Skip to main content
Search
Search
Advanced Search
Skip main navigation
Open access
Research Article
23 January 2024

Distinguishing cardiac catheter ablation energy modalities by applying natural language processing to electronic health records

Authors: Jamie Margetta https://orcid.org/0009-0003-7584-9404 and Alicia Sale https://orcid.org/0009-0003-3394-5246 [email protected]Author Info & Affiliations
Volume 13, Number 3
https://doi.org/10.57264/cer-2023-0053
PDFFormats

Abstract

Aim: Catheter ablation is used to treat symptomatic atrial fibrillation (AF) and is performed using either cryoballoon (CB) or radiofrequency (RF) ablation. There is limited real world data of CB and RF in the US as healthcare codes are agnostic of energy modality. An alternative method is to analyze patients' electronic health records (EHRs) using Optum's EHR database. Objective: To determine the feasibility of using patients' EHRs with natural language processing (NLP) to distinguish CB versus RF ablation procedures. Data Source: Optum® de-identified EHR dataset, Optum® Cardiac Ablation NLP Table. Methods: This was a retrospective analysis of existing de-identified EHR data. Medical codes were used to create an ablation validation table. Frequency analysis was used to assess ablation procedures and their associated note terms. Two cohorts were created (1) index procedures, (2) multiple procedures. Possible note term combinations included (1) cryoablation (2) radiofrequency (3) ablation, or (4) both. Results: Of the 40,810 validated cardiac ablations, 3777 (9%) index ablation procedures had available and matching NLP note terms. Of these, 22% (n = 844) were classified as ablation, 27% (n = 1016) as cryoablation, 49% (n = 1855) as radiofrequency ablation, and 1.6% (n = 62) as both. In the multiple procedures analysis, 5691 (14%) procedures had matching note terms. 24% (n = 1362) were classified as ablation, 27% as cryoablation, 47% as radiofrequency ablation, and 2% as both. Conclusion: NLP has potential to evaluate the frequency of cardiac ablation by type, however, for this to be a reliable real-world data source, mandatory data entry by providers and standardized electronic health reporting must occur.

Plain language summary

What was the aim of this research?

A proof-of-concept study to determine the feasibility of using patients' electronic health record (EHRs) with natural language processing (NLP) to distinguish cryoablation versus radiofrequency ablation procedures across the US.

How was the research carried out?

A retrospective analysis of existing de-identified EHR data using Optum® de-identified EHR dataset and Optum® Cardiac Ablation NLP Table. Medical codes were used to create an ablation validation table. Frequency analysis was used to assess ablation procedures and their associated note terms (Cryoablation, Radiofrequency).

What were the results?

Of the 40,810 validated cardiac ablations, 3777 (9%) index ablation procedures had available and matching NLP note terms. Of these, 22% (n = 844) were classified as generic ablation, 27% (n = 1016) as cryoablation, 49% (n = 1855) as radiofrequency ablation, and 1.6% (n = 62) as both cryoablation and radiofrequency ablation.

What do the results mean?

NLP has potential to evaluate the frequency of cardiac ablation by type, however, for this to be a reliable real-world data source, mandatory data entry by providers and standardized electronic health reporting must occur.

Supplementary Material

File (supplementary materials.docx)

