Abstract 15414: Diagnostic Performance of Deep Learning on 12-lead Electrocardiography to Distinguish Takotsubo Syndrome and Acute Anterior Myocardial Infarction

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Masato Shimizu ◽  
shummo cho ◽  
Yoshiki Misu ◽  
Mari Ohmori ◽  
Ryo Tateishi ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Deep Learning ◽  
Diagnostic Performance ◽  
P Wave ◽  
Takotsubo Syndrome ◽  
Anterior Myocardial Infarction ◽  
Color Mapping ◽  
Lead Avr ◽  
The Difference ◽  
And Gender

Introduction: Takotsubo syndrome (TTS) and acute anterior myocardial infarction (ant-AMI) show very similar 12-lead electrocardiography (ECG) featured at onset, and it is often difficult to distinguish them without cardiac catheterization. The difference of ECG between them was studied, but the diagnostic performance of machine learning (deep learning) for them had not been investigated. Hypothesis: Deep learning on 12-leads ECG has high diagnostic performance to diagnose TTS and ant-AMI at onset. Methods: Consecutive 50 patients of TTS were one-to-one matched to ant-AMI randomly by their age and gender, and total 100 patients were enrolled. No sinus rhythm patients were excluded. All ECGs were divided into each 12-lead, and 5 heart beats from one lead were extracted. For each lead, 250 ECG waves of TTS/AMI were sampled as 24bit bitmap image, and prediction model construction by convolutional neural network (CNN: transfer learning, using VGG16 architecture) underwent to distinguish the two diseases in each lead. Next, gradient weighted class activation color mapping (GradCam) was performed to detect the degree and position of convolutional importance in the leads. Results: Lead aVR (mean accuracy 0.748), I (0.733), and V1 (0.678) were the top 3 leads with high accuracy. In aVR lead, GradCam showed strong convolution of negative T wave in TTS, and sharp R wave in ant-AMI. In I lead, it spotlighted several parts of ECG wave in ant-AMI. However in TTS, whole shape of the wave, P wave onset, and negative T were invertedly convoluted in TTS. Conclusions: Deep learning was a powerful tool to distinguish TTS and ant-AMI at onset, and GradCam method gave us new insight of the difference on ECG between the two diseases.

Diagnostic performance of 18-leads electrocardiography to distinguish takotsubo syndrome and acute anterior myocardial infarction

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
M Shimizu ◽  
S Cho ◽  
K Hara ◽  
M Ohmori ◽  
T Kaneda ◽  
...  
Keyword(s):  
Machine Learning ◽  
Myocardial Infarction ◽  
Diagnostic Performance ◽  
Takotsubo Syndrome ◽  
Anterior Myocardial Infarction ◽  
T Wave ◽  
St Depression ◽  
St Elevation ◽  
The Difference ◽  
And Gender

Abstract Background Electrocardiographic (ECG) features on acute phase of Takotsubo syndrome (TTS) is recognized to mimic that of acute anterior myocardial infarction (ant AMI). However, the difference of synthesized 18-leads ECG of both diseases was not elucidated. Purpose To elucidate diagnostic performance of 18-leads ECG to distinguish TTS and acute anterior AMI. Methods We firstly enrolled consecutive 40 patients of TTS, and among 500 ant AMI patients, one to two matching was done by their age and gender. Finally, 40+80 patients (74.5±11.2 years, 87 females) were enrolled, and ECG at onset of both group was estimated. Because of multicollinearity, all significant differences were compared by machine learning (Random Forest method). Results Prevalence of Q wave had no difference. Conversely, ST depression in TTS and ST elevation in ant AMI were significant differences in V7–9 leads. T-wave polarity of V3R-V9 leads were significantly different (flat T-wave in TTS and positive in ant AMI). Machine learning revealed T wave polarity in V7 lead had the highest feature importance. Conclusion 18-leads ECG at onset had powerful diagnostic performance to distinguish the two diseases. Funding Acknowledgement Type of funding source: None

Abstract 13718: Automatic Microvolt-level Measurement of ST Level at J-point on 12-lead Electrocardiography Can Distinguish Takotsubo Syndrome and Acute Anterior Myocardial Infarction

