Detecting Adverse Drug Reactions from Twitter through Domain-Specific Preprocessing and BERT Ensembling

• URL: http://arxiv.org/abs/2005.06634v1
• Date: Mon, 11 May 2020 20:49:24 GMT
• Title: Detecting Adverse Drug Reactions from Twitter through Domain-Specific Preprocessing and BERT Ensembling
• Authors: Amy Breden, Lee Moore
• Abstract summary: We aim to develop a deep learning model to classify ADRs within Twitter tweets that contain drug mentions. Our approach involved fine-tuning $BERT_LARGE$ and two domain-specific BERT implementations, $BioBERT$ and $Bio + clinicalBERT$. Our final model resulted in state-of-the-art performance on both $F_1$-score (0.6681) and recall (0.7700) outperforming all models submitted in SMM4H 2019 and during post-evaluation to date.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The automation of adverse drug reaction (ADR) detection in social media would revolutionize the practice of pharmacovigilance, supporting drug regulators, the pharmaceutical industry and the general public in ensuring the safety of the drugs prescribed in daily practice. Following from the published proceedings of the Social Media Mining for Health (SMM4H) Applications Workshop & Shared Task in August 2019, we aimed to develop a deep learning model to classify ADRs within Twitter tweets that contain drug mentions. Our approach involved fine-tuning $BERT_{LARGE}$ and two domain-specific BERT implementations, $BioBERT$ and $Bio + clinicalBERT$, applying a domain-specific preprocessor, and developing a max-prediction ensembling approach. Our final model resulted in state-of-the-art performance on both $F_1$-score (0.6681) and recall (0.7700) outperforming all models submitted in SMM4H 2019 and during post-evaluation to date.

