1
|
Kujime K, Seno H, Nakajima K, Yamazaki M, Sakuma I, Yamagata K, Kusano K, Tomii N. Explainable localization of premature ventricular contraction using deep learning-based semantic segmentation of 12-lead electrocardiogram. J Arrhythm 2024; 40:948-957. [PMID: 39139876 PMCID: PMC11317653 DOI: 10.1002/joa3.13096] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/24/2024] [Revised: 05/18/2024] [Accepted: 06/06/2024] [Indexed: 08/15/2024] Open
Abstract
Background Predicting the origin of premature ventricular contraction (PVC) from the preoperative electrocardiogram (ECG) is important for catheter ablation therapies. We propose an explainable method that localizes PVC origin based on the semantic segmentation result of a 12-lead ECG using a deep neural network, considering suitable diagnosis support for clinical application. Methods The deep learning-based semantic segmentation model was trained using 265 12-lead ECG recordings from 84 patients with frequent PVCs. The model classified each ECG sampling time into four categories: background (BG), sinus rhythm (SR), PVC originating from the left ventricular outflow tract (PVC-L), and PVC originating from the right ventricular outflow tract (PVC-R). Based on the ECG segmentation results, a rule-based algorithm classified ECG recordings into three categories: PVC-L, PVC-R, as well as Neutral, which is a group for the recordings requiring the physician's careful assessment before separating them into PVC-L and PVC-R. The proposed method was evaluated with a public dataset which was used in previous research. Results The evaluation of the proposed method achieved neutral rate, accuracy, sensitivity, specificity, F1-score, and area under the curve of 0.098, 0.932, 0.963, 0.882, 0.945, and 0.852 on a private dataset, and 0.284, 0.916, 0.912, 0.930, 0.943, and 0.848 on a public dataset, respectively. These quantitative results indicated that the proposed method outperformed almost all previous studies, although a significant number of recordings resulted in requiring the physician's assessment. Conclusions The feasibility of explainable localization of premature ventricular contraction was demonstrated using deep learning-based semantic segmentation of 12-lead ECG.Clinical trial registration: M26-148-8.
Collapse
Affiliation(s)
- Kota Kujime
- Department of Precision EngineeringGraduate School of EngineeringThe University of TokyoTokyoJapan
| | - Hiroshi Seno
- Department of Precision EngineeringGraduate School of EngineeringThe University of TokyoTokyoJapan
| | - Kenzaburo Nakajima
- Department of Cardiovascular MedicineNational Cerebral and Cardiovascular CenterOsakaJapan
| | - Masatoshi Yamazaki
- Department of Precision EngineeringGraduate School of EngineeringThe University of TokyoTokyoJapan
- Department of CardiologyNagano HospitalOkayamaJapan
| | - Ichiro Sakuma
- Department of Precision EngineeringGraduate School of EngineeringThe University of TokyoTokyoJapan
| | - Kenichiro Yamagata
- Department of Cardiovascular MedicineGraduate School of MedicineThe University of TokyoTokyoJapan
| | - Kengo Kusano
- Department of Cardiovascular MedicineNational Cerebral and Cardiovascular CenterOsakaJapan
| | - Naoki Tomii
- Department of Precision EngineeringGraduate School of EngineeringThe University of TokyoTokyoJapan
| |
Collapse
|
2
|
Chen N, Wang L, Jiao J, Ju W, Wang Z, Zou C, Yi F, Xiao F, Shen W, Li C, Shi L, Chen L, Ji Y, Wei Y, Gu K, Yang G, Chen H, Li M, Liu H, Chen M. RV1+RV3 Index to Differentiate Idiopathic Ventricular Arrhythmias Arising From Right Ventricular Outflow Tract and Aortic Sinus of Valsalva: A Multicenter Study. J Am Heart Assoc 2024; 13:e033779. [PMID: 38533964 PMCID: PMC11179762 DOI: 10.1161/jaha.123.033779] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/05/2023] [Accepted: 03/03/2024] [Indexed: 03/28/2024]
Abstract
BACKGROUND This study aimed to investigate the predictive value of parameters of every precordial lead and their combinations in differentiating between idiopathic ventricular arrhythmias (IVAs) from the right ventricular outflow tract and aortic sinus of Valsalva (ASV). METHODS AND RESULTS Between March 1, 2018, and December 1, 2021, consecutive patients receiving successful ablation of right ventricular outflow tract or ASV IVAs were enrolled. The amplitude and duration of the R wave and S wave were measured in every precordial lead during IVAs. These parameters were either summed, subtracted, multiplied, or divided to create different indexes. The index with the highest area under the curve to predict ASV IVAs was developed, compared with established indexes, and validated in an independent prospective multicenter cohort. A total of 150 patients (60 men; mean age, 45.3±16.4 years) were included in the derivation cohort. The RV1+RV3 index (summed R-wave amplitude in leads V1 and V3) had the highest area under the curve (0.942) among the established indexes. An RV1+RV3 index >1.3 mV could predict ASV IVAs with a sensitivity of 95% and a specificity of 83%. Its predictive performance was maintained in the validation cohort (N=109). In patients with V3 R/S transition, an RV1+RV3 index >1.3 mV could predict ASV IVAs, with an area under the curve of 0.892, 93% sensitivity, and 75% specificity. CONCLUSIONS The RV1+RV3 index is a simple and novel criterion that accurately differentiates between right ventricular outflow tract and ASV IVAs. Its performance outperformed established indexes, making it a valuable tool in clinical practice.
