Automatic Extraction of Medication Mentions from Tweets-Overview of the BioCreative VII Shared Task 3 Competition.

This study presents the outcomes of the shared task competition BioCreative VII (Task 3) focusing on the extraction of medication names from a Twitter user's publicly available tweets (the user's 'timeline'). In general, detecting health-related tweets is notoriously challenging for natural language processing tools. The main challenge, aside from the informality of the language used, is that people tweet about any and all topics, and most of their tweets are not related to health. Thus, finding those tweets in a user's timeline that mention specific health-related concepts such as medications requires addressing extreme imbalance. Task 3 called for detecting tweets in a user's timeline that mentions a medication name and, for each detected mention, extracting its span. The organizers made available a corpus consisting of 182 049 tweets publicly posted by 212 Twitter users with all medication mentions manually annotated. The corpus exhibits the natural distribution of positive tweets, with only 442 tweets (0.2%) mentioning a medication. This task was an opportunity for participants to evaluate methods that are robust to class imbalance beyond the simple lexical match. A total of 65 teams registered, and 16 teams submitted a system run. This study summarizes the corpus created by the organizers and the approaches taken by the participating teams for this challenge. The corpus is freely available at https://biocreative.bioinformatics.udel.edu/tasks/biocreative-vii/track-3/. The methods and the results of the competing systems are analyzed with a focus on the approaches taken for learning from class-imbalanced data.

Analyzing transfer learning impact in biomedical cross-lingual named entity recognition and normalization.

BACKGROUND: The volume of biomedical literature and clinical data is growing at an exponential rate. Therefore, efficient access to data described in unstructured biomedical texts is a crucial task for the biomedical industry and research. Named Entity Recognition (NER) is the first step for information and knowledge acquisition when we deal with unstructured texts. Recent NER approaches use contextualized word representations as input for a downstream classification task. However, distributed word vectors (embeddings) are very limited in Spanish and even more for the biomedical domain. METHODS: In this work, we develop several biomedical Spanish word representations, and we introduce two Deep Learning approaches for pharmaceutical, chemical, and other biomedical entities recognition in Spanish clinical case texts and biomedical texts, one based on a Bi-STM-CRF model and the other on a BERT-based architecture. RESULTS: Several Spanish biomedical embeddigns together with the two deep learning models were evaluated on the PharmaCoNER and CORD-19 datasets. The PharmaCoNER dataset is composed of a set of Spanish clinical cases annotated with drugs, chemical compounds and pharmacological substances; our extended Bi-LSTM-CRF model obtains an F-score of 85.24% on entity identification and classification and the BERT model obtains an F-score of 88.80% . For the entity normalization task, the extended Bi-LSTM-CRF model achieves an F-score of 72.85% and the BERT model achieves 79.97%. The CORD-19 dataset consists of scholarly articles written in English annotated with biomedical concepts such as disorder, species, chemical or drugs, gene and protein, enzyme and anatomy. Bi-LSTM-CRF model and BERT model obtain an F-measure of 78.23% and 78.86% on entity identification and classification, respectively on the CORD-19 dataset. CONCLUSION: These results prove that deep learning models with in-domain knowledge learned from large-scale datasets highly improve named entity recognition performance. Moreover, contextualized representations help to understand complexities and ambiguity inherent to biomedical texts. Embeddings based on word, concepts, senses, etc. other than those for English are required to improve NER tasks in other languages.

The Impact of Pretrained Language Models on Negation and Speculation Detection in Cross-Lingual Medical Text: Comparative Study.

BACKGROUND: Negation and speculation are critical elements in natural language processing (NLP)-related tasks, such as information extraction, as these phenomena change the truth value of a proposition. In the clinical narrative that is informal, these linguistic facts are used extensively with the objective of indicating hypotheses, impressions, or negative findings. Previous state-of-the-art approaches addressed negation and speculation detection tasks using rule-based methods, but in the last few years, models based on machine learning and deep learning exploiting morphological, syntactic, and semantic features represented as spare and dense vectors have emerged. However, although such methods of named entity recognition (NER) employ a broad set of features, they are limited to existing pretrained models for a specific domain or language. OBJECTIVE: As a fundamental subsystem of any information extraction pipeline, a system for cross-lingual and domain-independent negation and speculation detection was introduced with special focus on the biomedical scientific literature and clinical narrative. In this work, detection of negation and speculation was considered as a sequence-labeling task where cues and the scopes of both phenomena are recognized as a sequence of nested labels recognized in a single step. METHODS: We proposed the following two approaches for negation and speculation detection: (1) bidirectional long short-term memory (Bi-LSTM) and conditional random field using character, word, and sense embeddings to deal with the extraction of semantic, syntactic, and contextual patterns and (2) bidirectional encoder representations for transformers (BERT) with fine tuning for NER. RESULTS: The approach was evaluated for English and Spanish languages on biomedical and review text, particularly with the BioScope corpus, IULA corpus, and SFU Spanish Review corpus, with F-measures of 86.6%, 85.0%, and 88.1%, respectively, for NeuroNER and 86.4%, 80.8%, and 91.7%, respectively, for BERT. CONCLUSIONS: These results show that these architectures perform considerably better than the previous rule-based and conventional machine learning-based systems. Moreover, our analysis results show that pretrained word embedding and particularly contextualized embedding for biomedical corpora help to understand complexities inherent to biomedical text.

