A morphology based deep learning model for atrial fibrillation detection using single cycle electrocardiographic samples

Abstract Background Electrocardiographic predictors of atrial fibrillation (AF) from a non-AF ECG–such as p wave abnormalities and supraventricular ectopy–have been extensively documented. However, risk prediction tools for AF utilize little if any of the wealth of information available from the ECG. Better AF prediction from the ECG may improve efficiency of screening and performance of AF risk tools. Deep learning methods have the potential to extract an unlimited number of features from the ECG to improve prediction of AF. Purpose We hypothesize that a deep learning model can identify patterns predictive of AF during normal sinus rhythm. To test the hypothesis, we trained and tested a neural network to predict AF from normal sinus rhythm ambulatory ECG data. Methods We trained a deep convolutional neural network to detect features of AF that are present in single-lead ECGs with normal sinus rhythm, recorded using a Food and Drug Administration (FDA)-cleared, smartphone-enabled device. A cohort of 27,526 patients with at least 50 ECGs recorded between January 7, 2013, and September, 19, 2018, and the FDA-cleared automated findings of Normal and Atrial Fibrillation associated with those ECGs, were used for model development. Specifically, we trained the deep learning model on 1,984,581 Normal ECGs from 19,267 patients with 1) only Normal ECG recordings, or 2) at least 30% ECGs with AF. Of the 27,526 patients, an internal set of 8,259 patients with 841,776 Normal ECGs was saved for testing (validation). Results Among 8,259 patients in the test set, 3,467 patients had at least 30% of their ECGs with an automated finding of AF. When the deep learning model was run on 841,776 Normal ECGs, it was able to predict whether the ECG was from a patient with no AF or with 30% or more AF, with an area under the curve (AUC) of 0.80. Using an operating point with equal sensitivity and specificity, the model's sensitivity and specificity were 73.1%. Using an operating point with high specificity (90.0%), the model's sensitivity was 48.0%. When the model was applied to a randomly-selected, broader cohort of 15,000 patients (at least 50 ECGs recorded, any amount of AF), a positive, non-linear relationship between neural network output and AF burden per patient was observed (Figure). Model Output vs AF Burden Per Patient Conclusions A deep learning model was able to predict AF from ECGs in normal sinus rhythm that were recorded on a smartphone-enabled device. The use of deep learning, if prospectively validated, may facilitate AF screening in patients with paroxysmal disease or warn patients who are at high risk for developing AF. Acknowledgement/Funding AliveCor

Download Full-text

Detection of Atrial Fibrillation from Short ECG Signals Using a Hybrid Deep Learning Model

Smart Health - Lecture Notes in Computer Science ◽

10.1007/978-3-030-34482-5_24 ◽

2019 ◽

pp. 269-282 ◽

Cited By ~ 2

Author(s):

Xiaodan Wu ◽

Zeyu Sui ◽

Chao-Hsien Chu ◽

Guanjie Huang

Keyword(s):

Atrial Fibrillation ◽

Deep Learning ◽

Learning Model ◽

Ecg Signals ◽

Deep Learning Model

Download Full-text

A Clinical Study on Atrial Fibrillation, Premature Ventricular Contraction, and Premature Atrial Contraction Screening Based on an ECG Deep Learning Model (Preprint)

10.2196/preprints.29734 ◽

2021 ◽

Author(s):

Jianyuan Hong ◽

Hua-Jung Li ◽

Chung-Chi Yang ◽

Chi-Lu Han ◽

Jui-Chien Hsieh

Keyword(s):

Atrial Fibrillation ◽

Deep Learning ◽

Premature Ventricular Contraction ◽

Learning Model ◽

Training Dataset ◽

Ventricular Contraction ◽

Atrial Contraction ◽

Premature Atrial Contraction ◽

Sensitivity Specificity ◽

Deep Learning Model

BACKGROUND As the results of this study indicate, electrocardiography (ECG) devices generating interpretations of atrial fibrillation (AF), premature ventricular contraction (PVC), and premature atrial contraction (PAC) have high ratios of false-positive errors. OBJECTIVE The aim of this study was to develop an electrocardiogram (ECG) interpreter to improve the performance of AF, PVC, and PAC screening based on an ECG. METHODS In this study, we first adopted a deep learning model to delineate ECG features such as P, QRS, and T waves based on 1160 8–10-s lead I or lead II ECG signals whose ECG device interpretation is AF as a training dataset. Second, a sliding window with 3-RR intervals in length is applied to the raw ECG to examine the delineated features in the window, and the ECG interpretation is then determined based on experiences of cardiologists. RESULTS The results indicate the following: (1) This delineator achieves a good performance on P-, QRS-, and T- wave delineation with a sensitivity/specificity of 0.94/0.98, 1.00/0.99, and 0.97/0.98, respectively, in 48 10-s test ECGs mixed with AF and non-AF ECGs. (2) As compared to ECG-device generated interpretations, the precision of the detection of AF, PVC, and PAC in this study was increased from 0.77 to 0.86, 0.76 to 0.84, and 0.82 to 0.87 in 188 10-s test ECGs. Finally, (3) the F1 scores on the detection of AF, PVC, and PAC were 0.92, 0.91, and 0.83, respectively. CONCLUSIONS In conclusion, this study improved the accuracy of ECG device interpretations, and we believe that the results can bridge the gap between research and clinical practice.

