Scalable, Multiplatform, and Autonomous ECG Processor Supported by AI for Telemedicine Center

0583011 - ÚPT 2024 RIV US eng C - Conference Paper (international conference)
Plešinger, Filip - Ivora, Adam - Vargová, Enikö - Smíšek, Radovan - Pavlus, Ján - Koščová, Zuzana - Nejedlý, Petr - Bulková, V. - Kozubík, R. - Halámek, Josef - Jurák, Pavel
Scalable, Multiplatform, and Autonomous ECG Processor Supported by AI for Telemedicine Center.
2022 Computing in Cardiology (CinC). New York: IEEE, 2022, 2022-eptember (2022), č. článku 052. ISBN 979-8-3503-0097-0. ISSN 2325-8861. E-ISSN 2325-887X.
[Computing in Cardiology 2022 /49./. Tampere (FI), 04.09.2022-07.09.2022]
R&D Projects: GA TA ČR(CZ) FW01010305
Institutional support: RVO:68081731
Keywords : software * AI * ECG * analysis
OECD category: Medical engineering
https://ieeexplore.ieee.org/document/10081823 https://www.cinc.org/archives/2022/pdf/CinC2022-052.pdf

Background: Wearable devices play an essential role in the early diagnosis of heart diseases. However, effective management of long-term ECG measurements (1-3 weeks) by a telemedicine center (TMC) requires specifically designed software. Method: We used the multiplatform framework.NET to build the application. Deep-learning models for QRS detection, classification, and rhythm analysis were trained in the PyTorch framework, models were trained using data from Medical Data Transfer, s. r. o. Czechia (N=73,450 and 12,111). The ONNX runtime libraries were used for model inference, including acceleration by graphic cards Results: The pre-production benchmark (recordings of 82 patients) showed a mean accuracy of 0.97 ± 0.04 for QRS detection and classification into three classes, it also showed a mean accuracy of 0.97 ± 0.03 for rhythm classification into seven classes. Conclusion: The presented software is a fully automated, multiplatform, and scalable back-end application to process incoming ECG data in the TMC Although it is not freely accessible, we are open to considering processing ECG data for research and strictly non-commercial purposes.
Permanent Link: https://hdl.handle.net/11104/0351425