scholarly journals Ontological Organization and Bioinformatic Analysis of Adverse Drug Reactions From Package Inserts: Development and Usability Study (Preprint)

2020 ◽  
Author(s):  
Xiaoying Li ◽  
Xin Lin ◽  
Huiling Ren ◽  
Jinjing Guo
Keyword(s):  
Language Processing ◽  
Adverse Reactions ◽  
Package Insert ◽  
Bioinformatic Analysis ◽  
Two Dimensions ◽  
Semantic Relations ◽  
Semantic Retrieval ◽  
Formal Representation ◽  
Package Inserts ◽  
Drug Databases

BACKGROUND Licensed drugs may cause unexpected adverse reactions in patients, resulting in morbidity, risk of mortality, therapy disruptions, and prolonged hospital stays. Officially approved drug package inserts list the adverse reactions identified from randomized controlled clinical trials with high evidence levels and worldwide postmarketing surveillance. Formal representation of the adverse drug reaction (ADR) enclosed in semistructured package inserts will enable deep recognition of side effects and rational drug use, substantially reduce morbidity, and decrease societal costs. OBJECTIVE This paper aims to present an ontological organization of traceable ADR information extracted from licensed package inserts. In addition, it will provide machine-understandable knowledge for bioinformatics analysis, semantic retrieval, and intelligent clinical applications. METHODS Based on the essential content of package inserts, a generic ADR ontology model is proposed from two dimensions (and nine subdimensions), covering the ADR information and medication instructions. This is followed by a customized natural language processing method programmed with Python to retrieve the relevant information enclosed in package inserts. After the biocuration and identification of retrieved data from the package insert, an ADR ontology is automatically built for further bioinformatic analysis. RESULTS We collected 165 package inserts of quinolone drugs from the National Medical Products Administration and other drug databases in China, and built a specialized ADR ontology containing 2879 classes and 15,711 semantic relations. For each quinolone drug, the reported ADR information and medication instructions have been logically represented and formally organized in an ADR ontology. To demonstrate its usage, the source data were further bioinformatically analyzed. For example, the number of drug-ADR triples and major ADRs associated with each active ingredient were recorded. The 10 ADRs most frequently observed among quinolones were identified and categorized based on the 18 categories defined in the proposal. The occurrence frequency, severity, and ADR mitigation method explicitly stated in package inserts were also analyzed, as well as the top 5 specific populations with contraindications for quinolone drugs. CONCLUSIONS Ontological representation and organization using officially approved information from drug package inserts enables the identification and bioinformatic analysis of adverse reactions caused by a specific drug with regard to predefined ADR ontology classes and semantic relations. The resulting ontology-based ADR knowledge source classifies drug-specific adverse reactions, and supports a better understanding of ADRs and safer prescription of medications.

scholarly journals Ontological Organization and Bioinformatic Analysis of Adverse Drug Reactions From Package Inserts: Development and Usability Study

10.2196/20443 ◽  
2020 ◽  
Vol 22 (7) ◽  
pp. e20443
Author(s):  
Xiaoying Li ◽  
Xin Lin ◽  
Huiling Ren ◽  
Jinjing Guo
Keyword(s):  
Language Processing ◽  
Adverse Reactions ◽  
Package Insert ◽  
Bioinformatic Analysis ◽  
Two Dimensions ◽  
Semantic Relations ◽  
Semantic Retrieval ◽  
Formal Representation ◽  
Package Inserts ◽  
Drug Databases

Background Licensed drugs may cause unexpected adverse reactions in patients, resulting in morbidity, risk of mortality, therapy disruptions, and prolonged hospital stays. Officially approved drug package inserts list the adverse reactions identified from randomized controlled clinical trials with high evidence levels and worldwide postmarketing surveillance. Formal representation of the adverse drug reaction (ADR) enclosed in semistructured package inserts will enable deep recognition of side effects and rational drug use, substantially reduce morbidity, and decrease societal costs. Objective This paper aims to present an ontological organization of traceable ADR information extracted from licensed package inserts. In addition, it will provide machine-understandable knowledge for bioinformatics analysis, semantic retrieval, and intelligent clinical applications. Methods Based on the essential content of package inserts, a generic ADR ontology model is proposed from two dimensions (and nine subdimensions), covering the ADR information and medication instructions. This is followed by a customized natural language processing method programmed with Python to retrieve the relevant information enclosed in package inserts. After the biocuration and identification of retrieved data from the package insert, an ADR ontology is automatically built for further bioinformatic analysis. Results We collected 165 package inserts of quinolone drugs from the National Medical Products Administration and other drug databases in China, and built a specialized ADR ontology containing 2879 classes and 15,711 semantic relations. For each quinolone drug, the reported ADR information and medication instructions have been logically represented and formally organized in an ADR ontology. To demonstrate its usage, the source data were further bioinformatically analyzed. For example, the number of drug-ADR triples and major ADRs associated with each active ingredient were recorded. The 10 ADRs most frequently observed among quinolones were identified and categorized based on the 18 categories defined in the proposal. The occurrence frequency, severity, and ADR mitigation method explicitly stated in package inserts were also analyzed, as well as the top 5 specific populations with contraindications for quinolone drugs. Conclusions Ontological representation and organization using officially approved information from drug package inserts enables the identification and bioinformatic analysis of adverse reactions caused by a specific drug with regard to predefined ADR ontology classes and semantic relations. The resulting ontology-based ADR knowledge source classifies drug-specific adverse reactions, and supports a better understanding of ADRs and safer prescription of medications.

