ECG-ViEW II, a freely accessible electrocardiogram database

Evaluation of rosuvastatin-induced QT prolongation risk using real-world data, in vitro cardiomyocyte studies, and mortality assessment

Drug-induced QT prolongation is attributed to several mechanisms, including hERG channel blockage. However, the risks, mechanisms, and the effects of rosuvastatin-induced QT prolongation remain unclear. Therefore, this study assessed the risk of rosuvastatin-induced QT prolongation using (1) real-world data with two different settings, namely case-control and retrospective cohort study designs; (2) laboratory experiments using human-induced pluripotent stem cell-derived cardiomyocytes (hiPSC-CM); (3) nationwide claim data for mortality risk evaluation. Real-world data showed an association between QT prolongation and the use of rosuvastatin (OR [95% CI], 1.30 [1.21-1.39]) but not for atorvastatin (OR [95% CI], 0.98 [0.89-1.07]). Rosuvastatin also affected the sodium and calcium channel activities of cardiomyocytes in vitro. However, rosuvastatin exposure was not associated with a high risk of all-cause mortality (HR [95% CI], 0.95 [0.89-1.01]). Overall, these results suggest that rosuvastatin use increased the risk of QT prolongation in real-world settings, significantly affecting the action potential of hiPSC-CMs in laboratory settings. Long-term rosuvastatin treatment was not associated with mortality. In conclusion, while our study links rosuvastatin use to potential QT prolongation and possible influence on the action potential of hiPSC-CMs, long-term use does not show increased mortality, necessitating further research for conclusive real-world applications.

A Two-Step Approach to Overcoming Data Imbalance in the Development of an Electrocardiography Data Quality Assessment Algorithm: A Real-World Data Challenge

Continuously acquired biosignals from patient monitors contain significant amounts of unusable data. During the development of a decision support system based on continuously acquired biosignals, we developed machine and deep learning algorithms to automatically classify the quality of ECG data. A total of 31,127 twenty-s ECG segments of 250 Hz were used as the training/validation dataset. Data quality was categorized into three classes: acceptable, unacceptable, and uncertain. In the training/validation dataset, 29,606 segments (95%) were in the acceptable class. Two one-step, three-class approaches and two two-step binary sequential approaches were developed using random forest (RF) and two-dimensional convolutional neural network (2D CNN) classifiers. Four approaches were tested on 9779 test samples from another hospital. On the test dataset, the two-step 2D CNN approach showed the best overall accuracy (0.85), and the one-step, three-class 2D CNN approach showed the worst overall accuracy (0.54). The most important parameter, precision in the acceptable class, was greater than 0.9 for all approaches, but recall in the acceptable class was better for the two-step approaches: one-step (0.77) vs. two-step RF (0.89) and one-step (0.51) vs. two-step 2D CNN (0.94) (p < 0.001 for both comparisons). For the ECG quality classification, where substantial data imbalance exists, the 2-step approaches showed more robust performance than the one-step approach. This algorithm can be used as a preprocessing step in artificial intelligence research using continuously acquired biosignals.

Interpretable Machine Learning Techniques in ECG-Based Heart Disease Classification: A Systematic Review

Heart disease is one of the leading causes of mortality throughout the world. Among the different heart diagnosis techniques, an electrocardiogram (ECG) is the least expensive non-invasive procedure. However, the following are challenges: the scarcity of medical experts, the complexity of ECG interpretations, the manifestation similarities of heart disease in ECG signals, and heart disease comorbidity. Machine learning algorithms are viable alternatives to the traditional diagnoses of heart disease from ECG signals. However, the black box nature of complex machine learning algorithms and the difficulty in explaining a model's outcomes are obstacles for medical practitioners in having confidence in machine learning models. This observation paves the way for interpretable machine learning (IML) models as diagnostic tools that can build a physician's trust and provide evidence-based diagnoses. Therefore, in this systematic literature review, we studied and analyzed the research landscape in interpretable machine learning techniques by focusing on heart disease diagnosis from an ECG signal. In this regard, the contribution of our work is manifold; first, we present an elaborate discussion on interpretable machine learning techniques. In addition, we identify and characterize ECG signal recording datasets that are readily available for machine learning-based tasks. Furthermore, we identify the progress that has been achieved in ECG signal interpretation using IML techniques. Finally, we discuss the limitations and challenges of IML techniques in interpreting ECG signals.

