Evidence Hub

Patterns of herbal combination for the treatment of insomnia commonly employed by highly experienced Chinese medicine physicians

Zhou XZ, Zhang RS, Shah J, Rajgor D, Wang YH, Pietrobon R, Liu BY, Chen J et al.

Chinese journal of integrative medicine, 2011

162 participants

Abstract

OBJECTIVE: To explore the most effective herbal combinations commonly used by highly experienced Chinese medicine (CM) physicians for the treatment of insomnia.

METHODS: We collected and analyzed data related to insomnia treatment from the clinics of 7 highly experienced CM physicians in Beijing. The sample included 162 patients and 460 consultations in total. Patient outcomes, such as sleep quality and sleep time per day, were manually collected from the medical records by trained CM clinicians. Three data mining methods, support vector machine (SVM), logistic regression and decision tree, and multifactor dimensionality reduction (MDR), were used to determine and confirm the herbal combinations that resulted in positive outcomes in patients suffering from insomnia.

RESULTS: Results show that MDR is the most efficient method to predict the effective herbal combinations. Using the MDR model, we identified several combinations of herbs with 100% positive outcomes, such as stir-fried spine date seed, Szechwan lovage rhizome, and prepared thinleaf milkwort root; white peony root, golden thread, and stir-fried spine date seed; and Asiatic cornelian cherry fruit with fresh rehmannia.

CONCLUSIONS: Results indicate that herbal combinations are effective treatments for patients with insomnia compared with individual herbs. It is also shown that MDR is a potent data mining method to identify the herbal combination with high rates of positive outcome.

How strong is the evidence?

Evidence Hub reads this as a meta-analysis, done in people. Its evidence level is 1 of 5 (Highest · pooled evidence). Pooled evidence from several studies sits at the top of the evidence pyramid. Reported size: 162 participants or records.

How the five levels of evidence work. The level is assigned automatically from the abstract and can be wrong, so check the paper.

Read the paper

Related studies

Go deeper in Evidence Hub

Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.

Open this study Sign up free