Skip header and navigation

Refine By

28 records – page 1 of 3.

Abbreviations in Swedish Clinical Text--use by three professions.

https://arctichealth.org/en/permalink/ahliterature262983
Source
Stud Health Technol Inform. 2014;205:720-4
Publication Type
Article
Date
2014
Author
Elin Lövestam
Sumithra Velupillai
Maria Kvist
Source
Stud Health Technol Inform. 2014;205:720-4
Date
2014
Language
English
Publication Type
Article
Keywords
Abbreviations as Topic
Electronic Health Records - classification - statistics & numerical data
Natural Language Processing
Nurses - statistics & numerical data
Nutritionists - statistics & numerical data
Physicians - statistics & numerical data
Sweden
Terminology as Topic
Abstract
A list of 266 abbreviations from dieticians' notes in patient records was used to extract the same abbreviations from patient records written by three professions: dieticians, nurses and physicians. A context analysis of 40 of the abbreviations showed that ambiguous meanings were common. Abbreviations used by dieticians were found to be used by other professions, but not always with the same meaning. This ambiguity of abbreviations might cause misunderstandings and put patient safety at risk.
PubMed ID
25160281 View in PubMed
Less detail

An example of an application of the semiotic inspection method in the domain of computerized patient record system.

https://arctichealth.org/en/permalink/ahliterature261683
Source
Stud Health Technol Inform. 2013;192:471-5
Publication Type
Article
Date
2013
Author
Weronika Tancredi
Olof Torgersson
Source
Stud Health Technol Inform. 2013;192:471-5
Date
2013
Language
English
Publication Type
Article
Keywords
Dental Records
Electronic Health Records
Health Records, Personal
Natural Language Processing
Software
Software Validation
Sweden
User-Computer Interface
Workflow
Abstract
Efficiently navigating through an interface and conducting work tasks in flow is what GUI designers strive for. Dental professionals, who alternate between examination and treatment of a patient and insertion of data into the Computerized Patient Record system, particularly need an interface that would facilitate the workflow. In this paper we present an inspection evaluation of an existing and widely used Computerized Patient Record system. The Semiotic Inspection Method was applied with the expectation that the method could provide evidence that task flow, navigation and wayfinding were major usability issues of the interface. Also expected was that the Semiotic Inspection would reveal the means and strategies used in the interface in order to communicate the flow. The analysis conducted using the Semiotic Inspection Method showed inconsistencies in the communication of the way forward through the interface. In addition, the profile of the users, regarding digital skills, appears to be ambiguous. Finally, the strategies used in the interface for conveying the workflow could be identified as well.
PubMed ID
23920599 View in PubMed
Less detail

Automated Spelling Correction for Clinical Text Mining in Russian.

https://arctichealth.org/en/permalink/ahliterature305544
Source
Stud Health Technol Inform. 2020 Jun 16; 270:43-47
Publication Type
Journal Article
Date
Jun-16-2020
Author
Ksenia Balabaeva
Anastasia Funkner
Sergey Kovalchuk
Author Affiliation
ITMO University, Saint Petersburg, Russia.
Source
Stud Health Technol Inform. 2020 Jun 16; 270:43-47
Date
Jun-16-2020
Language
English
Publication Type
Journal Article
Keywords
Algorithms
Data Mining
Electronic Health Records
Language
Machine Learning
Natural Language Processing
Russia
Abstract
The main goal of this paper is to develop a spell checker module for clinical text in Russian. The described approach combines string distance measure algorithms with technics of machine learning embedding methods. Our overall precision is 0.86, lexical precision - 0.975 and error precision is 0.74. We develop spell checker as a part of medical text mining tool regarding the problems of misspelling, negation, experiencer and temporality detection.
PubMed ID
32570343 View in PubMed
Less detail

The connection between terms used in medical records and coding system: a study on Swedish primary health care data.

