Electrocardiogram generation with a bidirectional LSTM-CNN generative adversarial network

Generating Synthetic Fermentation Data of Shindari, a Traditional Jeju Beverage, Using Multiple Imputation Ensemble and Generative Adversarial Networks

Fermentation is an age-old technique used to preserve food by restoring proper microbial balance. Boiled barley and nuruk are fermented for a short period to produce Shindari, a traditional beverage for the people of Jeju, South Korea. Shindari has been proven to be a drink of multiple health benefits if fermented for an optimal period. It is necessary to predict the ideal fermentation time required by each microbial community to keep the advantages of the microorganisms produced by the fermentation process in Shindari intact and to eliminate contamination. Prediction through machine learning requires past data but the process of obtaining fermentation data of Shindari is time consuming, expensive, and not easily available. Therefore, there is a need to generate synthetic fermentation data to explore various benefits of the drink and to reduce any risk from overfermentation. In this paper, we propose a model that takes incomplete tabular fermentation data of Shindari as input and uses multiple imputation ensemble (MIE) and generative adversarial networks (GAN) to generate synthetic fermentation data that can be later used for prediction and microbial spoilage control. For multiple imputation, we used multivariate imputation by chained equations and random forest imputation, and ensembling was done using the bagging and stacking method. For generating synthetic data, we remodeled the tabular GAN with skip connections and adapted the architecture of Wasserstein GAN with gradient penalty. We compared the performance of our model with other imputation and ensemble models using various evaluation metrics and visual representations. Our GAN model could overcome the mode collapse problem and converged at a faster rate than existing GAN models for synthetic data generation. Experiment results show that our proposed model executes with less error, is more accurate, and generates significantly better synthetic fermentation data compared to other models.

Electrocardiogram lead selection for intelligent screening of patients with systolic heart failure

Electrocardiogram (ECG)-based intelligent screening for systolic heart failure (HF) is an emerging method that could become a low-cost and rapid screening tool for early diagnosis of the disease before the comprehensive echocardiographic procedure. We collected 12-lead ECG signals from 900 systolic HF patients (ejection fraction, EF < 50%) and 900 individuals with normal EF in the absence of HF symptoms. The 12-lead ECG signals were converted by continuous wavelet transform (CWT) to 2D spectra and classified using a 2D convolutional neural network (CNN). The 2D CWT spectra of 12-lead ECG signals were trained separately in 12 identical 2D-CNN models. The 12-lead classification results of the 2D-CNN model revealed that Lead V6 had the highest accuracy (0.93), sensitivity (0.97), specificity (0.89), and f1 scores (0.94) in the testing dataset. We designed four comprehensive scoring methods to integrate the 12-lead classification results into a key diagnostic index. The highest quality result among these four methods was obtained when Leads V5 and V6 of the 12-lead ECG signals were combined. Our new 12-lead ECG signal–based intelligent screening method using straightforward combination of ECG leads provides a fast and accurate approach for pre-screening for systolic HF.

Deep Learning in Mining Biological Data

Recent technological advancements in data acquisition tools allowed life scientists to acquire multimodal data from different biological application domains. Categorized in three broad types (i.e. images, signals, and sequences), these data are huge in amount and complex in nature. Mining such enormous amount of data for pattern recognition is a big challenge and requires sophisticated data-intensive machine learning techniques. Artificial neural network-based learning systems are well known for their pattern recognition capabilities, and lately their deep architectures-known as deep learning (DL)-have been successfully applied to solve many complex pattern recognition problems. To investigate how DL-especially its different architectures-has contributed and been utilized in the mining of biological data pertaining to those three types, a meta-analysis has been performed and the resulting resources have been critically analysed. Focusing on the use of DL to analyse patterns in data from diverse biological domains, this work investigates different DL architectures' applications to these data. This is followed by an exploration of available open access data sources pertaining to the three data types along with popular open-source DL tools applicable to these data. Also, comparative investigations of these tools from qualitative, quantitative, and benchmarking perspectives are provided. Finally, some open research challenges in using DL to mine biological data are outlined and a number of possible future perspectives are put forward.

SynSigGAN: Generative Adversarial Networks for Synthetic Biomedical Signal Generation

Automating medical diagnosis and training medical students with real-life situations requires the accumulation of large dataset variants covering all aspects of a patient's condition. For preventing the misuse of patient's private information, datasets are not always publicly available. There is a need to generate synthetic data that can be trained for the advancement of public healthcare without intruding on patient's confidentiality. Currently, rules for generating synthetic data are predefined and they require expert intervention, which limits the types and amount of synthetic data. In this paper, we propose a novel generative adversarial networks (GAN) model, named SynSigGAN, for automating the generation of any kind of synthetic biomedical signals. We have used bidirectional grid long short-term memory for the generator network and convolutional neural network for the discriminator network of the GAN model. Our model can be applied in order to create new biomedical synthetic signals while using a small size of the original signal dataset. We have experimented with our model for generating synthetic signals for four kinds of biomedical signals (electrocardiogram (ECG), electroencephalogram (EEG), electromyography (EMG), photoplethysmography (PPG)). The performance of our model is superior wheen compared to other traditional models and GAN models, as depicted by the evaluation metric. Synthetic biomedical signals generated by our approach have been tested while using other models that could classify each signal significantly with high accuracy.