Artificial Intelligence in Healthcare Competition (TEKNOFEST-2021): Stroke Data Set

OBJECTIVE

The artificial intelligence competition in healthcare was organized for the first time at the annual aviation, space, and technology festival (TEKNOFEST), Istanbul/Türkiye, in September 2021. In this article, the data set preparation and competition processes were explained in detail; the anonymized and annotated data set is also provided via official website for further research.

MATERIALS AND METHODS

Data set recorded over the period covering 2019 and 2020 were centrally screened from the e-Pulse and Teleradiology System of the Republic of Türkiye, Ministry of Health using various codes and filtering criteria. The data set was anonymized. The data set was prepared, pooled, curated, and annotated by 7 radiologists. The training data set was shared with the teams via a dedicated file transfer protocol server, which could be accessed using private usernames and passwords given to the teams under a nondisclosure agreement signed by the representative of each team.

RESULTS

The competition consisted of 2 stages. In the first stage, teams were given 192 digital imaging and communications in medicine images that belong to 1 of 3 possible categories namely, hemorrhage, ischemic, or non-stroke. Teams were asked to classify each image as either stroke present or absent. In the second stage of the competition, qualifying 36 teams were given 97 digital imaging and communications in medicine images that contained hemorrhage, ischemia, or both lesions. Among the employed methods, Unet and DeepLabv3 were the most frequently observed ones.

CONCLUSION

Artificial intelligence competitions in healthcare offer good opportunities to collect data reflecting various cases and problems. Especially, annotated data set by domain experts is more valuable.

Deep Learning for Detecting and Locating Myocardial Infarction by Electrocardiogram: A Literature Review

Myocardial infarction is a common cardiovascular disorder caused by prolonged ischemia, and early diagnosis of myocardial infarction (MI) is critical for lifesaving. ECG is a simple and non-invasive approach in MI detection, localization, diagnosis, and prognosis. Population-based screening with ECG can detect MI early and help prevent it but this method is too labor-intensive and time-consuming to carry out in practice unless artificial intelligence (AI) would be able to reduce the workload. Recent advances in using deep learning (DL) for ECG screening might rekindle this hope. This review aims to take stock of 59 major DL studies applied to the ECG for MI detection and localization published in recent 5 years, covering convolutional neural network (CNN), long short-term memory (LSTM), convolutional recurrent neural network (CRNN), gated recurrent unit (GRU), residual neural network (ResNet), and autoencoder (AE). In this period, CNN obtained the best popularity in both MI detection and localization, and the highest performance has been obtained from CNN and ResNet model. The reported maximum accuracies of the six different methods are all beyond 97%. Considering the usage of different datasets and ECG leads, the network that trained on 12 leads ECG data of PTB database has obtained higher accuracy than that on smaller number leads data of other datasets. In addition, some limitations and challenges of the DL techniques are also discussed in this review.

Data-driven drug-induced QT prolongation surveillance using adverse reaction signals derived from 12-lead and continuous electrocardiogram data

Drug-induced QT prolongation is one of the most common side effects of drug use and can cause fatal outcomes such as sudden cardiac arrest. This study adopts the data-driven approach to assess the QT prolongation risk of all the frequently used drugs in a tertiary teaching hospital using both standard 12-lead ECGs and intensive care unit (ICU) continuous ECGs. We used the standard 12-lead ECG results (n = 1,040,752) measured in the hospital during 1994–2019 and the continuous ECG results (n = 4,835) extracted from the ICU’s patient-monitoring devices during 2016–2019. Based on the drug prescription frequency, 167 drugs were analyzed using 12-lead ECG data under the case-control study design and 60 using continuous ECG data under the retrospective cohort study design. Whereas the case-control study yielded the odds ratio, the cohort study generated the hazard ratio for each candidate drug. Further, we observed the possibility of inducing QT prolongation in 38 drugs in the 12-lead ECG analysis and 7 drugs in the continuous ECG analysis. The seven drugs (vasopressin, vecuronium, midazolam, levetiracetam, ipratropium bromide, nifedipine, and chlorpheniramine) that showed a significantly higher risk of QT prolongation in the continuous ECG analysis were also identified in the 12-lead ECG data analysis. The use of two different ECG sources enabled us to confidently assess drug-induced QT prolongation risk in clinical practice. In this study, seven drugs showed QT prolongation risk in both study designs.

