Development and Validation of an Algorithm for the Digitization of ECG Paper Images

Impact of ECG data format on the performance of machine learning models for the prediction of myocardial infarction

Background We aim to determine which electrocardiogram (ECG) data format is optimal for ML modelling, in the context of myocardial infarction prediction. We will also address the auxiliary objective of evaluating the viability of using digitised ECG signals for ML modelling. Methods Two ECG arrangements displaying 10s and 2.5 s of data for each lead were used. For each arrangement, conservative and speculative data cohorts were generated from the PTB-XL dataset. All ECGs were represented in three different data formats: Signal ECGs, Image ECGs, and Extracted Signal ECGs, with 8358 and 11,621 ECGs in the conservative and speculative cohorts, respectively. ML models were trained using the three data formats in both data cohorts. Results For ECGs that contained 10s of data, Signal and Extracted Signal ECGs were optimal and statistically similar, with AUCs [95% CI] of 0.971 [0.961, 0.981] and 0.974 [0.965, 0.984], respectively, for the conservative cohort; and 0.931 [0.918, 0.945] and 0.919 [0.903, 0.934], respectively, for the speculative cohort. For ECGs that contained 2.5 s of data, the Image ECG format was optimal, with AUCs of 0.960 [0.948, 0.973] and 0.903 [0.886, 0.920], for the conservative and speculative cohorts, respectively. Conclusion When available, the Signal ECG data should be preferred for ML modelling. If not, the optimal format depends on the data arrangement within the ECG: If the Image ECG contains 10s of data for each lead, the Extracted Signal ECG is optimal, however, if it only uses 2.5 s, then using the Image ECG data is optimal for ML performance.

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.

Artificial Intelligence ECG Analysis in Patients with Short QT Syndrome to Predict Life-Threatening Arrhythmic Events

Short QT syndrome (SQTS) is an inherited cardiac ion-channel disease related to an increased risk of sudden cardiac death (SCD) in young and otherwise healthy individuals. SCD is often the first clinical presentation in patients with SQTS. However, arrhythmia risk stratification is presently unsatisfactory in asymptomatic patients. In this context, artificial intelligence-based electrocardiogram (ECG) analysis has never been applied to refine risk stratification in patients with SQTS. The purpose of this study was to analyze ECGs from SQTS patients with the aid of different AI algorithms to evaluate their ability to discriminate between subjects with and without documented life-threatening arrhythmic events. The study group included 104 SQTS patients, 37 of whom had a documented major arrhythmic event at presentation and/or during follow-up. Thirteen ECG features were measured independently by three expert cardiologists; then, the dataset was randomly divided into three subsets (training, validation, and testing). Five shallow neural networks were trained, validated, and tested to predict subject-specific class (non-event/event) using different subsets of ECG features. Additionally, several deep learning and machine learning algorithms, such as Vision Transformer, Swin Transformer, MobileNetV3, EfficientNetV2, ConvNextTiny, Capsule Networks, and logistic regression were trained, validated, and tested directly on the scanned ECG images, without any manual feature extraction. Furthermore, a shallow neural network, a 1-D transformer classifier, and a 1-D CNN were trained, validated, and tested on ECG signals extracted from the aforementioned scanned images. Classification metrics were evaluated by means of sensitivity, specificity, positive and negative predictive values, accuracy, and area under the curve. Results prove that artificial intelligence can help clinicians in better stratifying risk of arrhythmia in patients with SQTS. In particular, shallow neural networks' processing features showed the best performance in identifying patients that will not suffer from a potentially lethal event. This could pave the way for refined ECG-based risk stratification in this group of patients, potentially helping in saving the lives of young and otherwise healthy individuals.

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.

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.

ECG Measurement Uncertainty Based on Monte Carlo Approach: An Effective Analysis for a Successful Cardiac Health Monitoring System

Measurement uncertainty is one of the widespread concepts applied in scientific works, particularly to estimate the accuracy of measurement results and to evaluate the conformity of products and processes. In this work, we propose a methodology to analyze the performance of measurement systems existing in the design phases, based on a probabilistic approach, by applying the Monte Carlo method (MCM). With this approach, it is feasible to identify the dominant contributing factors of imprecision in the evaluated system. In the design phase, this information can be used to identify where the most effective attention is required to improve the performance of equipment. This methodology was applied over a simulated electrocardiogram (ECG), for which a measurement uncertainty of the order of 3.54% of the measured value was estimated, with a confidence level of 95%. For this simulation, the ECG computational model was categorized into two modules: the preamplifier and the final stage. The outcomes of the analysis show that the preamplifier module had a greater influence on the measurement results over the final stage module, which indicates that interventions in the first module would promote more significant performance improvements in the system. Finally, it was identified that the main source of ECG measurement uncertainty is related to the measurand, focused towards the objective of better characterization of the metrological behavior of the measurements in the ECG.