https://arctichealth.org/en/permalink/ahliterature193243
Source
Med Inform Internet Med. 2001 Apr-Jun;26(2):87-99
Publication Type
Article
Author
H. Petersson
G. Nilsson
L E Strender
H. Ahlfeldt
Author Affiliation
Medical Informatics, Linköpings universitet, Linköping, Sweden. hakan.petersson@imt.liu.se
Source
Med Inform Internet Med. 2001 Apr-Jun;26(2):87-99
Language
English
Publication Type
Article
Keywords
Abstracting and Indexing as Topic
Artificial Intelligence
Forms and Records Control
Humans
Medical Informatics - standards
Medical Records Systems, Computerized - classification
Models, Theoretical
Natural Language Processing
Primary Health Care
Sweden
Terminology as Topic
Abstract
Implementation of problem lists and their relation to standardized coding systems have been approached and analysed in different ways. Most evaluations concern quantitative aspects such as content coverage in a specific domain. In order to reveal the qualitative aspects of diagnostic coding, medical record texts from primary health care encounters were compared with terms from a coding system that was used for describing them statistically. The records were coded by six general practitioners, and in some cases, an applied diagnostic term was found within the text, while other record text-coding system relationships were categorized as synonyms, alternative terms, and interpretations. Thus, the categories roughly corresponded to a measure of semantic distance between the terms in the record text and the rubrics of the coding system, and there was a correlation between semantic distance and inter-rater agreement. The subcategories of this scheme corresponded fairly well to recently published desiderata for clinical terminology servers, including functionality such as word normalization and spelling correction. However, not all problems could have been automatically coded by means of lexical methods, which can be partly explained by the fact that diagnostic coding also relies on clinical knowledge. In addition, proper automation relies on context representation within the records.
PubMed ID
11560294 View in PubMed
Less detail

Cue-based assertion classification for Swedish clinical text--developing a lexicon for pyConTextSwe.

https://arctichealth.org/en/permalink/ahliterature261420
Source
Artif Intell Med. 2014 Jul;61(3):137-44
Publication Type
Article
Date
Jul-2014
Author
Sumithra Velupillai
Maria Skeppstedt
Maria Kvist
Danielle Mowery
Brian E Chapman
Hercules Dalianis
Wendy W Chapman
Source
Artif Intell Med. 2014 Jul;61(3):137-44
Date
Jul-2014
Language
English
Publication Type
Article
Keywords
Artificial Intelligence
Cues
Electronic Health Records
Humans
Language
Natural Language Processing
Semantics
Sweden
Translations
Uncertainty
Vocabulary, Controlled
Abstract
The ability of a cue-based system to accurately assert whether a disorder is affirmed, negated, or uncertain is dependent, in part, on its cue lexicon. In this paper, we continue our study of porting an assertion system (pyConTextNLP) from English to Swedish (pyConTextSwe) by creating an optimized assertion lexicon for clinical Swedish.
We integrated cues from four external lexicons, along with generated inflections and combinations. We used subsets of a clinical corpus in Swedish. We applied four assertion classes (definite existence, probable existence, probable negated existence and definite negated existence) and two binary classes (existence yes/no and uncertainty yes/no) to pyConTextSwe. We compared pyConTextSwe's performance with and without the added cues on a development set, and improved the lexicon further after an error analysis. On a separate evaluation set, we calculated the system's final performance.
Following integration steps, we added 454 cues to pyConTextSwe. The optimized lexicon developed after an error analysis resulted in statistically significant improvements on the development set (83% F-score, overall). The system's final F-scores on an evaluation set were 81% (overall). For the individual assertion classes, F-score results were 88% (definite existence), 81% (probable existence), 55% (probable negated existence), and 63% (definite negated existence). For the binary classifications existence yes/no and uncertainty yes/no, final system performance was 97%/87% and 78%/86% F-score, respectively.
We have successfully ported pyConTextNLP to Swedish (pyConTextSwe). We have created an extensive and useful assertion lexicon for Swedish clinical text, which could form a valuable resource for similar studies, and which is publicly available.
Notes
Cites: J Am Med Inform Assoc. 2010 Nov-Dec;17(6):696-70120962133
Cites: J Am Med Inform Assoc. 2011 Sep-Oct;18(5):563-721515542
Cites: J Am Med Inform Assoc. 2011 Sep-Oct;18(5):557-6221565856
Cites: J Am Med Inform Assoc. 2011 Sep-Oct;18(5):552-621685143
Cites: J Biomed Inform. 2011 Oct;44(5):728-3721459155
Cites: J Am Med Inform Assoc. 2001 Nov-Dec;8(6):598-60911687566
Cites: J Biomed Inform. 2001 Oct;34(5):301-1012123149
Cites: J Am Med Inform Assoc. 1994 Mar-Apr;1(2):161-747719797
Cites: J Am Med Inform Assoc. 1999 Sep-Oct;6(5):393-41110495099
Cites: BMC Bioinformatics. 2008;9 Suppl 11:S1019025686
Cites: BMC Bioinformatics. 2008;9 Suppl 11:S919025695
Cites: J Am Med Inform Assoc. 2009 Jan-Feb;16(1):109-1518952931
Cites: J Biomed Inform. 2009 Oct;42(5):839-5119435614
PubMed ID
24556644 View in PubMed
Less detail