Collapse
Affiliation(s)
- Ning Chen
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Lei Wang
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Jincheng Jiao
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Weizhu Ju
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Zhe Wang
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Cao Zou
- The First Affiliated Hospital of Soochow UniversitySoochowChina
| | - Fu Yi
- Xijing HospitalXi’anChina
| | - Fangyi Xiao
- The First Affiliated Hospital of Wenzhou Medical UniversityWenzhouChina
| | | | - Chengzong Li
- The Affiliated Hospital of Xuzhou Medical UniversityXuzhouChina
| | - Linsheng Shi
- The Second Affiliated Hospital of Nantong UniversityNantongChina
| | | | - Yuan Ji
- Changzhou No.2 People’s HospitalChangzhouChina
| | - Youquan Wei
- The First Affiliated Yijishan Hospital of Wannan Medical CollegeWuhuChina
| | - Kai Gu
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Gang Yang
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Hongwu Chen
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Mingfang Li
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Hailei Liu
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| | - Minglong Chen
- The First Affiliated Hospital of Nanjing Medical UniversityNanjingChina
| |
Collapse
|
3
|
Penela D, Falasconi G, Carreño JM, Soto-Iglesias D, Fernández-Armenta J, Acosta J, Martí-Almor J, Benito B, Bellido A, Chauca A, Scherer C, Viveros D, Alderete J, Silva E, Ordoñez A, Francisco-Pascual J, Rivas-Gandara N, Meca-Santamaria J, Franco P, De Lucia C, Ali H, Cappato R, Cámara O, Francia P, Berruezo A. A hybrid clinical and electrocardiographic score to predict the origin of outflow tract ventricular arrhythmias. J Interv Card Electrophysiol 2023; 66:1877-1888. [PMID: 36795268 DOI: 10.1007/s10840-023-01507-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 11/12/2022] [Accepted: 02/04/2023] [Indexed: 02/17/2023]
Abstract
BACKGROUND To predict the outflow tract ventricular arrhythmias (OTVA) site of origin (SOO) before the ablation procedure has important practical implications. The present study sought to prospectively evaluate the accuracy of a clinical and electrocardiographic hybrid algorithm (HA) for the prediction of OTVAs-SOO, and at the same time to develop and to prospectively validate a new score with improved discriminatory capacity. METHODS In this multicenter study, we prospectively enrolled consecutive patients referred for OTVA ablation (N = 202), and we divided them in a derivation sample and a validation cohort. Surface ECGs during OTVA were analyzed to compare previous published ECG-only criteria and to develop a new score. RESULTS In the derivation sample (N = 105), the correct prediction rate of HA and ECG-only criteria ranged from 74 to 89%. R-wave amplitude in V3 was the best ECG parameter for discriminating LVOT origin in V3 precordial transition (V3PT) patients, and was incorporated to the novel weighted hybrid score (WHS). WHS correctly classified 99 (94.2%) patients, presenting 90% sensitivity and 96% specificity (AUC 0.97) in the entire population; WHS mantained a 87% sensitivity and 91% specificity (AUC 0.95) in patients with V3PT subgroup. The high discriminatory capacity was confirmed in the validation sample (N = 97): the WHS exhibited an AUC (0.93), and a WHS ≥ 2 allowed a correct prediction of LVOT origin in 87 (90.0%) cases, yielding a sensitivity of 87% and specificity of 90%; moreover, the V3PT subgroup showed an AUC of 0.92, and a punctuation ≥ 2 predicted an LVOT origin with a sensitivity of 94% and specificity of 78%. CONCLUSIONS The novel hybrid score has proved to accurately anticipate the OTVA's origin, even in those with a V3 precordial transition. A Weighted hybrid score. B Typical examples of the use of the weighted hybrid score. C ROC analysis of WHS and previous ECG criteria for prediction of LVOT origin in the derivation cohort. D ROC analysis of WHS and previous ECG criteria for prediction of LVOT origin in the V3 precordial transition OTVA subgroup.
Collapse
Affiliation(s)
- Diego Penela
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | - Giulio Falasconi
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
- University of Barcelona, Campus Clínic, Barcelona, Spain
| | - Jose Miguel Carreño
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | - David Soto-Iglesias
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | | | - Juan Acosta
- Virgen del Rocío University Hospital, Sevilla, Spain
| | - Julio Martí-Almor
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | - Begoña Benito
- Hospital Vall d'Hebron, Barcelona, Spain
- Universitat Autònoma de Barcelona, Barcelona, Spain
| | - Aldo Bellido
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | - Alfredo Chauca
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | - Claudia Scherer
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | - Daniel Viveros
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
- University of Barcelona, Campus Clínic, Barcelona, Spain
| | - Jose Alderete
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
- University of Barcelona, Campus Clínic, Barcelona, Spain
| | | | - Augusto Ordoñez
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | | | | | | | - Paula Franco
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain
| | | | - Hussam Ali
- IRCCS Multimedica Group, Sesto San Giovanni, Italy
| | | | | | - Pietro Francia
- Cardiology, Department of Clinical and Molecular Medicine, St. Andrea Hospital, Sapienza University, Rome, Italy
| | - Antonio Berruezo
- Heart Institute, Teknon Medical Centre, C/ Vilana, 12; 08022, Barcelona, Spain.
| |
Collapse
|
4
|
Bourquin L, Küffer T, Asatryan B, Badertscher P, Baldinger SH, Knecht S, Seiler J, Spies F, Servatius H, Kühne M, Noti F, Osswald S, Haeberlin A, Tanner H, Roten L, Reichlin T, Sticherling C. Validation of a clinical model for predicting left versus right ventricular outflow tract origin of idiopathic ventricular arrhythmias. Pacing Clin Electrophysiol 2023; 46:1186-1196. [PMID: 37616339 DOI: 10.1111/pace.14809] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/16/2022] [Revised: 07/26/2023] [Accepted: 08/15/2023] [Indexed: 08/26/2023]
Abstract
BACKGROUND Prediction of the chamber of origin in patients with outflow tract ventricular arrhythmias (OTVA) remains challenging. A clinical risk score based on age, sex and presence of hypertension was associated with a left ventricular outflow tract (LVOT) origin. We aimed to validate this clinical score to predict an LVOT origin in patients with OTVA. METHODS In a two-center observational cohort study, unselected patients undergoing catheter ablation (CA) for OTVA were enrolled. All procedures were performed using an electroanatomical mapping system. Successful ablation was defined as a ≥80% reduction of the initial overall PVC burden after 3 months of follow-up. Patients with unsuccessful ablation were excluded from this analysis. RESULTS We included 187 consecutive patients with successful CA of idiopathic OTVA. Mean age was 52 ± 15 years, 102 patients (55%) were female, and 74 (40%) suffered from hypertension. A LVOT origin was found in 64 patients (34%). A score incorporating age, sex and presence of hypertension reached 73% sensitivity and 67% specificity for a low (0-1) and high (2-3) score, to predict an LVOT origin. The combination of one ECG algorithm (V2 S/V3 R-index) with the clinical score resulted in a sensitivity and specificity of 81% and 70% for PVCs with R/S transition at V3 . CONCLUSION The published clinical score yielded a lower sensitivity and specificity in our cohort. However, for PVCs with R/S transition at V3, the combination with an existing ECG algorithm can improve the predictability of LVOT origin.
