Lexical Acquisition for Clinical Text Mining Using Distributional Similarity

Carroll, John; Koeling, Rob; Puri, Shivani

doi:10.1007/978-3-642-28601-8_20

Cited by 12 publications

(13 citation statements)

References 18 publications

(21 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, adapting such algorithms to medical text has proved difficult, for two main reasons: 1) patient privacy and confidentiality issues, which create difficulties in obtaining suitable data to develop and test algorithms on 27 , 28 and 2) the nuances of medical text, which make it difficult to obtain reliable clinical results using standard processing techniques 29 , 30 . The majority of tools for analysis of text are trained on edited text genres such as newspaper articles or scientific papers 31 . While medical discharge summaries, diagnostic test reports, and letters may be written in standard English, consultation notes are hastily written, and do not go through an editing process.…”

Section: Introductionmentioning

confidence: 99%

“…While medical discharge summaries, diagnostic test reports, and letters may be written in standard English, consultation notes are hastily written, and do not go through an editing process. These notes are terse, with a telegraphic style and limited use of full sentence syntax; in particular, sentential subjects are very rare, and even finite verbs are uncommon 31 . Standard NLP tools make many errors when applied to clinical notes.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extracting information from the text of electronic medical records to improve case detection: a systematic review

Ford

Carroll

Smith

et al. 2016

Journal of the American Medical Informatics Association

336

207

View full text Add to dashboard Cite

Background Electronic medical records (EMRs) are revolutionizing health-related research. One key issue for study quality is the accurate identification of patients with the condition of interest. Information in EMRs can be entered as structured codes or unstructured free text. The majority of research studies have used only coded parts of EMRs for case-detection, which may bias findings, miss cases, and reduce study quality. This review examines whether incorporating information from text into case-detection algorithms can improve research quality.Methods A systematic search returned 9659 papers, 67 of which reported on the extraction of information from free text of EMRs with the stated purpose of detecting cases of a named clinical condition. Methods for extracting information from text and the technical accuracy of case-detection algorithms were reviewed.Results Studies mainly used US hospital-based EMRs, and extracted information from text for 41 conditions using keyword searches, rule-based algorithms, and machine learning methods. There was no clear difference in case-detection algorithm accuracy between rule-based and machine learning methods of extraction. Inclusion of information from text resulted in a significant improvement in algorithm sensitivity and area under the receiver operating characteristic in comparison to codes alone (median sensitivity 78% (codes + text) vs 62% (codes), P = .03; median area under the receiver operating characteristic 95% (codes + text) vs 88% (codes), P = .025).Conclusions Text in EMRs is accessible, especially with open source information extraction algorithms, and significantly improves case detection when combined with codes. More harmonization of reporting within EMR studies is needed, particularly standardized reporting of algorithm accuracy metrics like positive predictive value (precision) and sensitivity (recall).

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Extracting information from the text of electronic medical records to improve case detection: a systematic review

Ford

Carroll

Smith

et al. 2016

Journal of the American Medical Informatics Association

336

207

View full text Add to dashboard Cite

show abstract

“…In future work we will add negation detection algorithms and model the context in which the keyword occurs, as well as expanding the indicators which are searched for in free text. We have obtained promising initial results in pilot experiments into deriving abbreviations and synonyms of indicators, using unsupervised machine learning techniques [35]. Other groups have had success with various text-processing algorithms in identifying RA cases and have even found these algorithms are portable between settings [18,19].…”

Section: Discussionmentioning

confidence: 99%

Optimising the use of electronic health records to estimate the incidence of rheumatoid arthritis in primary care: what information is hidden in free text?

Ford

Nicholson

Koeling

et al. 2013

BMC Med Res Methodol

Self Cite

View full text Add to dashboard Cite

BackgroundPrimary care databases are a major source of data for epidemiological and health services research. However, most studies are based on coded information, ignoring information stored in free text. Using the early presentation of rheumatoid arthritis (RA) as an exemplar, our objective was to estimate the extent of data hidden within free text, using a keyword search.MethodsWe examined the electronic health records (EHRs) of 6,387 patients from the UK, aged 30 years and older, with a first coded diagnosis of RA between 2005 and 2008. We listed indicators for RA which were present in coded format and ran keyword searches for similar information held in free text. The frequency of indicator code groups and keywords from one year before to 14 days after RA diagnosis were compared, and temporal relationships examined.ResultsOne or more keyword for RA was found in the free text in 29% of patients prior to the RA diagnostic code. Keywords for inflammatory arthritis diagnoses were present for 14% of patients whereas only 11% had a diagnostic code. Codes for synovitis were found in 3% of patients, but keywords were identified in an additional 17%. In 13% of patients there was evidence of a positive rheumatoid factor test in text only, uncoded. No gender differences were found. Keywords generally occurred close in time to the coded diagnosis of rheumatoid arthritis. They were often found under codes indicating letters and communications.ConclusionsPotential cases may be missed or wrongly dated when coded data alone are used to identify patients with RA, as diagnostic suspicions are frequently confined to text. The use of EHRs to create disease registers or assess quality of care will be misleading if free text information is not taken into account. Methods to facilitate the automated processing of text need to be developed and implemented.

show abstract

“…8 Building such data is labor-and cost-consuming, as every sentence needs to be manually examined and anonymized. Use of advanced NLP methods can remedy the training data bottleneck as suggested in [5]. The researchers used distributional similarity for acquiring lexical information from notes typed by general practitioners.…”

Section: Content-aware Data Leak Preventionmentioning

confidence: 99%

“…The PHI breaches are potent legal issues, as PHI protection acts have been enabled by governments: Health Insurance Portability and Accountability Act, often known as HIPAA (US), 5 Personal Health Information Protection Act, or PHIPA (Ontario, Canada), 6 Data Protection Directive, or Directive 95/46/EC (EU). 7 It is thus imperative to have a global knowledge of best protocols and systems that protect privacy and confidentiality in data.…”

Section: Data Leaksmentioning

confidence: 99%

Personal Privacy Protection in Time of Big Data

Sokolova

Matwin

2015

Studies in Computational Intelligence

View full text Add to dashboard Cite

Personal privacy protection increasingly becomes a story of privacy protection in electronic data format. Personal privacy protection also becomes a showcase of advantages and challenges of Big Data phenomenon. Accumulation of massive data volumes combined with development of intelligent Data Mining algorithms allows more data being analysed and linked. Unintended consequences of Big Data analytics include increasing risks of discovery new information about individuals. There are several approaches to protect privacy of individuals in the largeS. Matwin data sets, privacy-preserving Data Mining being an example. In this paper, we discuss content-aware prevention of data leaks. We concentrate on protection of personal health information (PHI), arguably the most vulnerable type of personal information. This paper discusses the applied methods and challenges which arise when we want to hold health information private. PHI leak prevention on the Web and on online social networks is our case study.

show abstract

Lexical Acquisition for Clinical Text Mining Using Distributional Similarity

Cited by 12 publications

References 18 publications

Extracting information from the text of electronic medical records to improve case detection: a systematic review

Extracting information from the text of electronic medical records to improve case detection: a systematic review

Optimising the use of electronic health records to estimate the incidence of rheumatoid arthritis in primary care: what information is hidden in free text?

Personal Privacy Protection in Time of Big Data

Contact Info

Product

Resources

About