Article
Health Care Sciences & Services
Sunyoung Yoon, Taerim Kim, Taehwan Roh, Hansol Chang, Sung Yeon Hwang, Hee Yoon, Tae Gun Shin, Min Seob Sim, Ik Joon Jo, Won Chul Cha
Summary: The study demonstrated that using P-ECG for ECG examination and result transmission during ambulance transport is faster than using C-ECG. This could provide more care to patients and help reduce symptoms-to-balloon time for patients with acute coronary syndrome.
JMIR MHEALTH AND UHEALTH
(2021)
Article
Multidisciplinary Sciences
Jiewei Lai, Huixin Tan, Jinliang Wang, Lei Ji, Jun Guo, Baoshi Han, Yajun Shi, Qianjin Feng, Wei Yang
Summary: Cardiovascular disease is a global public health problem, and intelligent diagnostic approaches are important in ECG analysis. Convenient wearable ECG devices can detect transient arrhythmias and enable intervention during continuous monitoring. The researchers collected a large dataset of wearable 12-lead ECGs and developed a model that can classify 60 ECG diagnostic terms using self-supervised learning.
NATURE COMMUNICATIONS
(2023)
Article
Cardiac & Cardiovascular Systems
C. Michael Gibson, Sameer Mehta, Mariana R. S. Ceschim, Alejandra Frauenfelder, Daniel Vieira, Roberto Botelho, Francisco Fernandez, Carlos Villagran, Sebastian Niklitschek, Cristina Matheus, Gladys Pinto, Isabella Vallenilla, Claudia Lopez, Maria Acosta, Anibal Munguia, Clara Fitzgerald, Jorge Mazzini, Lorena Pisana, Samantha Quintero
Summary: This study developed and validated a machine learning-guided algorithm for STEMI detection using single-lead ECG data from Latin American patients. The algorithm showed promising results in accurately detecting STEMI and localizing anterior and inferior wall STEMIs, although there is room for improvement in detecting lateral wall STEMIs. This AI-enhanced single-lead ECG technology offers a promising screening tool for early STEMI diagnosis and has the potential to improve patient outcomes in the long run.
INTERNATIONAL JOURNAL OF CARDIOLOGY
(2022)
Article
Chemistry, Analytical
Soonil Kwon, So-Ryoung Lee, Eue-Keun Choi, Hyo-Jeong Ahn, Hee-Seok Song, Young-Shin Lee, Seil Oh
Summary: This study compared 24-hour ECG monitoring between adhesive single-lead and Holter devices in patients with general arrhythmia, showing a high degree of agreement in diagnostics and monitoring parameters between the two devices, suggesting that the single-lead device could be an acceptable alternative for ambulatory ECG monitoring in patients with general arrhythmia.
Article
Engineering, Electrical & Electronic
Theekshana Dissanayake, Tharindu Fernando, Simon Denman, Sridha Sridharan, Clinton Fookes
Summary: Electrocardiograms (ECGs) are a viable method for diagnosing cardiovascular diseases (CVDs). Machine learning algorithms, such as deep neural networks trained on ECG signals, have shown promising results in identifying CVDs. However, existing models for ECG anomaly detection require long training times and computational resources. To overcome this, we propose a novel deep learning architecture that utilizes dilated convolution layers, allowing for learning from short ECG segments and flexibly diagnosing CVDs.
IEEE SENSORS JOURNAL
(2023)
Article
Computer Science, Interdisciplinary Applications
Qinghua Sun, Chunmiao Liang, Tianrui Chen, Bing Ji, Rugang Liu, Lei Wang, Min Tang, Yuguo Chen, Cong Wang
Summary: This study aims to construct generalizable models for the detection of myocardial ischemia in patients with subtle ECG waveform changes using ensemble learning to integrate ECG dynamic features acquired via deterministic learning. The proposed model combining ensemble learning and deterministic learning presents excellent diagnostic accuracy and generalization in clinical practice.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Computer Science, Information Systems
Majid Sepahvand, Fardin Abdali-Mohammadi
Summary: This paper proposes a method to bridge the gap between arrhythmia classification models using multi-lead ECG signals and those using single-lead ECG signals through knowledge distillation. The results show that the method successfully compresses the model size while maintaining a high level of accuracy.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Wenhan Liu, Qianxi Guo, Xinwei Gao, Sheng Chang, Hao Wang, Jin He, Qijun Huang
Summary: This article proposes a new unsupervised feature learning method for processing unlabeled 12-lead electrocardiogram signals. The method takes into account the characteristics of 12-lead ECGs and utilizes lead separation and combination to learn feature representations. Experimental results demonstrate that the method achieves good accuracy in myocardial infarction and atrial fibrillation detection.