Collapse
Affiliation(s)
- Luc Bourquin
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
| | - Thomas Küffer
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Babken Asatryan
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Patrick Badertscher
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
| | - Samuel H Baldinger
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Sven Knecht
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
| | - Jens Seiler
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Florian Spies
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
| | - Helge Servatius
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Michael Kühne
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
| | - Fabian Noti
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Stefan Osswald
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
| | - Andreas Haeberlin
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Hildegard Tanner
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Laurent Roten
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Tobias Reichlin
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
- Department of Cardiology, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Christian Sticherling
- Department of Cardiology and Cardiovascular Research Institute Basel (CRIB), University Hospital Basel, Basel, Switzerland
| |
Collapse
|
5
|
Tsiachris D, Botis M, Doundoulakis I, Bartsioka LI, Tsioufis P, Kordalis A, Antoniou CK, Tsioufis K, Gatzoulis KA. Electrocardiographic Characteristics, Identification, and Management of Frequent Premature Ventricular Contractions. Diagnostics (Basel) 2023; 13:3094. [PMID: 37835837 PMCID: PMC10572222 DOI: 10.3390/diagnostics13193094] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/17/2023] [Revised: 09/09/2023] [Accepted: 09/26/2023] [Indexed: 10/15/2023] Open
Abstract
Premature ventricular complexes (PVCs) are frequently encountered in clinical practice. The association of PVCs with adverse cardiovascular outcomes is well established in the context of structural heart disease, yet not so much in the absence of structural heart disease. However, cardiac magnetic resonance (CMR) seems to contribute prognostically in the latter subgroup. PVC-induced myocardial dysfunction refers to the impairment of ventricular function due to PVCs and is mostly associated with a PVC burden > 10%. Surface 12-lead ECG has long been used to localize the anatomic site of origin and multiple algorithms have been developed to differentiate between right ventricular and left ventricular outflow tract (RVOT and LVOT, respectively) origin. Novel algorithms include alternative ECG lead configurations and, lately, sophisticated artificial intelligence methods have been utilized to determine the origins of outflow tract arrhythmias. The decision to therapeutically address PVCs should be made upon the presence of symptoms or the development of PVC-induced myocardial dysfunction. Therapeutic modalities include pharmacological therapy (I-C antiarrhythmic drugs and beta blockers), as well as catheter ablation, which has demonstrated superior efficacy and safety.
Collapse
Affiliation(s)
- Dimitris Tsiachris
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
- Athens Heart Center, Athens Medical Center, 15125 Athens, Greece
| | - Michail Botis
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
| | - Ioannis Doundoulakis
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
| | - Lamprini Iro Bartsioka
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
| | - Panagiotis Tsioufis
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
| | - Athanasios Kordalis
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
| | - Christos-Konstantinos Antoniou
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
- Athens Heart Center, Athens Medical Center, 15125 Athens, Greece
| | - Konstantinos Tsioufis
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
| | - Konstantinos A. Gatzoulis
- First Department of Cardiology, School of Medicine, National and Kapodistrian University of Athens, “Hippokration” Hospital, 11527 Athens, Greece; (M.B.); (I.D.); (L.I.B.); (P.T.); (A.K.); (C.-K.A.); (K.T.); (K.A.G.)
| |
Collapse
|
6
|
A Four-Stepwise Electrocardiographic Algorithm for Differentiation of Ventricular Arrhythmias Originated from Left Ventricular Outflow Tract. J Clin Med 2022; 11:jcm11216398. [PMID: 36362626 PMCID: PMC9653710 DOI: 10.3390/jcm11216398] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/26/2022] [Revised: 10/21/2022] [Accepted: 10/27/2022] [Indexed: 11/17/2022] Open
Abstract
Several electrocardiographic algorithms have been proposed to identify the site of origin for the ventricular arrhythmias (VAs) from the left ventricular outflow tract (LVOT) versus right ventricular outflow tract. However, the electrocardiographic criteria for distinguishing VAs originated from the different sites of LVOT is lacking. We aimed to develop a simple and efficient ECG algorithm to differentiate LVOT VAs originated from the aortic root, AMC and LV summit. We analyzed 12-lead ECG characteristics of 68 consecutive patients who underwent successful radiofrequency catheter ablation of symptomatic VAs from LVOT. Patients were divided into RCC (right coronary cusp) group (n = 8), the L-RCC (the junction between the LCC and RCC) group (n = 21), the LCC (left coronary cusp) group (n = 24), the aortomitral continuity (AMC) group (n = 9) and the LV summit group (n = 6) according to the final ablation sites. Measurements with the highest diagnostic performance were modeled into a 4-stepwise algorithm to discriminate LVOT VAs. The performance of this novel algorithm was prospectively tested in a validation cohort of 43 consecutive patients undergoing LVOT VAs ablation. Based on the accuracy of AUC, a 4-stepwise ECG algorithm was developed. First, the QS duration in aVL > 134 ms was used to distinguish VAs from AMC, LV summit and VAs from aortic root (80% sensitivity and 76% specificity). Second, the R duration in II > 155 ms was used to differentiate VAs from LV summit and VAs from AMC (67% sensitivity and 56% specificity). Third, the ratio of III/II < 0.9 was used to discriminate VAs from RCC and VAs from LCC, L-RCC (82% sensitivity and 63% specificity). Fourth, the QS duration of aVR > 130 ms was used to discern VAs from LCC and VAs from L-RCC (75% sensitivity and 62% specificity). In the prospective evaluation, our 4-stepwise ECG algorithm exhibited a good predictive value. We have developed a novel and simple 4-stepwise ECG algorithm with good predictive value to discriminate the AVs from different sites of LVOT.
