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

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.

scholarly journals Prediction model for thyrotoxic atrial fibrillation: a retrospective study.

2021 ◽  
Author(s):  
Daria Aleksandrovna Ponomartseva ◽  
Ilia Vladislavovich Derevitskii ◽  
Sergey Valerevich Kovalchuk ◽  
Alina Yurevna Babenko
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Heart Rate ◽  
Retrospective Study ◽  
Prediction Model ◽  
Performance Metrics ◽  
Premature Ventricular Contraction ◽  
Ventricular Contraction ◽  
Atrial Contraction ◽  
Premature Atrial Contraction

Abstract Background: Thyrotoxic atrial fibrillation (TAF) is a recognized significant complication of hyperthyroidism. Early identification of the individuals predisposed to TAF would improve thyrotoxic patients’ management. However, to our knowledge, an instrument that establishes an individual risk of the condition is unavailable. Therefore, the aim of this study is to build a TAF prediction model and rank TAF predictors in order of importance. Methods: In this retrospective study, we have investigated 36 demographic and clinical features for 420 patients with overt hyperthyroidism, 30% of which had TAF. At first, the association of these features with TAF was evaluated by classical statistical methods. Then, we developed several TAF prediction models with eight different machine learning classifiers and compared them by performance metrics. The models included ten features that were selected based on their clinical effectuality and importance for model output. Finally, we ranked TAF predictors, elicited from the optimal final model, by the machine learning tehniques. Results: The best performance metrics prediction model was built with the extreme gradient boosting classifier. It had the reasonable accuracy of 84% and AUROC of 0.89 on the test set. The model confirmed such well-known TAF risk factors as age, sex, hyperthyroidism duration, heart rate and some concomitant cardiovascular diseases (arterial hypertension and conjestive heart rate). We also identified premature atrial contraction and premature ventricular contraction as new TAF predictors. The top five TAF predictors, elicited from the model, included (in order of importance) PAC, PVC, hyperthyroidism duration, heart rate during hyperthyroidism and age. Conclusions: We developed a machine learning model for TAF prediction. It seems to be the first available analytical tool for TAF risk assessment. In addition, we defined five most important TAF predictors, including premature atrial contraction and premature ventricular contraction as the new ones. These results have contributed to TAF prediction investigation and may serve as a basis for further research focused on TAF prediction improvement and facilitation of thyrotoxic patients’ management.

scholarly journals Prediction model for thyrotoxic atrial fibrillation: a retrospective study

2021 ◽  
Vol 21 (1) ◽  
Author(s):  
Daria Aleksandrovna Ponomartseva ◽  
Ilia Vladislavovich Derevitskii ◽  
Sergey Valerevich Kovalchuk ◽  
Alina Yurevna Babenko
Keyword(s):  
Machine Learning ◽  
Atrial Fibrillation ◽  
Heart Rate ◽  
Retrospective Study ◽  
Prediction Model ◽  
Performance Metrics ◽  
Premature Ventricular Contraction ◽  
Ventricular Contraction ◽  
Atrial Contraction ◽  
Premature Atrial Contraction

Abstract Background Thyrotoxic atrial fibrillation (TAF) is a recognized significant complication of hyperthyroidism. Early identification of the individuals predisposed to TAF would improve thyrotoxic patients’ management. However, to our knowledge, an instrument that establishes an individual risk of the condition is unavailable. Therefore, the aim of this study is to build a TAF prediction model and rank TAF predictors in order of importance using machine learning techniques. Methods In this retrospective study, we have investigated 36 demographic and clinical features for 420 patients with overt hyperthyroidism, 30% of which had TAF. At first, the association of these features with TAF was evaluated by classical statistical methods. Then, we developed several TAF prediction models with eight different machine learning classifiers and compared them by performance metrics. The models included ten features that were selected based on their clinical effectuality and importance for model output. Finally, we ranked TAF predictors, elicited from the optimal final model, by the machine learning tehniques. Results The best performance metrics prediction model was built with the extreme gradient boosting classifier. It had the reasonable accuracy of 84% and AUROC of 0.89 on the test set. The model confirmed such well-known TAF risk factors as age, sex, hyperthyroidism duration, heart rate and some concomitant cardiovascular diseases (arterial hypertension and conjestive heart rate). We also identified premature atrial contraction and premature ventricular contraction as new TAF predictors. The top five TAF predictors, elicited from the model, included (in order of importance) PAC, PVC, hyperthyroidism duration, heart rate during hyperthyroidism and age. Conclusions We developed a machine learning model for TAF prediction. It seems to be the first available analytical tool for TAF risk assessment. In addition, we defined five most important TAF predictors, including premature atrial contraction and premature ventricular contraction as the new ones. These results have contributed to TAF prediction investigation and may serve as a basis for further research focused on TAF prediction improvement and facilitation of thyrotoxic patients’ management.

scholarly journals NIMG-08. PREDICTION OF LOWER-GRADE GLIOMA MOLECULAR SUBTYPES USING DEEP LEARNING

