Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers

Aurore Lyon, Rina Ariga, Ana Mincholé, Masliza Mahmod, Elizabeth Ormondroyd, Pablo Laguna, Nando de Freitas, Stefan Neubauer, Hugh Watkins, Blanca Rodriguez

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

Aims: Ventricular arrhythmia triggers sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM), yet electrophysiological biomarkers are not used for risk stratification. Our aim was to identify distinct HCM phenotypes based on ECG computational analysis, and characterize differences in clinical risk factors and anatomical differences using cardiac magnetic resonance (CMR) imaging. Methods: High-fidelity 12-lead Holter ECGs from 85 HCM patients and 38 healthy volunteers were analyzed using mathematical modeling and computational clustering to identify phenotypic subgroups. Clinical features and the extent and distribution of hypertrophy assessed by CMR were evaluated in the subgroups. Results: QRS morphology alone was crucial to identify three HCM phenotypes with very distinct QRS patterns. Group 1 (n = 44) showed normal QRS morphology, Group 2 (n = 19) showed short R and deep S waves in V4, and Group 3 (n = 22) exhibited short R and long S waves in V4-6, and left QRS axis deviation. However, no differences in arrhythmic risk or distribution of hypertrophy were observed between these groups. Including T wave biomarkers in the clustering, four HCM phenotypes were identified: Group 1A (n = 20), with primary repolarization abnormalities showing normal QRS yet inverted T waves, Group 1B (n = 24), with normal QRS morphology and upright T waves, and Group 2 and Group 3 remaining as before, with upright T waves. Group 1A patients, with normal QRS and inverted T wave, showed increased HCM Risk-SCD scores (1A: 4.0%, 1B: 1.8%, 2: 2.1%, 3: 2.5%, p = 0.0001), and a predominance of coexisting septal and apical hypertrophy (p < 0.0001). HCM patients in Groups 2 and 3 exhibited predominantly septal hypertrophy (85 and 90%, respectively). Conclusion: HCM patients were classified in four subgroups with distinct ECG features. Patients with primary T wave inversion not secondary to QRS abnormalities had increased HCM Risk-SCD scores and coexisting septal and apical hypertrophy, suggesting that primary T wave inversion may increase SCD risk in HCM, rather than T wave inversion secondary to depolarization abnormalities. Computational ECG phenotyping provides insight into the underlying processes captured by the ECG and has the potential to be a novel and independent factor for risk stratification.

Original languageEnglish
Article number213
JournalFrontiers in Physiology
Volume9
Issue numberMAR
DOIs
Publication statusPublished - 13 Mar 2018
Externally publishedYes

Fingerprint

Hypertrophic Cardiomyopathy
Electrocardiography
Phenotype
Sudden Cardiac Death
Hypertrophy
Cluster Analysis
Biomarkers
Machine Learning
Cardiomegaly
Cardiac Arrhythmias
Healthy Volunteers
Magnetic Resonance Spectroscopy
Magnetic Resonance Imaging

Keywords

  • Computational clustering
  • E-cardiology
  • Electrocardiography
  • Hypertrophic cardiomyopathy
  • Phenotyping

ASJC Scopus subject areas

  • Physiology
  • Physiology (medical)

Cite this

Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers. / Lyon, Aurore; Ariga, Rina; Mincholé, Ana; Mahmod, Masliza; Ormondroyd, Elizabeth; Laguna, Pablo; de Freitas, Nando; Neubauer, Stefan; Watkins, Hugh; Rodriguez, Blanca.

In: Frontiers in Physiology, Vol. 9, No. MAR, 213, 13.03.2018.