Collapse
|
7
|
Qiu S, Sun Z, Li X, Li J, Huang X, Liu M, Bin J, Liao Y, Xiu J, Zha D, Xue Y, Wang L, Wang Y. A novel and effective ECG method to differentiate right from left ventricular outflow tract arrhythmias: Angle-corrected V2S. Front Cardiovasc Med 2022; 9:868634. [PMID: 36312235 PMCID: PMC9606339 DOI: 10.3389/fcvm.2022.868634] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2022] [Accepted: 09/16/2022] [Indexed: 11/13/2022] Open
Abstract
Background and aims Standard 12-lead electrocardiogram (ECG) patterns combined with the anatomical cardiac long-axis angle revealed by chest X-ray can prevent the influence of cardiac rotation, physical shape, and lead position, so it may be an ideal means to predict the origin of the outflow tract (OT) ventricular arrhythmias (OTVAs) for ablation procedures. The study explores the value of this strategy in identifying the origin of OTVA. Methods This study was conducted using a retrospective cohort and a prospective cohort of consecutive patients at two centers. The anatomical cardiac long-axis angle was calculated by measuring the angle between the cardiac long-axis (a line joining the apex to the midpoint of the mitral annulus) and the horizontal plane on a chest X-ray. The V2S angle was calculated as the V2S amplitude times the angle. We ultimately enrolled 147 patients with symptomatic OTVAs who underwent successful radiofrequency catheter ablation (RFCA) (98 women (66.7%); mean age 46.9 ± 14.7 years; 126 right ventricular OT (RVOT) origins, 21 left ventricular OT (LVOT) origins) as a development cohort. The new algorithm was validated in 48 prospective patients (12 men (25.0%); mean age 48.0 ± 15.8 years; 36 RVOT, 12 LVOT origins). Results Patients with RVOT VAs had greater V2S, long-axis angle, and V2S angle than patients with LVOT VA (all P < 0.001). The cut-off V2S angle obtained by receiver operating characteristic (ROC) curve analysis was 58.28 mV° for the prediction of RVOT origin (sensitivity: 85.7%; specificity: 95.2%; positive predictive value: 99.1%; negative predictive value: 52.6%). The AUC achieved using the V2S angle was 0.888 (P < 0.001), which was the highest among all indexes (V2S/V3R: 0.887 (P < 0.016); TZ index: 0.858 (P < 0.001); V1-2 SRd: 0.876 (P < 0.001); V3 transition: 0.651 (P < 0.001)). In the prospective cohort, the V2S angle had a high overall accuracy of 93.8% and decreased the procedure time (P = 0.002). Conclusion V2S angle can be a novel measure that can be used to accurately differentiate RVOT from LVOT origins. It could help decrease ablation duration and radiation exposure.
Collapse
Affiliation(s)
- Shifeng Qiu
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Zhuhua Sun
- Department of Health Management, The Third Affiliated Hospital of Southern Medical University, Guangzhou, China
| | - Xinzhong Li
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Jianyong Li
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Xiaobo Huang
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Menghui Liu
- Department of Cardiology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China,Key Laboratory on Assisted Circulation, Ministry of Health, Guangzhou, China
| | - Jianping Bin
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Yulin Liao
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Jiancheng Xiu
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Daogang Zha
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China
| | - Yumei Xue
- Guangdong Cardiovascular Institute, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China,Guangdong Provincial Key Laboratory of Clinical Pharmacology, Guangdong Provincial People’s Hospital, Guangdong Academy of Medical Sciences, Guangzhou, China,Yumei Xue,
| | - Lichun Wang
- Department of Cardiology, The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China,Key Laboratory on Assisted Circulation, Ministry of Health, Guangzhou, China,Lichun Wang,
| | - Yuegang Wang
- Department of Cardiology, Nanfang Hospital, Southern Medical University, Guangzhou, China,Guangdong Provincial Key Laboratory of Shock and Microcirculation, Nanfang Hospital, Southern Medical University, Guangzhou, China,State Key Laboratory of Organ Failure Research, Nanfang Hospital, Southern Medical University, Guangzhou, China,*Correspondence: Yuegang Wang,
| |
Collapse
|
8
|
Chang TY, Chen KW, Liu CM, Chang SL, Lin YJ, Lo LW, Hu YF, Chung FP, Lin CY, Kuo L, Chen SA. A High-Precision Deep Learning Algorithm to Localize Idiopathic Ventricular Arrhythmias. J Pers Med 2022; 12:jpm12050764. [PMID: 35629186 PMCID: PMC9145898 DOI: 10.3390/jpm12050764] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/28/2022] [Revised: 04/30/2022] [Accepted: 05/06/2022] [Indexed: 12/04/2022] Open
Abstract
Background: An accurate prediction of ventricular arrhythmia (VA) origins can optimize the strategy of ablation, and facilitate the procedure. Objective: This study aimed to develop a machine learning model from surface ECG to predict VA origins. Methods: We obtained 3628 waves of ventricular premature complex (VPC) from 731 patients. We chose to include all signal information from 12 ECG leads for model input. A model is composed of two groups of convolutional neural network (CNN) layers. We chose around 13% of all the data for model testing and 10% for validation. Results: In the first step, we trained a model for binary classification of VA source from the left or right side of the chamber with an area under the curve (AUC) of 0.963. With a threshold of 0.739, the sensitivity and specification are 90.7% and 92.3% for identifying left side VA. Then, we obtained the second model for predicting VA from the LV summit with AUC is 0.998. With a threshold of 0.739, the sensitivity and specificity are 100% and 98% for the LV summit. Conclusions: Our machine learning algorithm of surface ECG facilitates the localization of VPC, especially for the LV summit, which might optimize the ablation strategy.
Collapse
Affiliation(s)
- Ting-Yung Chang
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Department of Nursing, National Taipei University of Nursing and Health Sciences, Taipei 112303, Taiwan
| | - Ke-Wei Chen
- Department of BioMedical Engineering, National Cheng Kung University, Tainan City 701401, Taiwan;
| | - Chih-Min Liu
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
| | - Shih-Lin Chang
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Correspondence: ; Tel.: +886-2-7735-3832; Fax: +886-2-2872-4082
| | - Yenn-Jiang Lin
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
| | - Li-Wei Lo
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
| | - Yu-Feng Hu
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
| | - Fa-Po Chung
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
| | - Chin-Yu Lin
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
| | - Ling Kuo
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
| | - Shih-Ann Chen
- Heart Rhythm Center, Division of Cardiology, Department of Medicine, Taipei Veterans General Hospital, Taipei 11217, Taiwan; (T.-Y.C.); (C.-M.L.); (Y.-J.L.); (L.-W.L.); (Y.-F.H.); (F.-P.C.); (C.-Y.L.); (L.K.); (S.-A.C.)