2020 ◽  
Vol 22 (Supplement_2) ◽  
pp. ii148-ii148
Author(s):  
Yoshihiro Muragaki ◽  
Yutaka Matsui ◽  
Takashi Maruyama ◽  
Masayuki Nitta ◽  
Taiichi Saito ◽  
...  
Keyword(s):  
Deep Learning ◽  
Cross Validation ◽  
Molecular Subtype ◽  
Learning Model ◽  
Group Classification ◽  
Training Dataset ◽  
Lower Grade ◽  
Test Dataset ◽  
Ct Data ◽  
Deep Learning Model

Abstract INTRODUCTION It is useful to know the molecular subtype of lower-grade gliomas (LGG) when deciding on a treatment strategy. This study aims to diagnose this preoperatively. METHODS A deep learning model was developed to predict the 3-group molecular subtype using multimodal data including magnetic resonance imaging (MRI), positron emission tomography (PET), and computed tomography (CT). The performance was evaluated using leave-one-out cross validation with a dataset containing information from 217 LGG patients. RESULTS The model performed best when the dataset contained MRI, PET, and CT data. The model could predict the molecular subtype with an accuracy of 96.6% for the training dataset and 68.7% for the test dataset. The model achieved test accuracies of 58.5%, 60.4%, and 59.4% when the dataset contained only MRI, MRI and PET, and MRI and CT data, respectively. The conventional method used to predict mutations in the isocitrate dehydrogenase (IDH) gene and the codeletion of chromosome arms 1p and 19q (1p/19q) sequentially had an overall accuracy of 65.9%. This is 2.8 percent point lower than the proposed method, which predicts the 3-group molecular subtype directly. CONCLUSIONS AND FUTURE PERSPECTIVE A deep learning model was developed to diagnose the molecular subtype preoperatively based on multi-modality data in order to predict the 3-group classification directly. Cross-validation showed that the proposed model had an overall accuracy of 68.7% for the test dataset. This is the first model to double the expected value for a 3-group classification problem, when predicting the LGG molecular subtype. We plan to apply the techniques of heat map and/or segmentation for an increase in prediction accuracy.

scholarly journals Atrial Fibrillation Detection from Wrist Photoplethysmography Signals Using Smartwatches

2019 ◽  
Vol 9 (1) ◽  
Author(s):  
Syed Khairul Bashar ◽  
Dong Han ◽  
Shirin Hajeb-Mohammadalipour ◽  
Eric Ding ◽  
Cody Whitcomb ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Detection Algorithm ◽  
Motion Artifacts ◽  
False Alarms ◽  
Time Frequency ◽  
Non Invasive ◽  
Accelerometer Signal ◽  
Atrial Contraction ◽  
Premature Atrial Contraction ◽  
Sensitivity Specificity

Abstract Detection of atrial fibrillation (AF) from a wrist watch photoplethysmogram (PPG) signal is important because the wrist watch form factor enables long term continuous monitoring of arrhythmia in an easy and non-invasive manner. We have developed a novel method not only to detect AF from a smart wrist watch PPG signal, but also to determine whether the recorded PPG signal is corrupted by motion artifacts or not. We detect motion and noise artifacts based on the accelerometer signal and variable frequency complex demodulation based time-frequency analysis of the PPG signal. After that, we use the root mean square of successive differences and sample entropy, calculated from the beat-to-beat intervals of the PPG signal, to distinguish AF from normal rhythm. We then use a premature atrial contraction detection algorithm to have more accurate AF identification and to reduce false alarms. Two separate datasets have been used in this study to test the efficacy of the proposed method, which shows a combined sensitivity, specificity and accuracy of 98.18%, 97.43% and 97.54% across the datasets.

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

2020 ◽  
Vol 316 ◽  
pp. 130-136 ◽  
Author(s):  
Sarah W.E. Baalman ◽  
Florian E. Schroevers ◽  
Abel J. Oakley ◽  
Tom F. Brouwer ◽  
Willeke van der Stuijt ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Deep Learning ◽  
Learning Model ◽  
Single Cycle ◽  
Deep Learning Model ◽  
Atrial Fibrillation Detection

scholarly journals Accelerating the Automated Detection, Counting and Measurements of Reproductive Organs in Herbarium Collections in the Era of Deep Learning

2019 ◽  
Vol 3 ◽  
Author(s):  
Adán Mora-Fallas ◽  
Hervé Goëau ◽  
Susan Mazer ◽  
Natalie Love ◽  
Erick Mata-Montero ◽  
...  
Keyword(s):  
Deep Learning ◽  
Active Learning ◽  
Reproductive Organs ◽  
Learning Model ◽  
Learning Technologies ◽  
Training Dataset ◽  
Basic Information ◽  
Learning Mechanism ◽  
Deep Learning Model ◽  
Instance Segmentation

