Clinical Natural Language Processing in languages other than English: opportunities and challenges
Journal of Biomedical SemanticsPublished 30 March 2018Open access
Aurélie Névéol, Hercules Dalianis, Sumithra Velupillai, Guergana Savova, Pierre Zweigenbaum
Citations291
SJR quartileQ2
SJR score0.49
SNIP0.97
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
This paper offers the first broad overview of clinical Natural Language Processing for languages other than English and identifies major challenges and opportunities that will affect the impact of NLP on clinical practice and public health studies in a context that encompasses English as well as other languages.
Abstract
We show the advantages and drawbacks of each method, and highlight the appropriate application context. Finally, we identify major challenges and opportunities that will affect the impact of NLP on clinical practice and public health studies in a context that encompasses English as well as other languages.
Keywords
Computer ScienceBiochemistry, Genetics and Molecular Biology
Nucleic Acids ResearchThe Unified Medical Language System (UMLS): integrating biomedical terminology
4,224 Citations2003Olivier Bodenreider
The Unified Medical Language System is a repository of biomedical vocabularies developed by the US National Library of Medicine and includes tools for customizing the Metathesaurus (MetamorphoSys), for generating lexical variants of concept names (lvg) and for extracting UMLS concepts from text (MetaMap).
Computational LinguisticsThe Proposition Bank: An Annotated Corpus of Semantic Roles
2,302 Citations2005Martha Palmer, Daniel Gildea +1 more
An automatic system for semantic role tagging trained on the corpus is described and the effect on its performance of various types of information is discussed, including a comparison of full syntactic parsing with a flat representation and the contribution of the empty trace categories of the treebank.
Journal of the American Medical Informatics AssociationMayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications
2,017 Citations2010Guergana Savova, James Masanz +5 more
The cTAKES annotations are the foundation for methods and modules for higher-level semantic processing of clinical free-text, and its components, specifically trained for the clinical domain, create rich linguistic and semantic annotations.
Journal of the American Medical Informatics AssociationAn overview of MetaMap: historical perspective and recent advances
1,540 Citations2010Alan R. Aronson, François-Michel Lang
This study reports on MetaMap's evolution over more than a decade, concentrating on those features arising out of the research needs of the biomedical informatics community both within and outside of the National Library of Medicine.
BioinformaticsPheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene–disease associations
1,339 Citations2010Joshua C. Denny, Marylyn D. Ritchie +8 more
A novel method to scan phenomic data for genetic associations using International Classification of Disease billing codes, which are available in most EMR systems, and develops a code translation table to automatically define 776 different disease populations and their controls using prevalent ICD9 codes derived from EMR data.
Critical Care MedicineMultiparameter Intelligent Monitoring in Intensive Care II: A public-access intensive care unit database*
1,159 Citations2011M. A. Saeed, Mauricio Villarroel +8 more
MIMIC-II documents a diverse and very large population of intensive care unit patient stays and contains comprehensive and detailed clinical data, including physiological waveforms and minute-by-minute trends for a subset of records.
BMC Medical GenomicsThe eMERGE Network: A consortium of biorepositories linked to electronic medical records data for conducting genomic studies
729 Citations2011the eMERGE Team, Catherine A. McCarty +11 more
By combining advanced clinical informatics, genome science, and community consultation, eMERGE represents a first step in the development of data-driven approaches to incorporate genomic information into routine healthcare delivery.
Journal of Biomedical InformaticsWhat can natural language processing do for clinical decision support?
682 Citations2009Dina Demner‐Fushman, Wendy W. Chapman +1 more
This review focuses on the recently renewed interest in development of fundamental NLP methods and advances in the NLP systems for CDS, and the current solutions to challenges posed by distinct sublanguages, intended user groups, and support goals.
PLoS ONEThe Co-Morbidity Burden of Children and Young Adults with Autism Spectrum Disorders
556 Citations2012Isaac S. Kohane, Andrew McMurry +9 more
The comorbidities of ASD encompass disease states that are significantly overrepresented in ASD with respect to even the patient populations of tertiary health centers and requires broad multidisciplinary management that payors and providers will have to plan for.
Briefings in BioinformaticsExploiting drug-disease relationships for computational drug repositioning
531 Citations2011Joel T. Dudley, Teja Achyut Deshpande +1 more
In this review, it is shown that computational methods for drug repositioning can be classified in two axes: drug based, where discovery initiates from the chemical perspective, or disease based,where discovery begins from the clinical perspective of disease or its pathology.