- Institute of Cardiovascular Research, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Institute of Clinical Medicine, National Yang Ming Chiao Tung University, Taipei 11221, Taiwan
- Cardiovascular Center, Taichung Veterans General Hospital, Taichung 40705, Taiwan
| |
Collapse
|
9
|
Nakasone K, Nishimori M, Kiuchi K, Shinohara M, Fukuzawa K, Takami M, El Hamriti M, Sommer P, Sakai J, Nakamura T, Yatomi A, Sonoda Y, Takahara H, Yamamoto K, Suzuki Y, Tani K, Iwai H, Nakanishi Y, Hirata KI. Development of a Visualization Deep Learning Model for Classifying Origins of Ventricular Arrhythmias. Circ J 2022; 86:1273-1280. [PMID: 35387940 DOI: 10.1253/circj.cj-22-0065] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/09/2022]
Abstract
BACKGROUND Several algorithms have been proposed for differentiating the right and left outflow tracts (RVOT/LVOT) arrhythmia origins from 12-lead electrocardiograms (ECGs); however, the procedure is complicated. A deep learning (DL) model, a form of artificial intelligence, can directly use ECGs and depict the importance of the leads and waveforms. This study aimed to create a visualized DL model that could classify arrhythmia origins more accurately.Methods and Results: This study enrolled 80 patients who underwent catheter ablation. A convolutional neural network-based model that could classify arrhythmia origins with 12-lead ECGs and visualize the leads that contributed to the diagnosis using a gradient-weighted class activation mapping method was developed. The average prediction results of the origins by the DL model were 89.4% (88.2-90.6) for accuracy and 95.2% (94.3-96.2) for recall, which were significantly better than when a conventional algorithm is used. The ratio of the contribution to the prediction differed between RVOT and LVOT origins. Although leads V1 to V3 and the limb leads had a focused balance in the LVOT group, the contribution ratio of leads aVR, aVL, and aVF was higher in the RVOT group. CONCLUSIONS This study diagnosed the arrhythmia origins more accurately than the conventional algorithm, and clarified which part of the 12-lead waveforms contributed to the diagnosis. The visualized DL model was convincing and may play a role in understanding the pathogenesis of arrhythmias.
Collapse
Affiliation(s)
- Kazutaka Nakasone
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Makoto Nishimori
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine.,Division of Epidemiology, Kobe University Graduate School of Medicine
| | - Kunihiko Kiuchi
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine.,Section of Arrhythmia, Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | | | - Koji Fukuzawa
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine.,Section of Arrhythmia, Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Mitsuru Takami
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Mustapha El Hamriti
- Clinic of Electrophysiology, Heart and Diabetes Center NRW, University Hospital of Ruhr-University Bochum
| | - Philipp Sommer
- Clinic of Electrophysiology, Heart and Diabetes Center NRW, University Hospital of Ruhr-University Bochum
| | - Jun Sakai
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Toshihiro Nakamura
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Atsusuke Yatomi
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Yusuke Sonoda
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Hiroyuki Takahara
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Kyoko Yamamoto
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Yuya Suzuki
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Kenichi Tani
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Hidehiro Iwai
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Yusuke Nakanishi
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| | - Ken-Ichi Hirata
- Division of Cardiovascular Medicine, Department of Internal Medicine, Kobe University Graduate School of Medicine
| |
Collapse
|
10
|
Zheng J, Fu G, Struppa D, Abudayyeh I, Contractor T, Anderson K, Chu H, Rakovski C. A High Precision Machine Learning-Enabled System for Predicting Idiopathic Ventricular Arrhythmia Origins. Front Cardiovasc Med 2022; 9:809027. [PMID: 35360041 PMCID: PMC8962834 DOI: 10.3389/fcvm.2022.809027] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/04/2021] [Accepted: 02/15/2022] [Indexed: 11/22/2022] Open
Abstract
Background Radiofrequency catheter ablation (CA) is an efficient antiarrhythmic treatment with a class I indication for idiopathic ventricular arrhythmia (IVA), only when drugs are ineffective or have unacceptable side effects. The accurate prediction of the origins of IVA can significantly increase the operation success rate, reduce operation duration and decrease the risk of complications. The present work proposes an artificial intelligence-enabled ECG analysis algorithm to estimate possible origins of idiopathic ventricular arrhythmia at a clinical-grade level accuracy. Method A total of 18,612 ECG recordings extracted from 545 patients who underwent successful CA to treat IVA were proportionally sampled into training, validation and testing cohorts. We designed four classification schemes responding to different hierarchical levels of the possible IVA origins. For every classification scheme, we compared 98 distinct machine learning models with optimized hyperparameter values obtained through extensive grid search and reported an optimal algorithm with the highest accuracy scores attained on the testing cohorts. Results For classification scheme 4, our pioneering study designs and implements a machine learning-based ECG algorithm to predict 21 possible sites of IVA origin with an accuracy of 98.24% on a testing cohort. The accuracy and F1-score for the left three schemes surpassed 99%. Conclusion In this work, we developed an algorithm that precisely predicts the correct origins of IVA (out of 21 possible sites) and outperforms the accuracy of all prior studies and human experts.
Collapse
Affiliation(s)
- Jianwei Zheng
- Schmid College of Science and Technology, Chapman University, Orange, CA, United States
| | - Guohua Fu
- Arrhythmia Center, Ningbo First Hospital, Zhejiang University, Ningbo, China
| | - Daniele Struppa
- Schmid College of Science and Technology, Chapman University, Orange, CA, United States
| | - Islam Abudayyeh
- Interventional Cardiology, Loma Linda University Health, Loma Linda, CA, United States
| | - Tahmeed Contractor
- Interventional Cardiology, Loma Linda University Health, Loma Linda, CA, United States
| | - Kyle Anderson
- Schmid College of Science and Technology, Chapman University, Orange, CA, United States
| | - Huimin Chu
- Arrhythmia Center, Ningbo First Hospital, Zhejiang University, Ningbo, China
- *Correspondence: Huimin Chu
| | - Cyril Rakovski
- Schmid College of Science and Technology, Chapman University, Orange, CA, United States
| |
Collapse
|
11
|
Gabriels JK, Abdelrahman M, Nambiar L, Kim J, Ip JE, Thomas G, Liu CF, Markowitz SM, Lerman BB, Cheung JW. Reappraisal of electrocardiographic criteria for localization of idiopathic outflow region ventricular arrhythmias. Heart Rhythm 2021; 18:1959-1965. [PMID: 34375724 DOI: 10.1016/j.hrthm.2021.08.003] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/17/2021] [Revised: 07/20/2021] [Accepted: 08/01/2021] [Indexed: 11/25/2022]
Abstract
BACKGROUND Electrocardiographic (ECG) criteria have been proposed to localize the site of origin of outflow region ventricular arrhythmias (VAs). Many factors influence the QRS morphology of VAs and may limit the accuracy of these criteria. OBJECTIVE The purpose of this study was to assess the accuracy of ECG criteria that differentiate right from left outflow region VAs and localize VAs within the aortic sinus of Valsalva (ASV). METHODS One hundred one patients (mean age 52 ± 16 years; 55 [54%] women) undergoing catheter ablation of right ventricular outflow tract (RVOT) or ASV VAs with a left bundle branch block, inferior axis morphology were studied. ECG measurements including V2 transition ratio, transition zone index, R-wave duration index, R/S amplitude index, V2S/V3R index, V1-3 QRS morphology, R-wave amplitude in the inferior leads were tabulated for all VAs. Comparisons were made between the predicted site of origin using these criteria and the successful ablation site. RESULTS Patients had successful ablation of 71 RVOT and 38 ASV VAs. For the differentiation of RVOT from ASV VAs, the positive predictive values and negative predictive values for all tested ECG criteria ranged from 42% to 75% and from 71% to 82%, respectively, with the V2S/V3R index having the largest area under the curve of 0.852. Morphological QRS criteria in leads V1 through V3 did not localize ASV VAs. The maximum R-wave amplitude in the inferior leads was the sole criterion demonstrating a significant difference between right ASV, right-left ASV commissure, and left ASV sites. CONCLUSION ECG criteria for differentiating right from left ventricular outflow region VAs and for localizing ASV VAs have a limited accuracy.
