5105A deep neural network predicts atrial fibrillation from normal ECGs recorded on a smartphone-enabled device

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
C Galloway ◽  
D Treiman ◽  
J Shreibati ◽  
M Schram ◽  
Z Karbaschi ◽  
...  
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Deep Learning ◽  
Sinus Rhythm ◽  
Sensitivity And Specificity ◽  
Normal Sinus Rhythm ◽  
Learning Model ◽  
Normal Sinus ◽  
Normal Ecgs ◽  
Deep Learning Model

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

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

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.

scholarly journals ATRIAL FIBRILLATION DETECTION ON ELECTROCARDIOGRAMS WITH CONVOLUTIONAL NEURAL NETWORKS

2019 ◽  
Vol 9 (4) ◽  
pp. 69-73
Author(s):  
Viktor Kifer ◽  
Natalia Zagorodna ◽  
Olena Hevko
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Deep Neural Network ◽  
Normal Sinus Rhythm ◽  
Normal Sinus ◽  
Noisy Signals ◽  
Network Usage ◽  
Model Training

In this paper, we present our research which confirms the suitability of the convolutional neural network usage for the classification of single-lead ECG recordings. The proposed method was designed for classifying normal sinus rhythm, atrial fibrillation (AF), non-AF related other abnormal heart rhythms and noisy signals. The method combines manually selected features with the features learned by the deep neural network. The Physionet Challenge 2017 dataset of over 8500 ECG recordings was used for the model training and validation. The trained model reaches an average F1-score 0.71 in classifying normal sinus rhythm, AF and other rhythms respectively.

scholarly journals Diagnostic performance of a wearing dynamic ECG recorder for Atrial Fibrillation screening: The HUAMI heart study

2021 ◽  
Author(s):  
Fu Wenxia ◽  
Li Ruogu
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Normal Sinus Rhythm ◽  
False Negative ◽  
Upright Position ◽  
Normal Sinus ◽  
Heart Study ◽  
User Friendly

Abstract Background: Atrial fibrillation (AF) is the most prevalent cardiac dysrhythmia with a significant morbidity and mortality rate. Notably, one out of three patients with AF is asymptomatic. Given the asymptomatic and paroxysmal nature of AF, AF's timely detection with traditional instruments is somewhat unsatisfactory and delayed. Thus, wearing a dynamic electrocardiogram (ECG) recorder can help analyze, interpret, and distinguish AF from normal sinus rhythm accurately and safely, even in an upright position and after exercises, using an artificial intelligence (AI) algorithm.Methods: A total of 114 participants in the outpatient registry of our institution from June 24, 2020 to July 24, 2020, were enrolled. Participants were tested with a wearable dynamic ECG recorder and 12-lead ECG in a supine, an upright position and after exercises for 60seconds. Results: A total of 114 subjects (sixty-one with normal sinus rhythm, fifty-three with AF) were enrolled in the study. The number of cases unable to be determined by the dynamic ECG recorder wristband was two, one in each group. Case results not clinically objective were defined as false-negative or false-positive. The diagnostic accuracy, sensitivity and specificity using wearable dynamic ECG recorders in a supine position were 94.74% (95% CI% 88.76%-97.80%), 88.68% (95% CI 77.06%-95.07%) and100% (95% CI 92.91%-100%), respectively. Meanwhile, the diagnostic accuracy, sensitivity and specificity in an upright position were 97.37% (95% CI% 92.21%-99.44%), 94.34% (95% CI 84.03%-98.65%), and 100% (95% CI 92.91%-100%), respectively. The result after exercise was the same as the result of the upright position.Conclusion: AF can be detected using the widely accessible wearable dynamic ECG recorder with an AI algorithm after different postures and exercises. It may provide a useful and user-friendly screening tool, diagnosing AF early in at-risk individuals.

scholarly journals Detection of Brief Episodes of Atrial Fibrillation Based on Electrocardiomatrix and Convolutional Neural Network

2021 ◽  
Vol 12 ◽  
Author(s):  
Ricardo Salinas-Martínez ◽  
Johannes de Bie ◽  
Nicoletta Marzocchi ◽  
Frida Sandberg
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Thrombus Formation ◽  
Normal Sinus Rhythm ◽  
Morphological Characteristics ◽  
P Wave ◽  
Learning Approaches ◽  
Normal Sinus

