Use of electronic health record data mining for heart failure subtyping.
Data mining
Ejection fraction
Electronic health records
HFmrEF
HFpEF
HFrEF
Heart failure
Text mining
Journal
BMC research notes
ISSN: 1756-0500
Titre abrégé: BMC Res Notes
Pays: England
ID NLM: 101462768
Informations de publication
Date de publication:
11 Sep 2023
11 Sep 2023
Historique:
received:
14
10
2022
accepted:
22
08
2023
medline:
13
9
2023
pubmed:
12
9
2023
entrez:
12
9
2023
Statut:
epublish
Résumé
To assess whether electronic health record (EHR) data text mining can be used to improve register-based heart failure (HF) subtyping. EHR data of 43,405 individuals from two Finnish hospital biobanks were mined for unstructured text mentions of ejection fraction (EF) and validated against clinical assessment in two sets of 100 randomly selected individuals. Structured laboratory data was then incorporated for a categorization by HF subtype (HF with mildly reduced EF, HFmrEF; HF with preserved EF, HFpEF; HF with reduced EF, HFrEF; and no HF). In 86% of the cases, the algorithm-identified EF belonged to the correct HF subtype range. Sensitivity, specificity, PPV and NPV of the algorithm were 94-100% for HFrEF, 85-100% for HFmrEF, and 96%, 67%, 53% and 98% for HFpEF. Survival analyses using the traditional diagnosis of HF were in concordance with the algorithm-based ones. Compared to healthy individuals, mortality increased from HFmrEF (hazard ratio [HR], 1.91; 95% confidence interval [CI], 1.24-2.95) to HFpEF (2.28; 1.80-2.88) to HFrEF group (2.63; 1.97-3.50) over a follow-up of 1.5 years. We conclude that quantitative EF data can be efficiently extracted from EHRs and used with laboratory data to subtype HF with reasonable accuracy, especially for HFrEF.
Identifiants
pubmed: 37697398
doi: 10.1186/s13104-023-06469-x
pii: 10.1186/s13104-023-06469-x
pmc: PMC10496250
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
208Informations de copyright
© 2023. BioMed Central Ltd., part of Springer Nature.
Références
Janssens SP. Gene therapy for heart failure. Hear Fail Second Ed. 2012;457–73.
Ponikowski P, Voors A, Anker AD, Bueno S, Cleland HGF, Coats JJS. 2016 ESC GUIDELINES FOR THE DIAGNOSIS AND TREATMENT OF ACUTE AND CHRONIC HEART FAILURE. Russ J Cardiol. 2017;18(1):7–81.
doi: 10.15829/1560-4071-2017-1-7-81
Povl Munk-Jørgensen Aksel Bertelsen AADKLELKT. Implementation of ICD-10 in the nordic countries. Nord J Psychiatry. 1999;53(1):5–9.
doi: 10.1080/080394899426648
WHO. International Classification of Diseases 10th Revision [Internet]. [cited 2019 Sep 9]. Available from: http://apps.who.int/classifications/icd10/browse/2016/en (2018.
FinnGen. FinnGen Documentation of R4 release [Internet]. 2020. Available from: https://finngen.gitbook.io/documentation/
KELA. Statistics on reimbursements for prescription medicines [Internet]. [cited 2019 Aug 5]. Available from: https://www.kela.fi/web/en/492
Andrew S, Levey MD, Lesley A, Stevens MD, Christopher MS, Schmid H, PhD, Yaping (Lucy) Zhang, MS, Alejandro F, Castro MPH III, Harold I, Feldman MD, John MSCE, Kusek W. PhD, Paul Eggers, PhD, Frederick Van Lente, PhD, Tom Greene, PhD, Josef Coresh,. A New Equation to Estimate Glomerular Filtration Rate. Ann Intern Med. 2009;150(9):604–12.
Lauritsen J, Gustafsson F, Abdulla J. Characteristics and long-term prognosis of patients with heart failure and mid-range ejection fraction compared with reduced and preserved ejection fraction: a systematic review and meta-analysis. ESC Hear Fail. 2018;5(4):687–94.
Labrosse J, Lam T, Sebbag C, Benque M, Abdennebi I, Merckelbagh H et al. Text mining in Electronic Medical Records enables quick and efficient identification of pregnancy cases occurring after breast Cancer. JCO Clin Cancer Informatics. 2019;(3):1–12.
Xu H, Fu Z, Shah A, Chen Y, Peterson NB, Chen Q et al. Extracting and integrating data from entire electronic health records for detecting colorectal cancer cases. AMIA Annu Symp Proc. 2011;2011:1564–72.
Brunekreef TE, Otten HG, Bosch SC, Hoefer IE, Laar JM, Limper M, et al. Text mining of Electronic Health Records can accurately identify and characterize patients with systemic Lupus Erythematosus. ACR Open Rheumatol. 2021;3(2):65–71.
doi: 10.1002/acr2.11211
pubmed: 33434395
pmcid: 7882527
Mull HJ, Stolzmann KL, Shin MH, Kalver E, Schweizer ML, Branch-Elliman W. Novel method to flag Cardiac Implantable device infections by integrating text mining with Structured Data in the Veterans Health Administration’s Electronic Medical Record. JAMA Netw open. 2020;3(9):e2012264.
doi: 10.1001/jamanetworkopen.2020.12264
pubmed: 32955571
pmcid: 7506515