Manbyo Dictionary

A Large-scale Dictionary of Disease Names Used for Analysis in Clinics

The process of extracting a disease name from a medical document has been actively carried out in research in the medical language processing field. In most cases, the disease name specified by a standard such as ICD was used to extract the disease name. However, in actual medical practice, abbreviations and English names are often used instead of official names. Therefore, the standard disease name code alone cannot meet the demand for extracting all information about symptoms and disease names. Therefore, in the Social Computing Laboratory, we created data that widely extracted words related to symptoms and disease names from electronic medical records and discharge summaries written by medical staff, and named it “All Disease Dictionary”. This site publishes a universal dictionary and related data, so feel free to use it.


If you have any opinions or requests regarding the universal disease dictionary, please reply from the following.
The contents of your answers will be used as valuable materials for future improvement of the universal disease dictionary.


Manbyo dictionary data

<Latest version>

  • MANBYO_202106  (updated: 2021/06/02. file: zip (20.38MB) (file format: xlsx (15MB), csv (20.8MB), README: md, pdf))


<Past version>

  • MANBYO_201907 (updated:2019/07/ (14.5MB)(file format:xlsx (15.6MB),README: md, pdf))
  • MANBYO_201905 (updated:2019/05/ (14.6MB)(file format:xlsx (15.6MB),README: md, pdf))
  • MANBYO_201810 (updated:2018/10/ (4.5MB)(file format:xlsx (4.5MB),README: md, pdf))
  • MANBYO_201806 (updated:2018/06/ (3.4MB)(file format:xlsx (3.1MB),README: md))





Excerpt from Manbyo Dictionary