Journal of the American Medical Informatics AssociationExtracting medication information from clinical text
471 Citations2010Özlem Uzuner, Imre Solti +1 more
Although rule-based systems dominated the top 10, the best performing system was a hybrid and durations and reasons were the most difficult for all systems to detect.
Journal of the American Medical Informatics AssociationEvaluating the State-of-the-Art in Automatic De-identification
456 Citations2007Özlem Uzuner, Yuan Luo +1 more
An overview of this de-identification challenge is provided, the data and the annotation process are described, the evaluation metrics are explained, the nature of the systems that addressed the challenge are discussed, the results of received system runs are analyzed, and directions for future research are identified.
PLoS Computational BiologyGetting More Out of Biomedical Documents with GATE's Full Lifecycle Open Source Text Analytics
363 Citations2013Hamish Cunningham, Valentin Tablan +2 more
It is concluded that the deployment of text mining for document abstraction or rich search and navigation is best thought of as a process, and that with the right computational tools and data collection strategies this process can be made defined and repeatable.
Arthritis Care & ResearchElectronic medical records for discovery research in rheumatoid arthritis
347 Citations2010Katherine P. Liao, Tianxi Cai +10 more
This work assessed whether a classification algorithm incorporating narrative EMR data (typed physician notes) more accurately classifies subjects with rheumatoid arthritis (RA) compared with an algorithm using codified EMRData alone.
Journal of the American Medical Informatics AssociationUse of diverse electronic medical record systems to identify genetic risk for type 2 diabetes within a genome-wide association study
309 Citations2011Abel Kho, M. Geoffrey Hayes +18 more
An algorithm using commonly available data from five different EMR data collected through routine clinical care can accurately identify type 2 diabetes cases and controls for genetic study across multiple institutions.
Journal of the American Medical Informatics AssociationOvercoming barriers to NLP for clinical text: the role of shared tasks and the need for additional creative solutions
307 Citations2011Wendy W. Chapman, Prakash M. Nadkarni +4 more
This issue of JAMIA focuses on natural language processing (NLP) techniques for clinical-text information extraction and shared tasks like the i2b2/VA Challenge, a shared-task challenge co-sponsored by the Veteran's Administration for the last 2 years.
Journal of Biomedical SemanticsClinical Natural Language Processing in languages other than English: opportunities and challenges
291 Citations2018Aurélie Névéol, Hercules Dalianis +3 more
This paper offers the first broad overview of clinical Natural Language Processing for languages other than English and identifies major challenges and opportunities that will affect the impact of NLP on clinical practice and public health studies in a context that encompasses English as well as other languages.
PLoS Computational BiologyUsing Electronic Patient Records to Discover Disease Correlations and Stratify Patient Cohorts
284 Citations2011Francisco S. Roque, Peter Bjødstrup Jensen +10 more
A general approach for gathering phenotypic descriptions of patients from medical records in a systematic and non-cohort dependent manner is described, which shows how records from a Danish psychiatric hospital lead to the identification of disease correlations, which subsequently can be mapped to systems biology frameworks.
Transactions of the Association for Computational LinguisticsTemporal Annotation in the Clinical Domain
243 Citations2014William F. Styler, Steven Bethard +9 more
The implementation and extension of ISO-TimeML for annotating a corpus of clinical notes, known as the THYME corpus, is discussed and a new annotation guideline has been developed, “the THyME Guidelines to ISO- timeML (THYME-Time ML)”.
Cross-lingual Word Clusters for Direct Transfer of Linguistic Structure
239 Citations2012Oscar Täckström, Ryan McDonald +1 more
It is shown that by augmenting direct-transfer systems with cross-lingual cluster features, the relative error of delexicalized dependency parsers, trained on English treebanks and transferred to foreign languages, can be reduced by up to 13%.
Journal of the American Medical Informatics AssociationPortability of an algorithm to identify rheumatoid arthritis in electronic health records
238 Citations2012Robert J. Carroll, Will K Thompson +18 more
Electronic phenotype algorithms allow rapid identification of case populations in multiple sites with little retraining and are portable to two external hospitals using different EHR systems, different NLP systems, and different target NLP vocabularies.
Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015)
234 Citations2015Ojha, Atul Kr., Doğruöz, A. Seza +4 more
PubMedThe open biomedical annotator.
234 Citations2009Clément Jonquet, Nigam H. Shah +1 more
The Open Biomedical Annotator (OBA) is presented, an ontology-based Web service that annotates public datasets with biomedical ontology concepts based on their textual metadata ( www.bioontology.org).
