Benchmarks of ResNet Architecture for Atrial Fibrillation Classification
This work provides incremental insights for researchers and practitioners in medical AI by identifying key parameters for optimizing ResNet models in atrial fibrillation classification.
The study applied variations of ResNet architecture to atrial fibrillation classification, finding that models with different configurations showed similar performance within a certain size range, with overall parameter count playing a dominant role, while specific layout parameters consistently led to better results.
In this work we apply variations of ResNet architecture to the task of atrial fibrillation classification. Variations differ in number of filter after first convolution, ResNet block layout, number of filters in block convolutions and number of ResNet blocks between downsampling operations. We have found a range of model size in which models with quite different configurations show similar performance. It is likely that overall number of parameters plays dominant role in model performance. However, configuration parameters like layout have values that constantly lead to better results, which allows to suggest that these parameters should be defined and fixed in the first place, while others may be varied in a reasonable range to satisfy any existing constraints.