Background: Brief episodes of atrial fibrillation (AF) may evolve into longer AF episodes increasing the chances of thrombus formation, stroke, and death. Classical methods for AF detection investigate rhythm irregularity or P-wave absence in the ECG, while deep learning approaches profit from the availability of annotated ECG databases to learn discriminatory features linked to different diagnosis. However, some deep learning approaches do not provide analysis of the features used for classification. This paper introduces a convolutional neural network (CNN) approach for automatic detection of brief AF episodes based on electrocardiomatrix-images (ECM-images) aiming to link deep learning to features with clinical meaning.Materials and Methods: The CNN is trained using two databases: the Long-Term Atrial Fibrillation and the MIT-BIH Normal Sinus Rhythm, and tested on three databases: the MIT-BIH Atrial Fibrillation, the MIT-BIH Arrhythmia, and the Monzino-AF. Detection of AF is done using a sliding window of 10 beats plus 3 s. Performance is quantified using both standard classification metrics and the EC57 standard for arrhythmia detection. Layer-wise relevance propagation analysis was applied to link the decisions made by the CNN to clinical characteristics in the ECG.Results: For all three testing databases, episode sensitivity was greater than 80.22, 89.66, and 97.45% for AF episodes shorter than 15, 30 s, and for all episodes, respectively.Conclusions: Rhythm and morphological characteristics of the electrocardiogram can be learned by a CNN from ECM-images for the detection of brief episodes of AF.

scholarly journals Prediction of atrial fibrillation from normal ECG using artificial intelligence in patients with unexplained stroke

2020 ◽  
Vol 41 (Supplement_2) ◽  
Author(s):  
Y.S Baek ◽  
S.C Lee ◽  
W.I Choi ◽  
D.H Kim
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Normal Sinus Rhythm ◽  
Statistical Significance ◽  
Validation Dataset ◽  
Internal Validation ◽  
Normal Sinus ◽  
Group 2

Abstract Background Stroke related to embolic and of undetermined source constitute 20 to 30% of ischemic strokes. Many of these strokes are related to atrial fibrillation (AF), which might be underdetected due to its paroxysmal and silent nature. Purpose The aim of our study was to predict AF during normal sinus rhythm in a standard 12-lead ECG to train an artificial intelligence to train deep neural network in patients with unexplained stroke (embolic stroke of undetermined source; ESUS). Methods We analyzed digital raw data of 12-lead ECGs using artificial intelligence (AI) recurrent neural network (RNN) to detect the electrocardiographic signature of atrial fibrillation present during normal sinus rhythm using standard 12-lead ECGs. We included 2,585 cases aged 18 years or older with multiple ECGs at our university hospital between 2005 and 2017 validated by crossover analysis of two electrophysiologists. We defined the first recorded AF ECG as the index ECG and the first day of the window of interest as 14 days before the date of the index ECG. We allocated ECGs to the training, internal validation, and testing datasets in a 7:1:2 ratio. We calculated recall, F1 score, and the area under the curve (AUC) of the receiver operatoring characteristic curve (ROC) for the internal validation dataset to select a probability threshold. We applied this developed AI program to 169 ESUS patients who has been diagnosed and had standard 12-lead ECGs in our hospital. Results We acquired 1,266 NSR ECSs from real normal subjects and 1,319 NSR ECGs form paroxysmal AF patients. RNN AI-enabled ECG identified atrial fibrillation with an AUC of 0.79, recall of 82%, specificity of 78%, F1 score of 75% and overall accuracy of 72.8% (Figure). ESUS patients were divided into three groups according to calculated probabilities of AF using AI guided RNN program: group 1 (35 patients with probability of 0–25% of paroxysmal AF), group 2 (86 patients with probability of 25–75% of paroxysmal AF) and group 3 (48 patients with probability of 75–100% of paroxysmal AF). In Kaplan-Meier estimates, Group 2 and 3 (more than 25% of PAF probabilities) tended to have higher AF incidence although it did not reach statistical significance (log-rank p 0.678) (Figure). Conclusion AI may discriminate subtle changes between real and paroxysmal NSR and can also be helpful in patients with ESUS to identify if AF is the underlying cause of the stroke. Further studies are needed in order to evaluate their possible use in future prognostic models. Funding Acknowledgement Type of funding source: None

scholarly journals Diagnostic performance of a wearing dynamic ECG recorder for atrial fibrillation screening: the HUAMI heart study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Wenxia Fu ◽  
Ruogu Li
Keyword(s):  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Diagnostic Accuracy ◽  
Sensitivity And Specificity ◽  
Normal Sinus Rhythm ◽  
Screening Method ◽  
Upright Position ◽  
Great Promise ◽  
High Morbidity ◽  
Normal Sinus