Language Resources and EvaluationMultilingual and cross-domain temporal tagging
214 Citations2012Jannik Strötgen, Michael Gertz
The authors' publicly available temporal tagger HeidelTime is presented, which is easily extensible to further languages due to its strict separation of source code and language resources like patterns and rules.
SemEval-2014 Task 7: Analysis of Clinical Text
214 Citations2014Sameer Pradhan, Noémie Elhadad +3 more
This task was a follow-up to the ShARe/CLEF eHealth 2013 shared task, subtasks 1a and 1b, 2 but using a larger test set and the best group had the best strict accuracy.
Journal of the American Medical Informatics AssociationA comprehensive study of named entity recognition in Chinese clinical text
192 Citations2013Jianbo Lei, Bo Tang +4 more
It was showed that most types of feature were beneficial to Chinese NER systems, although the improvements were limited, and the system achieved the highest performance by combining word segmentation and section information, indicating that these two types of feature complement each other.
Inflammatory Bowel DiseasesImproving Case Definition of Crohnʼs Disease and Ulcerative Colitis in Electronic Medical Records Using Natural Language Processing
179 Citations2013Ashwin N. Ananthakrishnan, Tianxi Cai +14 more
Inclusion of narrative concepts identified using natural language processing improves the accuracy of electronic medical records case definition for CD and UC while simultaneously identifying more subjects compared with models using codified data alone.
Cancer ResearchUse of Natural Language Processing to Extract Clinical Cancer Phenotypes from Electronic Medical Records
177 Citations2019Guergana Savova, Ioana Danciu +6 more
Given the interdisciplinary nature of the fields of oncology and information extraction, this analysis serves as a critical trail marker on the path to higher fidelity oncologists phenotypes from real-world data.
SemEval-2015 Task 6: Clinical TempEval
173 Citations2015Steven Bethard, Leon Derczynski +3 more
Clinical TempEval 2015 brought the temporal information extraction tasks of past TempEeval campaigns to the clinical domain, with the best systems achieving near-human performance on identifying events and times, but with a large performance gap still remaining for temporal relations.
Clinical Pharmacology & TherapeuticsThe Emerging Role of Electronic Medical Records in Pharmacogenomics
171 Citations2011Russell A. Wilke, Hua Xu +8 more
This review explores each of these translational mechanisms within a historical framework for the field of pharmacogenomics through three distinct mechanisms: retrospective assessment of previously known findings in a clinical practice‐based setting, discovery of new associations in huge observational cohorts, and prospective application in a setting capable of providing real‐time decision support.
Journal of the American Medical Informatics AssociationA translational engine at the national scale: informatics for integrating biology and the bedside
155 Citations2011Isaac S. Kohane, Susanne Churchill +1 more
i2b2 has been used to generate genome-wide studies at less than one tenth of the cost and one tenth the time of conventionally performed studies as well as to identify important risk from commonly used medications.
Journal of Biomedical InformaticsRule-based information extraction from patients’ clinical data
146 Citations2009Agnieszka Mykowiecka, Małgorzata Marciniak +1 more
A rule-based information extraction (IE) system developed for Polish medical texts, which addressed such linguistic issues as: ambiguous keywords, negation, coordination or anaphoric expressions is described.
Journal of the American Medical Informatics AssociationLeveraging informatics for genetic studies: use of the electronic medical record to enable a genome-wide association study of peripheral arterial disease
141 Citations2010Iftikhar J. Kullo, Jin Fan +4 more
PLoS ONENegation’s Not Solved: Generalizability Versus Optimizability in Clinical Natural Language Processing
121 Citations2014Stephen Wu, Timothy A. Miller +5 more
This work proposes that an optimizable solution does not equal a generalizable solution, and introduces a new machine learning-based Polarity Module for detecting negation in clinical text, and extensively compare its performance across domains.
Journal of Biomedical InformaticsAutomatic recognition of disorders, findings, pharmaceuticals and body structures from clinical text: An annotation and machine learning study
118 Citations2014Maria Skeppstedt, Maria Kvist +2 more
The entity recognition results for the individual entities Disorder and Finding show that it is meaningful to separate the general category Medical Problem into these two more granular entity types, e.g. for knowledge mining of co-morbidity relations and disorder-finding relations.
