A fully-automated paper ECG digitisation algorithm using deep learning

Diagnostic and Prognostic Electrocardiogram-Based Models for Rapid Clinical Applications

Leveraging artificial intelligence (AI) for the analysis of electrocardiograms (ECGs) has the potential to transform diagnosis and estimate the prognosis of not only cardiac but, increasingly, noncardiac conditions. In this review, we summarize clinical studies and AI-enhanced ECG-based clinical applications in the early detection, diagnosis, and estimating prognosis of cardiovascular diseases in the past 5 years (2019-2023). With advancements in deep learning and the rapid increased use of ECG technologies, a large number of clinical studies have been published. However, most of these studies are single-centre, retrospective, proof-of-concept studies that lack external validation. Prospective studies that progress from development toward deployment in clinical settings account for < 15% of the studies. Successful implementations of ECG-based AI applications that have received approval from the Food and Drug Administration have been developed through commercial collaborations, with approximately half of them being for mobile or wearable devices. The field is in its early stages, and overcoming several obstacles is essential, such as prospective validation in multicentre large data sets, addressing technical issues, bias, privacy, data security, model generalizability, and global scalability. This review concludes with a discussion of these challenges and potential solutions. By providing a holistic view of the state of AI in ECG analysis, this review aims to set a foundation for future research directions, emphasizing the need for comprehensive, clinically integrated, and globally deployable AI solutions in cardiovascular disease management.

Automatic detection of cardiac conditions from photos of electrocardiogram captured by smartphones

BACKGROUND

Researchers have developed machine learning-based ECG diagnostic algorithms that match or even surpass cardiologist level of performance. However, most of them cannot be used in real-world, as older generation ECG machines do not permit installation of new algorithms.

OBJECTIVE

To develop a smartphone application that automatically extract ECG waveforms from photos and to convert them to voltage-time series for downstream analysis by a variety of diagnostic algorithms built by researchers.

METHODS

A novel approach of using objective detection and image segmentation models to automatically extract ECG waveforms from photos taken by clinicians was devised. Modular machine learning models were developed to sequentially perform waveform identification, gridline removal, and scale calibration. The extracted data were then analysed using a machine learning-based cardiac rhythm classifier.

RESULTS

Waveforms from 40 516 scanned and 444 photographed ECGs were automatically extracted. 12 828 of 13 258 (96.8%) scanned and 5399 of 5743 (94.0%) photographed waveforms were correctly cropped and labelled. 11 604 of 12 735 (91.1%) scanned and 5062 of 5752 (88.0%) photographed waveforms achieved successful voltage-time signal extraction after automatic gridline and background noise removal. In a proof-of-concept demonstration, an atrial fibrillation diagnostic algorithm achieved 91.3% sensitivity, 94.2% specificity, 95.6% positive predictive value, 88.6% negative predictive value and 93.4% F1 score, using photos of ECGs as input.

CONCLUSION

Object detection and image segmentation models allow automatic extraction of ECG signals from photos for downstream diagnostics. This novel pipeline circumvents the need for costly ECG hardware upgrades, thereby paving the way for large-scale implementation of machine learning-based diagnostic algorithms.

Cardiac Arrhythmia Classification Using Advanced Deep Learning Techniques on Digitized ECG Datasets

ECG classification or heartbeat classification is an extremely valuable tool in cardiology. Deep learning-based techniques for the analysis of ECG signals assist human experts in the timely diagnosis of cardiac diseases and help save precious lives. This research aims at digitizing a dataset of images of ECG records into time series signals and then applying deep learning (DL) techniques on the digitized dataset. State-of-the-art DL techniques are proposed for the classification of the ECG signals into different cardiac classes. Multiple DL models, including a convolutional neural network (CNN), a long short-term memory (LSTM) network, and a self-supervised learning (SSL)-based model using autoencoders are explored and compared in this study. The models are trained on the dataset generated from ECG plots of patients from various healthcare institutes in Pakistan. First, the ECG images are digitized, segmenting the lead II heartbeats, and then the digitized signals are passed to the proposed deep learning models for classification. Among the different DL models used in this study, the proposed CNN model achieves the highest accuracy of ∼92%. The proposed model is highly accurate and provides fast inference for real-time and direct monitoring of ECG signals that are captured from the electrodes (sensors) placed on different parts of the body. Using the digitized form of ECG signals instead of images for the classification of cardiac arrhythmia allows cardiologists to utilize DL models directly on ECG signals from an ECG machine for the real-time and accurate monitoring of ECGs.

