Learned Kernels for Sparse, Interpretable, and Efficient Medical Time Series Processing

arXiv:2307.05385v3 Announce Type: replace-cross
Abstract: Background: Rapid, reliable, and accurate interpretation of medical signals is crucial for high-stakes clinical decision-making. The advent of deep learning allowed for an explosion of new models that offered unprecedented performance in medical time series processing but at a cost: deep learning models are often compute-intensive and lack interpretability.
Methods: We propose Sparse Mixture of Learned Kernels (SMoLK), an interpretable architecture for medical time series processing. The method learns a set of lightweight flexible kernels …

abstract arxiv clinical cost cs.ai cs.lg decision deep learning eess.sp interpretation making medical performance processing series time series type