ICD-10 is an international diagnostic code published by the WHO, which can be used as a common language for international disease discussion and management. The payment of Taiwan’s National Health Insurance is also based on the ICD-10 coding system. However, according to Landseed International Hospital, the ICD-10 coding process of the hospital is as follows: first, the attending physician clicks on common phrases during diagnosis and treatment, and then is checked by the coding specialist. Attending physicians often do not understand the coding principles and cannot compile the most accurate and beneficial diagnosis codes. Coding specialists are not as clear as the attending physicians about the patient’s symptoms. As a result, the codes given by this hospital are often not as serious as other hospitals for the same condition. In this research project, we hope to develop a technology that can automatically produce ICD-10 recommended codes based on deep learning models and natural language processing, so as to help physicians obtain the best codes and reduce the workload of coding specialists.
|Effective start/end date||1/08/21 → 30/09/22|
UN Sustainable Development Goals
In 2015, UN member states agreed to 17 global Sustainable Development Goals (SDGs) to end poverty, protect the planet and ensure prosperity for all. This project contributes towards the following SDG(s):
- disease classification
- clinical record
- natural language processing
- deep learning
Explore the research topics touched on by this project. These labels are generated based on the underlying awards/grants. Together they form a unique fingerprint.