Collapse
Affiliation(s)
- James K Gabriels
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - Mohamed Abdelrahman
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - Lakshmi Nambiar
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - Jiwon Kim
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - James E Ip
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - George Thomas
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - Christopher F Liu
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - Steven M Markowitz
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - Bruce B Lerman
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York
| | - Jim W Cheung
- Division of Cardiology, Department of Medicine, Weill Cornell Medicine - New York Presbyterian Hospital, New York, New York.
| |
Collapse
|
12
|
Lee J, Adeola O, Garan H, Stevenson WG, Yarmohammadi H. Electrocardiographic recognition of benign and malignant right ventricular arrhythmias. Europace 2021; 23:1338-1349. [PMID: 33864080 DOI: 10.1093/europace/euab047] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/12/2020] [Accepted: 02/17/2021] [Indexed: 11/12/2022] Open
Abstract
Ventricular arrhythmias (VAs) can originate from different anatomical locations of the right ventricle. Ventricular arrhythmias originating from right ventricle have unique electrocardiographic (ECG) characteristics that can be utilized to localize the origin of the arrhythmia. This is crucial in pre-procedural planning particularly for ablation treatments. Moreover, non-ischaemic structural heart diseases, such as infiltrative and congenital heart diseases, are associated with the VAs that exhibit particular ECG findings. This article comprehensively reviews discriminatory ECG characteristics of VAs in the right ventricle with and without structural right ventricular diseases.
Collapse
Affiliation(s)
- John Lee
- Division of Cardiology, Mount Sinai Medical Center, Miami Beach, FL, USA
| | - Oluwaseun Adeola
- Division of Cardiology, Vanderbilt Heart and Vascular Institute, Nashville, TN, USA
| | - Hasan Garan
- Division of Cardiology, Department of Medicine, Columbia University Vagelos College of Physicians and Surgeons, 177 Fort Washington Avenue, Room 637, New York, NY 10032, USA
| | - William G Stevenson
- Division of Cardiology, Vanderbilt Heart and Vascular Institute, Nashville, TN, USA
| | - Hirad Yarmohammadi
- Division of Cardiology, Department of Medicine, Columbia University Vagelos College of Physicians and Surgeons, 177 Fort Washington Avenue, Room 637, New York, NY 10032, USA
| |
Collapse
|
13
|
Zheng J, Fu G, Abudayyeh I, Yacoub M, Chang A, Feaster WW, Ehwerhemuepha L, El-Askary H, Du X, He B, Feng M, Yu Y, Wang B, Liu J, Yao H, Chu H, Rakovski C. A High-Precision Machine Learning Algorithm to Classify Left and Right Outflow Tract Ventricular Tachycardia. Front Physiol 2021; 12:641066. [PMID: 33716788 PMCID: PMC7947246 DOI: 10.3389/fphys.2021.641066] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/13/2020] [Accepted: 01/18/2021] [Indexed: 12/03/2022] Open
Abstract
Introduction Multiple algorithms based on 12-lead ECG measurements have been proposed to identify the right ventricular outflow tract (RVOT) and left ventricular outflow tract (LVOT) locations from which ventricular tachycardia (VT) and frequent premature ventricular complex (PVC) originate. However, a clinical-grade machine learning algorithm that automatically analyzes characteristics of 12-lead ECGs and predicts RVOT or LVOT origins of VT and PVC is not currently available. The effective ablation sites of RVOT and LVOT, confirmed by a successful ablation procedure, provide evidence to create RVOT and LVOT labels for the machine learning model. Methods We randomly sampled training, validation, and testing data sets from 420 patients who underwent successful catheter ablation (CA) to treat VT or PVC, containing 340 (81%), 38 (9%), and 42 (10%) patients, respectively. We iteratively trained a machine learning algorithm supplied with 1,600,800 features extracted via our proprietary algorithm from 12-lead ECGs of the patients in the training cohort. The area under the curve (AUC) of the receiver operating characteristic curve was calculated from the internal validation data set to choose an optimal discretization cutoff threshold. Results The proposed approach attained the following performance: accuracy (ACC) of 97.62 (87.44–99.99), weighted F1-score of 98.46 (90–100), AUC of 98.99 (96.89–100), sensitivity (SE) of 96.97 (82.54–99.89), and specificity (SP) of 100 (62.97–100). Conclusions The proposed multistage diagnostic scheme attained clinical-grade precision of prediction for LVOT and RVOT locations of VT origin with fewer applicability restrictions than prior studies.
