Search

Background: In the Big Data era there is an increasing need to fully exploit and analyse the huge quantity of information available about health. Natural Language Processing (NLP) technologies can contribute to extract relevant information from unstructured data contained in Electronic Health Records (EHR) such as clinical notes, patient’s discharge summaries and radiology reports among others. Extracted information could help in health-related decision making processes. Named entity recognition (NER) devoted to detect important concepts in texts (diseases, symptoms, drugs, etc.) is a crucial task in information extraction processes especially in languages other than English. In this work, we develop a deep learning-based NLP pipeline for biomedical entity extraction in Spanish clinical narrative. Methods: We explore the use of contextualized word embeddings to enhance named entity recognition in Spanish language clinical text, particularly of pharmacological substances, compounds, and proteins. Various combinations of word and sense embeddings were tested on the evaluation corpus of the PharmacoNER 2019 task, the Spanish Clinical Case Corpus (SPACCC). This data set consists of clinical case sections derived from open access Spanish-language medical publications. Results: NER system integrates in-domain pre-trained Flair and FastText word embeddings, byte-pairwise encoded and the bi-LSTM-based character word embeddings. The system yielded the best performance measure with F-score of 90.84%. Error analysis showed that the main source of errors for the best model is the newly detected false positive entities with the half of that amount of errors belonged to longer than the actual ones detected entities. Conclusions: Our study shows that our deep-learning-based system with domain-specific contextualized embeddings coupled with stacking of complementary embeddings yields superior performance over the system with integrated standard and general-domain word embeddings. With this system, we achieve performance competitive with the state-of-the-art.

[EN] This article proposes an approach to solving the problem of multiclassification within the framework of aggressive language recognition in Twitter. At the stage of preprocessing external data is added to the existing dataset, which is based on information in the links in dataset. This made it possible to expand the training dataset and thereby to improve the quality of the classification. The model created is an ensemble of classical machine learning models included Logistic Regression, Support Vector Machines, Naive Bayes models and a combination of Logistic Regression and Naive Bayes. The obtained value of macro F1-score for one of the experiments achieved 0.61, which exceeds the state-of-art published value by 1 percentage point. This indicates the potential value of the proposed approach in the field of hate speech recognition in social media., The work of Paolo Rosso was partially funded by the Spanish MICINN under the research project MISMISFAKEnHATE on Misinformation and Miscommunication in social media: FAKE news and HATE speech (PGC2018-096212-B-C31).

In recent years., health social media has become a popular Internet resource., where various medicines and treatments are discussed and proposed. To make it useful for patients and doctors., different tools of opinion mining are developed and tested. In the paper., we study possibilities of Group Method of Data Handling (GMDH) to classify data from health social networks for the analysis of the most interesting cases for users. Here instead of usual 5-star classification., we use combined classes reflecting more practical view on medicines and treatments. The use of GMDH is provoked by two circumstances: (a) GMDH is essentially noise-immunity technology unlike the other ones used in Data Mining; b) GMDH-based classifiers use One-Vs-All approach being fit just for combined classes mentioned above. Our tool is the platform GMDH Shell including GMDH-based algorithms together with various procedures of pre-processing. The experimental material is the popular health social network AskaPatient. In the experiments, we use both the original and artificially noised data. The results prove to be promising in terms of its accuracy and stability.

The study of health-related topics on social media has become a useful tool for the early detection of the different adverse medical conditions. In particular, it concerns cases related to the treatment of mental diseases, as the effects of medications here often prove to be unpredictable. In our research, we use convolutional neural networks (CNN) with word2vec embedding to classify user comments on Twitter. The aim of the classification is to reveal adverse drug reactions of users. The results obtained are highly promising, showing the overall usefulness of neural network algorithms in this kind of tasks.

This paper surveys recent publications (2008–2017) on using social media data to study public health. The survey describes the main topics being discussed in forums and presents short information about methods and tools used for analysis health social media. We put especial attention on adverse drug reaction detection problem (ADR).