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.
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.
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.
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.
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.
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
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.
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.
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.
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.
Cites: J Am Med Inform Assoc. 1999 Sep-Oct;6(5):393-41110495099
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.