References

Papers of special note have been highlighted as: • of interest
1.
Hindricks G, Potpara T, Dagres N, ESC Scientific Document Group et al. 2020 ESC Guidelines for the diagnosis and management of atrial fibrillation developed in collaboration with the European Association for Cardio-Thoracic Surgery (EACTS): The Task Force for the diagnosis and management of atrial fibrillation of the European Society of Cardiology (ESC) Developed with the special contribution of the European Heart Rhythm Association (EHRA) of the ESC. Eur. Heart J. 42(5), 373–498 (2021).
PubMed
Google Scholar
2.
Coding and Payment Guide. Cardiac catheter ablation. Economics, reimbursement, and evidence (2021). https://asiapac.medtronic.com/content/dam/medtronic-com/us-en/hcp/reimbursement/documents/catheter-ablation-coding-reimbursement-guide.pdf
Google Scholar
• Cardiac ablation codes were sourced from here.
3.
Hachem AH, Marine JE, Tahboub HA et al. Radiofrequency ablation versus cryoablation in the treatment of paroxysmal atrial fibrillation: a meta-analysis. Cardiol. Res. Pract. 2018, 6276241 (2018).
PubMed
Google Scholar
4.
Shah RU, Mukherjee R, Zhang Y et al. Impact of different electronic cohort definitions to identify patients with atrial fibrillation from the electronic medical record. J. Am. Heart Assoc. 9(5), e014527 (2020).
PubMed
Google Scholar
• Similar analysis in arial fibrillation therapy area.
5.
Laaksonen N, Varjonen JM, Blomster M et al. Assessing an electronic health record research platform for identification of clinical trial participants. Contemp. Clin. Trials Commun. 21, 100692 (2020).
PubMed
Google Scholar
6.
Mehta N, Pandit A. Concurrence of big data analytics and healthcare: a systematic review. Int. J. Med. Inform. 114, 57–65 (2018).
PubMed
Google Scholar
7.
Optum. Using AI to solve health care's real problems. Natural Language Processing (2021). https://www.optum.com/business/resources/ai-in-healthcare/nlp-ai-roi.html
Google Scholar
8.
Koleck TA, Dreisbach C, Bourne PE, Bakken S. Natural language processing of symptoms documented in free-text narratives of electronic health records: a systematic review. J. Am. Med. Inform. Assoc. 26(4), 364–379 (2019).
PubMed
Google Scholar
9.
Fleuren WWM, Alkema W. Application of text mining in the biomedical domain. Methods 74, 97–106 (2015).
PubMed
Google Scholar
10.
Wang Y, Wang L, Rastegar-Mojarad M et al. Clinical information extraction applications: a literature review. J. Biomed. Inform. 77, 34–49 (2018).
PubMed
Google Scholar
11.
Savova GK, Masanz JJ, Ogren PV et al. Mayo clinical Text Analysis and Knowledge Extraction System (cTAKES): architecture, component evaluation and applications. J. Am. Med. Inform. Assoc. 17(5), 507–513 (2010).
PubMed
Google Scholar
12.
Pérez FJ, Schubert CM, Parvez B, Pathak V, Ellenbogen KA, Wood MA. Long-term outcomes after catheter ablation of cavo-tricuspid isthmus dependent atrial flutter: a meta-analysis. Circ. Arrhythm Electrophysiol. 2(4), 393–401 (2009).
PubMed
Google Scholar
13.
Della Rocca DG, Di Biase L, Mohanty S et al. Targeting non-pulmonary vein triggers in persistent atrial fibrillation: results from a prospective, multicentre, observational registry. Europace 23(12), 1939–1949 (2021).
PubMed
Google Scholar
14.
Loring Z, Holmes DN, Matsouaka RA et al. Procedural patterns and safety of atrial fibrillation ablation: findings from get with the guidelines-atrial fibrillation. Circ. Arrhythm Electrophysiol. 13(9), e007944 (2020).
PubMed
Google Scholar
15.
US Food and Drug Administration. Sentinel System – Five-Year Strategy 2019–2023 (2019). https://www.fda.gov/media/120333/download
Google Scholar
16.
Dhruva SS, Ross JS, Desai NR. Real-world evidence: promise and peril for medical product evaluation. PT 43(8), 464–472 (2018).
PubMed
Google Scholar
• Outlines real-world evidence possibilities.
17.
Divney AA, Lopez PM, Huang TT, Thorpe LE, Trinh-Shevrin C, Islam NS. Research-grade data in the real world: challenges and opportunities in data quality from a pragmatic trial in community-based practices. J. Am. Med. Inform. Assoc. 26(8–9), 847–854 (2019).
PubMed
Google Scholar
18.
Savitz ST, Savitz LA, Fleming NS, Shah ND, Go AS. How much can we trust electronic health record data? Healthc. (Amst.) 8(3), 100444 (2020).
PubMed
Google Scholar
19.
Johnson SB, Bakken S, Dine D et al. An electronic health record based on structured narrative. J. Am. Med. Inform. Assoc. 15(1), 54–64 (2008).
PubMed
Google Scholar
20.
Callahan A, Fries JA, Ré C et al. Medical device surveillance with electronic health records. NPJ Digit. Med. 2, 94 (2019).
PubMed
Google Scholar
|