Deep Neural Models for Medical Concept Normalization in User-Generated Texts

Miftahutdinov, Zulfat; Tutubalina, Elena

doi:10.18653/v1/p19-2055

Cited by 39 publications

(38 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, previous implementations of ADE normalization have often limited their target classes to the ones available only in the dataset thereby artificially inflating the reported performance [14, 15, 16]. We find that training on only the common identifiers available in the training set or limited number of identifiers may yield better accuracy but does not allow discovery of new ADEs because target classes outside those in the training data or the datasets are not considered.…”

Section: Introductionmentioning

confidence: 81%

DeepADEMiner: A Deep Learning Pharmacovigilance Pipeline for Extraction and Normalization of Adverse Drug Effect Mentions on Twitter

Magge

Tutubalina

Miftahutdinov

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

Objective: Research on pharmacovigilance from social media data has focused on mining adverse drug effects (ADEs) using annotated datasets, with publications generally focusing on one of three tasks: (i) ADE classification, (ii) named entity recognition (NER) for identifying the span of an ADE mentions, and (iii) ADE mention normalization to standardized vocabularies. While the common goal of such systems is to detect ADE signals that can be used to inform public policy, it has been impeded largely by limited end-to-end solutions to the three tasks for large-scale analysis of social media reports for different drugs. Materials and Methods: We present a dataset for training and evaluation of ADE pipelines where the ADE distribution is closer to the average `natural balance' with ADEs present in about 7% of the Tweets. The deep learning architecture involves an ADE extraction pipeline with individual components for all three tasks. Results: The system presented achieved a classification performance of F1 = 0.63, span detection performance of F1 = 0.44 and an end-to-end entity resolution performance of F1 = 0.34 on the presented dataset. Discussion: The performance of the models continue to highlight multiple challenges when deploying pharmacovigilance systems that use social media data. We discuss the implications of such models in the downstream tasks of signal detection and suggest future enhancements. Conclusion: Mining ADEs from Twitter posts using a pipeline architecture requires the different components to be trained and tuned based on input data imbalance in order to ensure optimal performance on the end-to-end resolution task.

show abstract

Section: Introductionmentioning

confidence: 81%

DeepADEMiner: A Deep Learning Pharmacovigilance Pipeline for Extraction and Normalization of Adverse Drug Effect Mentions on Twitter

Magge

Tutubalina

Miftahutdinov

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Following state-of-the-art research (Tutubalina et al, 2018;Miftahutdinov and Tutubalina, 2019), we view concept normalization as a classification task. Following (Miftahutdi-nov and Tutubalina, 2019), we convert each ADR mention into a vector representation using BERT or RNN.…”

Section: Methodsmentioning

confidence: 99%

“…For the first step, we use the NER model described in Section 3. The system used for concept normalization is based on our previous works (Tutubalina et al, 2018;Miftahutdinov and Tutubalina, 2019) and presented below.…”

Section: Task 3: Medical Concept Normalizationmentioning

confidence: 99%

Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task

2019

View full text Add to dashboard Cite

The organizing committee would like to thank the program committee, consisting of 13 researchers, for their thoughtful input on the submissions, as well as the organizers of the ACL for their support and management. Finally, a huge thanks to all authors who submitted a paper to the workshop or participated in the shared tasks; this workshop would not have been possible without them and their hard work.

show abstract

“…In this work, we take the task a step further from existing monolingual research in a single domain [2,3,6,12,13,20,22] by exploring multilingual transfer between EHRs and UGTs in different languages. Our goal is not to outperform state of the art models on each dataset separately, but to ask whether we can transfer knowledge from a high-resource language, such as English, to a lowresource one, e.g., Russian, for NER of biomedical entities.…”

Section: Introductionmentioning

confidence: 99%

On Biomedical Named Entity Recognition: Experiments in Interlingual Transfer for Clinical and Social Media Texts

Miftahutdinov

Alimova

Tutubalina

2020

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

Although deep neural networks yield state-of-the-art performance in biomedical named entity recognition (bioNER), much research shares one limitation: models are usually trained and evaluated on English texts from a single domain. In this work, we present a fine-grained evaluation intended to understand the efficiency of multilingual BERT-based models for bioNER of drug and disease mentions across two domains in two languages, namely clinical data and user-generated texts on drug therapy in English and Russian. We investigate the role of transfer learning (TL) strategies between four corpora to reduce the number of examples that have to be manually annotated. Evaluation results demonstrate that multi-BERT shows the best transfer capabilities in the zero-shot setting when training and test sets are either in the same language or in the same domain. TL reduces the amount of labeled data needed to achieve high performance on three out of four corpora: pretrained models reach 98-99% of the full dataset performance on both types of entities after training on 10-25% of sentences. We demonstrate that pretraining on data with one or both types of transfer can be effective.

show abstract

Deep Neural Models for Medical Concept Normalization in User-Generated Texts

Cited by 39 publications

References 19 publications

DeepADEMiner: A Deep Learning Pharmacovigilance Pipeline for Extraction and Normalization of Adverse Drug Effect Mentions on Twitter

DeepADEMiner: A Deep Learning Pharmacovigilance Pipeline for Extraction and Normalization of Adverse Drug Effect Mentions on Twitter

Proceedings of the Fourth Social Media Mining for Health Applications (#SMM4H) Workshop & Shared Task

On Biomedical Named Entity Recognition: Experiments in Interlingual Transfer for Clinical and Social Media Texts

Contact Info

Product

Resources

About