Athletes often have training-induced remodeling of the heart, and this can sometimes be seen as abnormal but non-pathological changes in the electrocardiogram. However, these changes can be confused with severe cardiovascular diseases that, in some cases, can cause cardiovascular death. Electrocardiogram data from athletes is therefore important to learn more about the difference between normal athletic remodeling and pathological remodeling of the heart. This work provides a dataset of electrocardiograms from 28 Norwegian elite endurance athletes. The electrocardiograms are standard 12-lead resting ECGs, recorded for 10 seconds while the athlete's lay supine on a bench. The electrocardiograms were then interpreted by an interpretation algorithm and by a trained cardiologist. The electrocardiogram waveform data and the interpretations were stored in Python Waveform Database format and made publicly available through PhysioNet.

Background: The electrocardiogram (ECG) is an almost universally accessible diagnostic tool for heart disease. An ECG is measured by using an electrocardiograph, and today’s electrocardiographs use built-in software to interpret the ECGs automatically after they are recorded. However, these algorithms exhibit limited performance, and therefore, clinicians usually have to manually interpret the ECG, regardless of whether an algorithm has interpreted it or not. Manual interpretation of the ECG can be time-consuming and requires specific skills. Therefore, better algorithms are clearly needed to make correct ECG interpretations more accessible and time-efficient. Algorithms based on artificial intelligence (AI) have demonstrated promising performance in various fields, including ECG interpretation, over the past few years and may represent an alternative to manual ECG interpretation by doctors. Results: We trained and validated a convolutional neural network with an Inception architecture on a dataset with 88253 12-lead ECGs, and classified 30 of the most frequent annotated cardiac conditions in the dataset. We assessed two different loss functions and different ECG sampling rates and the best-performing model used double soft F1-loss and ECGs downsampled to 75Hz. This model achieved an F1-score of $$0.420\pm 0.017$$ 0.420 ± 0.017 , accuracy $$= 0.954 \pm 0.002$$ = 0.954 ± 0.002 , and an AUROC score of $$0.832 \pm 0.019$$ 0.832 ± 0.019 . An aggregated saliency map, showing the global importance of all 12 ECG leads for the 30 cardiac conditions, was generated using Local Interpretable Model-Agnostic Explanations (LIME). The global saliency map showed that the Inception model paid the most attention to the limb leads and the augmented leads and less importance to the precordial leads. Conclusions: One of the more significant contributions that emerge from this study is the use of aggregated saliency maps to obtain global ECG lead importance for different cardiac conditions. In addition, we emphasized the relevance of evaluating different loss functions, and in this specific case, we found double soft F1-loss to be slightly better than binary cross-entropy (BCE). Finally, we found it somewhat surprising that drastic downsampling of the ECG led to higher performance than higher sampling frequencies, such as 500Hz. These findings contribute in several ways to our understanding of the artificial intelligence-based interpretation of ECGs, but further studies should be carried out to validate these findings in other datasets from other patient cohorts.

Athletes often have training-induced remodeling of the heart, and this can sometimes be seen as abnormal but non-pathological changes in the electrocardiogram. However, these changes can be confused with severe cardiovascular diseases that, in some cases, can cause cardiovascular death. Electrocardiogram data from athletes is therefore important to learn more about the difference between normal athletic remodeling and pathological remodeling of the heart. This work provides a dataset of electrocardiograms from 28 Norwegian elite endurance athletes. The electrocardiograms are standard 12-lead resting ECGs, recorded for 10 seconds while the athlete’s lay supine on a bench. The electrocardiograms were then interpreted by an interpretation algorithm and by a trained cardiologist. The electrocardiogram waveform data and the interpretations were stored in Python Waveform Database format and made publicly available through PhysioNet. This is the first open dataset with electrocardiograms recorded from athletes. With the recent advances in artificial intelligence-based ECG interpretation, this might be an important contribution towards future interpretation models.

Electrocardiography is one of the most frequently used methods to evaluate cardiovascular diseases. However, the last decade has shown that deep convolutional neural networks (CNN) can extract information from the electrocardiogram (ECG) that goes beyond traditional diagnostics, such as predicting a persons age. In this study, we trained two different 1-dimensional CNNs on open datasets to predict age from a persons ECG. The models were trained and validated using 10 seconds long 12-lead ECG records, resampled to 100Hz. 59355 ECGs were used for training and cross-validation, while 21748 ECGs from a separate cohort were used as the test set. We compared the performance achieved on the cross-validation with the performance on the test set. Furthermore, we used cardiologist annotated cardiovascular conditions to categorize the patients in the test set in order to assess whether some cardiac condition leads to greater discrepancies between CNN-predicted age and chronological age. The best CNN model, using an Inception Time architecture, showed a significant drop in performance, in terms of mean absolute error (MAE), from cross-validation on the training set (7.90 ± 0.04 years) to the performance on the test set (8.3 years). On the other hand, the mean squared error (MSE) improved from the training set (117.5 ± 2.7 years^2) to the test set (111 years^2). We also observed that the cardiovascular condition that showed the highest deviation between predicted and biological age, in terms of MAE, was the patients with pacing rhythm (10.5 years), while the patients with prolonged QT-interval had the smallest deviation (7.4 years) in terms of MAE. This work contributes to existing knowledge of age prediction using deep CNNs on ECGs by showing how a trained model performs on a test set from a separate cohort to that used in the training set.

Aim: Artificial intelligence applied to electrocardiography (AI-ECG) can derive a heart age or ECG-age , potentially reflecting waveform patterns that indicate cumulative myocardial stress. The heart age gap (HA-gap, Δ _age ) is defined as the difference between a person’s ECG-age and chronological age. Former studies suggest a threshold of Δ _age > 8 yrs as a biomarker for accelerated biological age, associated with higher risk for cardiovascular events. In this study, we investigate whether Δ _age differentiates training-induced physiological from pathological left ventricular remodeling. Methods: An AI-ECG was applied to 162 resting 12-lead ECGs of each professional footballers, population controls without cardiovascular disease, and patients with systolic heart failure (HF). Explainable AI identified contributing leads and waveforms, and results were compared with established ECG voltage criteria for left ventricular hypertrophy (Sokolow–Lyon, Cornell) and low QRS voltage (LQRSV). Results: Accelerated HA (Δ _{age ,+} ) was present in 38.9% of athletes, 35.8% of community controls, and 96.9% of HF patients. As a diagnostic criterion, accelerated HA achieved 96.9% sensitivity and 62.7% specificity for distinguishing diseased from healthy cohorts. In contrast, classical ECG voltage criteria showed lower sensitivity (6–17%) but higher specificity (85–100%). Correlation analyses confirmed significant associations of HA-gap with Cornell voltage ( ρ = 0.25, p < 0.001) and LQRSV (limb: ρ = − 0.43, p < 0.001; precordial: ρ = − 0.32, p < 0.001). Conclusions: The AI-based HA-gap is a multi-factorial marker of ventricular remodeling beyond mass and can separate benign athletic hypertrophy from pathological remodeling with high sensitivity. Incorporating athlete and youth cohorts into model development could further improve specificity to enable future application in preventive and sports cardiology.

Aker Solutions in Horten is a supplier to the oil industry. They are interested to see how electric winches with wave compensation work, to possibly replace traditional hydraulic winches. The reason is that more and more oil exploration is happening in the arctic sea where failure and oil spill are more fatal. Removing hydraulic winches can reduce the risk of such a catastrophe.