Collapse
Affiliation(s)
- Jianwei Zheng
- Computational and Data Science, Chapman University, Orange, CA, United States
| | - Guohua Fu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Islam Abudayyeh
- Department of Cardiology, Loma Linda University, Loma Linda, CA, United States
| | - Magdi Yacoub
- Harefield Heart Science Center, Imperial College London, London, United Kingdom
| | | | | | | | - Hesham El-Askary
- Computational and Data Science, Chapman University, Orange, CA, United States.,Department of Environmental Sciences, Faculty of Science, Alexandria University, Alexandria, Egypt
| | - Xianfeng Du
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Bin He
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Mingjun Feng
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Yibo Yu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Binhao Wang
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Jing Liu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Hai Yao
- Zhejiang Cachet Jetboom Medical Devices Co., Ltd., Hangzhou, China
| | - Huimin Chu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Cyril Rakovski
- Computational and Data Science, Chapman University, Orange, CA, United States
| |
Collapse
|
14
|
Zheng J, Fu G, Abudayyeh I, Yacoub M, Chang A, Feaster WW, Ehwerhemuepha L, El-Askary H, Du X, He B, Feng M, Yu Y, Wang B, Liu J, Yao H, Chu H, Rakovski C. A High-Precision Machine Learning Algorithm to Classify Left and Right Outflow Tract Ventricular Tachycardia. Front Physiol 2021. [PMID: 33716788 DOI: 10.6084/m9.figshare.c.4668086.v2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/06/2022] Open
Abstract
Introduction Multiple algorithms based on 12-lead ECG measurements have been proposed to identify the right ventricular outflow tract (RVOT) and left ventricular outflow tract (LVOT) locations from which ventricular tachycardia (VT) and frequent premature ventricular complex (PVC) originate. However, a clinical-grade machine learning algorithm that automatically analyzes characteristics of 12-lead ECGs and predicts RVOT or LVOT origins of VT and PVC is not currently available. The effective ablation sites of RVOT and LVOT, confirmed by a successful ablation procedure, provide evidence to create RVOT and LVOT labels for the machine learning model. Methods We randomly sampled training, validation, and testing data sets from 420 patients who underwent successful catheter ablation (CA) to treat VT or PVC, containing 340 (81%), 38 (9%), and 42 (10%) patients, respectively. We iteratively trained a machine learning algorithm supplied with 1,600,800 features extracted via our proprietary algorithm from 12-lead ECGs of the patients in the training cohort. The area under the curve (AUC) of the receiver operating characteristic curve was calculated from the internal validation data set to choose an optimal discretization cutoff threshold. Results The proposed approach attained the following performance: accuracy (ACC) of 97.62 (87.44-99.99), weighted F1-score of 98.46 (90-100), AUC of 98.99 (96.89-100), sensitivity (SE) of 96.97 (82.54-99.89), and specificity (SP) of 100 (62.97-100). Conclusions The proposed multistage diagnostic scheme attained clinical-grade precision of prediction for LVOT and RVOT locations of VT origin with fewer applicability restrictions than prior studies.
Collapse
Affiliation(s)
- Jianwei Zheng
- Computational and Data Science, Chapman University, Orange, CA, United States
| | - Guohua Fu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Islam Abudayyeh
- Department of Cardiology, Loma Linda University, Loma Linda, CA, United States
| | - Magdi Yacoub
- Harefield Heart Science Center, Imperial College London, London, United Kingdom
| | | | | | | | - Hesham El-Askary
- Computational and Data Science, Chapman University, Orange, CA, United States.,Department of Environmental Sciences, Faculty of Science, Alexandria University, Alexandria, Egypt
| | - Xianfeng Du
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Bin He
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Mingjun Feng
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Yibo Yu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Binhao Wang
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Jing Liu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Hai Yao
- Zhejiang Cachet Jetboom Medical Devices Co., Ltd., Hangzhou, China
| | - Huimin Chu
- Department of Cardiology, Ningbo First Hospital of Zhejiang University, Hangzhou, China
| | - Cyril Rakovski
- Computational and Data Science, Chapman University, Orange, CA, United States
| |
Collapse
|
15
|
Wang J, Miao C, Yang G, Xu L, Xing R, Jia Y, Zhang R, Wang Y, Huang L, Liu S. Lead I R-wave amplitude to distinguish ventricular arrhythmias with lead V 3 transition originating from the left versus right ventricular outflow tract. Clin Cardiol 2020; 44:100-107. [PMID: 33300652 PMCID: PMC7803356 DOI: 10.1002/clc.23511] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/17/2020] [Revised: 11/02/2020] [Accepted: 11/02/2020] [Indexed: 01/02/2023] Open
Abstract
BACKGROUND The electrophysiology algorithm for localizing left or right origins of outflow tract ventricular arrhythmias (OT-VAs) with lead V3 transition still needs further investigation in clinical practice. HYPOTHESIS Lead I R-wave amplitude is effective in distinguishing the left or right origin of OT-VAs with lead V3 transition. METHODS We measured lead I R-wave amplitude in 82 OT-VA patients with lead V3 transition and a positive complex in lead I who underwent successful catheter ablation from the right ventricular outflow tract (RVOT) and left ventricular outflow tract (LVOT). The optimal R-wave threshold was identified, compared with the V2 S/V3 R index, transitional zone (TZ) index, and V2 transition ratio, and validated in a prospective cohort study. RESULTS Lead I R-wave amplitude for LVOT origins was significantly higher than that for RVOT origins (0.55 ± 0.13 vs. 0.32 ± 0.15 mV; p < .001). The area under the curve (AUC) for lead I R-wave amplitude as assessed by receiver operating characteristic (ROC) analysis was 0.926, with a cutoff value of ≥0.45 predicting LVOT origin with 92.9% sensitivity and 88.2% specificity, superior to the V2 S/V3 R index, TZ index, and V2 transition ratio. VAs in the LVOT group mainly originated from the right coronary cusp (RCC) and left and right coronary cusp junction (L-RCC). In the prospective study, lead I R-wave amplitude identified the LVOT origin with 92.3% accuracy. CONCLUSION Lead I R-wave amplitude provides a useful and simple criterion to identify RCC or L-RCC origin in OT-VAs with lead V3 transition.