Download Full-text

Contactless facial video recording with deep learning models for the detection of atrial fibrillation

Scientific Reports ◽

10.1038/s41598-021-03453-y ◽

2022 ◽

Vol 12 (1) ◽

Author(s):

Yu Sun ◽

Yin-Yin Yang ◽

Bing-Jhang Wu ◽

Po-Wei Huang ◽

Shao-En Cheng ◽

...

Keyword(s):

Atrial Fibrillation ◽

Deep Learning ◽

Large Scale ◽

Normal Sinus Rhythm ◽

Video Recording ◽

Learning Model ◽

Accuracy Rate ◽

Normal Sinus ◽

Deep Learning Model ◽

Large Scale Screening

AbstractAtrial fibrillation (AF) is often asymptomatic and paroxysmal. Screening and monitoring are needed especially for people at high risk. This study sought to use camera-based remote photoplethysmography (rPPG) with a deep convolutional neural network (DCNN) learning model for AF detection. All participants were classified into groups of AF, normal sinus rhythm (NSR) and other abnormality based on 12-lead ECG. They then underwent facial video recording for 10 min with rPPG signals extracted and segmented into 30-s clips as inputs of the training of DCNN models. Using voting algorithm, the participant would be predicted as AF if > 50% of their rPPG segments were determined as AF rhythm by the model. Of the 453 participants (mean age, 69.3 ± 13.0 years, women, 46%), a total of 7320 segments (1969 AF, 1604 NSR & 3747others) were analyzed by DCNN models. The accuracy rate of rPPG with deep learning model for discriminating AF from NSR and other abnormalities was 90.0% and 97.1% in 30-s and 10-min recording, respectively. This contactless, camera-based rPPG technique with a deep-learning model achieved significantly high accuracy to discriminate AF from non-AF and may enable a feasible way for a large-scale screening or monitoring in the future.

Download Full-text

Deep Learning Model Selection of Suboptimal Complexity

Автоматика и телемеханика ◽

10.31857/s000523100001252-1 ◽

2018 ◽

pp. 129-147

Author(s):

Oleg Bakhteev ◽

◽

Vadim Strijov ◽

Keyword(s):

Deep Learning ◽

Model Selection ◽

Learning Model ◽

Deep Learning Model ◽

Selection Of

Download Full-text

Improving Sentiment Analysis using Hybrid Deep Learning Model

Recent Advances in Computer Science and Communications ◽

10.2174/2213275912666190328200012 ◽

2020 ◽

Vol 13 (4) ◽

pp. 627-640 ◽

Cited By ~ 1

Author(s):

Avinash Chandra Pandey ◽

Dharmveer Singh Rajpoot

Keyword(s):

Neural Network ◽

Deep Learning ◽

Sentiment Analysis ◽

Classification Accuracy ◽

Short Term Memory ◽

Computational Cost ◽

Extraction Process ◽

Learning Model ◽

Sentiment Classification ◽

Deep Learning Model

Background: Sentiment analysis is a contextual mining of text which determines viewpoint of users with respect to some sentimental topics commonly present at social networking websites. Twitter is one of the social sites where people express their opinion about any topic in the form of tweets. These tweets can be examined using various sentiment classification methods to find the opinion of users. Traditional sentiment analysis methods use manually extracted features for opinion classification. The manual feature extraction process is a complicated task since it requires predefined sentiment lexicons. On the other hand, deep learning methods automatically extract relevant features from data hence; they provide better performance and richer representation competency than the traditional methods. Objective: The main aim of this paper is to enhance the sentiment classification accuracy and to reduce the computational cost. Method: To achieve the objective, a hybrid deep learning model, based on convolution neural network and bi-directional long-short term memory neural network has been introduced. Results: The proposed sentiment classification method achieves the highest accuracy for the most of the datasets. Further, from the statistical analysis efficacy of the proposed method has been validated. Conclusion: Sentiment classification accuracy can be improved by creating veracious hybrid models. Moreover, performance can also be enhanced by tuning the hyper parameters of deep leaning models.

Download Full-text