Modeling of dynamical systems through deep learning

This review presents a modern perspective on dynamical systems in the context of current goals and open challenges. In particular, our review focuses on the key challenges of discovering dynamics from data and finding data-driven representations that make nonlinear systems amenable to linear analysis. We explore various challenges in modern dynamical systems, along with emerging techniques in data science and machine learning to tackle them. The two chief challenges are (1) nonlinear dynamics and (2) unknown or partially known dynamics. Machine learning is providing new and powerful techniques for both challenges. Dimensionality reduction methods are used for projecting dynamical methods in reduced form, and these methods perform computational efficiency on real-world data. Data-driven models drive to discover the governing equations and give laws of physics. The identification of dynamical systems through deep learning techniques succeeds in inferring physical systems. Machine learning provides advanced new and powerful algorithms for nonlinear dynamics. Advanced deep learning methods like autoencoders, recurrent neural networks, convolutional neural networks, and reinforcement learning are used in modeling of dynamical systems.

HAN-ECG: An interpretable atrial fibrillation detection model using hierarchical attention networks

Atrial fibrillation (AF) is one of the most prevalent cardiac arrhythmias that affects the lives of many people around the world and is associated with a five-fold increased risk of stroke and mortality. Like other problems in the healthcare domain, artificial intelligence (AI)-based models have been used to detect AF from patients' ECG signals. The cardiologist level performance in detecting this arrhythmia is often achieved by deep learning-based methods, however, they suffer from the lack of interpretability. In other words, these approaches are unable to explain the reasons behind their decisions. The lack of interpretability is a common challenge toward a wide application of machine learning (ML)-based approaches in the healthcare which limits the trust of clinicians in such methods. To address this challenge, we propose HAN-ECG, an interpretable bidirectional-recurrent-neural-network-based approach for the AF detection task. The HAN-ECG employs three attention mechanism levels to provide a multi-resolution analysis of the patterns in ECG leading to AF. The detected patterns by this hierarchical attention model facilitate the interpretation of the neural network decision process in identifying the patterns in the signal which contributed the most to the final detection. Experimental results on two AF databases demonstrate that our proposed model performs better than the existing algorithms. Visualization of these attention layers illustrates that our proposed model decides upon the important waves and heartbeats which are clinically meaningful in the detection task (e.g., absence of P-waves, and irregular R-R intervals for the AF detection task).

Feature matching based ECG generative network for arrhythmia event augmentation

Recent developments in the field of deep learning has shown a rise in its use for clinical applications such as electrocardiogram (ECG) analysis and cardiac arrhythmia classification. Such systems are essential in the early detection and management of cardiovascular diseases. However, due to privacy concerns and also the lack of resources, there is a gap in the data available to run such powerful and data-intensive models. To address the lack of annotated, high-quality ECG data for heart disease research, ECG data generation from a small set of ECG to obtain huge annotated data is seen as an effective solution. Generative Feature Matching Network (GFMN) was shown to resolve few drawbacks of commonly used generative adversarial networks (GAN). Based on this, we developed a deep learning model to generate ECGs that resembles real ECG by feature matching with the existing data.Clinical relevance- This work addresses the lack of a large quantity of good quality, publicly available annotated ECG data required to build deep learning models for cardiac signal processing research. We can use the model presented in this paper to generate ECG signals of a target rhythm pattern and also subject-specific ECG morphology that could improve their cardiac health monitoring while maintaining privacy.

Deep Learning Algorithm Classifies Heartbeat Events Based on Electrocardiogram Signals

Cardiovascular diseases (CVDs) have become the number 1 threat to human health. Their numerous complications mean that many countries remain unable to prevent the rapid growth of such diseases, although significant health resources have been invested toward their prevention and management. Electrocardiogram (ECG) is the most important non-invasive physiological signal for CVD screening and diagnosis. For exploring the heartbeat event classification model using single- or multiple-lead ECG signals, we proposed a novel deep learning algorithm and conducted a systemic comparison based on the different methods and databases. This new approach aims to improve accuracy and reduce training time by combining the convolutional neural network (CNN) with the bidirectional long short-term memory (BiLSTM). To our knowledge, this approach has not been investigated to date. In this study, Database I with single-lead ECG and Database II with 12-lead ECG were used to explore a practical and viable heartbeat event classification model. An evolutionary neural system approach (Method I) and a deep learning approach (Method II) that combines CNN with BiLSTM network were compared and evaluated in processing heartbeat event classification. Overall, Method I achieved slightly better performance than Method II. However, Method I took, on average, 28.3 h to train the model, whereas Method II needed only 1 h. Method II achieved an accuracy of 80, 82.6, and 85% compared with the China Physiological Signal Challenge 2018, PhysioNet Challenge 2017, and Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) Arrhythmia datasets, respectively. These results are impressive compared with the performance of state-of-the-art algorithms used for the same purpose.

