TASK	DATASET	MODEL	METRIC NAME	METRIC VALUE	GLOBAL RANK
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	DNN	F1 (1dAVb)	0.893	# 1
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	DNN	F1 (RBBB)	0.932	# 1
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	DNN	F1 (LBBB)	0.984	# 1
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	DNN	F1 (SB)	0.882	# 1
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	DNN	F1 (AF)	0.857	# 1
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	DNN	F1 (ST)	0.933	# 1
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	4th year cardiology resident	F1 (1dAVb)	0.776	# 2
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	4th year cardiology resident	F1 (RBBB)	0.917	# 3
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	4th year cardiology resident	F1 (LBBB)	0.947	# 2
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	4th year cardiology resident	F1 (SB)	0.882	# 1
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	4th year cardiology resident	F1 (AF)	0.769	# 2
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	4th year cardiology resident	F1 (ST)	0.896	# 3
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	3rd year emergency resident	F1 (1dAVb)	0.719	# 4
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	3rd year emergency resident	F1 (RBBB)	0.852	# 4
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	3rd year emergency resident	F1 (LBBB)	0.912	# 4
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	3rd year emergency resident	F1 (SB)	0.848	# 3
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	3rd year emergency resident	F1 (AF)	0.696	# 4
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	3rd year emergency resident	F1 (ST)	0.932	# 2
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	5th year medical student	F1 (1dAVb)	0.732	# 3
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	5th year medical student	F1 (RBBB)	0.928	# 2
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	5th year medical student	F1 (LBBB)	0.915	# 3
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	5th year medical student	F1 (SB)	0.750	# 4
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	5th year medical student	F1 (AF)	0.706	# 3
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	5th year medical student	F1 (ST)	0.857	# 4

Badge	Markdown
	`[![PWC](https://img.shields.io/endpoint.svg?url=https://paperswithcode.com/badge/automatic-diagnosis-of-the-short-duration-12/ecg-classification-on-electrocardiography-ecg)](https://paperswithcode.com/sota/ecg-classification-on-electrocardiography-ecg?p=automatic-diagnosis-of-the-short-duration-12)`

Automatic diagnosis of the 12-lead ECG using a deep neural network

2 Apr 2019 · Antônio H. Ribeiro, Manoel Horta Ribeiro, Gabriela M. M. Paixão, Derick M. Oliveira, Paulo R. Gomes, Jéssica A. Canazart, Milton P. S. Ferreira, Carl R. Andersson, Peter W. Macfarlane, Wagner Meira Jr., Thomas B. Schön, Antonio Luiz P. Ribeiro ·

The role of automatic electrocardiogram (ECG) analysis in clinical practice is limited by the accuracy of existing models. Deep Neural Networks (DNNs) are models composed of stacked transformations that learn tasks by examples. This technology has recently achieved striking success in a variety of task and there are great expectations on how it might improve clinical practice. Here we present a DNN model trained in a dataset with more than 2 million labeled exams analyzed by the Telehealth Network of Minas Gerais and collected under the scope of the CODE (Clinical Outcomes in Digital Electrocardiology) study. The DNN outperform cardiology resident medical doctors in recognizing 6 types of abnormalities in 12-lead ECG recordings, with F1 scores above 80% and specificity over 99%. These results indicate ECG analysis based on DNNs, previously studied in a single-lead setup, generalizes well to 12-lead exams, taking the technology closer to the standard clinical practice.

PDF Abstract

Code

Add Remove Mark official

antonior92/automatic-ecg-diagnosis official

307

Tasks

Add Remove

ECG Classification

Electrocardiography (ECG)

Specificity

Datasets

Introduced in the Paper:

CODE-15%

Results from the Paper

Edit

Ranked #1 on ECG Classification on Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)

Get a GitHub badge

Task	Dataset	Model	Metric Name	Metric Value	Global Rank	Benchmark
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	DNN	F1 (1dAVb)	0.893	# 1	Compare
			F1 (RBBB)	0.932	# 1	Compare
			F1 (LBBB)	0.984	# 1	Compare
			F1 (SB)	0.882	# 1	Compare
			F1 (AF)	0.857	# 1	Compare
			F1 (ST)	0.933	# 1	Compare
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	4th year cardiology resident	F1 (1dAVb)	0.776	# 2	Compare
			F1 (RBBB)	0.917	# 3	Compare
			F1 (LBBB)	0.947	# 2	Compare
			F1 (SB)	0.882	# 1	Compare
			F1 (AF)	0.769	# 2	Compare
			F1 (ST)	0.896	# 3	Compare
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	3rd year emergency resident	F1 (1dAVb)	0.719	# 4	Compare
			F1 (RBBB)	0.852	# 4	Compare
			F1 (LBBB)	0.912	# 4	Compare
			F1 (SB)	0.848	# 3	Compare
			F1 (AF)	0.696	# 4	Compare
			F1 (ST)	0.932	# 2	Compare
ECG Classification	Electrocardiography (ECG) on Telehealth Network of Minas Gerais (TNMG)	5th year medical student	F1 (1dAVb)	0.732	# 3	Compare
			F1 (RBBB)	0.928	# 2	Compare
			F1 (LBBB)	0.915	# 3	Compare
			F1 (SB)	0.750	# 4	Compare
			F1 (AF)	0.706	# 3	Compare
			F1 (ST)	0.857	# 4	Compare

Methods

Add Remove

No methods listed for this paper. Add relevant methods here

Edit Social Preview

Automatic diagnosis of the 12-lead ECG using a deep neural network

Code Edit Add Remove Mark official

Tasks Edit Add Remove

Datasets Edit

Results from the Paper Edit

Methods Edit Add Remove

Code

Add Remove Mark official

Tasks

Add Remove

Datasets

Results from the Paper

Edit

Methods

Add Remove