VFPred combines signal processing and machine learning for VF detection from short ECG signals.
problem Detecting Ventricular Fibrillation from short ECG signals.
method VFPred uses Empirical Mode Decomposition, Discrete Time Fourier Transform, and Support Vector Machine.
result VFPred achieves high sensitivity and specificity even from short 5-second signals.
Model predicts ventricular tachyarrhythmias with high accuracy.
problem Predicting ventricular tachyarrhythmias for patient care.
method Multi-task neural network architecture with patient metadata.
result 74.02% prediction accuracy 60 seconds in advance.
Compact neural network for ECG classification reduces resource needs.
problem Current reliance on deep learning for ECG analysis requires extensive resources and large datasets.
method Simple ANN architecture with advanced feature engineering.
result Achieved 97.36% accuracy in classifying 4 types of arrhythmias.
Deep learning detects atrial fibrillation from wearable sensor data.
problem Detecting atrial fibrillation from raw sensor data.
method Convolutional-recurrent neural network with long short-term memory, end-to-end learning.
result State-of-the-art AFib detection with high accuracy.
ResNet architectures improve atrial fibrillation classification.
problem Improving atrial fibrillation classification accuracy.
method Varying ResNet architecture parameters (filter count, block layout, etc.) across different model sizes.
result Similar performance across models with varying configurations, suggesting parameter dominance.
Deep learning detects atrial fibrillation with high accuracy.
problem Detecting atrial fibrillation in ECG signals.
method Extracted deep features from spectrograms using convolutional networks.
result Convolutional network achieved 93.16% classification accuracy.
Model predicts uncertainty for ECG signals to detect atypical recordings.
problem Detecting atypical ECG recordings with improved algorithm quality.
method Predicts parameters of the beta distribution over class probabilities.
result Significantly improves algorithm quality on confident predictions.
We tackle the problem of classifying Electrocardiography (ECG) signals with the aim of predicting the onset of Paroxysmal Atrial Fibrillation (PAF). Atrial fibrillation is the most common type of arrhythmia, but in many cases PAF episodes are asymptomatic. Therefore, in order to help diagnosing PAF, it is important to …
Novel ECG classification for AF using spectro-temporal Kalman filtering and deep CNN.
problem Atrial fibrillation (AF) detection in ECG signals.
method Spectro-temporal representation using Kalman filter and deep convolutional neural networks.
result Proposed method achieves an overall F1 score of 80.2% on the PhysioNet/Computing in Cardiology (CinC) 2017 dataset.
New method learns disentangled representations from ECG data for VT origin classification.
problem Challenges in learning subject-specific models from ECG data due to inter-subject variations.
method Conditional Variational Autoencoder (VAE) with maximum mean discrepancy regularization and contrastive regularization.
result Demonstrated efficacy in classifying VT origin segments compared to standard VAE.
The development of new technology such as wearables that record high-quality single channel ECG, provides an opportunity for ECG screening in a larger population, especially for atrial fibrillation screening. The main goal of this study is to develop an automatic classification algorithm for normal sinus rhythm (NSR), …
AdaCGP learns dynamic graph topology from time series data, improving over existing methods.
problem Learning dynamic graph topology from time-varying signals, especially in real-time applications.
method AdaCGP is a sparsity-aware adaptive algorithm that recursively estimates the Graph Shift Operator (GSO) through variable splitting.
result AdaCGP outperforms state-of-the-art methods in GSO estimation, achieving improvements exceeding 83%.
Paper introduces rational Gaussian wavelets for efficient signal approximation.
problem Efficiently approximating complex signals with few coefficients.
method Continuous wavelet transform using rational Gaussian wavelets with adjustable parameters.
result Proposed rational Gaussian wavelets provide accurate signal approximations.
Study shows GAN and GMM data augmentation improves AF signal classification accuracy.
problem Class imbalance in atrial fibrillation ECG datasets.
method Investigated various data augmentation techniques (oversampling, GMMs, GANs).
result GAN and GMM data augmentation lead to better AF signal classification accuracy.
GPMI method interpolates uncertain atrial conduction velocity on non-Euclidean manifolds.
problem Uncertainty in atrial conduction velocity calculations.
method Gaussian Process Manifold Interpolation (GPMI) on human atrial manifolds.
result GPMI accounts for atrial topology and calculates CV uncertainty.
CNNs improve ECG noise detection for better heart condition monitoring.
problem Signal noise in mobile ECGs hinders accurate diagnosis.
method Developed and trained a 16-layer CNN on a noise-annotated dataset.
result 16-layer CNN achieves 0.977 AUC on ECG noise detection.