A hybrid unsupervised-Deep learning tandem for electrooculography time series analysis

Medical data are often tricky to get mined for patterns even by the generally demonstrated successful modern methodologies of deep learning. This paper puts forward such a medical classification task, where patient registers of two of the categories are sometimes hard to be distinguished because of samples showing characteristics of both labels in turn in several repetitions of the screening procedure. To this end, the current research appoints a pre-processing clustering step (through self-organizing maps) to group the data based on shape similarity and relabel it accordingly. Subsequently, a deep learning approach (a tandem of convolutional and long short-term memory networks) performs the training classification phase on the ‘cleaned’ samples. The dual methodology was applied for the computational diagnosis of electrooculography tests within spino-cerebral ataxia of type 2. The accuracy obtained for the discrimination into three classes was of 78.24%. The improvement that this duo brings over the deep learner alone does not stem from significantly higher accuracy results when the performance is considered for all classes. The major finding of this combination is that half of the presymptomatic cases were correctly found, in opposition to the single deep model, where this category was sacrificed by the learner in favor of a good accuracy overall. A high accuracy in general is desirable for any medical task, however the correct identification of cases before the symptoms become evident is more important.

Ranking Information Extracted from Uncertainty Quantification of the Prediction of a Deep Learning Model on Medical Time Series Data

Uncertainty quantification in deep learning models is especially important for the medical applications of this complex and successful type of neural architectures. One popular technique is Monte Carlo dropout that gives a sample output for a record, which can be measured statistically in terms of average probability and variance for each diagnostic class of the problem. The current paper puts forward a convolutional–long short-term memory network model with a Monte Carlo dropout layer for obtaining information regarding the model uncertainty for saccadic records of all patients. These are next used in assessing the uncertainty of the learning model at the higher level of sets of multiple records (i.e., registers) that are gathered for one patient case by the examining physician towards an accurate diagnosis. Means and standard deviations are additionally calculated for the Monte Carlo uncertainty estimates of groups of predictions. These serve as a new collection where a random forest model can perform both classification and ranking of variable importance. The approach is validated on a real-world problem of classifying electrooculography time series for an early detection of spinocerebellar ataxia 2 and reaches an accuracy of 88.59% in distinguishing between the three classes of patients.

Opportunities and challenges of deep learning methods for electrocardiogram data: A systematic review

BACKGROUND

The electrocardiogram (ECG) is one of the most commonly used diagnostic tools in medicine and healthcare. Deep learning methods have achieved promising results on predictive healthcare tasks using ECG signals.

OBJECTIVE

This paper presents a systematic review of deep learning methods for ECG data from both modeling and application perspectives.

METHODS

We extracted papers that applied deep learning (deep neural network) models to ECG data that were published between January 1st of 2010 and February 29th of 2020 from Google Scholar, PubMed, and the Digital Bibliography & Library Project. We then analyzed each article according to three factors: tasks, models, and data. Finally, we discuss open challenges and unsolved problems in this area.

RESULTS

The total number of papers extracted was 191. Among these papers, 108 were published after 2019. Different deep learning architectures have been used in various ECG analytics tasks, such as disease detection/classification, annotation/localization, sleep staging, biometric human identification, and denoising.

CONCLUSION

The number of works on deep learning for ECG data has grown explosively in recent years. Such works have achieved accuracy comparable to that of traditional feature-based approaches and ensembles of multiple approaches can achieve even better results. Specifically, we found that a hybrid architecture of a convolutional neural network and recurrent neural network ensemble using expert features yields the best results. However, there are some new challenges and problems related to interpretability, scalability, and efficiency that must be addressed. Furthermore, it is also worth investigating new applications from the perspectives of datasets and methods.

SIGNIFICANCE

This paper summarizes existing deep learning research using ECG data from multiple perspectives and highlights existing challenges and problems to identify potential future research directions.

Parkinson's Disease EMG Data Augmentation and Simulation with DCGANs and Style Transfer

This paper proposes two new data augmentation approaches based on Deep Convolutional Generative Adversarial Networks (DCGANs) and Style Transfer for augmenting Parkinson’s Disease (PD) electromyography (EMG) signals. The experimental results indicate that the proposed models can adapt to different frequencies and amplitudes of tremor, simulating each patient’s tremor patterns and extending them to different sets of movement protocols. Therefore, one could use these models for extending the existing patient dataset and generating tremor simulations for validating treatment approaches on different movement scenarios.

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

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.