Clinical Natural Language Processing in languages other than English: opportunities and challenges

Névéol, Aurélie; Dalianis, Hercules; Velupillai, Sumithra; Savova, Guergana; Zweigenbaum, Pierre

doi:10.1186/s13326-018-0179-8

Cited by 188 publications

(122 citation statements)

References 107 publications

Supporting

Mentioning

116

Contrasting

Unclassified

Order By: Relevance

“…This situa- 2 Wu et al [29,Table 3(b)] found that 71% of the corpora they screened were English, 20% Chinese, 2% Spanish, Japanese or Finnish and all other languages ranked below 1%. For a survey on medical NLP dealing explicitly with languages other than English, see [36]. tion might be remedied by a recently proposed common evaluation framework for biomedical NLP, the BLUE (Biomedical Language Understanding Evaluation) benchmark 3 [22], which consists of five different biomedical NLP tasks (including NER and REX) with ten corpora (including BC5CDR, DDI, and i2b2 that also occur in the tables below), or the one proposed by Chauhan et al [37] 4 enabling a more lucid comparison of various training methodologies, pre-processing, modeling techniques, and evaluation metrics.…”

Section: Deep Neural Network For Medical Information Extractionmentioning

confidence: 99%

Medical Information Extraction in the Age of Deep Learning

Hahn

Oleynik

2020

Yearb Med Inform

View full text Add to dashboard Cite

Objectives: We survey recent developments in medical Information Extraction (IE) as reported in the literature from the past three years. Our focus is on the fundamental methodological paradigm shift from standard Machine Learning (ML) techniques to Deep Neural Networks (DNNs). We describe applications of this new paradigm concentrating on two basic IE tasks, named entity recognition and relation extraction, for two selected semantic classes—diseases and drugs (or medications)—and relations between them. Methods: For the time period from 2017 to early 2020, we searched for relevant publications from three major scientific communities: medicine and medical informatics, natural language processing, as well as neural networks and artificial intelligence. Results: In the past decade, the field of Natural Language Processing (NLP) has undergone a profound methodological shift from symbolic to distributed representations based on the paradigm of Deep Learning (DL). Meanwhile, this trend is, although with some delay, also reflected in the medical NLP community. In the reporting period, overwhelming experimental evidence has been gathered, as illustrated in this survey for medical IE, that DL-based approaches outperform non-DL ones by often large margins. Still, small-sized and access-limited corpora create intrinsic problems for data-greedy DL as do special linguistic phenomena of medical sublanguages that have to be overcome by adaptive learning strategies. Conclusions: The paradigm shift from (feature-engineered) ML to DNNs changes the fundamental methodological rules of the game for medical NLP. This change is by no means restricted to medical IE but should also deeply influence other areas of medical informatics, either NLP- or non-NLP-based.

show abstract

Section: Deep Neural Network For Medical Information Extractionmentioning

confidence: 99%

Medical Information Extraction in the Age of Deep Learning

Hahn

Oleynik

2020

Yearb Med Inform

View full text Add to dashboard Cite

show abstract

“…In addition, J. Luo, M. Wu, et al in their review [11] draw attention to the fact that the application of artificial intelligence technologies and Big Data to solve health problems based on EHC has its own specifics and differs from such areas biomedical informatics, as computer modeling of organs, image processing and analysis, genome research. In this context, the researchers such as L. Luo, L. Li, J. Hu, et al [12]; K. Kreimeyer, M. Foster, A. Pandey, et al [13]; A. Névéol, H. Dalianis, S. Velupillai, et al [14] highlight the problem of extracting objective information from medical texts included in EHR. They note the objectivity of the fact that there are many natural language processing systems (NLP) for English medical texts processing.…”

Section: Big Biomedical Data Mining: Related Workmentioning

confidence: 99%

Infrastructure of the Electronic Health Record Data Management for Digital Patient Phenotype Creating

Zakharov¹,

Потапов²,

Zakharova³

et al. 2019

Proceedings of the 7th Scientific Conference on Information Technologies for Intelligent Decision Making Support (ITIDS 2019)

View full text Add to dashboard Cite

improving the health care system requires the effective use of digitized biomedical data already accumulated and constantly updated due to the widespread introduction of applied information systems. One of the priorities here is the creation of a patient's digital phenotype based on data from an electronic health record (EHR). To solve this problem, it is necessary to rely on an ecosystem that provides secure storage, processing and analysis of large volumes of heterogeneous information (tables, images, texts in natural language). The main goal of the article is to study the possibilities of Big Data methods and technologies for the reuse of digitized biomedical data. We have considered designing and implementing of the EHR data management infrastructure that provides tools for digital patient phenotype creating. We designed the data lake prototype "5P Medicine-Big Data" based on the original "Big Data to Smart Data" (BD2SD) multi-layer approach. We have developed an information repository based on the generalized NoSQL approach and the "document repository" model, as well as the system of services. These services provide solutions for the secure data transfer from medical information systems, data storage, validation of information, preliminary data analysis and visualization, data extraction from unstructured documents, and sampling for the machine and deep learning methods. We offered methods for analyzing a significant amount of EHR based on machine learning and Big Data technologies. We applied these methods to extract valid information from unstructured EHR data (first of all, patient examination protocols) and identify characteristic patient categories. We constructed digital patient phenotype, represented by exactly those features extracted from the EHR data that are key in the context of a specific medical problem. Digital phenotypes were formed based on more than 30,000 medical texts for about 2,000 patients. We have shown the effectiveness of the proposed approach by examining the problem of identifying patterns in the patient's visits to a doctor before and after the cardiovascular diseases (angina pectoris, myocardial infarction, and ischemic heart disease) appeared in the electronic health record.

show abstract

“…One of those problems is related to formulate the question or query that should include all important information without ambiguity and about the information retrieval. Névéol et al [3] had identified the opportunities and challenges to work with clinical natural language processing. They had also described the problems with different methods/algorithms with respect to language context.…”

Section: Introductionmentioning

confidence: 99%

Developing Disease Classification System based on Keyword Extraction and Supervised Learning

Suffian¹,

Khan²,

Wasi³

2018

ijacsa

View full text Add to dashboard Cite

The Evidence-Based Medicine (EBM) is emerged as the helpful practice for medical practitioners to make decisions with available shreds of evidence along with their professional expertise. In EBM, the medical practitioners suggest the medication on the basis of underlying information of patients descriptions and medical records (mostly available in textual form). This paper presents a novel and efficient method for predicting the correct disease. Since these type of tasks are generally accounted as the multi-class classifying problem, therefore, a large number of records are needed, so a large number of records will be entertained in higher n-dimensional space. Our system, as proposed in this paper, will utilise the key-phrases extraction techniques to scoop out the meaningful information to reduce the size of textual dimension, and, the suite of machine learning algorithms for classifying the diseases efficiently. We have tested the proposed approach on 6 different diseases i.e. Asthma, Hypertension, Diabetes, Fever, Abdominal issues, and Heart problems over the dataset of 690 patients. With key-phrases tested in the range [3,7] features, SVM has shown the highest (93.34%, 95%) F1-score and accuracy.

show abstract

Clinical Natural Language Processing in languages other than English: opportunities and challenges

Cited by 188 publications

References 107 publications

Medical Information Extraction in the Age of Deep Learning

Medical Information Extraction in the Age of Deep Learning

Infrastructure of the Electronic Health Record Data Management for Digital Patient Phenotype Creating

Developing Disease Classification System based on Keyword Extraction and Supervised Learning

Contact Info

Product

Resources

About