Measuring the effect of different types of unsupervised word representations on Medical Named Entity Recognition

Named Entity Recognition in Electronic Health Records: A Methodological Review

OBJECTIVES

A substantial portion of the data contained in Electronic Health Records (EHR) is unstructured, often appearing as free text. This format restricts its potential utility in clinical decision-making. Named entity recognition (NER) methods address the challenge of extracting pertinent information from unstructured text. The aim of this study was to outline the current NER methods and trace their evolution from 2011 to 2022.

METHODS

We conducted a methodological literature review of NER methods, with a focus on distinguishing the classification models, the types of tagging systems, and the languages employed in various corpora.

RESULTS

Several methods have been documented for automatically extracting relevant information from EHRs using natural language processing techniques such as NER and relation extraction (RE). These methods can automatically extract concepts, events, attributes, and other data, as well as the relationships between them. Most NER studies conducted thus far have utilized corpora in English or Chinese. Additionally, the bidirectional encoder representation from transformers using the BIO tagging system architecture is the most frequently reported classification scheme. We discovered a limited number of papers on the implementation of NER or RE tasks in EHRs within a specific clinical domain.

CONCLUSIONS

EHRs play a pivotal role in gathering clinical information and could serve as the primary source for automated clinical decision support systems. However, the creation of new corpora from EHRs in specific clinical domains is essential to facilitate the swift development of NER and RE models applied to EHRs for use in clinical practice.

Advances in monolingual and crosslingual automatic disability annotation in Spanish

BACKGROUND

Unlike diseases, automatic recognition of disabilities has not received the same attention in the area of medical NLP. Progress in this direction is hampered by obstacles like the lack of annotated corpus. Neural architectures learn to translate sequences from spontaneous representations into their corresponding standard representations given a set of samples. The aim of this paper is to present the last advances in monolingual (Spanish) and crosslingual (from English to Spanish and vice versa) automatic disability annotation. The task consists of identifying disability mentions in medical texts written in Spanish within a collection of abstracts from journal papers related to the biomedical domain.

RESULTS

In order to carry out the task, we have combined deep learning models that use different embedding granularities for sequence to sequence tagging with a simple acronym and abbreviation detection module to boost the coverage.

CONCLUSIONS

Our monolingual experiments demonstrate that a good combination of different word embedding representations provide better results than single representations, significantly outperforming the state of the art in disability annotation in Spanish. Additionally, we have experimented crosslingual transfer (zero-shot) for disability annotation between English and Spanish with interesting results that might help overcoming the data scarcity bottleneck, specially significant for the disabilities.

Negation-based transfer learning for improving biomedical Named Entity Recognition and Relation Extraction

BACKGROUND AND OBJECTIVES

Named Entity Recognition (NER) and Relation Extraction (RE) are two of the most studied tasks in biomedical Natural Language Processing (NLP). The detection of specific terms and entities and the relationships between them are key aspects for the development of more complex automatic systems in the biomedical field. In this work, we explore transfer learning techniques for incorporating information about negation into systems performing NER and RE. The main purpose of this research is to analyse to what extent the successful detection of negated entities in separate tasks helps in the detection of biomedical entities and their relationships.

METHODS

Three neural architectures are proposed in this work, all of them mainly based on Bidirectional Long Short-Term Memory (Bi-LSTM) networks and Conditional Random Fields (CRFs). While the first architecture is devoted to detecting triggers and scopes of negated entities in any domain, two specific models are developed for performing isolated NER tasks and joint NER and RE tasks in the biomedical domain. Then, weights related to negation detection learned by the first architecture are incorporated into those last models. Two different languages, Spanish and English, are taken into account in the experiments.

RESULTS

Performance of the biomedical models is analysed both when the weights of the neural networks are randomly initialized, and when weights from the negation detection model are incorporated into them. Improvements of around 3.5% of F-Measure in the English language and more than 7% in the Spanish language are achieved in the NER task, while the NER+RE task increases F-Measure scores by more than 13% for the NER submodel and around 2% for the RE submodel.

CONCLUSIONS

The obtained results allow us to conclude that negation-based transfer learning techniques are appropriate for performing biomedical NER and RE tasks. These results highlight the importance of detecting negation for improving the identification of biomedical entities and their relationships. The explored techniques show robustness by maintaining consistent results and improvements across different tasks and languages.

Improving personalised query reformulation with embeddings

As a mechanism to guide users towards a better representation of their information needs, the query reformulation method generates new queries based on users’ historical queries. To preserve the original search intent, query reformulations should be context-aware and should attempt to meet users’ personal information needs. The mainstream method aims to generate candidate queries first, according to their past frequencies, and then score (re-rank) these candidates based on the semantic consistency of terms, dependency among latent semantic topics and user preferences. We exploit embeddings (i.e. term, user and topic embeddings) to use contextual information and individual preferences more effectively to improve personalised query reformulation. Our work involves two major tasks. In the first task, candidate queries are generated from an original query by substituting or adding one term, and the contextual similarities between the terms are calculated based on the term embeddings and augmented with user personalisation. In the second task, the candidate queries generated in the first task are evaluated and scored (re-ranked) according to the consistency of the semantic meaning of the candidate query and the user preferences based on a graphical model with the term, user and topic embeddings. Experiments show that our proposed model yields significant improvements compared with the current state-of-the-art methods.

The Automatic Detection of Dataset Names in Scientific Articles

We study the task of recognizing named datasets in scientific articles as a Named Entity Recognition (NER) problem. Noticing that available annotated datasets were not adequate for our goals, we annotated 6000 sentences extracted from four major AI conferences, with roughly half of them containing one or more named datasets. A distinguishing feature of this set is the many sentences using enumerations, conjunctions and ellipses, resulting in long BI+ tag sequences. On all measures, the SciBERT NER tagger performed best and most robustly. Our baseline rule based tagger performed remarkably well and better than several state-of-the-art methods. The gold standard dataset, with links and offsets from each sentence to the (open access available) articles together with the annotation guidelines and all code used in the experiments, is available on GitHub.

Artificial Intelligence for Screening Chinese Electronic Medical Record and Biobank Information

Objective: To establish a structured and integrated platform of clinical data and biobank data, and a client to retrieve these data. Study Design: Initially, the hospital information system (HIS) and biobank information system (BIS) were integrated through the patients' ID numbers. Then, natural language processing (NLP) was used to process the integrated unstructured clinical information. A query interface was designed for this system, which enabled researchers to retrieve clinical or biobank data. Finally, several queries were listed and manually checked to test the retrieval performance of the system. Results: The construction of the biobank screening system (BSS) was completed, and the data were structured. The BSS took an average of 2 seconds to perform a search for target patients/samples. The retrieval results were consistent with the HIS and BIS. For complex queries, we manually checked the retrieved patients/samples, and the system's accuracy was 100%. Conclusion: This NLP-based system improved biological sample screening and using of clinical data. We will continue to improve this system, enhance resource sharing, and promote the development of translational medicine.