ECGMiner: A flexible software for accurately digitizing ECG

BACKGROUND AND OBJECTIVE

The electrocardiogram (ECG) is the most important non-invasive method for elucidating information about heart and cardiovascular disease diagnosis. Typically, the ECG system manufacturing companies provide ECG images, but store the numerical data in a proprietary format that is not interpretable and is not therefore useful for automatic diagnosis. There have been many efforts to digitize paper-based ECGs. The main limitations of previous works in ECG digitization are that they require manual selection of the regions of interest, only partly provide signal digitization, and offer limited accuracy.

METHODS

We have developed the ECGMiner, an open-source software to digitize ECG images. It is precise, fast, and simple to use. This software digitizes ECGs in four steps: 1) recognizing the image composition; 2) removing the gridline; 3) extracting the signals; 4) post-processing and storing the data.

RESULTS

We have evaluated the ECGMiner digitization capabilities using the Pearson Correlation Coefficient (PCC) and the Root Mean Square Error (RMSE) measures, and we consider ECG from two large, public, and widely used databases, LUDB and PTB-XL. The actual and digitized values of signals in both databases have been compared. The software's ability to correctly identify the location of characteristic waves has also been validated. Specifically, the PCC values are between 0.971 and 0.995, and the RMSE values are between 0.011 and 0.031 mV.

CONCLUSIONS

The ECGMiner software presented in this paper is open access, easy to install, easy to use, and capable of precisely recovering the paper-based/digital ECG signal data, regardless of the input format and signal complexity. ECGMiner outperforms existing digitization algorithms in terms of PCC and RMSE values.

Automatic digitization of paper electrocardiograms - A systematic review

The digitization of electrocardiogram paper records is an essential step to preserve and analyze cardiac data. This digitization process is not flawless as it involves several challenges, such as skew correction, binarization, and signal extraction. Various approaches have been proposed to address these challenges and recent studies have introduced innovative solutions, such as deep learning models and automation processes. Although existing approaches have shown promising results, there is a lack of common databases and metrics where authors could evaluate and compare their methods. Furthermore, the limited accessibility of code or software hinders the comparison process. Overall, while digitization of paper ECG recordings is important in advancing cardiology research, additional efforts are needed to standardize the evaluation process while improving code accessibility. This article provides a systematic review of this process.

Machine learning discriminates P2X7-mediated intracellular calcium sparks in human-induced pluripotent stem cell-derived neural stem cells

Adenosine triphosphate (ATP) is an extracellular signaling molecule that mainly affects the pathophysiological situation in the body and can be sensed by purinergic receptors, including ionotropic P2X7. Neuronal stem cells (NSCs) remain in adult neuronal tissues and can contribute to physiological processes via activation by evoked pathophysiological situations. In this study, we revealed that human-induced pluripotent stem cell-derived NSCs (iNSCs) have ATP-sensing ability primarily via the purinergic and ionotropic receptor P2X7. Next, to develop a machine learning (ML)-based screening system for food-derived neuronal effective substances and their effective doses, we collected ATP-triggered calcium responses of iNSCs pretreated with several substances and doses. Finally, we discovered that ML was performed using composite images, each containing nine waveform images, to achieve a better ML model (MLM) with higher precision. Our MLM can correctly sort subtle unidentified changes in waveforms produced by pretreated iNSCs with each substance and/or dose into the positive group, with common mRNA expression changes belonging to the gene ontology signatures.

What Else Can AI See in a Digital ECG?

The electrocardiogram (ECG), considered by some diagnosticians of cardiovascular diseases to be a slightly anachronistic tool, has acquired a completely new face and importance thanks to its three modern features: the digital form of recording, its very frequent use, and the possibility of processing thousands of records by artificial intelligence (AI). In this review of the literature on this subject from the first 3 months of 2023, the use of many types of software for extracting new information from the ECG is described. These include, among others, natural language processing, backpropagation neural network and convolutional neural network. AI tools of this type allow physicians to achieve high accuracy not only in ECG-based predictions of the patient's age or sex but also of the abnormal structure of heart valves, abnormal electrical activity of the atria, distorted immune response after transplantation, good response to resynchronization therapy and an increased risk of sudden cardiac death. The attractiveness of the presented results lies in the simplicity of the examination by the staff, relatively low costs and even the possibility of performing the examination remotely. The twelve studies presented here are just a fraction of the novelties that the current year will bring.