Identifying QT prolongation from ECG impressions using Natural Language Processing and Negation Detection
Electrocardiogram (ECG) impressions provide significant information for decision support and clinical research. We investigated the presence of QT prolongation, an important risk factor for sudden cardiac death, compared to the automated calculation of corrected QT (QTc) by ECG machines. We integrated a negation tagging algorithm into the KnowledgeMap concept identifier (KMCI), then applied it to impressions from 44,080 ECGs to identify Unified Medical Language System concepts. We compared the instances of QT prolongation identified by KMCI to the calculated QTc. The algorithm for negation detection had a recall of 0.973 and precision of 0.982 over 10,490 concepts. A concept query for QT prolongation matched 2,364 ECGs with precision of 1.00. The positive predictive value of the common QTc cutoffs was 6-21%. ECGs not identified by KMCI as prolonged but with QTc>450ms revealed potential causes of miscalculated QTc intervals in 96% of the cases; no definite concept query false negatives were detected. We conclude that a natural language processing system can effectively identify QT prolongation and other cardiac diagnoses from ECG impressions for potential decision support and clinical research.
Available from: Joshua C Denny
Available from: Stephane M Meystre
Available from: utah.edu
[Show abstract] [Hide abstract]
ABSTRACT: We examine recent published research on the extraction of information from textual documents in the Electronic Health Record (EHR).
Literature review of the research published after 1995, based on PubMed, conference proceedings, and the ACM Digital Library, as well as on relevant publications referenced in papers already included.
174 publications were selected and are discussed in this review in terms of methods used, pre-processing of textual documents, contextual features detection and analysis, extraction of information in general, extraction of codes and of information for decision-support and enrichment of the EHR, information extraction for surveillance, research, automated terminology management, and data mining, and de-identification of clinical text.
Performance of information extraction systems with clinical text has improved since the last systematic review in 1995, but they are still rarely applied outside of the laboratory they have been developed in. Competitive challenges for information extraction from clinical text, along with the availability of annotated clinical text corpora, and further improvements in system performance are important factors to stimulate advances in this field and to increase the acceptance and usage of these systems in concrete clinical and biomedical research contexts.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.