De-Identifying Swedish EHR Text Using Public Resources in the General Domain.

https://arctichealth.org/en/permalink/ahliterature305543
Source
Stud Health Technol Inform. 2020 Jun 16; 270:148-152
Publication Type
Journal Article
Date
Jun-16-2020
Author
Taridzo Chomutare
Kassaye Yitbarek Yigzaw
Andrius Budrionis
Alexandra Makhlysheva
Fred Godtliebsen
Hercules Dalianis
Author Affiliation
Norwegian Centre for E-health Research, Tromsø, Norway.
Source
Stud Health Technol Inform. 2020 Jun 16; 270:148-152
Date
Jun-16-2020
Language
English
Publication Type
Journal Article
Keywords
Electronic Health Records
Language
Machine Learning
Natural Language Processing
Sweden
Abstract
Sensitive data is normally required to develop rule-based or train machine learning-based models for de-identifying electronic health record (EHR) clinical notes; and this presents important problems for patient privacy. In this study, we add non-sensitive public datasets to EHR training data; (i) scientific medical text and (ii) Wikipedia word vectors. The data, all in Swedish, is used to train a deep learning model using recurrent neural networks. Tests on pseudonymized Swedish EHR clinical notes showed improved precision and recall from 55.62% and 80.02% with the base EHR embedding layer, to 85.01% and 87.15% when Wikipedia word vectors are added. These results suggest that non-sensitive text from the general domain can be used to train robust models for de-identifying Swedish clinical text; and this could be useful in cases where the data is both sensitive and in low-resource languages.
PubMed ID
32570364 View in PubMed
Less detail

Developing a standard for de-identifying electronic patient records written in Swedish: precision, recall and F-measure in a manual and computerized annotation trial.

https://arctichealth.org/en/permalink/ahliterature150672
Source
Int J Med Inform. 2009 Dec;78(12):e19-26
Publication Type
Article
Date
Dec-2009
Author
Sumithra Velupillai
Hercules Dalianis
Martin Hassel
Gunnar H Nilsson
Author Affiliation
Department of Computer and Systems Sciences, Stockholm University/KTH, Kista, Sweden. sumithra@dsv.su.se
Source
Int J Med Inform. 2009 Dec;78(12):e19-26
Date
Dec-2009
Language
English
Publication Type
Article
Keywords
Confidentiality
Electronic Health Records
Humans
Medical Records Systems, Computerized
Natural Language Processing
Sweden
Abstract
Electronic patient records (EPRs) contain a large amount of information written in free text. This information is considered very valuable for research but is also very sensitive since the free text parts may contain information that could reveal the identity of a patient. Therefore, methods for de-identifying EPRs are needed. The work presented here aims to perform a manual and automatic Protected Health Information (PHI)-annotation trial for EPRs written in Swedish.
This study consists of two main parts: the initial creation of a manually PHI-annotated gold standard, and the porting and evaluation of an existing de-identification software written for American English to Swedish in a preliminary automatic de-identification trial. Results are measured with precision, recall and F-measure.
This study reports fairly high Inter-Annotator Agreement (IAA) results on the manually created gold standard, especially for specific tags such as names. The average IAA over all tags was 0.65 F-measure (0.84 F-measure highest pairwise agreement). For name tags the average IAA was 0.80 F-measure (0.91 F-measure highest pairwise agreement). Porting a de-identification software written for American English to Swedish directly was unfortunately non-trivial, yielding poor results.
Developing gold standard sets as well as automatic systems for de-identification tasks in Swedish is feasible. However, discussions and definitions on identifiable information is needed, as well as further developments both on the tag sets and the annotation guidelines, in order to get a reliable gold standard. A completely new de-identification software needs to be developed.
PubMed ID
19482543 View in PubMed
Less detail

Development of a SNOMED CT based national medication decision support system.

