The MareNostrum supercomputer will participate in the #BitsxlaMarató hackathon, to collaborate with the Marató of TV3 dedicated to to cardiovascular health

25 November 2022

BSC co-organizes the activity and propose a challenge on computing for stroke risk models based on biomedical signals from portable devices.

This year Bitsxlamarató is organized by the Faculty of Computer Science of Barcelona (FIB), Hackers@UPC (organizers of HackUPC), the Barcelona Supercomputing Center - Centro Nacional de Supercomputación (BSC-CNS) and the Escuela Superior de Enfermería del Mar (Hospital del Mar) which will wholeheartedly contribute to La Marató de TV3.

After three editions, we join forces again to help find solutions and disseminate cardiovascular problems. It is a hackathon full of creativity, health and technology, where teachers, research staff and any professional from the fields of health and technology (but also from other areas!), will work as a team, for 3 consecutive days. Together they will seek and develop solutions to face all the challenges posed by cardiovascular health, the main cause of death in developed countries and one of the most relevant current public health problems.

The hackathon will take place from December 16 to 18 and will include educational talks. Participants who request it may use the MareNostrum supercomputer.

During the last day of the hackathon, the teams will make presentations and demonstrations of the solutions, and proposals for solutions obtained in the challenges posed on the first day. There will be prizes and a prize for the best project.

BSC Challenge: Cloud-edge computing for stroke risk models based on biomedical signals from wearable devices

The challenge posed this year by BSC, together with the AI-SPRINT project, focuses on developing an application for mobile phones that is capable of capturing and processing biomedical signals from a portable device. This information is used to power AI/ML models for stroke risk assessment residing in a cluster with on-demand inference capability. The expected result is the simulation of a realistic scenario in which stroke risk predictions based on sensor data occur in the edge-cloud continuum.

The BSC participates in the AI-SPRINT project contributing its experience in programming and parallelization of applications in distributed infrastructures