"THERAPEUTIC ORPHANS" AND THE PACKAGE INSERT

PEDIATRICS ◽  
1970 ◽  
Vol 46 (5) ◽  
pp. 811-813
Author(s):  
Keyword(s):  
Chemical Structure ◽  
Adverse Reactions ◽  
Package Insert ◽  
Drug Manufacturer ◽  
Full Disclosure ◽  
Package Inserts ◽  
Federal Food ◽  
The Status ◽  
Definition Of ◽  
Official Information

In the practice of pediatrics, drugs which are not approved by the Food and Drug Administration (FDA)* as safe and effective in children are prescribed daily. This is due in part to the fact that many drugs released since 1962 carry an "orphaning clause" in the package insert such as, "not to be used in children, since clinical studies have been insufficient to establish recommendations for its use." What is the status of the package insert? Is it a legal directive to the physician, or is it intended as a guide for the physician in prescribing a drug? The package insert, by legal definition of the Federal Food, Drug and Cosmetic Law, is the official information piece for a drug. The information it contains is derived from data supplied by investigators and submitted by the pharmaceutical firm to the FDA. The insert is written and printed by the drug manufacturer, but its contents must be approved by the FDA. The Food, Drug and Cosmetic Law, as amended in 1962, requires full disclosure of all known facts pertaining to the use of the drug. Therefore, a great deal of information is included in the insert, including the chemical structure of the drug, a summary of its pharmacological and toxicological action, its clinical indications and contraindications, precautions, reported adverse reactions, dosage recommendations, and available dosage forms. Many drugs have package inserts approved by the FDA before the Drug Amendments of 1962 when manufacturers were required to show the safety but not the effectiveness of their products.

Fast Neural Network Engine for Natural Science Language Processing: A Drug-Search Case.

2020 ◽  
Author(s):  
Vadim V. Korolev ◽  
Artem Mitrofanov ◽  
Kirill Karpov ◽  
Valery Tkachenko
Keyword(s):  
Neural Network ◽  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Natural Science ◽  
Therapeutic Agent ◽  
Semantic Relations ◽  
Chemical Data ◽  
Processing Methods ◽  
Modern Natural

The main advantage of modern natural language processing methods is a possibility to turn an amorphous human-readable task into a strict mathematic form. That allows to extract chemical data and insights from articles and to find new semantic relations. We propose a universal engine for processing chemical and biological texts. We successfully tested it on various use-cases and applied to a case of searching a therapeutic agent for a COVID-19 disease by analyzing PubMed archive.

Interaction between Traditional Chinese Medicine and Anticoagulant/Antiplatelet Drugs

2019 ◽  
Vol 20 (9) ◽  
pp. 701-713 ◽  
Author(s):  
Jiajia Li ◽  
Qing Liang ◽  
GuangChun Sun
Keyword(s):  
Chinese Medicine ◽  
Traditional Chinese Medicine ◽  
Drug Interactions ◽  
Adverse Reactions ◽  
Bleeding Risk ◽  
Antiplatelet Drugs ◽  
Pharmacokinetic Studies ◽  
Drug Databases ◽  
Concurrent Use ◽  
Anticoagulant Drugs

