Prototype Learning for Interpretable Respiratory Sound Analysis
This work addresses the need for interpretable models in high-stakes medical diagnostics, providing understandable explanations for physicians and patients, though it is incremental in applying prototype learning to a specific domain.
The authors tackled the problem of interpretable respiratory sound classification for remote disease screening by proposing a prototype learning framework that integrates exemplar samples into deep neural networks, achieving state-of-the-art performance on the largest public database.
Remote screening of respiratory diseases has been widely studied as a non-invasive and early instrument for diagnosis purposes, especially in the pandemic. The respiratory sound classification task has been realized with numerous deep neural network (DNN) models due to their superior performance. However, in the high-stake medical domain where decisions can have significant consequences, it is desirable to develop interpretable models; thus, providing understandable reasons for physicians and patients. To address the issue, we propose a prototype learning framework, that jointly generates exemplar samples for explanation and integrates these samples into a layer of DNNs. The experimental results indicate that our method outperforms the state-of-the-art approaches on the largest public respiratory sound database.