Jul 2026
Deep Label-Wise Attentive Temporal Convolutional Networks Improve Medical Coding
A deep neural model consisting of a multi-layer temporal convolution network (TCN) followed by label-wise attention followed by label-wise attention is proposed for medical coding, achieving significantly better F-1 scores and a remarkable increase in recall score.
Muhammed Yavuz Nuzumlali, Alexander R. Fabbri, Irene Li et al.
· arXiv.org · 0 citations