Background: Traditional Chinese medicine (TCM) has been used for medical purposes since the ancient time and has gradually gained recognition worldwide. Nowadays, patients with thrombus presiding to anticoagulant/ antiplatelet drugs prefer taking TCM. However, an increasing number of studies on herb–drug interactions have been shown. Nevertheless, findings are frequently conflicting and vague. In this review, we discuss the herb–drug interactions between TCM and anticoagulant/antiplatelet drugs to provide guidance on concomitant ingestion with anticoagulant/antiplatelet drugs. Methods: We undertook a structured search of medicine and drug databases for peer-reviewed literature using focused review questions. Results: Danshen, Ginkgo, Ginger, H. Perforatum, SMY and Puerarin injection had directional regulation effects on the efficacy of anticoagulant drugs by altering the CYPs, pharmacokinetic indexs and hemorheological parameters. H. Perforatum inhibited the efficacy of Clopidogrel by enhancing the CYP3A4 activity and Ginkgo increased the efficacy of Ticlopidine. Additionally, Renshen, the formulae except SMY and injections except Puerarin injection could increase or decrease the efficacy of anticoagulant/antiplatelet drugs via regulating the CYPs, platelet aggregation, hemorheological parameters and others. Conclusion: Some cases have reported that TCMs may increase the bleeding risk or has no effect on coagulation when anticoagulant/antiplatelet drugs are concurrently used. However, pharmacokinetic studies have presented either consistent or slightly varying results. So it is difficult to ascertain whether the concurrent use of TCM may increase or reduce the pharmacologic effects of anticoagulant/antiplatelet drugs with adverse reactions. Therefore, herb–drug interactions of TCM and anticoagulant/antiplatelet drugs should be further explored and defined.

scholarly journals Word Embedding for Semantically Relative Words: an Experimental Study

2018 ◽  
Vol 25 (6) ◽  
pp. 726-733
Author(s):  
Maria S. Karyaeva ◽  
Pavel I. Braslavski ◽  
Valery A. Sokolov
Keyword(s):  
Experimental Study ◽  
Natural Language Processing ◽  
Language Processing ◽  
Intelligent Systems ◽  
Russian Language ◽  
Word Embedding ◽  
Semantic Relations ◽  
Automatic Extraction ◽  
Semantic Relationships ◽  
The Russian Language

The ability to identify semantic relations between words has made a word2vec model widely used in NLP tasks. The idea of word2vec is based on a simple rule that a higher similarity can be reached if two words have a similar context. Each word can be represented as a vector, so the closest coordinates of vectors can be interpreted as similar words. It allows to establish semantic relations (synonymy, relations of hypernymy and hyponymy and other semantic relations) by applying an automatic extraction. The extraction of semantic relations by hand is considered as a time-consuming and biased task, requiring a large amount of time and some help of experts. Unfortunately, the word2vec model provides an associative list of words which does not consist of relative words only. In this paper, we show some additional criteria that may be applicable to solve this problem. Observations and experiments with well-known characteristics, such as word frequency, a position in an associative list, might be useful for improving results for the task of extraction of semantic relations for the Russian language by using word embedding. In the experiments, the word2vec model trained on the Flibusta and pairs from Wiktionary are used as examples with semantic relationships. Semantically related words are applicable to thesauri, ontologies and intelligent systems for natural language processing.

scholarly journals Comparison of Templates with Word2vec in Finding Semantic Relations Between Words

2018 ◽  
pp. 13-17
Author(s):  
Kaan Ant ◽  
Ugur Sogukpinar ◽  
Mehmet Fatif Amasyali
Keyword(s):  
Natural Language Processing ◽  
Natural Language ◽  
Language Processing ◽  
Large Scale ◽  
Semantic Relations ◽  
Template Method ◽  
Semantic Relationships ◽  
Semantic Spaces

The use of databases those containing semantic relationships between words is becoming increasingly widespread in order to make natural language processing work more effective. Instead of the word-bag approach, the suggested semantic spaces give the distances between words, but they do not express the relation types. In this study, it is shown how semantic spaces can be used to find the type of relationship and it is compared with the template method. According to the results obtained on a very large scale, while is_a and opposite are more successful for semantic spaces for relations, the approach of templates is more successful in the relation types at_location, made_of and non relational.

scholarly journals Efecto de la Escolarización en la Producción de Relaciones Causales y Contracausales: Evidencia Psicolingüística para el Ámbito Educativo

2016 ◽  
Vol 6 (3) ◽  
pp. 258
Author(s):  
Gabriela Mariel Zunino
Keyword(s):  
Empirical Evidence ◽  
Language Processing ◽  
Formal Education ◽  
Educational Process ◽  
Semantic Relations ◽  
Practical Application ◽  
Discourse Comprehension ◽  
Educational Processes ◽  
Different Characteristics ◽  
Different Levels

