific domain requires a knowledge base for this domain, that often exists only in the form of text documentation and manuals.Lacks of properly built datasets and often expensiveness in resources and time to build one from scratch to apply data-driven methods with high quality. It motivates to seek a solution that can work without such data or require only a small amount of it though having reduced quality.The reformulation of the task into an information retrieval problem where the assistant responds with a piece of documentation instead of generated sentences may make the task easier but doesn’t solve the whole problem. It allows using of metrics-based methods with reduced search quality or data-driven methods which also needs a great amount of data.In this paper, we propose a new ensemble-based data-driven method that tries to learn a scoring function by combining independent functions from a predefined set. The method may substantially improve the quality of the search in comparison with pure metrics-based methods while requiring significantly less data for training than data-driven methods.

Text Document Classification by using WordNet Ontology and Neural Network

Text Document Classification by using WordNet Ontology and Neural Network

Isabelle/jEdit as IDE for Domain-specific Formal Languages and Informal Text Documents

Isabelle/jEdit is the main application of the Prover IDE (PIDE) framework and the default user-interface of Isabelle, but it is not limited to theorem proving. This paper explores possibilities to use it as a general IDE for formal languages that are defined in user-space, and embedded into informal text documents. It covers overall document structure with auxiliary files and document antiquotations, formal text delimiters and markers for interpretation (via control symbols). The ultimate question behind this: How far can we stretch a plain text editor like jEdit in order to support semantic text processing, with support by the underlying PIDE framework?

FRBR: Application of the Model to Textual Documents

The FRBR (Functional Requirements for Bibliographic Records) model was a revolutionary development that presented a new view of the bibliographic universe. Although FRBR has been widely accepted and extensively studied, actual implementations have been limited. This can be partly attributed to: (1) the vague and controversial definitions of the group 1 entities—work, expression, manifestation, and item, (2) that various types of information resources pose different issues, and (3) the rapid digitization of information. The various definitions of information resources are identified and reviewed here. To simplify the modeling, this study is limited to a single type of information resource: textual documents consisting of a sequence of words that may include non-textual material in the form of tables, symbols, equations, and/or illustrations. The FRBR model is analyzed in the context of textual documents with particular emphasis on digital documents to better understand the group 1 entities. An overview of the problematic aspects of the FRBR model is discussed and possible solutions are proposed.

The Administration of Storage in Early Babylonia

This article examines the epigraphic sources from the late third millennium BC from the city of Ur in southern Mesopotamia in order to reconstruct the organization of the city’s centrally controlled storehouse e2-kisib3-ba, and to analyze the in- and outflow of products and commodities in this facility. It is argued that a better understanding of the administrative context of this institution as it is reflected in the textual documentation can help us reconstruct in more concrete terms the overall structure of the higher levels of the so called household economy of the third millennium Sumerian city-states.

An Improved K-Lion Optimization Algorithm With Feature Selection Methods for Text Document Cluster

International Journal of Computer Sciences and Engineering (A UGC Approved and indexed with DOI, ICI and Approved, DPI Digital Library) is one of the leading and growing open access, peer-reviewed, monthly, and scientific research journal for scientists, engineers, research scholars, and academicians, which gains a foothold in Asia and opens to the world, aims to publish original, theoretical and practical advances in Computer Science,Information Technology, Engineering (Software, Mechanical, Civil, Electronics & Electrical), and all interdisciplinary streams of Computing Sciences. It intends to disseminate original, scientific, theoretical or applied research in the field of Computer Sciences and allied fields. It provides a platform for publishing results and research with a strong empirical component. It aims to bridge the significant gap between research and practice by promoting the publication of original, novel, industry-relevant research.

Morbidity and Mortality Conferences in the Gastrointestinal Department and Endoscopist Behaviors: Timeless Tradition or Effective Tool for Change?