IEEE INTERNET OF THINGS JOURNAL
(2022)
Article
Engineering, Electrical & Electronic
Xiaoyun Xie, Hui Liu, Da Chen, Minglei Shu, Yinglong Wang
Summary: This study proposes a multilabel ECG classification method based on the leadwise grouping multibranch network, which extracts lead features using a leadwise grouping strategy and a multibranch network, while solving the class imbalance problem using an extended focal loss. The proposed method was evaluated on two large-scale real-world ECG databases and achieved better results with fewer parameters and lower computational cost.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
Article
Health Care Sciences & Services
Ju-Seung Kwun, Jang Hoon Lee, Bo Eun Park, Jong Sung Park, Hyeon Jeong Kim, Sun-Hwa Kim, Ki-Hyun Jeon, Hyoung-won Cho, Si-Hyuck Kang, Wonjae Lee, Tae-Jin Youn, In-Ho Chae, Chang-Hwan Yoon
Summary: This study found that the use of a patch-type device (AT-Patch) increased the detection rate of new-onset atrial fibrillation in high-risk patients. Further research is needed to investigate the value of early detection of atrial fibrillation and its potential in reducing adverse clinical outcomes.
JOURNAL OF MEDICAL INTERNET RESEARCH
(2023)
Article
Engineering, Electrical & Electronic
Zuhao Liu, Huan Wang, Yibo Gao, Shunchen Shi
Summary: This article introduces a new attention learning method based on NAS for detecting cardiovascular diseases, which outperforms existing methods in experiments.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Chemistry, Analytical
Prashanth Shyam Kumar, Mouli Ramasamy, Kamala Ramya Kallur, Pratyush Rai, Vijay K. Varadan
Summary: The prevalence of chronic cardiovascular diseases (CVDs) has increased globally. This study focuses on deriving multiple ECG leads from a subset of leads to reduce the number of electrodes in wearable devices. Personalized derivations are compared to generalized derivations in terms of diagnostic accuracy and error metrics.
Article
Chemistry, Analytical
Pasquale Daponte, Luca De Vito, Grazia Iadarola, Francesco Picariello
Summary: This paper presents an innovative method for multiple lead electrocardiogram monitoring based on Compressed Sensing. The proposed method can achieve a high Compression Ratio without compromising signal quality.
Article
Instruments & Instrumentation
Marco Chu, Hani E. Naguib
Summary: This study assessed the performance of various conductive composite polymers in collecting electrical signals from the heart, and found that adding 5% carbon nanotubes significantly increased the elastic modulus and conductivity of the composites. SBS-CNT composites at 5% and 10% showed the best performance in detecting ECG waves from the heart.
SMART MATERIALS AND STRUCTURES
(2021)
Article
Cardiac & Cardiovascular Systems
Jessica J. Orchard, John W. Orchard, Hariharan Raju, Andre La Gerche, Rajesh Puranik, Chris Semsarian
Summary: New and highly portable technology, such as smartphone electrocardiogram (ECG) devices, may be useful in documenting and diagnosing exercise-induced arrhythmias. Data regarding the new Kardia 6 lead device (6L) are limited, with no information available on its use in athletic populations.
JOURNAL OF ELECTROCARDIOLOGY
(2021)
Article
Chemistry, Analytical
Heesang Eom, Dongseok Lee, Seungwoo Han, Yuli Sun Hariyani, Yonggyu Lim, Illsoo Sohn, Kwangsuk Park, Cheolsoo Park
Article
Chemistry, Analytical
Dongseok Lee, Hyunbin Kwon, Dongyeon Son, Heesang Eom, Cheolsoo Park, Yonggyu Lim, Chulhun Seo, Kwangsuk Park
Summary: A cuffless blood pressure estimation model using deep learning algorithms was proposed, with features extracted from electrocardiogram, photoplethysmogram, and ballistocardiogram. The model achieved high accuracy in both one-day and multi-day tests, showing its potential for continuous blood pressure monitoring for patients with hypertension.