Research output: Contribution to journalArticle

Lyon, A, Ariga, R, Mincholé, A, Mahmod, M, Ormondroyd, E, Laguna, P, de Freitas, N, Neubauer, S, Watkins, H & Rodriguez, B 2018, 'Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers', Frontiers in Physiology, vol. 9, no. MAR, 213. https://doi.org/10.3389/fphys.2018.00213
Lyon, Aurore ; Ariga, Rina ; Mincholé, Ana ; Mahmod, Masliza ; Ormondroyd, Elizabeth ; Laguna, Pablo ; de Freitas, Nando ; Neubauer, Stefan ; Watkins, Hugh ; Rodriguez, Blanca. / Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers. In: Frontiers in Physiology. 2018 ; Vol. 9, No. MAR.
@article{65b024496c9c4db7a93495f7676c4f24,
title = "Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers",
abstract = "Aims: Ventricular arrhythmia triggers sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM), yet electrophysiological biomarkers are not used for risk stratification. Our aim was to identify distinct HCM phenotypes based on ECG computational analysis, and characterize differences in clinical risk factors and anatomical differences using cardiac magnetic resonance (CMR) imaging. Methods: High-fidelity 12-lead Holter ECGs from 85 HCM patients and 38 healthy volunteers were analyzed using mathematical modeling and computational clustering to identify phenotypic subgroups. Clinical features and the extent and distribution of hypertrophy assessed by CMR were evaluated in the subgroups. Results: QRS morphology alone was crucial to identify three HCM phenotypes with very distinct QRS patterns. Group 1 (n = 44) showed normal QRS morphology, Group 2 (n = 19) showed short R and deep S waves in V4, and Group 3 (n = 22) exhibited short R and long S waves in V4-6, and left QRS axis deviation. However, no differences in arrhythmic risk or distribution of hypertrophy were observed between these groups. Including T wave biomarkers in the clustering, four HCM phenotypes were identified: Group 1A (n = 20), with primary repolarization abnormalities showing normal QRS yet inverted T waves, Group 1B (n = 24), with normal QRS morphology and upright T waves, and Group 2 and Group 3 remaining as before, with upright T waves. Group 1A patients, with normal QRS and inverted T wave, showed increased HCM Risk-SCD scores (1A: 4.0{\%}, 1B: 1.8{\%}, 2: 2.1{\%}, 3: 2.5{\%}, p = 0.0001), and a predominance of coexisting septal and apical hypertrophy (p < 0.0001). HCM patients in Groups 2 and 3 exhibited predominantly septal hypertrophy (85 and 90{\%}, respectively). Conclusion: HCM patients were classified in four subgroups with distinct ECG features. Patients with primary T wave inversion not secondary to QRS abnormalities had increased HCM Risk-SCD scores and coexisting septal and apical hypertrophy, suggesting that primary T wave inversion may increase SCD risk in HCM, rather than T wave inversion secondary to depolarization abnormalities. Computational ECG phenotyping provides insight into the underlying processes captured by the ECG and has the potential to be a novel and independent factor for risk stratification.",
keywords = "Computational clustering, E-cardiology, Electrocardiography, Hypertrophic cardiomyopathy, Phenotyping",
author = "Aurore Lyon and Rina Ariga and Ana Minchol{\'e} and Masliza Mahmod and Elizabeth Ormondroyd and Pablo Laguna and {de Freitas}, Nando and Stefan Neubauer and Hugh Watkins and Blanca Rodriguez",
year = "2018",
month = "3",
day = "13",
doi = "10.3389/fphys.2018.00213",
language = "English",
volume = "9",
journal = "Frontiers in Physiology",
issn = "1664-042X",
publisher = "Frontiers Research Foundation",
number = "MAR",

}

TY - JOUR

T1 - Distinct ECG phenotypes identified in hypertrophic cardiomyopathy using machine learning associate with arrhythmic risk markers