DeepBeat uses deep learning to assess signal quality and detect arrhythmia in wearable devices.
problem Detecting atrial fibrillation from wearable devices with noise.
method Multi-task deep learning approach using convolutional denoising autoencoders.
result Significantly improved AF detection accuracy compared to traditional methods.
Deep learning predicts AF recurrence from MRI images without pre-processing.
problem Estimating AF recurrence from MRI images efficiently and accurately.
method Deep learning approach to predict shape descriptors directly from MRI images.
result Deep learning method produces similar outcomes to state-of-the-art methods.
V-FCNN neural network segments atria from clinical images.
problem Automatic segmentation of atria from high-resolution images.
method Volumetric Fully Convolution Neural Network (V-FCNN) with a mixed loss function.
result 92.5% Dice similarity coefficient in 54 patients.
Personalized deep learning reduces inappropriate shocks in VA detection.
problem High inappropriate shock rate in traditional VA detection methods.
method Personalized deep learning framework using CNN for real-time VA detection and collaborative inference.
result 6.6% reduction in inappropriate shock rate compared to traditional methods.
Machine learning enhances cardiac arrhythmia treatment through predictive modelling.
problem Improving catheter ablation success rates for treating atrial fibrillation.
method Combining machine learning and predictive modelling with cardiac electrophysiology data.
result Enhanced accuracy in predicting and inferring parameters of cardiac models.
Generative adversarial network system improves ECG arrhythmia classification.
problem Improving automatic ECG arrhythmia classification accuracy.
method Generative adversarial network with patient-specific normal beats and generated abnormal beats.
result Superior overall classification performance for SVEB and VEB on MIT-BIH arrhythmia database.
Background: Cardiac MRI derived biventricular mass and function parameters, such as end-systolic volume (ESV), end-diastolic volume (EDV), ejection fraction (EF), stroke volume (SV), and ventricular mass (VM) are clinically well established. Image segmentation can be challenging and time-consuming, due to the complex a…
In this paper, we propose a new deep feature selection method based on deep architecture. Our method uses stacked auto-encoders for feature representation in higher-level abstraction. We developed and applied a novel feature learning approach to a specific precision medicine problem, which focuses on assessing and prio…
Study estimates treatment effect on survival outcomes using targeted maximum likelihood estimation.
problem Estimating treatment effect on time-to-event outcomes in clinical settings.
method Divided into three phases: estimation, feature selection, and targeted maximum likelihood estimation.
result Method performs well in high sample size or event rate conditions.
GANs improve echo frame generation with labeled patches.
problem Automated echocardiography with limited labels.
method Conditional GAN with patch-based discriminator.
result GAN-enhanced echo frames match given segmentation masks.
MS-FCN improves cardiac left ventricle segmentation accuracy.
problem Accurate segmentation of left ventricle from MRI images.
method Multi-scale fully convolutional network with dense connectivity.
result MS-FCN achieves state-of-the-art Dice scores (0.93 on endocardium, 0.96 on epicardium).
We aim to produce predictive models that are not only accurate, but are also interpretable to human experts. Our models are decision lists, which consist of a series of if...then... statements (e.g., if high blood pressure, then stroke) that discretize a high-dimensional, multivariate feature space into a series of sim…
Flexible Cox model for time-dependent covariates with complex sparsity patterns.
problem Lack of flexibility in enforcing specific sparsity patterns in time-dependent Cox models.
method Proposes a flexible framework for variable selection in time-dependent Cox models, accommodating complex selection rules.
result Achieves accurate estimation with low false alarm rates for complex covariate structures.
Model predicts VKA dosage for Indian patients, aiding in safe medication.
problem Safe and accurate dosing of VKA drugs for Indian patients.
method Support Vector Machine (SVM) Regression model trained on patient data.
result Predicted dosages closely match actual dosages.
SCRIB assigns multiple labels to each example to control class-specific prediction risks.
problem Lack of a sound mechanism to decide when to refrain from predicting in DL classifiers.
method Set-classifier with Class-specific Risk Bounds (SCRIB) that assigns multiple labels to each example and controls class-specific prediction risks.
result SCRIB obtained class-specific risks 35%-88% closer to the target risks than baseline methods.
Proposes a novel anomaly detection method for echocardiogram videos.
problem Anomaly detection in echocardiogram videos.
method Dynamic Variational Trajectory Models (TVAE-C, TVAE-R, TVAE-S) trained on healthy infant echocardiogram videos.
result Superior performance in detecting congenital heart defects and pulmonary hypertension.
Causal graph aids observational study insights in aSAH patients.
problem Lack of clear objectives and tools for identifying necessary adjustments in observational studies.
method Uses causal directed acyclic graphs (DAGs) to provide insights mid-study and identify necessary data enhancements.
result Midway insights and necessary data enhancements identified for meaningful causal questions.