Journal of the American Medical Informatics AssociationNormalization and standardization of electronic health records for high-throughput phenotyping: the SHARPn consortium
115 Citations2013Jyotishman Pathak, Kent R. Bailey +30 more
A data-normalization platform that ensures data security, end-to-end connectivity, and reliable data flow within and across institutions is developed and demonstrated by executing a QDM-based MU quality measure that determines the percentage of patients between 18 and 75 years with diabetes whose most recent low-density cholesterol test result during the measurement year was <100 mg/dL.
Self-training for biomedical parsing
115 Citations2008David McClosky, Eugene Charniak
This work self-train the standard Charniak/Johnson Penn-Treebank parser using unlabeled biomedical abstracts, achieving an f-score of 84.3% and a 20% error reduction over the best previous result on biomedical data.
International Journal of Medical InformaticsmedSynDiKATe—a natural language system for the extraction of medical information from findings reports
110 Citations2002Udo Hahn, Martin Romacker +1 more
The strong demands MEDSYNDIKATE poses on the availability of expressive knowledge sources are accounted for by two alternative approaches to acquire medical domain knowledge (semi)automatically.
BMC BioinformaticsNatural language processing of radiology reports for the detection of thromboembolic diseases and clinically relevant incidental findings
108 Citations2014Anne-Dominique Pham, Aurélie Névéol +6 more
This study demonstrates the benefits of developing an automated method to identify medical concepts, modality and relations from radiology reports in French by evaluating the combination of NLP and machine learning to detect thromboembolic disease diagnosis and incidental clinically relevant findings from angiography and venography reports written in French.
Journal of Biomedical SemanticsSynonym extraction and abbreviation expansion with ensembles of semantic spaces
97 Citations2014Aron Henriksson, Hans Moen +3 more
It is demonstrated that ensembles of semantic spaces can yield improved performance on the tasks of automatically extracting synonyms and abbreviation-expansion pairs, potentially allowing enhanced performance to be obtained on a wide range of natural language processing tasks.
Journal of Digital ImagingDiscerning Tumor Status from Unstructured MRI Reports—Completeness of Information in Existing Reports and Utility of Automated Natural Language Processing
96 Citations2009Lionel Tim‐Ee Cheng, Jiaping Zheng +2 more
Most reports contained sufficient information for tumor status determination, though variable features were used to describe status, and NLP demonstrated good accuracy for tumors status classification and may have novel application for automated disease status classification from electronic databases.
PLoS ONEAutomatic Prediction of Rheumatoid Arthritis Disease Activity from the Electronic Medical Records
96 Citations2013Chen Lin, Elizabeth W. Karlson +10 more
Automatic Rheumatoid Arthritis disease activity discovery from Electronic Medical Record data is a learnable task approximating human performance and might have several research applications, such as the identification of patients for genome-wide pharmacogenetic studies that require large sample sizes with precise definitions of disease activity and response to therapies.
Journal of Biomedical InformaticsOn the creation of a clinical gold standard corpus in Spanish: Mining adverse drug reactions
90 Citations2015Maite Oronoz, Koldo Gojenola +3 more
The creation of the IxaMed-GS gold standard composed of real electronic health records written in Spanish and manually annotated by experts in pharmacology and pharmacovigilance, and used for the automatic extraction of adverse drug reaction events using machine learning.
Journal of the American Medical Informatics AssociationDictionary construction and identification of possible adverse drug events in Danish clinical narrative text
89 Citations2013Robert Eriksson, Peter Bjødstrup Jensen +3 more
A dictionary-building method that allows synonyms to be identified and anatomical location descriptions can be merged to allow appropriate grouping of effects in the same location and could be used to identify possible ADEs in Danish clinical narratives.
Journal of Korean Medical ScienceA De-identification Method for Bilingual Clinical Texts of Various Note Types
77 Citations2014Soo-Yong Shin, Yu Rang Park +8 more
This study proposes a regular expression-based de-identification method used to address bilingual clinical records written in Korean and English and successfully removed the identifiers in diverse types of bilingual clinical narrative texts.
Journal of the American Medical Informatics AssociationJoint segmentation and named entity recognition using dual decomposition in Chinese discharge summaries
74 Citations2013Yan Xu, Yining Wang +6 more
The joint model is efficient and effective in both segmentation and recognition compared with the two individual tasks, and achieves encouraging results, demonstrating the feasibility of the two tasks.
PubMedExtending the NegEx lexicon for multiple languages.