A two-stage deep learning approach for extracting entities and relationships from medical texts.

This work presents a two-stage deep learning system for Named Entity Recognition (NER) and Relation Extraction (RE) from medical texts. These tasks are a crucial step to many natural language understanding applications in the biomedical domain. Automatic medical coding of electronic medical records, automated summarizing of patient records, automatic cohort identification for clinical studies, text simplification of health documents for patients, early detection of adverse drug reactions or automatic identification of risk factors are only a few examples of the many possible opportunities that the text analysis can offer in the clinical domain. In this work, our efforts are primarily directed towards the improvement of the pharmacovigilance process by the automatic detection of drug-drug interactions (DDI) from texts. Moreover, we deal with the semantic analysis of texts containing health information for patients. Our two-stage approach is based on Deep Learning architectures. Concretely, NER is performed combining a bidirectional Long Short-Term Memory (Bi-LSTM) and a Conditional Random Field (CRF), while RE applies a Convolutional Neural Network (CNN). Since our approach uses very few language resources, only the pre-trained word embeddings, and does not exploit any domain resources (such as dictionaries or ontologies), this can be easily expandable to support other languages and clinical applications that require the exploitation of semantic information (concepts and relationships) from texts. During the last years, the task of DDI extraction has received great attention by the BioNLP community. However, the problem has been traditionally evaluated as two separate subtasks: drug name recognition and extraction of DDIs. To the best of our knowledge, this is the first work that provides an evaluation of the whole pipeline. Moreover, our system obtains state-of-the-art results on the eHealth-KD challenge, which was part of the Workshop on Semantic Analysis at SEPLN (TASS-2018).

[Economic evaluation of antiviral treatment for chronic hepatitis B: a systematic review]. / Revisión sistemática de evaluaciones económicas de fármacos antivirales para el tratamiento de la hepatitis B crónica.

OBJECTIVE: To revise the available evidence on the cost-effectiveness of antiviral regimens for treatment of chronic hepatitis B. MATERIAL AND METHODS: We performed a systematic revision on MEDLINE, LILACS NICE and COCHRANE databases, searching for economic evaluations of antiviral regimens for treatment of chronic hepatitis B. We included original studies, systematic revisions and management guidelines including information on the cost-effectiveness of this treatment. We registered the characteristics and results of the retrieved documents. RESULTS: We obtained 29 original papers, 4 revision articles and 4 management guidelines. Most of these publications have been done in the last 5 years. There was conflict of interest in 73% of original articles, due to authors working for the pharmaceutical industry. 93% of articles that evaluate the cost-effectiveness of giving treatment for chronic hepatitis B against management of its complications find that it is indeed cost-effective to give antiviral treatment. 3/6 studies that evaluate lamivudine against other drugs find it as a dominant strategy, 3/5 find entecavir as the dominant strategy, 1/1 find tenofovir dominant, » find conventional interferon as dominant and none of them find adefovir or pegylated interferon as dominant strategies. CONCLUSIONS: We consider that the available evidence suggests that to give antiviral treatment for chronic hepatitis B is a cost-effective intervention for many health systems, including ours. It has varying indexes of cost-effectiveness according to the evaluated regimens. Ideally , we should perform local economic evaluations in this issue.

[Effect of levonorgestrel in the ovulation, endometrium, and spermatozoa for emergency oral contraception]. / Efecto del levonorgestrel como anticonceptivo oral de emergencia en la ovulación, el endometrio y los espermatozoides.

There is wide controversy about the mechanism of action of the levonorgestrel used for emergency oral contraception, and many organizations, both scientific as well as from the civil society, show their discrepancy with its use, due to its possible action as an abortion- inducer. In order to evaluate the scientific evidence available on the mechanisms of action of the levonorgestrel used for emergency oral contraception (EOC), a systematic revision was performed in the Medline and Cochrane library databases. We found 444 articles. After reviewing the abstracts, we selected 22 articles, whose complete texts were evaluated. We found that the main mechanism of action of the levonorgestrel, given at the doses recommended for EOC, is the inhibition or retardation of the ovulation, it doesn't affect the spermatozoa in their migration or egg-penetration capacities. No morphological or molecular alterations in the endometrium that could interfere with the implantation of the fertilized egg have been demonstrated. There is no actual scientific evidence available supporting that the use of levonorgestrel for EOC is abortive.

