A Unified Review of Deep Learning for Automated Medical Coding
This review provides a structured overview for researchers and practitioners in healthcare AI, but it is incremental as it synthesizes existing work without new empirical results.
The authors tackled the lack of a unified framework in deep learning for automated medical coding by proposing a decomposition into four components, summarizing recent models under this framework.
Automated medical coding, an essential task for healthcare operation and delivery, makes unstructured data manageable by predicting medical codes from clinical documents. Recent advances in deep learning and natural language processing have been widely applied to this task. However, deep learning-based medical coding lacks a unified view of the design of neural network architectures. This review proposes a unified framework to provide a general understanding of the building blocks of medical coding models and summarizes recent advanced models under the proposed framework. Our unified framework decomposes medical coding into four main components, i.e., encoder modules for text feature extraction, mechanisms for building deep encoder architectures, decoder modules for transforming hidden representations into medical codes, and the usage of auxiliary information. Finally, we introduce the benchmarks and real-world usage and discuss key research challenges and future directions.