Medical Coding
Medical coding, the process of assigning standardized codes to patient records, is being revolutionized by advancements in natural language processing (NLP) and machine learning. Current research focuses on improving the accuracy and efficiency of automated coding systems using various deep learning architectures, including transformer models like BERT and recurrent neural networks, often incorporating techniques like attention mechanisms and curriculum learning to handle the complexity and high dimensionality of medical terminology. These efforts aim to reduce the time and cost associated with manual coding, improve data interoperability, and facilitate large-scale clinical research and analysis.
Papers
Beyond Label Attention: Transparency in Language Models for Automated Medical Coding via Dictionary Learning
John Wu, David Wu, Jimeng Sun
Artificial intelligence to improve clinical coding practice in Scandinavia: a crossover randomized controlled trial
Taridzo Chomutare, Therese Olsen Svenning, Miguel Ángel Tejedor Hernández, Phuong Dinh Ngo, Andrius Budrionis, Kaisa Markljung, Lill Irene Hind, Torbjørn Torsvik, Karl Øyvind Mikalsen, Aleksandar Babic, Hercules Dalianis