74 Citations2013Wendy W. Chapman, Dieter Hillert +8 more
Natural Language EngineeringA Reference Architecture for Natural Language Generation Systems
74 Citations2006Chris Mellish, Donia Scott +4 more
The RAGS (Reference Architecture for Generation Systems) framework is presented: a specification of an abstract Natural Language Generation system architecture to support sharing, re-use, comparison and evaluation of NLG technologies.
Journal of Biomedical InformaticsExtracting important information from Chinese Operation Notes with natural language processing methods
72 Citations2014Hui Wang, Weide Zhang +4 more
The development and evaluation of extracting tumor-related information from operation notes of hepatic carcinomas which were written in Chinese are reported and both rule-based and supervised machine-learning approaches are explored.
Proceedings of the BioNLP 2018 workshop
71 Citations2018Dina Demner-Fushman, Kevin Cohen +2018 more
International Journal of Methods in Psychiatric ResearchUse of emergency department electronic medical records for automated epidemiological surveillance of suicide attempts: a French pilot study
70 Citations2016Marie-Hélène Metzger, Nastassia Tvardik +4 more
It is demonstrated that machine‐learning methods can improve the quality of epidemiological indicators as compared to current national surveillance of suicide attempts.
Systematic ReviewsData extraction from machine-translated versus original language randomized trial reports: a comparative study
69 Citations2013Ethan M. Balk, Mei Chung +3 more
Using machine translation has the potential to reduce language bias in systematic reviews; however, pending additional empirical data, reviewers should be cautious about using translated data.
Journal of Biomedical SemanticsNegation detection in Swedish clinical text: An adaption of NegEx to Swedish
69 Citations2011Maria Skeppstedt
The precision was significantly lower for the Swedish adaptation of the English rule-based negation detection system NegEx than published results for the English version, but it was concluded that the same trigger phrase approach is possible in a Swedish context, even though it needs to be further developed.
Clinical Pharmacology & TherapeuticsArtificial intelligence (AI) systems for interpreting complex medical datasets
69 Citations2017Russ B. Altman
Artificial intelligence applications in medical data have several technical challenges: complex and heterogeneous datasets, noisy medical datasets, and explaining their output to users.
BMC BioinformaticsBilingual term alignment from comparable corpora in English discharge summary and Chinese discharge summary
65 Citations2015Yan Xu, Luoxin Chen +6 more
The experiments have shown that the LP-based method augmented with the term alignment method will contribute to reduction of manual work required to compile a bilingual sydictionary of clinical terms.
Journal of Biomedical InformaticsSpeculation detection for Chinese clinical notes: Impacts of word segmentation and embedding models
63 Citations2016Shaodian Zhang, Tian Kang +4 more
It is demonstrated that word segmentation is critical to produce high quality word embedding to facilitate downstream information extraction applications, and it is suggested that a domain dependent word segmenter can be vital to such a clinical NLP task in Chinese language.
BMC BioinformaticsContextD: an algorithm to identify contextual properties of medical terms in a Dutch clinical corpus
61 Citations2014Zubair Afzal, Ewoud Pons +4 more
The ContextD showed good performance in identifying negation and experiencer property values across all Dutch clinical document types and accurate identification of the temporality property proved to be difficult and requires further work.
Journal of Biomedical SemanticsDe-identifying Swedish clinical text - refinement of a gold standard and experiments with Conditional random fields
57 Citations2010Hercules Dalianis, Sumithra Velupillai
Journal of Biomedical InformaticsAn enhanced CRFs-based system for information extraction from radiology reports
56 Citations2013Andrea Esuli, Diego Marcheggiani +1 more
Two novel approaches to IE for radiology reports are presented: a cascaded, two-stage method based on pipelining two taggers generated via the well known linear-chain conditional random fields learner and a confidence-weighted ensemble method that combines standard LC-CRFs and the proposed two- stage method.
Journal of the American Medical Informatics AssociationA multilingual gold-standard corpus for biomedical concept recognition: the Mantra GSC
55 Citations2015Jan A. Kors, Simon Clematide +3 more
This is the first gold-standard corpus for biomedical concept recognition in languages other than English, and the inter-annotator agreement scores provide a reference standard for gauging the performance of automatic annotation techniques.
Lecture notes in computer scienceAn Approach to Detect Negation on Medical Documents in Spanish
53 Citations2014Roberto Costumero, Federico López +3 more
The adoption of hospital EHR technology is significantly growing and expected to grow, and there seems to be no algorithm for negation detection in medical texts written in that language.
A Unified Multilingual Semantic Representation of Concepts
53 Citations2015José Camacho-Collados, Mohammad Taher Pilehvar +1 more
A novel multilingual concept representation, called MUFFIN, is put forward, which not only enables accurate representation of word senses in different languages, but also provides multiple advantages over existing approaches.