Study forecasts aortic pressure with deep learning models.
problem Forecasting noisy, non-stationary aortic pressure.
method Used deep learning models, specifically recurrent neural networks with Legendre Memory Unit, on 25 Hz time series data.
result Recurrent neural networks with Legendre Memory Unit achieved the best performance with an overall forecasting error of 1.8 mmHg.
This technical note considers the problems of blind sparse learning and inference of electrogram (EGM) signals under atrial fibrillation (AF) conditions. First of all we introduce a mathematical model for the observed signals that takes into account the multiple foci typically appearing inside the heart during AF. Then…
Objectives: Atrial fibrillation (AF) is a common heart rhythm disorder associated with deadly and debilitating consequences including heart failure, stroke, poor mental health, reduced quality of life and death. Having an automatic system that diagnoses various types of cardiac arrhythmias would assist cardiologists to…
Generative Adversarial Model improves RV segmentation accuracy in MRI.
problem Accurate segmentation of the right ventricular blood pool from cine MRI sequences.
method Combines FCNN, Gated Recurrent Units (GRU), Generative Adversarial Networks (GAN), and L1 loss function.
result Improves Dice Index and Hausdorff Distance by 0.05 and 3.49 mm respectively.
Semi-supervised learning classifies cardiac pathology using motion features from cine MRI.
problem Classifying cardiac pathology based on motion features from cine MRI.
method Semi-supervised learning of apparent flow to generate motion features from non-segmented images.
result The model achieves 95% classification accuracy on ACDC test set.
Method estimates model performance on external samples from limited statistical characteristics.
problem Limited access to multiple datasets due to privacy and commercial restrictions.
method Search for weights that match external statistics and are closest to uniform, using model performance on weighted internal sample as an estimation.
result Estimated external performance is closer to actual performance than internal performance.
Independent component analysis (ICA) aims at decomposing an observed random vector into statistically independent variables. Deflation-based implementations, such as the popular one-unit FastICA algorithm and its variants, extract the independent components one after another. A novel method for deflationary ICA, referr…
Study explores DNNs' reliance on existing vs. new features in physiological signals.
problem Understanding how deep neural networks discover new features in physiological signals.
method Proposes a method to remove hand-engineered features and force DNNs to learn new representations.
result DNNs often rediscover known features, but can also learn new ones.
LU-Net improves cardiac segmentation accuracy and robustness.
problem Robustness and accuracy of deep learning cardiac segmentation.
method Multi-task end-to-end network designed to improve cardiac segmentation.
result Outperforms current best deep learning solution, reducing outliers and improving clinical indices.
Deep learning improves LV segmentation and volume estimation from cardiac MRI.
problem Accurate LV segmentation and volume estimation for cardiac MRI.
method Image preprocessing, U-Net architecture, postprocessing, end-to-end analytics pipeline.
result Improved accuracy in LV segmentation and volume estimation.
Generative model combines shape and intensity priors for left atrium segmentation.
problem Challenges in segmenting left atrium MRI images due to shape variation and multimodality.
method Generative image model with mixture of Gaussians for shape priors and autoencoders for intensity priors.
result Maximizes posterior probability using a mixture of Gaussians for shape priors and autoencoders for intensity priors.
Paper proposes DCDG for semi-supervised learning with MRI data.
problem Lack of labeled data and distribution mismatch between labeled and unlabeled data.
method Double-sided domain adaptation for feature space fusion and indirect learning for discriminativeness.
result Proposed DCDG achieves compelling segmentation results for LGE-CMRI images.
Deep learning models trained on adult cardiac MRI data struggle to accurately segment rare congenital heart diseases.
problem Accuracy of U-Net-based segmentation models trained on adult cardiac MRI data when applied to rare congenital heart diseases like Tetralogy of Fallot.
method Cross-validation with four-fold, evaluation on unseen data from different pathologies.
result Deep learning models overfit to the training data, leading to significant accuracy drops when applied to other pathologies.
System detects and predicts cardiac anomalies from ECG data.
problem Early detection of cardiac anomalies to reduce healthcare costs and mortality.
method Discrete Wavelet Transform (DWT) and Undecimated Wavelet Transform (UWT) for feature extraction; Bayesian Network Classifier for anomaly prediction.
result Average accuracy of 96.6% for PAC, 92.8% for MI, and 87% for PVC on real ECG datasets.
A new model classifies multi-lead ECGs better than single-channel models.
problem Classifying multi-lead ECGs for accurate diagnosis.
method Channel-wise attention mechanism in CNNs for multi-lead ECG classification.
result The model achieves better sensitivity and precision than plain ResNet models.