Atrial Fibrillation Classification Using QRS Complex Features and LSTM

Maknickas, Vykintas; Maknickas, Algirdas

doi:10.22489/cinc.2017.350-114

Cited by 30 publications

(19 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent applications implemented a convolutional neural network (CNN) and multilayer perceptron (MLP) for fetal heart rate records assessment and reached 85% accuracy [48]; a recurrent neural network (RNN) was also suggested for automatic detection of irregular beating rhythm in records with 83% accuracy [49]. A long-short term memory (LSTM) network was used for atrial fibrillation classification from diverse electrocardiographic signals and reached 78% accuracy in [50], and 79% F1 score in [51]. A pediatric heart disease screening application was also solved using a CNN model for the task of automatic structural heart abnormality risk detection from digital phonocardiogram (PCG) signals [52].…”

Section: Related Workmentioning

confidence: 99%

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

et al. 2020

View full text Add to dashboard Cite

Heart diseases are highly ranked among the leading causes of mortality in the world. They have various types including vascular, ischemic, and hypertensive heart disease. A large number of medical features are reported for patients in the Electronic Health Records (EHR) that allow physicians to diagnose and monitor heart disease. We collected a dataset from Medica Norte Hospital in Mexico that includes 800 records and 141 indicators such as age, weight, glucose, blood pressure rate, and clinical symptoms. Distribution of the collected records is very unbalanced on the different types of heart disease, where 17% of records have hypertensive heart disease, 16% of records have ischemic heart disease, 7% of records have mixed heart disease, and 8% of records have valvular heart disease. Herein, we propose an ensemble-learning framework of different neural network models, and a method of aggregating random under-sampling. To improve the performance of the classification algorithms, we implement a data preprocessing step with features selection. Experiments were conducted with unidirectional and bidirectional neural network models and results showed that an ensemble classifier with a BiLSTM or BiGRU model with a CNN model had the best classification performance with accuracy and F1-score between 91% and 96% for the different types of heart disease. These results are competitive and promising for heart disease dataset. We showed that ensemble-learning framework based on deep models could overcome the problem of classifying an unbalanced heart disease dataset. Our proposed framework can lead to highly accurate models that are adapted for clinical real data and diagnosis use.

show abstract

Section: Related Workmentioning

confidence: 99%

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

et al. 2020

View full text Add to dashboard Cite

show abstract

“…In order to validate the performances of the proposed HADLN method, several state-of-the-art methods, such as ResNet ( Hannun et al, 2019 ), CL3 ( Warrick and Homsi, 2017 ), QRS-LSTM ( Maknickas, 2017 ), and Dense-net ( Rubin et al, 2017 ), are also provided as a comparison. In addition, self-attention based ResNet method, ResNet_A, is also investigated for arrhythmia classification.…”

Section: Resultsmentioning

confidence: 99%

HADLN: Hybrid Attention-Based Deep Learning Network for Automated Arrhythmia Classification

Jiang

et al. 2021

Front. Physiol.

View full text Add to dashboard Cite

In recent years, with the development of artificial intelligence, deep learning model has achieved initial success in ECG data analysis, especially the detection of atrial fibrillation. In order to solve the problems of ignoring the correlation between contexts and gradient dispersion in traditional deep convolution neural network model, the hybrid attention-based deep learning network (HADLN) method is proposed to implement arrhythmia classification. The HADLN can make full use of the advantages of residual network (ResNet) and bidirectional long–short-term memory (Bi-LSTM) architecture to obtain fusion features containing local and global information and improve the interpretability of the model through the attention mechanism. The method is trained and verified by using the PhysioNet 2017 challenge dataset. Without loss of generality, the ECG signal is classified into four categories, including atrial fibrillation, noise, other, and normal signals. By combining the fusion features and the attention mechanism, the learned model has a great improvement in classification performance and certain interpretability. The experimental results show that the proposed HADLN method can achieve precision of 0.866, recall of 0.859, accuracy of 0.867, and F1-score of 0.880 on 10-fold cross-validation.

show abstract

“…Electrocardiography (ECG) is a common tool for diagnosing heart diseases in Western medicine. Numerous studies on ECG show convincing cardiac disease classification results obtained by using the QSR complex as feature points [29] - [32] and ECG signal classification with ANN [33] - [35]. In Figure 5(a), a normal ECG sinus rhythm is marked by the QRS complex [36], which is a combination of three deflections on a typical ECG.…”

Section: Definition Of An Arterial Pulse In Our Systemmentioning

confidence: 89%

Deciphering 3D Human Sphygmopalpation Pulse Patterns using “X-ray” Images Acquired from Tactile Robotic Fingers

Kong

Chan

Xie

et al. 2021

Preprint

View full text Add to dashboard Cite

Sphygmopalpation at specific locations of human wrists has been used as a medical measurement technique in China since the Han Dynasty (202 BC – 220 AD); it is now generally accepted that traditional Chinese medicine (TCM) doctors are able to decipher 28 types of basic pulse patterns using their fingertips. This TCM technique of examining individual arterial pulses by palpation has undergone an upsurge recently in popularity as a low-cost and non-invasive diagnostic technique for monitoring patient health status. We have developed a pulse sensing platform for studying and digitalizing arterial pulse patterns via a TCM approach. This platform consists of a robotic hand with three fingers for pulse measurement and an artificial neural network (ANN) together with pulse signal preprocessing for pulse pattern recognition. The platforms previously reported by other research groups or marketed commercially exhibit one or more of the following imperfections: a single channel for data acquisition, low sensitivity and rigid sensors, lack of control of the applied pressure, and in many reported works, lack of an intelligent data analysis system. The platform presented here features up to three-dimensional (3D) tactile sensing channels for recording data and uses highly sensitive capacitive MEMS (microelectromechanical systems) flexible sensing arrays, pressure-feedback-controlled robotic fingers, and machine learning algorithms. We also proposed a methodology of obtaining “X-ray” image of pulse information constructed based on the sensing data from 3 locations and 3 applied pressures (i.e., mimicking TCM doctors), which contains all arterial pulse information in both spatial and temporal spans, and which could be used as an input to a deep learning algorithm. By applying our developed platform and algorithms, 3 types of consistent pulse patterns, i.e., “HUA” , “XI” , and “CHEN” , as described by TCM doctors, could be identified in a selected group of 3 subjects who were diagnosed by TCM practitioners. We have shown the classification rates is 98.7% in training process and 84.2% in testing result for these 3 basic pulse patterns. The high classification rate of the developed platform could lead to further development of a high-level artificial intelligence system incorporating knowledge from TCM – the robotics finger system could become a standard clinical equipment for digitalizing and visualizing human arterial pulses

show abstract

Atrial Fibrillation Classification Using QRS Complex Features and LSTM

Cited by 30 publications

References 3 publications

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

Ensemble Deep Learning Models for Heart Disease Classification: A Case Study from Mexico

HADLN: Hybrid Attention-Based Deep Learning Network for Automated Arrhythmia Classification

Deciphering 3D Human Sphygmopalpation Pulse Patterns using “X-ray” Images Acquired from Tactile Robotic Fingers

Contact Info

Product

Resources

About