https://arctichealth.org/en/permalink/ahliterature261968
Source
Stud Health Technol Inform. 2013;192:1147
Publication Type
Article
Date
2013
Author
Kell Greibe
Source
Stud Health Technol Inform. 2013;192:1147
Date
2013
Language
English
Publication Type
Article
Keywords
Adverse Drug Reaction Reporting Systems - organization & administration
Decision Support Systems, Clinical - organization & administration
Denmark
Electronic Health Records - organization & administration
Information Storage and Retrieval - methods
Medical Order Entry Systems - organization & administration
Medication Systems, Hospital - organization & administration
Natural Language Processing
Systematized Nomenclature of Medicine
User-Computer Interface
Abstract
Physicians often lack the time to familiarize themselves with the details of particular allergies or other drug restrictions. Clinical Decision Support (CDS), based on a structured terminology as SNOMED CT (SCT), can help physicians get an overview, by automatically alerting allergy, interactions and other important information. The centralized CDS platform based on SCT, controls Allergy, Interactions, Risk Situation Drugs and Max Dose restrictions by the help of databases developed for these specific purposes. The CDS will respond to automatic web service requests from the hospital or GP electronic medication system (EMS) during prescription, and return alerts and information. The CDS also contains a Physicians Preference Database where the physicians individually can set which kind of alerts they want to see. The result is clinically useful information physicians can use as a base for a more effective and safer treatment, without developing alert fatigue.
PubMed ID
23920921 View in PubMed
Less detail

Extending the NegEx lexicon for multiple languages.

https://arctichealth.org/en/permalink/ahliterature261680
Source
Stud Health Technol Inform. 2013;192:677-81
Publication Type
Article
Date
2013
Author
Wendy W Chapman
Dieter Hillert
Sumithra Velupillai
Maria Kvist
Maria Skeppstedt
Brian E Chapman
Mike Conway
Melissa Tharp
Danielle L Mowery
Louise Deleger
Source
Stud Health Technol Inform. 2013;192:677-81
Date
2013
Language
English
Publication Type
Article
Keywords
Artificial Intelligence
France
Germany
Medical Records Systems, Computerized
Natural Language Processing
Semantics
Sweden
Terminology as Topic
Translating
United States
Vocabulary, Controlled
Abstract
We translated an existing English negation lexicon (NegEx) to Swedish, French, and German and compared the lexicon on corpora from each language. We observed Zipf's law for all languages, i.e., a few phrases occur a large number of times, and a large number of phrases occur fewer times. Negation triggers "no" and "not" were common for all languages; however, other triggers varied considerably. The lexicon is available in OWL and RDF format and can be extended to other languages. We discuss the challenges in translating negation triggers to other languages and issues in representing multilingual lexical knowledge.
Notes
Cites: J Am Med Inform Assoc. 1999 Sep-Oct;6(5):393-41110495099
Cites: J Biomed Inform. 2001 Oct;34(5):301-1012123149
Cites: BMC Med Inform Decis Mak. 2006;6:3016872495
Cites: J Am Med Inform Assoc. 2009 Jul-Aug;16(4):561-7019390096
Cites: J Am Med Inform Assoc. 2010 May-Jun;17(3):229-3620442139
Cites: BMC Med Inform Decis Mak. 2005;5:1315876352
Cites: J Am Med Inform Assoc. 2011 Sep-Oct;18(5):552-621685143
Cites: J Biomed Inform. 2011 Oct;44(5):728-3721459155
Cites: AMIA Annu Symp Proc. 2006;:534-817238398
Cites: Proc AMIA Symp. 2001;:105-911825163
Cites: J Am Med Inform Assoc. 2001 Nov-Dec;8(6):598-60911687566
Cites: J Am Med Inform Assoc. 2010 Sep-Oct;17(5):507-1320819853
PubMed ID
23920642 View in PubMed
Less detail

From capturing nursing knowledge to retrieval of data from a data warehouse.

https://arctichealth.org/en/permalink/ahliterature264083
Source
Stud Health Technol Inform. 2014;201:79-86
Publication Type
Article
Date
2014
Author
Asta Thoroddsen
Hanna K Guðjónsdóttir
Elisabet Guðjónsdóttir
Source
Stud Health Technol Inform. 2014;201:79-86
Date
2014
Language
English
Publication Type
Article
Keywords
Data Curation - standards
Electronic Health Records - standards
Iceland
Information Storage and Retrieval - standards
Natural Language Processing
Nursing Informatics - standards
Nursing Records - standards
Practice Guidelines as Topic
Terminology as Topic
Abstract
The purpose of the project was to capture nursing data and knowledge, represent it for use and re-use by retrieval from a data warehouse, which contains both clinical and financial hospital data. Today nurses at LUH use standardized nursing terminologies to document information related to patients and the nursing care in the EHR at all times. Pre-defined order sets for nursing care have been developed using best practice where available and tacit nursing knowledge has been captured and coded with standardized nursing terminologies and made explicit for dissemination in the EHR. All patient-nursing data is permanently stored in a data repository. Core nursing data elements have been selected for transfer and storage in the data warehouse and patient-nursing data are now captured, stored, can be related to other data elements from the warehouse and be retrieved for use and re-use.
PubMed ID
24943528 View in PubMed
Less detail

28 records – page 1 of 3.