Collapse
Affiliation(s)
- Jue Wang
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Chenglong Miao
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Guangmin Yang
- Department of Joint Surgery, Third Hospital of Hebei Medical University, Shijiazhuang, China
| | - Lu Xu
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Ru Xing
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Yan Jia
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Ruining Zhang
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Yanwei Wang
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Liu Huang
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| | - Suyun Liu
- Department of Cardiology, Second Hospital of Hebei Medical University, Shijiazhuang, China
| |
Collapse
|
16
|
El Moheb MN, Refaat MM. Idiopathic right ventricular arrhythmias with changes in the QRS morphology after ablation. J Cardiovasc Electrophysiol 2020; 31:2665-2667. [PMID: 32639594 DOI: 10.1111/jce.14656] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/06/2020] [Accepted: 07/06/2020] [Indexed: 12/01/2022]
Affiliation(s)
- Mohamad N El Moheb
- Division of Trauma Emergency Surgery and Surgical Critical Care, Massachusetts General Hospital, Boston, Massachusetts, USA
| | - Marwan M Refaat
- Division of Cardiology, Department of Internal Medicine, American University of Beirut Medical Center, Beirut, Lebanon
| |
Collapse
|
17
|
Zheng J, Fu G, Anderson K, Chu H, Rakovski C. A 12-Lead ECG database to identify origins of idiopathic ventricular arrhythmia containing 334 patients. Sci Data 2020; 7:98. [PMID: 32251335 PMCID: PMC7090065 DOI: 10.1038/s41597-020-0440-8] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/16/2019] [Accepted: 02/27/2020] [Indexed: 12/12/2022] Open
Abstract
Cardiac catheter ablation has shown the effectiveness of treating the idiopathic premature ventricular complex and ventricular tachycardia. As the most important prerequisite for successful therapy, criteria based on analysis of 12-lead ECGs are employed to reliably speculate the locations of idiopathic ventricular arrhythmia before a subsequent catheter ablation procedure. Among these possible locations, right ventricular outflow tract and left outflow tract are the major ones. We created a new 12-lead ECG database under the auspices of Chapman University and Ningbo First Hospital of Zhejiang University that aims to provide high quality data enabling detection of the distinctions between idiopathic ventricular arrhythmia from right ventricular outflow tract to left ventricular outflow tract. The dataset contains 334 subjects who successfully underwent a catheter ablation procedure that validated the accurate origins of idiopathic ventricular arrhythmia.
Collapse
Affiliation(s)
| | - Guohua Fu
- Ningbo First Hospital of Zhejiang University, Ningbo, China
| | | | - Huimin Chu
- Ningbo First Hospital of Zhejiang University, Ningbo, China.
| | | |
Collapse
|
18
|
Electrocardiographic features, mapping and ablation of idiopathic outflow tract ventricular arrhythmias. J Interv Card Electrophysiol 2019; 57:207-218. [PMID: 31650457 DOI: 10.1007/s10840-019-00617-9] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/02/2019] [Accepted: 08/27/2019] [Indexed: 01/01/2023]
Abstract
PURPOSE Idiopathic outflow tract ventricular arrhythmias are ventricular tachycardias or premature ventricular contractions presumably not related to myocardial scar or disorders of ion channels. These arrhythmias have focal origin and display characteristic electrocardiographic features. The purpose of this article is to review the state of the art of diagnosis and treatment of idiopathic outflow tract ventricular arrhythmias. METHODS We systematically reviewed scientific literature about idiopathic outflow tract ventricular arrhythmias selecting the most relevant papers on this topic. RESULTS The right ventricle outflow tract is the most common site of origin for outflow tract ventricular arrhythmias, but also left ventricle outflow tract can harbour these arrhythmias. Outflow tract ventricular arrhythmias are generally benign and may require treatment if they are symptomatic, incessant or give rise to cardiomyopathy. Radiofrequency catheter ablation is an effective and safe therapeutic strategy. A successful procedure requires a thorough preoperative analysis of the 12-lead electrocardiogram of the spontaneous arrhythmia combined with a detailed electroanatomical mapping and intracardiac echocardiography. CONCLUSIONS Idiopathic outflow tract arrhythmias are frequent in daily clinical practice and can be successfully eliminated through discrete radiofrequency catheter ablation with low rates of complications.
Collapse
|
19
|
Mountantonakis SE, Vaishnav AS, Jacobson JD, Bernstein NE, Bhasin K, Coleman KM, Skipitaris NT. Conduction patterns of idiopathic arrhythmias from the endocardium and epicardium of outflow tracts: New insights with noninvasive electroanatomic mapping. Heart Rhythm 2019; 16:1562-1569. [DOI: 10.1016/j.hrthm.2019.04.026] [Citation(s) in RCA: 12] [Impact Index Per Article: 2.4] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/25/2019] [Indexed: 10/27/2022]
|
20
|
Liang JJ, Shirai Y, Lin A, Dixit S. Idiopathic Outflow Tract Ventricular Arrhythmia Ablation: Pearls and Pitfalls. Arrhythm Electrophysiol Rev 2019; 8:116-121. [PMID: 31114686 PMCID: PMC6528030 DOI: 10.15420/aer.2019.6.2] [Citation(s) in RCA: 8] [Impact Index Per Article: 1.6] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/04/2022] Open
Abstract
Idiopathic outflow tract ventricular arrhythmias (VAs) occur typically in patients without structural heart disease. They are often symptomatic and can sometimes lead to left ventricular systolic dysfunction. Both activation and pace mapping are utilised for successful ablation of these arrhythmias. Pace mapping is particularly helpful when the VA is infrequent and/or cannot be elucidated during the ablation procedure. VAs originating from different sites in the outflow tract region have distinct QRS patterns on the 12-lead ECG and careful analysis of the latter can help predict the site of origin of these arrhythmias. Successful ablation of these VAs requires understanding of the detailed anatomy of the OT region, which can be accomplished through electroanatomic mapping tools and intracardiac echocardiography.
Collapse
Affiliation(s)
- Jackson J Liang
- Electrophysiology Section, Division of Cardiology, Hospital of the University of Pennsylvania Philadelphia PA, US
| | - Yasuhiro Shirai
- Electrophysiology Section, Division of Cardiology, Hospital of the University of Pennsylvania Philadelphia PA, US
| | - Aung Lin
- Electrophysiology Section, Division of Cardiology, Hospital of the University of Pennsylvania Philadelphia PA, US
| | - Sanjay Dixit
- Electrophysiology Section, Division of Cardiology, Hospital of the University of Pennsylvania Philadelphia PA, US
| |
Collapse
|
21
|
Cheung JW, Anderson RH, Markowitz SM, Lerman BB. Catheter Ablation of Arrhythmias Originating From the Left Ventricular Outflow Tract. JACC Clin Electrophysiol 2019; 5:1-12. [DOI: 10.1016/j.jacep.2018.11.012] [Citation(s) in RCA: 11] [Impact Index Per Article: 2.2] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/22/2018] [Revised: 11/13/2018] [Accepted: 11/21/2018] [Indexed: 12/12/2022]
|