Computers in Biology and MedicineUnsupervised entity and relation extraction from clinical records in Italian
52 Citations2016Anita Alicante, Anna Corazza +2 more
The unsupervised approach proposed is promising and well suited for a semi-automatic labelling of the extracted relations, and has been tested on a fairly large data set of clinical records in Italian.
BMC Medical Informatics and Decision MakingDetection of sentence boundaries and abbreviations in clinical narratives
49 Citations2015Markus Kreuzthaler, Stefan Schulz
Sentence detection is an important task, which should be performed at the beginning of a text processing pipeline, and it was shown that support vector machines exploiting a linear kernel produce state of the art results for sentence boundary detection.
BMJAssociation between randomised trial evidence and global burden of disease: cross sectional study (Epidemiological Study of Randomized Trials--ESORT)
48 Citations2015Connor A. Emdin, Ayodele Odutayo +5 more
Overall, a weak association existed between global burden of disease and number of published randomised trials, and a global observatory for research is needed to monitor and reduce the discordance between the output ofrandomised trials and globalurden of disease.
Journal of Biomedical SemanticsA shortest-path graph kernel for estimating gene product semantic similarity
47 Citations2011Marco A. Alvarez, Xiaojun Qi +1 more
Spgk uses a graph kernel method in polynomial time to exploit the structure of the GO to calculate semantic similarity between gene products, and provides an alternative to both methods that use external resources and "intrinsic" methods with comparable performance.
Journal of Biomedical SemanticsExpansion of medical vocabularies using distributional semantics on Japanese patient blogs
46 Citations2016Magnus Ahltorp, Maria Skeppstedt +4 more
Different settings for corpus pre-processing, window sizes and cluster sizes were suitable for different semantic categories and for different lengths of candidate lists, showing the need to adapt parameters, not only to the language and text genre used, but also to the semantic category for which the vocabulary is to be expanded.
Journal of Biomedical InformaticsDe-identification of clinical notes in French: towards a protocol for reference corpus development
45 Citations2014Cyril Grouin, Aurélie Névéol
Behavior Research MethodsUnraveling the linguistic nature of specific autobiographical memories using a computerized classification algorithm
44 Citations2016Keisuke Takano, Mayumi Ueno +4 more
The present study explored the linguistic nature of specific memories generated with the Autobiographical Memory Test by developing a computerized classifier that distinguishes between specific and nonspecific memories, suggesting that memory specificity can be identified with a relatively small number of words.
PubMedClinical Information Extraction at the CLEF eHealth Evaluation lab 2016.
43 Citations2016Aurélie Névéol, Kevin Bretonnel Cohen +9 more
The task continued with named entity recognition and normalization in French narratives, and introduced a large-scale classification task in French death certificates, which consisted of extracting causes of death as coded in the International Classification of Diseases, tenth revision (ICD10).
BMC OphthalmologyCataract research using electronic health records
42 Citations2011Carol Waudby, Richard L. Berg +5 more
Using electronic health records can be a viable and efficient tool to identify cataracts for research, however, using retrospective data from this source can be confounded by historical limits on data availability, differences in the utilization of healthcare, and changes in exposures over time.
BMC Medical Informatics and Decision MakingCare episode retrieval: distributional semantic models for information retrieval in the clinical domain
42 Citations2015Hans Moen, Filip Ginter +4 more
Several methods for information retrieval, focusing on care episode retrieval, based on textual similarity, are presented, which suggest that several of the methods proposed outperform a state-of-the art search engine (Lucene) on the retrieval task.
Journal of the American Medical Informatics AssociationFunctional evaluation of out-of-the-box text-mining tools for data-mining tasks
42 Citations2014Kenneth Jung, Paea LePendu +4 more
For a variety of tasks, employing simple term recognition methods instead of advanced NLP methods results in little or no impact on accuracy when using large datasets, while simpler dictionary-based methods have the advantage of scaling well to very large datasets.
Artificial Intelligence in MedicineCue-based assertion classification for Swedish clinical text—Developing a lexicon for pyConTextSwe
41 Citations2014Sumithra Velupillai, Maria Skeppstedt +5 more
An extensive and useful assertion lexicon for Swedish clinical text is created, which could form a valuable resource for similar studies, and which is publicly available.
