Discovering Potential Effects of Dietary Supplements from Twitter Data

Jiang, Keyuan; Tang, Yongbing; Cook, Geoff; Madden, Michael M.

doi:10.1145/3079452.3079467

Cited by 5 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhang et al (2015) employ machine learning techniques to filter supplement interaction relationships in SemMedDB, a database of relationships extracted from Medline articles. Jiang et al (2017) develop a model for identifying adverse effects related to dietary supplements as reported by consumers on Twitter, and discover 191 adverse effects pertaining to 4 dietary supplements. Fan et al (2016) and Fan and Zhang (2018) analyze unstructured clinical notes to predict whether a patient started, continued or discontinued a dietary supplement, which can be useful as a building block for identifying adverse effects in clinical notes (as attempted by the same authors in Fan et al (2017) for the drug warfarin).…”

Section: Related Workmentioning

confidence: 99%

SUPP.AI: finding evidence for supplement-drug interactions

Wang¹,

Tafjord²,

Cohan³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

View full text Add to dashboard Cite

Dietary supplements are used by a large portion of the population, but information on their pharmacologic interactions is incomplete. To address this challenge, we present SUPP.AI, an application for browsing evidence of supplement-drug interactions (SDIs) extracted from the biomedical literature. We train a model to automatically extract supplement information and identify such interactions from the scientific literature. To address the lack of labeled data for SDI identification, we use labels of the closely related task of identifying drug-drug interactions (DDIs) for supervision. We fine-tune the contextualized word representations of the RoBERTa language model using labeled DDI data, and apply the fine-tuned model to identify supplement interactions. We extract 195k evidence sentences from 22M articles (P=0.82, R=0.58, F1=0.68) for 60k interactions. We create the SUPP.AI application for users to search evidence sentences extracted by our model. SUPP.AI is an attempt to close the information gap on dietary supplements by making upto-date evidence on SDIs more discoverable for researchers, clinicians, and consumers.

show abstract

Section: Related Workmentioning

confidence: 99%

SUPP.AI: finding evidence for supplement-drug interactions

Wang¹,

Tafjord²,

Cohan³

et al. 2020

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations

View full text Add to dashboard Cite

show abstract

“…Additionally, there are efforts to explore social media and other online platforms—these platforms reflect the ongoing and rapidly evolving ways in which health data are being exchanged and shared (bioinformatics) by consumers, and signal the potential for new streams of safety information on the “real‐world” use of dietary supplements. Preliminary evidence suggests that Twitter and online discussion groups could be useful for detecting new signals; however, there is significant work still required to overcome challenges, including data quality and signal validation, methods for follow‐up and standardization, and aggregation and cleaning of large volumes of data. The utility of social media is preliminary at this time; however, the potential importance of new sources of information is recognized for dietary supplements, where reports of adverse effects tend to get diverted to other sources, e.g., social media, poison centers, rather than through traditional reporting mechanisms.…”

Section: New Horizonsmentioning

confidence: 99%

Safety Surveillance of Dietary Supplements: Importance, Challenges, and New Horizons

Jordan

Jack

Pless

2018

Clin Pharma and Therapeutics

View full text Add to dashboard Cite

Pharmacovigilance is defined as the science and activities relating to the detection, assessment, understanding, and prevention of adverse effects or any other possible drug-related problems. While current models of pharmacovigilance, with their tools and methodologies, were developed for prescription drugs, safety surveillance is just as important for over-the-counter health products such as dietary supplements. The practice of pharmacovigilance is challenging in itself; however, there are unique challenges associated with dietary supplements..

show abstract

“…Although a small portion of tweets is PETs, the bootstrap approach efficiently improves the balance of two class dataset with a reduced amount of annotations. In another study, Jiang et al employed the same ensemble of machine learning-based classifiers to identify the PETs from the same dataset [Jiang et al 2017]. Moreover, the PETs were further annotated to extract the potential dietary supplement effects (adverse and beneficial) which were mapped to clinical concepts with SNOMED CT (Systematized Nomenclature of Medicine -Clinical Terms) using an open-source tool called medpie [Benton et al 2012].…”

Section: Introductionmentioning

confidence: 99%

Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations

Jarashanth¹,

Nawarathna²

2022

jucs

View full text Add to dashboard Cite

Individuals with health anomalies often share their experiences on social media sites, such as Twitter, which yields an abundance of data on a global scale. Nowadays, social media data constitutes a leading source to build drug monitoring and surveillance systems. However, a proper assessment of such data requires discarding mentions which do not express drug-related personal health experiences. We automate this process by introducing a novel deep learning model. The model includes character-level and word-level embeddings, embedding-level attention, convolu- tional neural networks (CNN), bidirectional gated recurrent units (BiGRU), and context-aware attentions. An embedding for a word is produced by integrating both word-level and character-level embeddings using an embedding-level attention mechanism, which selects the salient features from both embeddings without expanding dimensionality. The resultant embedding is further analyzed by three CNN layers independently, where each extracts unique n-grams. BiGRUs followed by attention layers further process the outputs from each CNN layer. Besides, the resultant embedding is also encoded by a BiGRU with attention. Our model is developed to cope with the intricate attributes inherent to tweets such as vernacular texts, descriptive medical phrases, frequently misspelt words, abbreviations, short messages, and others. All these four outputs are summed and sent to a softmax classifier. We built a dataset by incorporating tweets from two benchmark datasets designed for the same objective to evaluate the performance. Our model performs substantially better than existing models, including several customized Bidirectional Encoder Representations from Transformers (BERT) models with an F1-score of 0.772.

show abstract

Discovering Potential Effects of Dietary Supplements from Twitter Data

Cited by 5 publications

References 11 publications

SUPP.AI: finding evidence for supplement-drug interactions

SUPP.AI: finding evidence for supplement-drug interactions

Safety Surveillance of Dietary Supplements: Importance, Challenges, and New Horizons

Identifying Tweets with Personal Medication Intake Mentions using Attentive Character and Localized Context Representations

Contact Info

Product

Resources

About