Learn more about
We want to save lives
More than 300 million electrocardiograms (ECGs) are obtained annually worldwide and the correct interpretation of the ECG is pivotal for accurate diagnosis of many cardiac abnormalities. Computerized interpretation has not been able to reach physician level accuracy in detecting cardiac abnormalities, however.
We have developed a triage algorithm on 700.000 ECGs, that diagnoses hospital ECGs to either acute, subacute or normal. With the implementation of this triage algorithm a significant amount of time can be saved by not having the cardiologist to evaluate normal ECGs in the hospital.
Watch the demo video
Unique features
01
Powerful algorithm
The most promising development in the time of artificial intelligence and big data is the use of integrated self-learning algorithms, called deep neural networks. We propose to use deep learning for automated ECG interpretation, feature discovery and implementation in a multi lead smart phone sized home monitoring ECG device.
02
Device and app integration
The final product will be a CE-ready standalone device, combined with software running on an external device that will analyze the data.
03
GP and private use
We aim to make the algorithm available for GPs using the same backend to allow quick triage of GP acquired 12-lead ECGs. This will allow GP ECGs to be immediately triaged without the need for consultation of a cardiologist, thereby saving valuable time and resources, and in case of suspected acute disorders reducing time to treatment.
Development
Although home-monitoring devices for rhythm disorders are getting more common, there is no multi-lead electrocardiography device available to detect acute ischemic heart disease in the home setting. The device can be used by patients at home, but also by the GP or in hospital settings where the standard 12-lead ECG is not readily available. The deep learning algorithm will be trained and optimized to process the output without human interaction and will provide the user with immediate feedback. With this device, patients will be able to keep track of their cardiac health and if required data can be send to a cardiologist for further analysis.
We have already developed a smart phone sized proof of principle device that can acquire a multi-lead ECG within 30 seconds at the push of button without the need for ECG-patches or professional equipment.
For the further development of this device we will closely work together with the UMCU department of Medical Technology and Clinical Physics and private partners experienced in medical software development and implementation. The final product will be a CE-ready standalone device, combined with software running on an external device that will analyze the data.
Our Team
Our team is multidisciplinary and consists of cardiologists, technical physicians, epidemiologists, health technology assessment experts, deep learning experts, psychologists, ethicists, software engineers, industrial engineers, electronics developers, hardware engineers and MDR, innovation and valorization experts. Completion of this project will result in 3 PhDs, 1 medical (implementation), 1 technical medical (algorithms and deep learning), and 1 technical (product development).
Outside of the consortium, we work closely together with the University of Amsterdam QUVA Deep Vision Lab for expertise in deep learning techniques, the Julius Centre and Healthcare Innovation Centre (THINC) for expertise in epidemiology, health technology assessment and implementation studies and provider of general practitioner data and the University of Tilburg Center of Research on Psychology in Somatic Diseases for expertise in the psychological aspects of implementation.
The user committee will be a group with representatives of the researchers, implementation experts and healthcare professionals that will use the software. A separate end-user committee will be assembled for the device of WP2 and will, in addition to the already mentioned group, also include patients and general practitioners. Both groups will be consulted early in the hardware and software development stages.
- van de Leur, R. R., Blom, L. J., Gavves, E., Hof, I. E., van der Heijden, J. F., Clappers, N. C., Doevendans, P. A., Hassink, R. J., & van Es, R. (2020). Automatic Triage of 12-Lead ECGs Using Deep Convolutional Neural Networks. Journal of the American Heart Association, 9(10), e015138. https://doi.org/10.1161/JAHA.119.015138
- Van De Leur, R. R., Taha, K., Bos, M. N., Van Der Heijden, J. F., Gupta, D., Cramer, M. J., Hassink, R. J., Van Der Harst, P., Doevendans, P. A., Asselbergs, F. W., & Van Es, R. (2021). Discovering and Visualizing Disease-Specific Electrocardiogram Features Using Deep Learning: Proof-of-Concept in Phospholamban Gene Mutation Carriers. Circulation: Arrhythmia and Electrophysiology. https://doi.org/10.1161/CIRCEP.120.009056
- Bos, M. N., Van De Leur, R. R., Vranken, J. F., Gupta, D. K., Van Der Harst, P., Doevendans, P. A., & Van Es, R. (2020). Automated Comprehensive Interpretation of 12-lead Electrocardiograms Using Pre-trained Exponentially Dilated Causal Convolutional Neural Networks. Computing in Cardiology, 2020-Septe, 2–5. https://doi.org/10.22489/CinC.2020.253
- Vranken, J. F., van de Leur, R. R., Gupta, D. K., Juarez Orozco, L. E., Hassink, R. J., van der Harst, P., Doevendans, P. A., Gulshad, S., & van Es, R. (2021). Uncertainty estimation for deep learning-based automated analysis of 12-lead electrocardiograms. European Heart Journal – Digital Health, 1–41. https://doi.org/10.1093/ehjdh/ztab045
- Rutger R van de Leur, Machteld J Boonstra, Ayoub Bagheri, Rob W Roudijk, Arjan Sammani, Karim Taha, Pieter AFM Doevendans, Pim van der Harst, Peter M van Dam, Rutger J Hassink, René van Es, Folkert W Asselbergs, Big Data and Artificial Intelligence: Opportunities and Threats in Electrophysiology. Arrhythmia Electrophysiol Rev. 2020;9(3):146–54. https://doi.org/10.15420/aer.2020.26