There are limited data on how morbidity and mortality (M+M) conferences impact physician behaviors. These conferences are present at all major teaching hospitals, however, it is unclear what impact they have on physician behavior. At a tertiary care center, a patient underwent 2 esophagogastroduodenoscopies (EGDs) and high-resolution manometry for dysphagia and voice hoarseness. A third EGD revealed a mass in the hypopharynx that had been missed on the previous 2 EGDs. The mass was resected and found to be a poorly differentiated squamous cell carcinoma. This case was presented at the gastrointestinal department M+M/quality improvement conference as an opportunity to discuss the role of EGD in diagnosing hypopharyngeal pathology. After the conference, physician endoscopic behaviors were tracked and compared to historical controls to see if the conference changed the way they performed/documented EGDs. All EGDs performed in the month after the M+M presentation were reviewed for text or image documentation of a hypopharynx examination. Data from the same month but 1-year prior were used as a historical control. After the initial month, the electronic medical record (EMR) was updated to include a text prompt for hypopharynx documentation. Data were collected in the subsequent month and compared to the historical control. Data were divided based on attendance at the initial M+M conference with the primary outcome of hypopharynx documentation compared between attendees of the conferences and those who did not attend. There was a significant increase in hypopharynx documentation after M+M conference and EMR update compared to historical control (Table 1). No significant difference in documentation rate between post-M+M and post-EMR update. No aspiration events were noted in any EGDs where hypopharynx documentation occurred. Four cases (of 564 EGDs) of hypopharyngeal pathology were identified. Attending participation at M+M conference was associated with a significant increase in hypopharynx documentation in June 2017 and August 2017 data (Table 2). The addition of the EMR prompt did not significantly increase rate of documentation in cases where no provider attended the M+M conference. After the presentation of a missed hypopharynx cancer at an M+M conference, providers adjusted their endoscopic and documentation behaviors to note the appearance of the hypopharynx more often. The addition of the EMR prompt in the following month did not significantly increase the overall documentation rate or the rate in procedures where no provider attended the M+M conference. It is possible that the EMR prompt helped with retention of the behavior change. Further data will be collected to determine long-term retention and overall rate of hypopharynx pathology seen on EGD to determine whether routine examination of the hypopharynx should be performed during upper endoscopy.Table 1Hypopharynx Documentation During Upper EndoscopyData set% of any mentionEGDs, nAny mention of hypopharynx, nOnly photo of hypopharynx, nOnly text mention of hypopharynx, nBoth text and photo, nCases with pathology found in the hypopharynx, nP valueJune 20168.23763128210NAJune 2017 (month after M+M)3230698813143<.0001August 2017 (month after EMR update; 2 mo after M+M)36.4258943120431<.0001 compared to June 2016; .2723 compared to June 2017NA, not available. Open table in a new tab Table 2August 2017 SubgroupsAugust 2017 subgroups% of EGDs with hypopharynx documentationTotal number of EGDs performedAny form of hypopharynx documentation, nOnly text documentation of hypopharynx exam, nBoth picture and text documentation, nP valuesAttending physician attended M+M conference44.1145641726.0036Attending physician did not attend M+M conference26.511330317—Either attending or fellow attended M+M conference48.3172831840<.0001 comparing either attending/fellow with neither attending/fellow; .0331 comparing both attending/fellow attending M+M to neither attending.Neither attending or fellow attended M+M conference12.8861123Both attending and fellow attended M+M conference70.4271909 Open table in a new tab

Automatic Text Document Summarization Using Graph Based Centrality Measures on Lexical Network

This article proposes a new concept of Lexical Network for Automatic Text Document Summarization. Instead of a number of chains, the authors are getting a network of sentences which is called as Lexical Network termed as LexNetwork. This network is created between sentences based on different lexical and semantic relations. In this network, a node is representing sentences and edges are representing strength between two sentences. Strength means the number of relations present between the two sentences. The importance of the sentences is decided based on different centrality measures and extracted for the summary. WSD is done with Simple Lesk technique, and Cosine-Similarity threshold (Ɵ, TH) is used as post processing task. In this article, the authors are suggesting that a Cosine similarity threshold 10% is better vs. 5%, and an Eigen-Value based centrality measure is better for summarization process. At last for comparison, they are using Semantrica-Lexalytics System.