AU - Lyon, Aurore

AU - Ariga, Rina

AU - Mincholé, Ana

AU - Mahmod, Masliza

AU - Ormondroyd, Elizabeth

AU - Laguna, Pablo

AU - de Freitas, Nando

AU - Neubauer, Stefan

AU - Watkins, Hugh

AU - Rodriguez, Blanca

PY - 2018/3/13

Y1 - 2018/3/13

N2 - Aims: Ventricular arrhythmia triggers sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM), yet electrophysiological biomarkers are not used for risk stratification. Our aim was to identify distinct HCM phenotypes based on ECG computational analysis, and characterize differences in clinical risk factors and anatomical differences using cardiac magnetic resonance (CMR) imaging. Methods: High-fidelity 12-lead Holter ECGs from 85 HCM patients and 38 healthy volunteers were analyzed using mathematical modeling and computational clustering to identify phenotypic subgroups. Clinical features and the extent and distribution of hypertrophy assessed by CMR were evaluated in the subgroups. Results: QRS morphology alone was crucial to identify three HCM phenotypes with very distinct QRS patterns. Group 1 (n = 44) showed normal QRS morphology, Group 2 (n = 19) showed short R and deep S waves in V4, and Group 3 (n = 22) exhibited short R and long S waves in V4-6, and left QRS axis deviation. However, no differences in arrhythmic risk or distribution of hypertrophy were observed between these groups. Including T wave biomarkers in the clustering, four HCM phenotypes were identified: Group 1A (n = 20), with primary repolarization abnormalities showing normal QRS yet inverted T waves, Group 1B (n = 24), with normal QRS morphology and upright T waves, and Group 2 and Group 3 remaining as before, with upright T waves. Group 1A patients, with normal QRS and inverted T wave, showed increased HCM Risk-SCD scores (1A: 4.0%, 1B: 1.8%, 2: 2.1%, 3: 2.5%, p = 0.0001), and a predominance of coexisting septal and apical hypertrophy (p < 0.0001). HCM patients in Groups 2 and 3 exhibited predominantly septal hypertrophy (85 and 90%, respectively). Conclusion: HCM patients were classified in four subgroups with distinct ECG features. Patients with primary T wave inversion not secondary to QRS abnormalities had increased HCM Risk-SCD scores and coexisting septal and apical hypertrophy, suggesting that primary T wave inversion may increase SCD risk in HCM, rather than T wave inversion secondary to depolarization abnormalities. Computational ECG phenotyping provides insight into the underlying processes captured by the ECG and has the potential to be a novel and independent factor for risk stratification.

AB - Aims: Ventricular arrhythmia triggers sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HCM), yet electrophysiological biomarkers are not used for risk stratification. Our aim was to identify distinct HCM phenotypes based on ECG computational analysis, and characterize differences in clinical risk factors and anatomical differences using cardiac magnetic resonance (CMR) imaging. Methods: High-fidelity 12-lead Holter ECGs from 85 HCM patients and 38 healthy volunteers were analyzed using mathematical modeling and computational clustering to identify phenotypic subgroups. Clinical features and the extent and distribution of hypertrophy assessed by CMR were evaluated in the subgroups. Results: QRS morphology alone was crucial to identify three HCM phenotypes with very distinct QRS patterns. Group 1 (n = 44) showed normal QRS morphology, Group 2 (n = 19) showed short R and deep S waves in V4, and Group 3 (n = 22) exhibited short R and long S waves in V4-6, and left QRS axis deviation. However, no differences in arrhythmic risk or distribution of hypertrophy were observed between these groups. Including T wave biomarkers in the clustering, four HCM phenotypes were identified: Group 1A (n = 20), with primary repolarization abnormalities showing normal QRS yet inverted T waves, Group 1B (n = 24), with normal QRS morphology and upright T waves, and Group 2 and Group 3 remaining as before, with upright T waves. Group 1A patients, with normal QRS and inverted T wave, showed increased HCM Risk-SCD scores (1A: 4.0%, 1B: 1.8%, 2: 2.1%, 3: 2.5%, p = 0.0001), and a predominance of coexisting septal and apical hypertrophy (p < 0.0001). HCM patients in Groups 2 and 3 exhibited predominantly septal hypertrophy (85 and 90%, respectively). Conclusion: HCM patients were classified in four subgroups with distinct ECG features. Patients with primary T wave inversion not secondary to QRS abnormalities had increased HCM Risk-SCD scores and coexisting septal and apical hypertrophy, suggesting that primary T wave inversion may increase SCD risk in HCM, rather than T wave inversion secondary to depolarization abnormalities. Computational ECG phenotyping provides insight into the underlying processes captured by the ECG and has the potential to be a novel and independent factor for risk stratification.

KW - Computational clustering

KW - E-cardiology

KW - Electrocardiography

KW - Hypertrophic cardiomyopathy

KW - Phenotyping

UR - http://www.scopus.com/inward/record.url?scp=85043516149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85043516149&partnerID=8YFLogxK

U2 - 10.3389/fphys.2018.00213

DO - 10.3389/fphys.2018.00213

M3 - Article

AN - SCOPUS:85043516149

VL - 9

JO - Frontiers in Physiology

JF - Frontiers in Physiology

SN - 1664-042X

IS - MAR

M1 - 213

ER -