Risk of QT prolongation through drug interactions between hydroxychloroquine and concomitant drugs prescribed in real world practice

Hydroxychloroquine has recently received attention as a treatment for COVID-19. However, it may prolong the QTc interval. Furthermore, when hydroxychloroquine is administered concomitantly with other drugs, it can exacerbate the risk of QT prolongation. Nevertheless, the risk of QT prolongation due to drug-drug interactions (DDIs) between hydroxychloroquine and concomitant medications has not yet been identified. To evaluate the risk of QT prolongation due to DDIs between hydroxychloroquine and 118 concurrent drugs frequently used in real-world practice, we analyzed the electrocardiogram results obtained for 447,632 patients and their relevant electronic health records in a tertiary teaching hospital in Korea from 1996 to 2018. We repeated the case–control analysis for each drug. In each analysis, we performed multiple logistic regression and calculated the odds ratio (OR) for each target drug, hydroxychloroquine, and the interaction terms between those two drugs. The DDIs were observed in 12 drugs (trimebutine, tacrolimus, tramadol, rosuvastatin, cyclosporin, sulfasalazine, rofecoxib, diltiazem, piperacillin/tazobactam, isoniazid, clarithromycin, and furosemide), all with a p value of < 0.05 (OR 1.70–17.85). In conclusion, we found 12 drugs that showed DDIs with hydroxychloroquine in the direction of increasing QT prolongation.

Fall Detection from Electrocardiogram (ECG) Signals and Classification by Deep Transfer Learning

Fall is a prominent issue due to its severe consequences both physically and mentally. Fall detection and prevention is a critical area of research because it can help elderly people to depend less on caregivers and allow them to live and move more independently. Using electrocardiograms (ECG) signals independently for fall detection and activity classification is a novel approach used in this paper. An algorithm has been proposed which uses pre-trained convolutional neural networks AlexNet and GoogLeNet as a classifier between the fall and no fall scenarios using electrocardiogram signals. The ECGs for both falling and no falling cases were obtained as part of the study using eight volunteers. The signals are pre-processed using an elliptical filter for signal noises such as baseline wander and power-line interface. As feature extractors, frequency-time representations (scalograms) were obtained by applying a continuous wavelet transform on the filtered ECG signals. These scalograms were used as inputs to the neural network and a significant validation accuracy of 98.08% was achieved in the first model. The trained model is able to distinguish ECGs with a fall activity from an ECG with a no fall activity with an accuracy of 98.02%. For the verification of the robustness of the proposed algorithm, our experimental dataset was augmented by adding two different publicly available datasets to it. The second model can classify fall, daily activities and no activities with an accuracy of 98.44%. These models were developed by transfer learning from the domain of real images to the medical images. In comparison to traditional deep learning approaches, the transfer learning not only avoids “reinventing the wheel,” but also presents a lightweight solution to otherwise computationally heavy problems.

Deep Learning-Based Electrocardiogram Signal Noise Detection and Screening Model

Objectives

Biosignal data captured by patient monitoring systems could provide key evidence for detecting or predicting critical clinical events; however, noise in these data hinders their use. Because deep learning algorithms can extract features without human annotation, this study hypothesized that they could be used to screen unacceptable electrocardiograms (ECGs) that include noise. To test that, a deep learning-based model for unacceptable ECG screening was developed, and its screening results were compared with the interpretations of a medical expert.

Methods

To develop and apply the screening model, we used a biosignal database comprising 165,142,920 ECG II (10-second lead II electrocardiogram) data gathered between August 31, 2016 and September 30, 2018 from a trauma intensive-care unit. Then, 2,700 and 300 ECGs (ratio of 9:1) were reviewed by a medical expert and used for 9-fold cross-validation (training and validation) and test datasets. A convolutional neural network-based model for unacceptable ECG screening was developed based on the training and validation datasets. The model exhibiting the lowest cross-validation loss was subsequently selected as the final model. Its performance was evaluated through comparison with a test dataset.

