Ben J M Hermans1, Frank C Bennis2, Arja S Vink3, Tijmen Koopsen4, Aurore Lyon4, Arthur A M Wilde5, Dieter Nuyens6, Tomas Robyns7, Laurent Pison6, Pieter G Postema5, Tammo Delhaas4. 1. Department of Biomedical Engineering, Maastricht University, Maastricht, The Netherlands; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, The Netherlands. Electronic address: ben.hermans@maastrichtuniversity.nl. 2. Department of Biomedical Engineering, Maastricht University, Maastricht, The Netherlands; MHeNS School for Mental Health and Neuroscience, Maastricht University, Maastricht, The Netherlands. 3. Department of Clinical and Experimental Cardiology, Amsterdam UMC, University of Amsterdam, Heart Center, Amsterdam, The Netherlands; Department of Pediatric Cardiology, Emma Children's Hospital, Amsterdam UMC, University of Amsterdam, Amsterdam, The Netherlands. 4. Department of Biomedical Engineering, Maastricht University, Maastricht, The Netherlands; Cardiovascular Research Institute Maastricht (CARIM), Maastricht University, Maastricht, The Netherlands. 5. Department of Clinical and Experimental Cardiology, Amsterdam UMC, University of Amsterdam, Heart Center, Amsterdam, The Netherlands. 6. Department of Cardiology, Ziekenhuis Oost-Limburg, Genk, Belgium. 7. Department of Cardiovascular Diseases, University Hospitals Leuven, Leuven, Belgium.
Abstract
BACKGROUND: Diagnosing long QT syndrome (LQTS) remains challenging because of a considerable overlap in QT interval between patients with LQTS and healthy subjects. Characterizing T-wave morphology might improve LQTS diagnosis. OBJECTIVE: The purpose of this study was to improve LQTS diagnosis by combining new polynomial-based T-wave morphology parameters with the corrected QT interval (QTc), age, and sex in a model. METHODS: A retrospective cohort consisting of 333 patients with LQTS and 345 genotype-negative family members was used in this study. For each patient, a linear combination of the first 2 Hermite-Gauss (HG) polynomials was fitted to the STT segments of an average complex of all precordial leads and limb leads I and II. The weight coefficients as well as the error of the best fit were used to characterize T-wave morphology. Subjects were classified as patients with LQTS or controls by clinical QTc cutoffs and 3 support vector machine models fed with different features. An external cohort consisting of 72 patients and 45 controls was finally used to check the robustness of the models. RESULTS: Baseline QTc cutoffs were specific but had low sensitivity in diagnosing LQTS. The model with T-wave morphology features, QTc, age, and sex had the best overall accuracy (84%), followed by a model with QTc, age, and sex (79%). The model with T-wave morphology features especially performed better in LQTS type 3 patients (69%). CONCLUSION: T-wave morphologies can be characterized by fitting a linear combination of the first 2 Hermite-Gauss polynomials. Adding T-wave morphology characterization to age, sex, and QTc in a support vector machine model improves LQTS diagnosis.
BACKGROUND: Diagnosing long QT syndrome (LQTS) remains challenging because of a considerable overlap in QT interval between patients with LQTS and healthy subjects. Characterizing T-wave morphology might improve LQTS diagnosis. OBJECTIVE: The purpose of this study was to improve LQTS diagnosis by combining new polynomial-based T-wave morphology parameters with the corrected QT interval (QTc), age, and sex in a model. METHODS: A retrospective cohort consisting of 333 patients with LQTS and 345 genotype-negative family members was used in this study. For each patient, a linear combination of the first 2 Hermite-Gauss (HG) polynomials was fitted to the STT segments of an average complex of all precordial leads and limb leads I and II. The weight coefficients as well as the error of the best fit were used to characterize T-wave morphology. Subjects were classified as patients with LQTS or controls by clinical QTc cutoffs and 3 support vector machine models fed with different features. An external cohort consisting of 72 patients and 45 controls was finally used to check the robustness of the models. RESULTS: Baseline QTc cutoffs were specific but had low sensitivity in diagnosing LQTS. The model with T-wave morphology features, QTc, age, and sex had the best overall accuracy (84%), followed by a model with QTc, age, and sex (79%). The model with T-wave morphology features especially performed better in LQTS type 3 patients (69%). CONCLUSION: T-wave morphologies can be characterized by fitting a linear combination of the first 2 Hermite-Gauss polynomials. Adding T-wave morphology characterization to age, sex, and QTc in a support vector machine model improves LQTS diagnosis.
Authors: Jens Cosedis Nielsen; Yenn-Jiang Lin; Marcio Jansen de Oliveira Figueiredo; Alireza Sepehri Shamloo; Alberto Alfie; Serge Boveda; Nikolaos Dagres; Dario Di Toro; Lee L Eckhardt; Kenneth Ellenbogen; Carina Hardy; Takanori Ikeda; Aparna Jaswal; Elizabeth Kaufman; Andrew Krahn; Kengo Kusano; Valentina Kutyifa; Han S Lim; Gregory Y H Lip; Santiago Nava-Townsend; Hui-Nam Pak; Gerardo Rodríguez Diez; William Sauer; Anil Saxena; Jesper Hastrup Svendsen; Diego Vanegas; Marmar Vaseghi; Arthur Wilde; T Jared Bunch; Alfred E Buxton; Gonzalo Calvimontes; Tze-Fan Chao; Lars Eckardt; Heidi Estner; Anne M Gillis; Rodrigo Isa; Josef Kautzner; Philippe Maury; Joshua D Moss; Gi-Byung Nam; Brian Olshansky; Luis Fernando Pava Molano; Mauricio Pimentel; Mukund Prabhu; Wendy S Tzou; Philipp Sommer; Janice Swampillai; Alejandro Vidal; Thomas Deneke; Gerhard Hindricks; Christophe Leclercq Journal: Europace Date: 2020-08-01 Impact factor: 5.214
Authors: Simona Aufiero; Hidde Bleijendaal; Tomas Robyns; Bert Vandenberk; Christian Krijger; Connie Bezzina; Aeilko H Zwinderman; Arthur A M Wilde; Yigal M Pinto Journal: BMC Med Date: 2022-05-03 Impact factor: 11.150