Detecting drugs and adverse events from Spanish social media streams

Segura-Bedmar, Isabel; Revert, Ricardo; Martı́nez, Paloma

doi:10.3115/v1/w14-1117

Cited by 33 publications

(46 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To the best of our knowledge, the system described in (Segura-Bedmar et al, 2014) is the only one that has dealt with the detection of drugs and their effects from Spanish social media streams. The system used the Textalytics tool 3 , which follows a dictionary-based approach to identify entities in texts.…”

Section: Related Workmentioning

confidence: 99%

“…However to the best of our knowledge, only one work in the literature has focused on the detection of ADRs from social media in Spanish (Segura-Bedmar et al, 2014). Indeed, it is only concerned with the detection of mentions of drugs and their effects, without dealing with the extraction of the relationships between them.…”

Section: Introductionmentioning

confidence: 99%

“…Precision and recall were calculated by comparing the adverse effects from their drug labels and the adverse effects obtained by the system. The system obtained an average precision of 77% and an average recall of 35.1% for all four drugs.To the best of our knowledge, the system described in (Segura-Bedmar et al, 2014) is the only one that has dealt with the detection of drugs and their effects from Spanish social media streams. The system used the Textalytics tool 3 , which follows a dictionary-based approach to identify entities in texts.…”

mentioning

confidence: 99%

“…As in the system (Segura-Bedmar et al, 2014), we applied the Textalytics tool, which follows a dictionarybased approach, to identify drugs and their effects occurring in the messages. We created a GATE 10 pipeline application integrating the Textalytic module and the gazetteers collected from the Vademecum website and the ATC system proposed in (Segura-Bedmar et al, 2014). In addition, we created an additional gazetteer in order to increase the coverage.…”

mentioning

confidence: 99%

“…Thus, the dictionary and the two gazetteers contained a total of 7,593 drugs and 74,865 effects. The system yielded a precision of 87% for drugs and 85% for effects, and a recall of 80% for drugs and 56% for effects.3 The SpanishADR corpus Segura-Bedmar et al, (2014) created the first Spanish corpus of user comments annotated with drugs and their effects. The corpus consists of 400 comments, which were gathered from ForumClinic 8 , an interactive health social platform, where patients exchange information about their diseases and their treatments.…”

mentioning

confidence: 99%

See 4 more Smart Citations

Proceedings of BioNLP 2014

2014

View full text Add to dashboard Cite

IntroductionThe first day of the BioNLP 2014 workshop continues following the course set by the first ACL workshop on Natural Language Processing in the Biomedical Domain that was held in 2002: BioNLP 2014 provides a venue for exploring challenges and techniques in processing biomedical language and brings together researchers from computational linguistics and biomedical informatics. The submissions to the first day of 2014 workshop organized by SIGBioMed were traditionally very strong and continued demonstrating the considerable breadth of research in biomedical language processing. The 2014 workshop has accepted 12 full and short papers for oral presentations and 7 posters. The first day of the workshop features a keynote that expands the scope of BioNLP beyond its already remarkable breadth The second day of the workshop features a paper submitted to the special track on NLP approaches for assessment of clinical conditions. Kathleen C. Fraser presents the featured talk on using statistical parsing to detect agrammatic aphasia. The track organizers, Thamar Solorio and Yang Liu, serve as discussants.The second day further features an exciting panel that brings together organizers of several shared tasks in biomedical information retrieval and natural language processing. The panel introduces the workshop participants to the long-standing and relatively new community-wide challenges in biomedical and clinical language processing. It also provides an opportunity to discuss the future of the shared tasks in this domain. AcknowledgmentsAs always, we are profoundly grateful to the authors who chose BioNLP as venue for presenting their innovative research. The authors' willingness to share their work through BioNLP consistently makes the workshop noteworthy among the increasing numbers of available venues. We are equally indebted to the program committee members (listed elsewhere in this volume) who produced at least three thorough reviews per paper on a tight review schedule and with an admirable level of insight.iii AbstractZoonotic viruses, viruses that are transmittable between animals and humans, represent emerging or re-emerging pathogens that pose significant public health threats throughout the world. It is therefore crucial to advance current surveillance mechanisms for these viruses through outlets such as phylogeography. Phylogeographic techniques may be applied to trace the origins and geographical distribution of these viruses using sequence and location data, which are often obtained from publicly available databases such as GenBank. Despite the abundance of zoonotic viral sequence data in GenBank records, phylogeographic analysis of these viruses is greatly limited by the lack of adequate geographic metadata. Although more detailed information may often be found in the related articles referenced in these records, manual extraction of this information presents a severe bottleneck. In this work, we propose an automated system for extracting this information using Natural Language Processing (NLP)...