Results

When the screening results of the proposed model were compared to the test dataset, the area under the receiver operating characteristic curve and the F1-score of the model were 0.93 and 0.80 (sensitivity = 0.88, specificity = 0.89, positive predictive value = 0.74, and negative predictive value = 0.96).

Conclusions

The deep learning-based model developed in this study is capable of detecting and screening unacceptable ECGs efficiently.

Construction of an Electrocardiogram Database Including 12 Lead Waveforms

Objectives

Electrocardiogram (ECG) data are important for the study of cardiovascular disease and adverse drug reactions. Although the development of analytical techniques such as machine learning has improved our ability to extract useful information from ECGs, there is a lack of easily available ECG data for research purposes. We previously published an article on a database of ECG parameters and related clinical data (ECG-ViEW), which we have now updated with additional 12-lead waveform information.

Methods

All ECGs stored in portable document format (PDF) were collected from a tertiary teaching hospital in Korea over a 23-year study period. We developed software which can extract all ECG parameters and waveform information from the ECG reports in PDF format and stored it in a database (meta data) and a text file (raw waveform).

Results

Our database includes all parameters (ventricular rate, PR interval, QRS duration, QT/QTc interval, P-R-T axes, and interpretations) and 12-lead waveforms (for leads I, II, III, aVR, aVL, aVF, V1, V2, V3, V4, V5, and V6) from 1,039,550 ECGs (from 447,445 patients). Demographics, drug exposure data, diagnosis history, and laboratory test results (serum calcium, magnesium, and potassium levels) were also extracted from electronic medical records and linked to the ECG information.

Conclusions

Electrocardiogram information that includes 12 lead waveforms was extracted and transformed into a form that can be analyzed. The description and programming codes in this case report could be a reference for other researchers to build ECG databases using their own local ECG repository.

Cadmium stress assessment based on the electrocardiogram characteristics of zebra fish (Danio rerio): QRS complex could play an important role

The electrocardiogram (ECG) of zebra fish (Danio rerio) expresses cardiac features that are similar to humans. Here we use sharp microelectrode measurements to obtain ECG characteristics in adult zebra fish and analyze the effects of cadmium chloride (CdCl₂) on the heart. We observe the overall changes of ECG parameters in different treatments (0.1 TU, 0.5 TU and 1.0 TU CdCl₂), including P wave, Q wave, R wave, S wave, T wave, PR interval (atrial contraction), QRS complex (ventricular depolarization), ST segment, and QT interval (ventricular repolarization). The trends of the ECG parameters showed some responses to the concentration and exposure time of CdCl₂, but it was difficult to obtain more information about the useful indicators in water quality assessment depending on tendency analysis alone. A self-organizing map (SOM) showed that P values, R values, and T values were similar; R wave and T wave amplitude were similar; and most important, QRS value was similar to the CdCl₂ stress according to the classified data patterns including CdCl₂ stress (E) and ECG components based on the Ward linkage. It suggested that the duration of QRS complex was related to environmental stress E directly. The specification and evaluation of ECG parameters in Cd²⁺ pollution suggested that there is a markedly significant correlation between QRS complex and CdCl₂ stress with the highest r (0.729) and the smallest p (0.002) among all ECG characteristics. In this case, it is concluded that QRS complex can be used as an indicator in the CdCl₂ stress assessment due to the lowest AIC data abased on the linear regression model between the CdCl₂ stress and ECG parameters.

Physiological Informatics: Collection and Analyses of Data from Wearable Sensors and Smartphone for Healthcare

Physiological data from wearable sensors and smartphone are accumulating rapidly, and this provides us the chance to collect dynamic and personalized information as phenotype to be integrated to genotype for the holistic understanding of complex diseases. This integration can be applied to early prediction and prevention of disease, therefore promoting the shifting of disease care tradition to the healthcare paradigm. In this chapter, we summarize the physiological signals which can be detected by wearable sensors, the sharing of the physiological big data, and the mining methods for the discovery of disease-associated patterns for personalized diagnosis and treatment. We discuss the challenges of physiological informatics about the storage, the standardization, the analyses, and the applications of the physiological data from the wearable sensors and smartphone. At last, we present our perspectives on the models for disentangling the complex relationship between early disease prediction and the mining of physiological phenotype data.