Real-Time Heart Monitoring of Thousands of Patients
Presentation of the problem and objective of the experiment
A heart monitoring center for remote long-term continuous monitoring of patients in their home environment outside of a hospital, based on wearable ECG sensors will shorten hospitalization time and prevent serious heart damages, providing better healthcare. A large-scale demonstration of processing 10K simultaneous ECG data streams with real-time responses implementing efficient methods and approaches on HPC resources capable of processing several TFLOPS for computationally-intensive signal processing algorithms to classify arrhythmia is planned to be carried out.
Short description of the experiment
CardioHPC aims to improve the existing DL solution with advanced HPC services, as they cannot be computed with conventional computing resources. Planned simulation of 10K patients in a heart-monitoring center addresses combined problems of the real-time ECG data streaming and computational-intensive pipelined tasks for detection and elimination of noise and artefacts, beat, rhythm, interval and segment detection/classification, calculation of heart rate variability, and alerting on dangerous arrhythmia. Processing of millions of parallel threads needs a cloud-based HPC system and sophisticated architecture to process and efficiently orchestrate functions as a serverless data analytics platform with highly scalable throughput to minimize delays.
Organisations involved:
End user: Innovation Dooel
HPC expert: University of Klagenfurt
National HPC Competence Centre: Ss Cyril and Methodius University in Skopje
Partner Ss Cyril and Methodius University in Skopje is part of the NCC North Macedonia.