Proceedings of the 15th Workshop on Biomedical Natural Language Processing
41 Citations2016Kevin Cohen, Sophia Ananiadou +2610 more
Text, speech and language technologyEvaluating the Impact of Re-training a Lexical Disambiguation Model on Domain Adaptation of an HPSG Parser
41 Citations2010Tadayoshi Hara, Yusuke Miyao +1 more
Experimental results show that the combination of the proposed method and the existing method achieves parsing accuracy that is as high as that of an HPSG parser retrained from scratch, but with much lower training cost.
Syntactic methods for negation detection in radiology reports in Spanish
41 Citations2016Viviana Cotik, Vanesa Stricker +2 more
Different algorithms developed to determine if a term of interest is under the scope of negation in radiology reports written in Spanish are introduced and outperform a simple dictionary lookup algorithm developed as baseline.
Artificial Intelligence in MedicineAdaptation of machine translation for multilingual information retrieval in the medical domain
39 Citations2014Pavel Pecina, Ondřej Dušek +12 more
Most of the MT techniques employed in the experiments improve MT of medical search queries and translation quality does not appear to correlate with the IR performance - better translation does not necessarily yield better retrieval.
Journal of Biomedical InformaticsTranslating medical terminologies through word alignment in parallel text corpora
38 Citations2009Louise Deléger, Magnus Merkel +1 more
Good quality new translations of medical terms based on word alignment in parallel text corpora are obtained, which underlines the suitability of using alignment inText corpora to help translating terminologies.
Applying deep learning on electronic health records in Swedish to predict healthcare-associated infections
38 Citations2016Olof H. Jacobson, Hercules Dalianis
The results indicate that there was room for improvement and therefore deep learning methods were applied and a network of stacked sparse auto encoders and stacked restricted Boltzmann machines were implemented.
Journal of Biomedical InformaticsPredicting patient acuity from electronic patient records
37 Citations2014Elina Kontio, Antti Airola +6 more
By applying language technology to electronic patient documents it is possible to accurately predict the value of the acuity scores of the coming day based on the previous daýs assigned scores and nursing notes.
Journal of Biomedical SemanticsCharacteristics of Finnish and Swedish intensive care nursing narratives: a comparative analysis to support the development of clinical language technologies
35 Citations2011Helen Allvin, Elin Carlsson +12 more
A comparison of characteristics in Finnish and Swedish free-text nursing narratives from intensive care creates a framework for characterising and comparing clinical text and lays the groundwork for developing clinical language technologies.
Yearbook of Medical InformaticsClinical Natural Language Processing in 2014: Foundational Methods Supporting Efficient Healthcare
35 Citations2015Aurélie Névéol, Pierre Zweigenbaum +1 more
The field of clinical NLP is thriving through the contributions of both NLP researchers and healthcare professionals interested in applying NLP techniques for concrete healthcare purposes, and is becoming mature for practical applications with a significant clinical impact.
Proceedings of the Fourth Linguistic Annotation Workshop
34 Citations2010Nianwen Xue, Massimo Poesio
This year's LAW provides a forum to facilitate the exchange and propagation of research results concerned with the annotation, manipulation, and exploitation of corpora, and work towards the harmonization and interoperability from the perspective of the increasingly large number of tools and frameworks for annotated language resources.
Journal of Biomedical InformaticsSecondary use of electronic health records for building cohort studies through top-down information extraction
32 Citations2014Markus Kreuzthaler, Stefan Schulz +1 more
A cohort study based on a cohort study highlights challenges for mining electronic health records targeting free text entry fields within semi-structured data sources and highlights challenges and future directions for the secondary use of routine data in general.
International Journal of Environmental Research and Public HealthUtilizing Chinese Admission Records for MACE Prediction of Acute Coronary Syndrome
31 Citations2016Danqing Hu, Zhengxing Huang +4 more
Experimental results reveal that using admission records can effectively provide MACE prediction service for ACS patients at the early stage of their hospitalizations, and indicates that the proposed approach can obtain competitive performance in Mace prediction.
BioMed Research InternationalNatural Language Processing Based Instrument for Classification of Free Text Medical Records
29 Citations2016Manana Khachidze, Magda Tsintsadze +1 more
The present work introduces the instrument for classification of medical records based on the Georgian language, the first attempt of such classification of the Georgia language based medical records, and the overall results of the study were successful.
International Conference on Computational LinguisticsNegation Detection in Clinical Reports Written in German.
29 Citations2016Viviana Cotik, Roland Roller +4 more
This work presents a system for detecting mentions of clinical findings that are negated or just speculated in German clinical texts, built on top of NegEx, a well known algorithm for identifying non-factive mentions of medical findings.