Related papers

• DrugAgent: Automating AI-aided Drug Discovery Programming through LLM Multi-Agent Collaboration [31.892593155710625]
  We introduce DrugAgent, a multi-agent framework aimed at automating machine learning (ML) programming in drug discovery. DrugAgent incorporates domain expertise by identifying specific requirements and building domain-specific tools, while systematically exploring different ideas to find effective solutions. For example, DrugAgent is able to complete the ML programming pipeline end-to-end, from data acquisition to performance evaluation for the ADMET prediction task, and finally select the best model.
  arXiv  Detail & Related papers  (2024-11-24T03:06:59Z)
• $\texttt{PatentAgent}$: Intelligent Agent for Automated Pharmaceutical Patent Analysis [17.569006298922783]
  We introduce the $textbffirst$ intelligent agent in this domain, $texttPatentAgent$, poised to advance and potentially revolutionize the landscape of pharmaceutical research. $texttPatentAgent$ comprises three key end-to-end modules -- $textitPA-QA$, $textitPA-Img2Mol$, and $textitPA-CoreId$ -- that respectively perform (1) patent question-answering, (2) image-to-molecular-structure conversion, and (3) core chemical structure identification.
  arXiv  Detail & Related papers  (2024-10-25T19:15:08Z)
• Exploiting Pre-trained Models for Drug Target Affinity Prediction with Nearest Neighbors [58.661454334877256]
  Drug-Target binding Affinity (DTA) prediction is essential for drug discovery. Despite the application of deep learning methods to DTA prediction, the achieved accuracy remain suboptimal. We propose $k$NN-DTA, a non-representation embedding-based retrieval method adopted on a pre-trained DTA prediction model.
  arXiv  Detail & Related papers  (2024-07-21T15:49:05Z)
• Utilizing AI and Social Media Analytics to Discover Adverse Side Effects of GLP-1 Receptor Agonists [0.0]
  Adverse side effects (ASEs) of drugs, revealed after FDA approval, pose a threat to patient safety. We developed a digital methodology capable of analyzing massive public data from social media. We uncovered 21 potentials associated with the glucagon-like peptide 1 receptor agonists (GLP-1 RA) market.
  arXiv  Detail & Related papers  (2024-04-01T09:48:14Z)
• Learning to Describe for Predicting Zero-shot Drug-Drug Interactions [54.172575323610175]
  Adverse drug-drug interactions can compromise the effectiveness of concurrent drug administration. Traditional computational methods for DDI prediction may fail to capture interactions for new drugs due to the lack of knowledge. We propose TextDDI with a language model-based DDI predictor and a reinforcement learning(RL)-based information selector.
  arXiv  Detail & Related papers  (2024-03-13T09:42:46Z)
• AD-BERT: Using Pre-trained contextualized embeddings to Predict the Progression from Mild Cognitive Impairment to Alzheimer's Disease [14.59521645987661]
  We develop a deep learning framework based on the pre-trained Bidirectional Representations from Transformers (BERT) model. We predict the risk of disease progression from Mild Cognitive Impairment (MCI) to Alzheimer's Disease (AD) using unstructured clinical notes.
  arXiv  Detail & Related papers  (2022-11-07T04:05:46Z)
• Fine-Tuning BERT for Automatic ADME Semantic Labeling in FDA Drug Labeling to Enhance Product-Specific Guidance Assessment [7.776014050139462]
  Product-specific guidances (PSGs) recommended by the United States Food and Drug Administration (FDA) are instrumental to promote and guide generic drug product development. To assess a PSG, the FDA assessor needs to take extensive time and effort to manually retrieve supportive drug information of absorption, distribution, metabolism, and excretion (ADME) from the reference listed drug labeling. We developed a novel application of ADME semantic labeling, which can automatically retrieve ADME paragraphs from drug labeling instead of manual work.
  arXiv  Detail & Related papers  (2022-07-25T17:43:36Z)
• Multi-View Substructure Learning for Drug-Drug Interaction Prediction [69.34322811160912]
  We propose a novel multi- view drug substructure network for DDI prediction (MSN-DDI) MSN-DDI learns chemical substructures from both the representations of the single drug (intra-view) and the drug pair (inter-view) simultaneously and utilizes the substructures to update the drug representation iteratively. Comprehensive evaluations demonstrate that MSN-DDI has almost solved DDI prediction for existing drugs by achieving a relatively improved accuracy of 19.32% and an over 99% accuracy under the transductive setting.
  arXiv  Detail & Related papers  (2022-03-28T05:44:29Z)
• DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotations [90.27736364704108]
  We present DrugOOD, a systematic OOD dataset curator and benchmark for AI-aided drug discovery. DrugOOD comes with an open-source Python package that fully automates benchmarking processes. We focus on one of the most crucial problems in AIDD: drug target binding affinity prediction.
  arXiv  Detail & Related papers  (2022-01-24T12:32:48Z)
• Mining Adverse Drug Reactions from Unstructured Mediums at Scale [0.0]
  Adverse drug reactions / events (ADR/ADE) have a major impact on patient health and health care costs. Most ADR's are not reported via formal channels, but they are often documented in unstructured conversations. We propose a natural language processing (NLP) solution that detects ADR's in such unstructured free-text conversations.
  arXiv  Detail & Related papers  (2022-01-05T01:52:42Z)
• SafeDrug: Dual Molecular Graph Encoders for Safe Drug Recommendations [59.590084937600764]
  We propose a DDI-controllable drug recommendation model named SafeDrug to leverage drugs' molecule structures and model DDIs explicitly. On a benchmark dataset, our SafeDrug is relatively shown to reduce DDI by 19.43% and improves 2.88% on Jaccard similarity between recommended and actually prescribed drug combinations over previous approaches.
  arXiv  Detail & Related papers  (2021-05-05T00:20:48Z)
• Ensemble Transfer Learning for the Prediction of Anti-Cancer Drug Response [49.86828302591469]
  In this paper, we apply transfer learning to the prediction of anti-cancer drug response. We apply the classic transfer learning framework that trains a prediction model on the source dataset and refines it on the target dataset. The ensemble transfer learning pipeline is implemented using LightGBM and two deep neural network (DNN) models with different architectures.
  arXiv  Detail & Related papers  (2020-05-13T20:29:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.