Circulation ◽  
2020 ◽  
Vol 142 (Suppl_3) ◽  
Author(s):  
Masato Shimizu ◽  
shummo cho ◽  
Yoshiki Misu ◽  
Mari Ohmori ◽  
Ryo Tateishi ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Automated System ◽  
P Value ◽  
Takotsubo Syndrome ◽  
Random Matching ◽  
Anterior Myocardial Infarction ◽  
St Depression ◽  
Level Measurement ◽  
St Elevation ◽  
And Gender

Introduction: ST elevation/depression on 12-leads electrocardiography (ECG) at onset was recognized difficult to distinguish Takotsubo syndrome (TTS) and acute anterior myocardial infarction (ant AMI). Diagnostic performance of automatic microvolt-level measurement of the ST levels was not elucidated. Hypothesis: Microvolt-level differences of ST level at J-point on ECG can distinguish TTS and ant AMI in acute phase. Methods: We firstly enrolled consecutive 40 patients of TTS, and among 500 ant AMI patients, one to two random matching was done by their age and gender. Finally, 40+80 patients (74.5±11.2 years, 87 females) were enrolled. ECG at onset of both group was measured by automated system (ECAPs12c: Nihon-Koden). Results: ST level of TTS at J-point in I/II/V4-6 lead was significantly elevated comparing to that of ant AMI. Conversely, Conversely, significant ST depression in aVR and no ST elevation in V1 of TTS was observed in TTS. Logistic regression analysis revealed that ST elevation in I lead and no ST elevation in V1 lead showed high odds ratio and low P value. Conclusions: Automated measurement of microvolt-level difference of ST level at J-point was a powerful tool to distinguish TTS and ant AMI at onset.

Differences of ST level at J-point on 12-lead electrocardiography can distinguish takotsubo syndrome and acute anterior myocardial infarction

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
M Shimizu ◽  
S Cho ◽  
K Hara ◽  
M Ohmori ◽  
T Kaneda ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Quantitative Difference ◽  
Qualitative Difference ◽  
Automated System ◽  
P Value ◽  
Takotsubo Syndrome ◽  
Anterior Myocardial Infarction ◽  
St Depression ◽  
St Elevation ◽  
And Gender

Abstract Background Qualitative difference of ST elevation/depression on 12-leads electrocardiography (ECG) at onset was reported in patients with Takotsubo syndrome (TTS) and acute anterior myocardial infarction (ant AMI). However, quantitative difference of those was not elucidated. Purpose To investigate differences of ST level at J point on ECG between TTS and ant AMI by automated calculating system. Methods We firstly enrolled consecutive 40 patients of TTS, and among 500 ant AMI patients, one to two random matching was done by their age and gender. Finally, 40+80 patients (74.5±11.2 years, 87 females) were enrolled. ECG at onset of both group was measured by automated system (ECAPs12c: Nihon-Koden). Results ST level of TTS at J-point in I/II/V4–6 lead was significantly elevated comparing to that of ant AMI. Conversely, Conversely, significant ST depression in aVR and no ST elevation in V1 of TTS was observed in TTS. Logistic regression analysis revealed that ST elevation in I lead and no ST elevation in V1 lead showed high odds ratio and low P value. Conclusion Automated measured ST level at J-point was a powerful tool to distinguish TTS and ant AMI at onset. Funding Acknowledgement Type of funding source: None

scholarly journals Diagnostic performance of deep learning on 12-leads electrocardiography for recurrence after pulmonary vein isolation in patients with persistent atrial fibrillation

2021 ◽  
Vol 42 (Supplement_1) ◽  
Author(s):  
M Shimizu ◽  
H Miyazaki ◽  
S Cho ◽  
Y Misu ◽  
R Tateishi ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Pulmonary Vein ◽  
Pulmonary Vein Isolation ◽  
Diagnostic Performance ◽  
Persistent Atrial Fibrillation ◽  
P Wave ◽  
Color Mapping ◽  
Funding Sources ◽  
Recurrent Case