Studies in health technology and informaticsCan Multilingual Machine Translation Help Make Medical Record Content More Comprehensible to Patients?
27 Citations2010Qing Zeng‐Treitler, Kim Hyeoneui +2 more
This study used a popular general-purpose machine translation tool called Babel Fish to translate 213 medical record sentences from English into Spanish, Chinese, Russian and Korean, and found that the majority of translations were incomprehensible and/or incorrect.
BMC OphthalmologyTrends in refractive surgery at an academic center: 2007-2009
27 Citations2011Irene C. Kuo
The characteristics of patients completing excimer laser refractive surgery and the types of procedures performed in the summer quarter in 2007 and the same quarter in 2009 at an academic center were compared to determine whether the volume of astigmatism- or presbyopia-correcting intraocular lenses (IOLs) has concurrently changed.
International Journal of Medical InformaticsProposal and evaluation of FASDIM, a Fast And Simple De-Identification Method for unstructured free-text clinical records
26 Citations2013Emmanuel Chazard, Capucine Mouret +4 more
FASDIM gets good results in French and is freely available and it is easy to implement and does not require any predefined dictionary.
BMC BioinformaticsCombining MEDLINE and publisher data to create parallel corpora for the automatic translation of biomedical text
24 Citations2013Antonio Jimeno Yepes, Élise Prieur-Gaston +1 more
It is shown how a large-sized parallel corpus can automatically be obtained for the biomedical domain, using the MEDLINE database, and a statistical machine translation model is trained that outperforms previous models for automatic translation of biomedical text.
PubMedStatistical machine translation for biomedical text: are we there yet?
24 Citations2011Cuijun Wu, Fei Xia +2 more
This paper addressed the research question: "Has machine translation achieved sufficiently high quality to translate PubMed titles for patients?", and evaluated Google Translate's performance specifically within the biomedical domain.
Yearbook of Medical InformaticsClinical Natural Language Processing in 2015: Leveraging the Variety of Texts of Clinical Interest
23 Citations2016Pierre Zweigenbaum, A. Névéol +1 more
The clinical NLP best paper selection shows thatclinical NLP is making use of a variety of texts of clinical interest to contribute to the analysis of clinical information and the building of a body of clinical knowledge.
BMC Medical Informatics and Decision MakingSNOMED CT in a language isolate: an algorithm for a semiautomatic translation
23 Citations2015Olatz Perez-de-Viñaspre, Maite Oronoz
The first attempt to semi-automatically translate the SNOMED CT terminology content to Basque, a less resourced language is presented, to use the authors' language to access rich multilingual resources and to strengthen the use of the Basque language in the biomedical area.
Overview of the NTCIR-11 MedNLP-2 Task
23 Citations2014Eiji Aramaki, Mizuki Morita +2 more
Results are presented of groups with discussions that are to clarify the issues to be resolved in medical natural language processing fields to evaluate technologies to retrieve important information from medical reports written in Japanese.
BMC Medical Informatics and Decision MakingRecent advances in Swedish and Spanish medical entity recognition in clinical texts using deep neural approaches
22 Citations2019Rebecka Weegar, Alicia Pérez +2 more
A recurrent neural network with in-domain embeddings improved the medical named entity recognition compared to shallow learning methods, showing this combination to be suitable for entity recognition in clinical text for both languages.
British Journal of CancerBreast cancer: patient information needs reflected in English and German web sites
22 Citations2004Christian Weißenberger, Sinje Jonassen +9 more
The results have implications for patient education by physicians and may help to improve patient support by tailoring information, considering the weak points in information provision by web sites and intercultural differences in patient needs.
PubMedAutomatic computation of CHA2DS2-VASc score: information extraction from clinical texts for thromboembolism risk assessment.
22 Citations2011Cyril Grouin, Louise Deléger +6 more
A system based on natural language processing (lexicon and linguistic modules), including negation and speculation handling, which extracts medical concepts from French clinical records and uses them as criteria to compute the CHA2DS2-VASc score is presented.
International Journal of Medical InformaticsMorphosemantic parsing of medical compound words: Transferring a French analyzer to English
21 Citations2008Louise Deléger, Fiammetta Namer +1 more
The adaptation of a morphosemantic analyzer dedicated to French (DériF) to analyze English medical neo-classical compounds confirmed the hypothesis of transferability and can produce more complete analyses of English medical compounds than existing systems.
…