In order to promote the practical application of psycholinguistic data in educational fields and expecting that this transfer would enhance the development of both the pedagogical field and the investigation in experimental psycholinguistics, we present two experiments to analyse the production of semantic relations in discourse, especially the causality/countercausality dimension. We found that the pattern of causal advantage is cross-wise and consistent in subjects with different levels of formal education, so it could be a suitable scaffold to develop other aspects of discourse comprehension and production. We compare our results with previous findings about discourse comprehension and interpret the data in the framework of educational processes. To use of empirical evidence about language processing on educational fields allows not only to review specific issues such as the characteristics of teaching materials, but also to improve educational process in a comprehensive way, making possible to adapt different approaches to populations with different characteristics.

scholarly journals Analysis of package inserts of orally administered drugs available in the Indian market

2017 ◽  
Vol 5 (2) ◽  
pp. 529
Author(s):  
Maheshi U. Chhaya
Keyword(s):  
Shelf Life ◽  
Package Insert ◽  
Complete Information ◽  
Indian Market ◽  
Package Inserts ◽  
Source Of Information

Background: The package insert of a medication forms an important source of information to the patient while taking a drug. The package insert is expected to contain complete information regarding the drug aiding the patient to obtain additional knowledge regarding the drug.Methods: 100 package inserts of orally administered drugs were obtained from local chemists and were analysed according to the Sections 6.2 and 6.3 of Schedule D (II), Drugs and Cosmetics Act (1940) and Rules (1945).Results: The posology and contraindications were mentioned in 98% and 96% of the inserts, respectively, whereas the list of excipients, incompatibilities and shelf life was mentioned in 12%, 19%, 16% of the inserts, respectively.Conclusions: There is a wide variation in the information available on the package inserts of drugs available in the Indian market. The package inserts should be carefully scrutinized for completeness before the respective drug is marketed.

Narrowband Influencers and Global Icons: Universality and Media Compatibility in the Communication Patterns of Political Leaders Worldwide

2020 ◽  
Vol 28 (1) ◽  
pp. 48-65
Author(s):  
Renana Peres ◽  
Sunali Talwar ◽  
Liav Alter ◽  
Michal Elhanan ◽  
Yuval Friedmann
Keyword(s):  
Language Processing ◽  
Arab World ◽  
Two Dimensions ◽  
Global Media ◽  
Political Leaders ◽  
Country Characteristics ◽  
The Media ◽  
High Level ◽  
Universal Communication ◽  
Global World

This article analyzes how political leaders communicate with their target audiences and examines whether they adopt a country-specific communication persona, or react to the global media-intensive environment by offering more universal communication. Politicians communicate through presentational (e.g., social media) and representational (e.g., press) outlets, and the compatibility between these outlets represents the leader’s effectiveness in transmitting the desired messages to the audience. The authors of this study suggest a theoretical framework that classifies public figures’ communication along two dimensions: universality (particular–universal) and media compatibility (low–high). The authors used language processing tools to study the sentiment, topic mixture, and use of pronouns by 61 global world leaders in more than 300,000 messages from the leaders’ Twitter accounts and press articles. The results show a high level of universality across political leaders in sentiment, topic mixture, and pronoun usage. The media compatibility is high, with Twitter being slightly more positive. Most leaders fall within the categories of Cosmopolitan Antagonist (high universality, low media compatibility) and Global Icon (high universality, high media compatibility). Overall, the sentiment of their communications is positive. Popular topics include diplomacy, economy, corruption, and the Arab world. No significant relationship was found between the sentiment or communication topics and country characteristics.

scholarly journals Word from the editors

2015 ◽  
Vol 21 (5) ◽  
pp. 661-664
Author(s):  
ZORNITSA KOZAREVA ◽  
VIVI NASTASE ◽  
RADA MIHALCEA
Keyword(s):  
Artificial Intelligence ◽  
Language Processing ◽  
Semantic Networks ◽  
Human Mind ◽  
Semantic Relations ◽  
Web Pages ◽  
Regular Graphs ◽  
Knowledge Repositories ◽  
Knowledge Stores ◽  
The Web

Graph structures naturally model connections. In natural language processing (NLP) connections are ubiquitous, on anything between small and web scale. We find them between words – as grammatical, collocation or semantic relations – contributing to the overall meaning, and maintaining the cohesive structure of the text and the discourse unity. We find them between concepts in ontologies or other knowledge repositories – since the early ages of artificial intelligence, associative or semantic networks have been proposed and used as knowledge stores, because they naturally capture the language units and relations between them, and allow for a variety of inference and reasoning processes, simulating some of the functionalities of the human mind. We find them between complete texts or web pages, and between entities in a social network, where they model relations at the web scale. Beyond the more often encountered ‘regular’ graphs, hypergraphs have also appeared in our field to model relations between more than two units.

Sign in / Sign up

Export Citation Format

Share Document