Abstract Background Several patients with persistent atrial fibrillation (per-AF) suffer from recurrence after pulmonary vein isolation (PVI). Various methods to predict the recurrence were tried, but deep learning on 12-leads electrocardiography (ECG) after PVI was not studied. Purpose To elucidate diagnostic performance of deep learning on 12-leads ECG after PVI in patients with per-AF Methods We enrolled consecutive 109 patients with per-AF who underwent PVI (68.8±10.0 years, 83 males) excluding failure cases. We defined recurrence in 3–12 months after PVI. From the ECG just after PVI, five beats of each lead were sampled separately. Deep learning (convolutional neural network on bitmap ECG image) was performed by transfer learning of Inception-Resnet-V2 model. Gradient weighted class activation color mapping (GradCam) was performed to detect convolutional importance in the lead. Results Thirty-six patients showed recurrence in the period. Lead II (accuracy 0.701), aVR (0.690) were the top 2 leads of prediction, which showed larger accuracy than statistical accuracies of Non PV foci = SVC (accuracy = 0.541) and left atrial diameter >50mm (0.596). In lead II, GradCam spotlighted strong convolution of latter half of P wave in recurrent case, and former half of P wave and T wave in no-recurrent case. Conclusions Deep learning on ECG was a powerful tool to predict recurrence of per-AF after PVI. FUNDunding Acknowledgement Type of funding sources: None. Results of deep learning Results of GradCam

scholarly journals THE VALUE OF LEAD AVR IN IDENTIFYING THE INFARCTED-RELATED ARTERY AND PROGNOSIS IN PATIENTS WITH ACUTE ANTERIOR MYOCARDIAL INFARCTION

Heart ◽  
2012 ◽  
Vol 98 (Suppl 2) ◽  
pp. E92.4-E93
Author(s):  
Ma Cai-Yun ◽  
Zhang Jian-Mei ◽  
Xu Yan-Cheng ◽  
Ren Feng-Xue ◽  
Liu Fang ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Anterior Myocardial Infarction ◽  
Lead Avr

scholarly journals Acute anterior myocardial infarction complicated by takotsubo syndrome: the value of multimodality imaging

2020 ◽  
Author(s):  
Takao Konishi ◽  
Naohiro Funayama ◽  
Tadashi Yamamoto ◽  
Daisuke Hotta ◽  
Shinya Tanaka ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Multimodality Imaging ◽  
Takotsubo Syndrome ◽  
Anterior Myocardial Infarction

scholarly journals Prediction of Reperfusion and Infarct Related Artery Patency after Thrombolysis in Acute Anterior Myocardial Infarction by Degree of P Wave Dispersion on ECG

2018 ◽  
Vol 10 (2) ◽  
pp. 158-163
Author(s):  
Md Monir Hossain Khan ◽  
Md Afzalur Rahman ◽  
Abdullah Al Shafi Majumder ◽  
Khondker Shaheed Hussain ◽  
Md Toufiqur Rahman ◽  
...  
Keyword(s):  
Myocardial Infarction ◽  
Thrombolytic Therapy ◽  
Wave Dispersion ◽  
P Wave ◽  
Anterior Myocardial Infarction ◽  
P Wave Dispersion ◽  
Timi Flow Grade ◽  
Group I ◽  
Before And After ◽  
Group Ii

Background: Early detection IRA patency following thrombolytic therapy is of great importance in terms of prognosis and identification of candidates for rescue percutaneous coronary intervention (PCI). P wave dispersion (PWD), a new parameter measured before and after thrombolytic therapy is supposed to predict successful reperfusion in patients with anterior acute myocardial infarction (AMI).Methods: 132 patients were selected and divided into two groups on the basis of ST Segment resolution (STR) after 120 minutes of thrombolysis. Group I: patients with STR >70%; Group II: patients with STR < 70%. P wave dispersion was measured in both groups before and after thrombolysis. All patients underwent coronary angiography (CAG). IRA was considered patent if TIMI flow grade was e”2.Results: It was observed that diabetes mellitus and dyslipidemia were significantly higher in group II patients (p=0.04 and p=0.03, respectively). PWD before thrombolysis (PWD0) and 90 minutes after thrombolysis (PWD90) in both groups were statistically insignificant (p=0.45 and p=0.19, respectively). The mean level of PWD120 was statistically significant (p=0.001). After multivariate regression analysis PWD120 was found to be the significant predictor of IRA patency (OR = 1.101; 95% CI = 1.012 – 1.240; p = 0.01).Conclusion: P wave dispersion in patients receiving thrombolytic therapy can be a predictor of successful reperfusion and patent IRA. PWD values, in combination with other reperfusion parameters, can contribute to the identification of rescue PCI candidates.Cardiovasc. j. 2018; 10(2): 158-163

Sign in / Sign up

Export Citation Format

Share Document