{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/using-deep-convolutional-neural-networks-to-2","title":"Using deep convolutional neural networks to predict patients age based on ECGs from an independent test cohort","arxiv_id":null,"date":"2022-10-06","proceeding":"medRxiv 2022 10","authors":["Bjørn-Jostein Singstad","Belal Tavashi"],"abstract":"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.\r\n\r\nThe 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.\r\n\r\nThe 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.\r\n\r\nThis 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.","url_abs":"https://www.medrxiv.org/content/10.1101/2022.10.03.22280640v3","url_pdf":"https://www.medrxiv.org/content/10.1101/2022.10.03.22280640v3.full.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"using-deep-convolutional-neural-networks-to-2","repo_url":"https://github.com/Bsingstad/ECG-age","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"age-estimation","task_name":"Age Estimation"},{"task_slug":"rhythm","task_name":"Rhythm"}],"methods":[{"method_slug":"mae","method_name":"MAE"},{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/age-estimation-on-physionet-challenge-2021","task":"Age Estimation","dataset":"PhysioNet Challenge 2021","model":"Inception Time","rank_in_archive_order":1,"of":1,"metrics":{"Mean Absolute Error (cross-val)":"7.90±0.04","Mean Squared Error":"111","Mean Squared Error (cross-val)":"117.5±2.7","Mean absolute error":"8.3"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}