A novel application for real-time arrhythmia detection using YOLOv8

In recent years, there has been an increasing need to reduce healthcare costs in remote monitoring of cardiovascular health. Detecting and classifying cardiac arrhythmia is critical to diagnosing patients with cardiac abnormalities. This paper shows that complex systems such as electrocardiograms (ECG) can be applicable for at-home monitoring. This paper proposes a novel application for arrhythmia detection using the state-of-the-art You-Only-Look-Once (YOLO)v8 algorithm to classify single-lead ECG signals. A custom YOLOv8 model was fine-tuned on the MIT-BIH dataset to detect arrhythmia in real-time to allow continuous monitoring. Results show that our model can detect heartbeats with a mAP@50 of 0.961 with a detection time of 0.002s on an NVIDIA Tesla V100. Our study demonstrated the potential of real-time arrhythmia detection, where the model output can be visually interpreted for at-home users. Furthermore, this study could be extended into a real-time XAI model, deployed in the healthcare industry, and significantly advancing healthcare needs.

Scenario adaptive disruption prediction study for next generation burning-plasma tokamaks

Next generation high performance (HP) tokamaks risk damage from unmitigated disruptions at high current and power. Achieving reliable disruption prediction for a device's HP operation based on its low performance (LP) data is key to success. In this letter, through explorative data analysis and dedicated numerical experiments on multiple existing tokamaks, we demonstrate how the operational regimes of tokamaks can affect the power of a trained disruption predictor. First, our results suggest data-driven disruption predictors trained on abundant LP discharges work poorly on the HP regime of the same tokamak, which is a consequence of the distinct distributions of the tightly correlated signals related to disruptions in these two regimes. Second, we find that matching operational parameters among tokamaks strongly improves cross-machine accuracy which implies our model learns from the underlying scalings of dimensionless physics parameters like q_{95}, \beta_{p} and confirms the importance of these parameters in disruption physics and cross machine domain matching from the data-driven perspective. Finally, our results show how in the absence of HP data from the target devices, the best predictivity of the HP regime for the target machine can be achieved by combining LP data from the target with HP data from other machines. These results provide a possible disruption predictor development strategy for next generation tokamaks, such as ITER and SPARC, and highlight the importance of developing on existing machines baseline scenario discharges of future tokamaks to collect more relevant disruptive data.