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 3 more Smart Citations

Proceedings of BioNLP 2014

2014

View full text Add to dashboard Cite

show abstract

Incorporating patient generated health data into pharmacoepidemiological research

Bourke

Dixon

Roddam³

et al. 2020

Pharmacoepidemiology and Drug

View full text Add to dashboard Cite

Epidemiology and pharmacoepidemiology frequently employ Real-World Data (RWD) from healthcare teams to inform research. These data sources usually include signs, symptoms, tests, and treatments, but may lack important information such as the patient's diet or adherence or quality of life. By harnessing digital tools a new fount of evidence, Patient (or Citizen/Person) Generated Health Data (PGHD), is becoming more readily available. This review focusses on the advantages and considerations in using PGHD for pharmacoepidemiological research. New and corroborative types of data can be collected directly from patients using digital devices, both passively and actively. Practical issues such as patient engagement, data linking, validation, and analysis are among important considerations in the use of PGHD. In our ever increasingly patient-centric world, PGHD incorporated into more traditional Real-Word data sources offers innovative opportunities to expand our understanding of the complex factors involved in health and the safety and effectiveness of disease treatments. Pharmacoepidemiologists have a unique role in realizing the potential of PGHD by ensuring that robust methodology, governance, and analytical techniques underpin its use to generate meaningful research results. K E Y W O R D S big data, data privacy, digital epidemiology, mobile apps, mobile health, patient generated health data, patient reported outcomes, pharmacoepidemiology, real world data, real world evidence, social media This article reflects the personal views of the authors and should not be construed to represent FDA's views or policies.

show abstract

Proposal of the First International Workshop on Semantic Indexing and Information Retrieval for Health from Heterogeneous Content Types and Languages (SIIRH)

Couto

Krallinger

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

The application of Information Retrieval (IR) and deep learning strategies to explore the vast amount of rapidly growing healthrelated content is of utmost importance, but is also particularly challenging, due to the very specialized domain language, and implicit differences in language characteristics depending on the content type.This workshop aims at presenting and discussing current and future directions for IR and machine learning approaches devoted to the retrieval and classification of different types of health-related documents ranging from layman or patient generated texts to highly specialized medical literature or clinical records. It includes a session on the MESINESP shared task, supported by the Spanish National Language Technology plan (Plan TL), in order to address the importance and impact of community evaluation efforts, in particular BioASQ, BioCreative, eHealth CLEF, MEDIQA and TREC, as scenarios for exploring evaluation settings and generate data collections of key importance for promoting the development and comparison of IR resources.Additionally, an open session will address IR technologies for heterogeneous health-related content open to multiple languages with a particular interest in the exploitation of structured controlled vocabularies and entity linking, covering the following topics: multilingual and non-English health-related IR, concept indexing, text categorization, generation of evaluation resources biomedical document IR strategies; scalability, robustness and reproducibility of health IR and text mining resources; use of specialized machine translation and advanced deep learning approaches for improving health related search results; medical Question Answering search tools; retrieval of multilingual health related web-content; and other related topics.

show abstract

Detecting drugs and adverse events from Spanish social media streams

Cited by 33 publications

References 27 publications

Proceedings of BioNLP 2014

Proceedings of BioNLP 2014

Incorporating patient generated health data into pharmacoepidemiological research

Proposal of the First International Workshop on Semantic Indexing and Information Retrieval for Health from Heterogeneous Content Types and Languages (SIIRH)

Contact Info

Product

Resources

About