Efecto del levonorgestrel como anticonceptivo oral de emergencia en la ovulación, el endometrio y los espermatozoides / Effect of levonorgestrel in the ovulation, endometrium, and spermatozoa for emergency oral contraception

Existe amplia controversia acerca del mecanismo de acción del levonorgestrel como anticonceptivo oral de emergencia; numerosas organizaciones, tanto científicas como de la sociedad civil, muestran su disconformidad con su uso, debido a su posible acción como inductor de aborto. Con el objetivo de evaluar la evidencia científica disponible sobre los mecanismos de acción del levonorgestrel utilizado como anticonceptivo oral de emergencia (AOE), se realizó una revisión sistemática en las bases de datos Medline y Cochrane Library donde se encontró 444 artículos; después de revisar los resúmenes, se seleccionó 22 artículos, los cuales fueron evaluados a texto completo. Se encontró que el principal mecanismo de acción del levonorgestrel, a las dosis recomendadas como AOE, es la inhibición o retraso de la ovulación; no afecta a los espermatozoides en su capacidad de migración ni de penetración al óvulo. No se ha demostrado alteraciones morfológicas ni moleculares en el endometrio que puedan interferir con la implantación del huevo fecundado. No existe evidencia científica actual disponible que sustente que el uso de levonorgestrel como AOE sea abortivo.

There is wide controversy about the mechanism of action of the levonorgestrel used for emergency oral contraception, and many organizations, both scientific as well as from the civil society, show their discrepancy with its use, due to its possible action as an abortion-inducer. In order to evaluate the scientific evidence available on the mechanisms of action of the levonorgestrel used for emergency oral contraception (EOC), a systematic revision was performed in the Medline and Cochrane library databases. We found 444 articles. After reviewing the abstracts, we selected 22 articles, whose complete texts were evaluated. We found that the main mechanism of action of the levonorgestrel, given at the doses recommended for EOC, is the inhibition or retardation of the ovulation, it doesn't affect the spermatozoa in their migration or egg-penetration capacities. No morphological or molecular alterations in the endometrium that could interfere with the implantation of the fertilized egg have been demonstrated. There is no actual scientific evidence available supporting that the use of levonorgestrel for EOC is abortive.

Revisión sistemática de evaluaciones económicas de fármacos antivirales para el tratamiento de la hepatitis B crónica / Economic evaluation of antiviral treatment for chronic hepatitis B: a systematic review

Objetivo. Revisar la evidencia disponible acerca de la costo-efectividad de los regímenes antivirales en el tratamiento de la hepatitis B crónica. Material y Métodos. Se realizó una revisión sistemática de las bases de datos de MEDLINE, LILACS, NICE guidelines y COCHRANE sobre evaluaciones económicas de regímenes antivirales para el tratamiento de hepatitis B crónica. Se incluyó los estudios originales, revisiones sistemáticas y guías de manejo conteniendo información acerca de la costo-efectividad de dicho tratamiento. Se registró las características y resultados de los documentos obtenidos. Resultados. Se obtuvo 29 artículos originales, cuatro artículos de revisión y cuatro guías de manejo clínico. La mayoría de las publicaciones fueron hechas en los cinco últimos años. Los autores tenían conflicto deinterés, por trabajar en la industria farmacéutica, en 73 por ciento de los artículos originales. El 93 por ciento de los artículos que evalúan costo-efectividad de brindar tratamiento para hepatitis B crónica frente a manejo de complicaciones, encuentran que es costo-efectivo el tratamiento antiviral; 3/6 estudios que evalúan lamivudina frente a otros esquemas la encuentran como estrategia dominante, 3/5 encuentran a entecavir como estrategia dominante, 1/1 a tenofovir como dominante, 1/4 a interferón convencional como dominante y ninguno encuentra a adefovir ni interferón pegilado como estrategia dominante. Conclusiones. Consideramos que la evidencia disponible sugiere que brindar tratamiento antiviral para hepatitis B crónica sea una intervención costo-efectiva para muchos sistemas de salud, incluyendo el nuestro, con índicesvariables de costo-efectividad de acuerdo con los esquemas evaluados. Idealmente, se debe realizar evaluaciones económicas locales en este aspecto.

Objective. To revise the available evidence on the cost-effectiveness of antiviral regimens for treatment of chronic hepatitis B. Material and methods. We performed a systematic revision on MEDLINE, LILACS NICE and COCHRANE databases, searching for economic evaluations of antiviral regimens for treatment of chronic hepatitis B. We included original studies, systematic revisions and management guidelines including information on the cost-effectiveness of this treatment. We registered the characteristics and results of the retrieved documents. Results. We obtained 29 originalpapers, 4 revision articles and 4 management guidelines. Most of these publications have been done in the last 5 years. There was conflict of interest in 73 per cent of original articles, due to authors working for the pharmaceutical industry. 93 per cent of articles that evaluate the cost-effectiveness of giving treatment for chronic hepatitis B against management of its complications find that it is indeed cost-effective to give antiviral treatment. 3/6 studies that evaluate lamivudine against other drugs find it as a dominant strategy, 3/5 find entecavir as the dominant strategy, 1/1 find tenofovir dominant, » find conventional interferon as dominant and none of them find adefovir or pegylated interferon as dominant strategies. Conclusions. We consider that the available evidence suggests that to give antiviral treatment for chronic hepatitis B is a cost-effective intervention for many health systems, including ours. It has varying indexes of cost-effectiveness according to the evaluated regimens. Ideally , we should perform local economic evaluations in this issue.