Extracting Information from Textual Documents in the Electronic Health Record: A Review of Recent Research

By Stéphane M. Meystre, Guergana K. Savova, K. Kipper-Schuler, John F. Hurdle. Yearbook of Medical Informatics, 2008

957 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Health Information Management, Molecular Biology

View Paper: https://www.semanticscholar.org/paper/c2dedd7ac6bf7828534ebd7853a402c238d9307f

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Health Information Management

In Molecular Biology

Citations in the corpus

Challenges of Using Text Classifiers for Causal Inference (2018, background): “Many health studies have used text classiﬁers to extract clinical variables from EHR data ( Meystre et al., 2008).”
Automatic de-identification of textual documents in the electronic health record: a review of recent research (2010, background): “The most common types of clinical text targeted by these systems-discharge summaries and surgical pathology reports-are often dictated and are composed deliberately for clear communication, while other texts like progress notes are written mainly for documentation purposes [6].”
Electronic Health Records: Then, Now, and in the Future (2016, positive): “This spawned the need for the use of Natural Language Processing (NLP) to read and code free-text data which has become common within most EHRs [119-121].”
A large language model for electronic health records (2022, background): “4 There is an increasing number of medical AI systems exploring the rich, more fine-grained patient information captured in clinical narratives to improve diagnostic and prognostic models.”
Using Electronic Patient Records to Discover Disease Correlations and Stratify Patient Cohorts (2011, background): “For relevant reviews on methods in text mining see e.g. ([37,63,64,65]).”
Big data in health care: using analytics to identify and manage high-risk and high-cost patients. (2014, background): “62,63 Essential elements of the narrative, such as temporal relationships and co-references (that is, narrative that refers to more than one thing), may be lost or incorrectly assigned.”
Enhancing clinical concept extraction with distributional semantics (2011, background): “…text mining from clinical records, particularly from narrative-style ﬁelds (such as discharge summaries and progress reports), has proven to be an elusive target for clinical Natural Language Processing (NLP) [1], due in part to the lack of availability of annotated corpora speciﬁc to the task.”
Automated determination of metastases in unstructured radiology reports for eligibility screening in oncology clinical trials (2013, background): “(NLP) is growing rapidly, IE use to support research is limited.(23) Cancer metastatic status is frequently a key inclusion or exclusion criterion for oncology clinical trials.”
Extracting and integrating data from entire electronic health records for detecting colorectal cancer cases. (2011, methodology): “The MedLEE system has shown good coverage on concept extraction in many studies [29]; therefore our focus in this study was to improve the assertion determination – to decide if a CRC concept is positive or negative.”
Lessons from Natural Language Inference in the Clinical Domain (2018, background): “Moreover, since this domain has a distinct sublanguage (Friedman et al., 2002), clinical text it also presents unique challenges (abbreviations, inconsistent punctuation, misspellings, etc.) that differentiate it from open-domain data (Meystre et al., 2008).”
Automated identification of postoperative complications within an electronic medical record using natural language processing. (2011, background): “13 Nevertheless Nevertheless, there have been few studies investigating natural language processing tools for the detection of adverse events.”
EpiDEA: Extracting Structured Epilepsy and Seizure Information from Patient Discharge Summaries for Cohort Identification (2012, background): “Parsing and analyzing clinical narratives presents a unique set of challenges that distinguish it from the broader biomedical natural language processing (NLP) approaches [5].”
Recent Advances in Clinical Natural Language Processing in Support of Semantic Analysis (2015, methodology): “In the comprehensive clinical NLP review by Meystre et al. in 2008 [4], a number of future challenges were mentioned, such as the need for more efficient methods for corpus creation in terms of effort required as well as patient confidentiality, the need for further research in complex semantic…”
Clinical Information Extraction Applications: A Literature Review (2017, background): “[11] conducted a review of studies published from 1995 to 2008.”
Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications (2010, methodology): “Each discovered named entity belongs to one of the dictionary semantic types and has attributes for (1) the text span associated with the named entity (‘span’ attribute), (2) the terminology/ontology code the named entity maps to (‘concept’ attribute), (3) whether the named entity is negated (‘negat”