Abstract Background Atrial fibrillation (AF) is the most prevalent cardiac dysrhythmia with high morbidity and mortality rate. Evidence shows that in every three patients with AF, one is asymptomatic. The asymptomatic and paroxysmal nature of AF is the reason for unsatisfactory and delayed detection using traditional instruments. Research indicates that wearing a dynamic electrocardiogram (ECG) recorder can guide accurate and safe analysis, interpretation, and distinction of AF from normal sinus rhythm. This is also achievable in an upright position and after exercises, assisted by an artificial intelligence (AI) algorithm. Methods This study enrolled 114 participants from the outpatient registry of our institution from June 24, 2020 to July 24, 2020. Participants were tested with a wearable dynamic ECG recorder and 12-lead ECG in a supine, an upright position and after exercises for 60 s. Results Of the 114 subjects enrolled in the study, 61 had normal sinus rhythm and 53 had AF. The number of cases that could not be determined by the wristband of dynamic ECG recorder was two, one and one respectively. Case results that were not clinically objective were defined as false-negative or false-positive. Results for diagnostic accuracy, sensitivity, and specificity tested by wearable dynamic ECG recorders in a supine position were 94.74% (95% CI% 88.76–97.80%), 88.68% (95% CI 77.06–95.07%), and 100% (95% CI 92.91–100%), respectively. Meanwhile, the diagnostic accuracy, sensitivity and specificity in an upright position were 97.37% (95% CI 92.21–99.44%), 94.34% (95% CI 84.03–98.65%), and 100% (95% CI 92.91–100%), respectively. Similar results as those of the upright position were obtained after exercise. Conclusion The widely accessible wearable dynamic ECG recorder integrated with an AI algorithm can efficiently detect AF in different postures and after exercises. As such, this tool holds great promise as a useful and user-friendly screening method for timely AF diagnosis in at-risk individuals.

Improving Sentiment Analysis using Hybrid Deep Learning Model

2020 ◽  
Vol 13 (4) ◽  
pp. 627-640 ◽  
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.

scholarly journals Performance Comparison of the Deep Learning and the Human Endoscopist for Bleeding Peptic Ulcer Disease

2021 ◽  
Author(s):  
Hsu-Heng Yen ◽  
Ping-Yu Wu ◽  
Pei-Yuan Su ◽  
Chia-Wei Yang ◽  
Yang-Yuan Chen ◽  
...  
Keyword(s):  
Peptic Ulcer ◽  
Deep Learning ◽  
Sensitivity And Specificity ◽  
Endoscopic Therapy ◽  
Learning Model ◽  
Ulcer Bleeding ◽  
Learning Models ◽  
Peptic Ulcer Bleeding ◽  
Ulcer Disease ◽  
Deep Learning Model

Abstract Purpose Management of peptic ulcer bleeding is clinically challenging. Accurate characterization of the bleeding during endoscopy is key for endoscopic therapy. This study aimed to assess whether a deep learning model can aid in the classification of bleeding peptic ulcer disease. Methods Endoscopic still images of patients (n = 1694) with peptic ulcer bleeding for the last 5 years were retrieved and reviewed. Overall, 2289 images were collected for deep learning model training, and 449 images were validated for the performance test. Two expert endoscopists classified the images into different classes based on their appearance. Four deep learning models, including Mobile Net V2, VGG16, Inception V4, and ResNet50, were proposed and pre-trained by ImageNet with the established convolutional neural network algorithm. A comparison of the endoscopists and trained deep learning model was performed to evaluate the model’s performance on a dataset of 449 testing images. Results The results first presented the performance comparisons of four deep learning models. The Mobile Net V2 presented the optimal performance of the proposal models. The Mobile Net V2 was chosen for further comparing the performance with the diagnostic results obtained by one senior and one novice endoscopists. The sensitivity and specificity were acceptable for the prediction of “normal” lesions in both 3-class and 4-class classifications. For the 3-class category, the sensitivity and specificity were 94.83% and 92.36%, respectively. For the 4-class category, the sensitivity and specificity were 95.40% and 92.70%, respectively. The interobserver agreement of the testing dataset of the model was moderate to substantial with the senior endoscopist. The accuracy of the determination of endoscopic therapy required and high-risk endoscopic therapy of the deep learning model was higher than that of the novice endoscopist. Conclusions In this study, the deep learning model performed better than inexperienced endoscopists. Further improvement of the model may aid in clinical decision-making during clinical practice, especially for trainee endoscopist.

Sign in / Sign up

Export Citation Format

Share Document