Symptoms selection using random forest based on Chinese medicine diagnostic cases of stomachache

• Published in: Journal of physics. Conference series Vol. 1168; no. 6; pp. 62025 - 62029
• Main Author: Wang, Ruixiang
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.02.2019
• Subjects: Algorithms; Criteria; Diagnosis; Diagnostic systems; Disorders; Signs and symptoms; Traditional Chinese medicine
• ISSN: 1742-6588; 1742-6596; 1742-6596
• DOI: 10.1088/1742-6596/1168/6/062025

Stomachache is a disease characterized by pain in the upper part of the stomach in the diagnosis of Traditional Chinese Medicine (TCM). TCM has a history of thousands of years of diagnosis and treatment for stomachache and has accumulated rich experience. There are several syndromes for each disease in TCM. When the doctor faces the patient, he will judge which syndrome the patient's condition belongs to by observing the patient's symptoms and the theory of TCM. There are eight syndromes of stomachache based on TCM theory. Due to the different experience and understandings of TCM theory, there has been a lack of clinically diagnostic criteria for stomachache. In this paper, we collected 279 cases of TCM stomachache, and adopted features selection algorithm based on random forest, to select the most important features of the cases. After research, it is found that there are eleven most important symptoms in TCM stomachache diagnosis. The results of this study can provide a basis for clinicians to diagnose stomachache, and can provide data support for the development of diagnostic criteria of TCM stomachache.