Natural Language Mapping of Electrocardiogram Interpretations to a Standardized Ontology

Abstract

Background Interpretations of the electrocardiogram (ECG) are often prepared using software outside the electronic health record (EHR) and imported via an interface as a narrative note. Thus, natural language processing is required to create a computable representation of the findings. Challenges include misspellings, nonstandard abbreviations, jargon, and equivocation in diagnostic interpretations.

Objectives Our objective was to develop an algorithm to reliably and efficiently extract such information and map it to the standardized ECG ontology developed jointly by the American Heart Association, the American College of Cardiology Foundation, and the Heart Rhythm Society. The algorithm was to be designed to be easily modifiable for use with EHRs and ECG reporting systems other than the ones studied.

Methods An algorithm using natural language processing techniques was developed in structured query language to extract and map quantitative and diagnostic information from ECG narrative reports to the cardiology societies' standardized ECG ontology. The algorithm was developed using a training dataset of 43,861 ECG reports and applied to a test dataset of 46,873 reports.

Results Accuracy, precision, recall, and the F1-measure were all 100% in the test dataset for the extraction of quantitative data (e.g., PR and QTc interval, atrial and ventricular heart rate). Performances for matches in each diagnostic category in the standardized ECG ontology were all above 99% in the test dataset. The processing speed was approximately 20,000 reports per minute. We externally validated the algorithm from another institution that used a different ECG reporting system and found similar performance.

Conclusion The developed algorithm had high performance for creating a computable representation of ECG interpretations. Software and lookup tables are provided that can easily be modified for local customization and for use with other EHR and ECG reporting systems. This algorithm has utility for research and in clinical decision-support where incorporation of ECG findings is desired.

Keywords

natural language processing - electrocardiogram - electronic health record

Publication History

Received: 21 July 2021

Accepted: 20 August 2021

Article published online:
05 October 2021

• References

• 1 Williams CB, Andrade JG, Hawkins NM. et al. Establishing reference ranges for ambulatory electrocardiography parameters: meta-analysis. Heart 2020; 106 (22) 1732-1739
• 2 Smulyan H. The computerized ECG: friend and foe. Am J Med 2019; 132 (02) 153-160
• 3 Turley A, Roberts A, Evemy K, Haq I, Irvine T, Adams P. Diagnostic accuracy of automated computerised electrocardiogram interpretation compared with a panel of experienced cardiologists. Crit Care 2007; 11 (02) 245
• 4 Rasmussen LV. The electronic health record for translational research. J Cardiovasc Transl Res 2014; 7 (06) 607-614
• 5 Mason JW, Hancock EW, Gettes LS. et al; American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology, American College of Cardiology Foundation, Heart Rhythm Society. Recommendations for the standardization and interpretation of the electrocardiogram: part II: electrocardiography diagnostic statement list a scientific statement from the American Heart Association Electrocardiography and Arrhythmias Committee, Council on Clinical Cardiology; the American College of Cardiology Foundation; and the Heart Rhythm Society Endorsed by the International Society for Computerized Electrocardiology. J Am Coll Cardiol 2007; 49 (10) 1128-1135
• 6 Denny JC, Miller RA, Waitman LR, Arrieta MA, Peterson JF. Identifying QT prolongation from ECG impressions using a general-purpose natural language processor. Int J Med Inform 2009; 78 (Suppl. 01) S34-S42
• 7 Unified Medical Language System. Accessed July 10, 2021 at: https://www.nlm.nih.gov/research/umls/index.html
• 8 Nath C, Albaghdadi MS, Jonnalagadda SR. A natural language processing tool for large-scale data extraction from echocardiography reports. PLoS One 2016; 11 (04) e0153749
• 9 Patterson OV, Freiberg MS, Skanderson M, J FodehS, Brandt CA, DuVall SL. Unlocking echocardiogram measurements for heart disease research through natural language processing. BMC Cardiovasc Disord 2017; 17 (01) 151
• 10 Prutkin JM. ECG tutorial: basic principles of ECG analysis. Accessed July 10, 2021 at: https://www.uptodate.com/contents/ecg-tutorial-basic-principles-of-ecg-analysis
• 11 de Jong JSSG. Accessed July 10, 2021 at: https://en.ecgpedia.org/index.php?title=Textbook
• 12 12-Lead ECG: The art of interpretation. Accessed July 10, 2021 at: http://www.12leadecg.com/full/glossary.aspx
• 13 The Gutenberg Webster's Unabridged Dictionary by Project Gutenberg. Accessed October 28, 2020 at: http://www.gutenberg.org/cache/epub/673/pg673.txt
• 14 Philips Medical Systems. The Philips 12-Lead Algorithm Physician's Guide. Accessed July 10, 2021 at: http://incenter.medical.philips.com/doclib/enc/fetch/577817/577818/12-Lead_Algorithm_Physician_s_Guide_for_Algorithm_Verion_PH080A%2C_(ENG).pdf%3Fnodeid%3D3325283%26vernum%3D-2
• 15 Denny JC, Spickard III A, Miller RA. et al. Identifying UMLS concepts from ECG Impressions using KnowledgeMap. AMIA Annu Symp Proc 2005; 2005: 196-200
• 16 SQL—ANSI (American National Standards Institute) SQL. (Standard|Reference|Specification). Accessed July 10, 2021 at: https://datacadamia.com/data/type/relation/sql/ansi