Zhou Archive for TCM Study
In this page, we introduce the Zhou Archive, an expert-specific database containing Electronic Medical Records (EMRs) of 73,000+ visits to Prof. Zhou Zhongying by 26,000+ distinct patients over 35 years from 1980 to 2015. Recording the complete data of Prof. Zhou's clinical practice since 1980, the archive provides an ideal opportunity to understand Traditional Chinese Medicine (TCM) from the data-driven perspective.
- Professor & President (1983-1991)
Nanjing University of Traditional Chinese Medicine - Entitled to the Master of TCM (国医大师) in 2009
Professor Zhongying Zhou
1. Patient Coverage
Diseases covered by the archive
TCM Diseases covered by the archive
Total number of visits and number of distinct diseases in different disease categories
Landscape change of the patient pool from 1980 to 2015
Number of visits per year
Gender distribution
Age distribution
2. Data Structure
The archive contains 14 data fields of 6 categories including: (1) Patient ID and Demographics (ID, Gender, Age), (2) Visit Date, (3) Clinical Features (Symptoms, Tongue Picture, Pulse Type, Labe Tests), (4) Western Medicine Diagnosis (Disease, Disease Category), (5) TCM Diagnosis (TCM Disease, TCM Pathogenesis) and (6) TCM Treatments (TCM Therapy, TCM Prescription). A demonstration is given below:
3. Data Processing
To transfer the raw EMRs into a well-structured database, for which data analysis can be conveniently implemented, we implemented the following data processing procedure to produce based on the original archive: (1) a feature codebook F which encodes all features generated from the archive, (2) a term dictionary D which fully covers the vocabulary specific to the archive (including all background words, common TCM terms and special terms used by Prof. Zhou), (3) a term-feature map M which links terms in D and the standard feature codes they correspond to, and the most importantly, (4) a well-organized structured feature table T with columns for different features and rows for different records.
Flowchart of text data processing procedure
4. Acknowledgement
Prof. Zhou & the Zhou Zhongying’s Studio at Nanjing University of Chinese Medicine made great contribution on collecting, managing and sharing this valuable archive. The Deng Lab at the Statistical Center of Tsinghua University help design and implement the data processing procedure and tools. Related works were partially supported by Supporting Grant to the TCM Master Zhou Zhouying’s Studio 201159 by the State Administration of TCM of China, and National Natural Science Foundation of China Grants 11771242 & 11401338.
5. Data Access
The feature codebook, term dictionary and term-feature map produced in the data processing procedure can be downloaded by link: ZhouArchiveTerm-Feature.zip
To get access to the original archive, please fill up the data access application form and get contact with TCM Master Zhou Zhongying's Studio in Nanjing University of Chinese Medicine, or email it to Prof. Fang Ye (260958@njucm.edu.cn).