Millions of herbarium records provide an invaluable legacy and knowledge of the spatial and temporal distributions of plants over centuries across all continents (Soltis et al. 2018). Due to recent efforts to digitize and to make publicly accessible most major natural collections, investigations of ecological and evolutionary patterns at unprecedented geographic scales are now possible (Carranza-Rojas et al. 2017, Lorieul et al. 2019). Nevertheless, biologists are now facing the problem of extracting from a huge number of herbarium sheets basic information such as textual descriptions, the numbers of organs, and measurements of various morphological traits. Deep learning technologies can dramatically accelerate the extraction of such basic information by automating the routines of organ identification, counts and measurements, thereby allowing biologists to spend more time on investigations such as phenological or geographic distribution studies. Recent progress on instance segmentation demonstrated by the Mask-RCNN method is very promising in the context of herbarium sheets, in particular for detecting with high precision different organs of interest on each specimen, including leaves, flowers, and fruits. However, like any deep learning approach, this method requires a significant number of labeled examples with fairly detailed outlines of individual organs. Creating such a training dataset can be very time-consuming and may be discouraging for researchers. We propose in this work to integrate the Mask-RCNN approach within a global system enabling an active learning mechanism (Sener and Savarese 2018) in order to minimize the number of outlines of organs that researchers must manually annotate. The principle is to alternate cycles of manual annotations and training updates of the deep learning model and predictions on the entire collection to process. Then, the challenge of the active learning mechanism is to estimate automatically at each cycle which are the most useful objects that must be manually extracted in the next manual annotation cycle in order to learn, in as few cycles as possible, an accurate model. We discuss experiments addressing the effectiveness, the limits and the time required of our approach for annotation, in the context of a phenological study of more than 10,000 reproductive organs (buds, flowers, fruits and immature fruits) of Streptanthus tortuosus, a species known to be highly variable in appearance and therefore very difficult to be processed by an instance segmentation deep learning model.

scholarly journals A Deep Learning Model for Estimation of Patients with Undiagnosed Diabetes

2020 ◽  
Vol 10 (1) ◽  
pp. 421 ◽  
Author(s):  
Kwang Sun Ryu ◽  
Sang Won Lee ◽  
Erdenebileg Batbaatar ◽  
Jae Wook Lee ◽  
Kui Son Choi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Medical Care ◽  
Smoking Status ◽  
Learning Model ◽  
Machine Learning Techniques ◽  
Undiagnosed Diabetes ◽  
Training Dataset ◽  
Family History Of Diabetes ◽  
Screening Model ◽  
Deep Learning Model

A screening model for undiagnosed diabetes mellitus (DM) is important for early medical care. Insufficient research has been carried out developing a screening model for undiagnosed DM using machine learning techniques. Thus, the primary objective of this study was to develop a screening model for patients with undiagnosed DM using a deep neural network. We conducted a cross-sectional study using data from the Korean National Health and Nutrition Examination Survey (KNHANES) 2013–2016. A total of 11,456 participants were selected, excluding those with diagnosed DM, an age < 20 years, or missing data. KNHANES 2013–2015 was used as a training dataset and analyzed to develop a deep learning model (DLM) for undiagnosed DM. The DLM was evaluated with 4444 participants who were surveyed in the 2016 KNHANES. The DLM was constructed using seven non-invasive variables (NIV): age, waist circumference, body mass index, gender, smoking status, hypertension, and family history of diabetes. The model showed an appropriate performance (area under curve (AUC): 80.11) compared with existing previous screening models. The DLM developed in this study for patients with undiagnosed diabetes could contribute to early medical care.

scholarly journals Prediction of steady flows passing fixed cylinders using deep learning

2022 ◽  
Vol 12 (1) ◽  
Author(s):  
Hiroto Ozaki ◽  
Takeshi Aoyagi
Keyword(s):  
Deep Learning ◽  
Velocity Field ◽  
Computational Cost ◽  
Learning Model ◽  
Dynamics Simulation ◽  
Machine Learning Techniques ◽  
Training Dataset ◽  
Steady Flows ◽  
Fluid Force ◽  
Deep Learning Model

AbstractConsiderable attention has been given to deep-learning and machine-learning techniques in an effort to reduce the computational cost of computational fluid dynamics simulation. The present paper addresses the prediction of steady flows passing many fixed cylinders using a deep-learning model and investigates the accuracy of the predicted velocity field. The deep-learning model outputs the x- and y-components of the flow velocity field when the cylinder arrangement is input. The accuracy of the predicted velocity field is investigated, focusing on the velocity profile of the fluid flow and the fluid force acting on the cylinders. The present model accurately predicts the flow when the number of cylinders is equal to or close to that set in the training dataset. The extrapolation of the prediction to a smaller number of cylinders results in error, which can be interpreted as internal friction of the fluid. The results of the fluid force acting on the cylinders suggest that the present deep-learning model has good generalization performance for systems with a larger number of cylinders.

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

Sign in / Sign up

Export Citation Format

Share Document