Back to Search
Start Over
Research on TCM Diabetes Assisted Diagnosis and Treatment Plan Integrating Association Mining and Quantitative Calculation
- Source :
- Procedia Computer Science. 188:52-60
- Publication Year :
- 2021
- Publisher :
- Elsevier BV, 2021.
-
Abstract
- This paper attempts to explore more precise and intelligent assisted methodological references for the diagnosis and treatment of diabetes in Traditional Chinese Medicine (TCM) by using medical record data from TCM diabetes, and to construct a TCM diabetes assisted diagnosis and treatment framework of “association mining-quantifying calculation-intelligent assisted diagnosis and treatment” what can be described as cluster analyzing and match mining for symptom and drug by association mining, as quantitatively calculating and evaluating for the condition of diabetes; as disease diagnosis, drug recommendation and decision making by intelligent assisted diagnosis and treatment. This paper synthetically employs the technical methodology of association rules, topic clustering, emotion recognition and content recommendation, to realize the knowledge mining, quantify the evaluation and assist decision-making of TCM diabetes, and to propose a reference for the process of consultation and treatment. Overall, the study contributes to the academic and practical value in diabetes by elaborating a new technical methodology and providing a brief empirical test for doctors and researchers.
- Subjects :
- Association mining
Knowledge management
Association rule learning
Computer science
business.industry
Medical record
medicine.disease
ComputingMethodologies_PATTERNRECOGNITION
Empirical research
Treatment plan
Diabetes mellitus
medicine
General Earth and Planetary Sciences
Construct (philosophy)
Cluster analysis
business
General Environmental Science
Subjects
Details
- ISSN :
- 18770509
- Volume :
- 188
- Database :
- OpenAIRE
- Journal :
- Procedia Computer Science
- Accession number :
- edsair.doi...........1287e939f4833e0a0504a2b72b3fa7c3
- Full Text :
- https://doi.org/10.1016/j.procs.2021.05.052