Objective: To identify clinically significant symptoms associated with Traditional Medicine (TM) syndromes in patients with type 2 diabetes mellitus using a machine learning model.
Subjects and Methods: A cross-sectional descriptive study was conducted on 326 patients with type 2 diabetes mellitus receiving treatment at Thong Nhat Hospital, Traditional Medicine Hospital in Ho Chi Minh City, and the University Medical Center Ho Chi Minh City – Branch 3. The Boruta-SHAP algorithm was employed to develop a machine learning model for selecting important symptoms based on their contribution to each TM syndrome.
Results: Most patients exhibited concurrent manifestations of four TM syndromes. The most prevalent syndrome was Liver-Kidney Yin Deficiency, with key symptoms including dry mouth, blurred vision, and soreness or pain in the lower back and knees. The least common syndrome was the Phlegm-Heat Accumulation, characterized by key symptoms such as fatigue, palpitations, sticky and foul-smelling stools, and a deep, rapid, and slippery pulse.
Conclusion: Patients with type 2 diabetes mellitus in this study were predominantly elderly, retired, or had ceased working due to severe illness, and exhibited poor glycemic control. Most patients concurrently exhibited four TM syndromes, with Liver-Kidney Yin Deficiency being the most frequent. Furthermore, this study highlights the key symptoms associated with each TM syndrome in patients with type 2 diabetes mellitus.