Application of constraint-based frequent closed itemsets Mining in TCM Clinical data Analysis
Jinlong Yu, Lei Zhang, Ning Xu, Lifeng Fa, Kuo Yang · 2023
Objective: To propose a frequent closed itemsets mining method based on item constraints to study the combination rules between symptoms, diagnoses, and herbs in clinical data of TCM. Methods: Based on the Charm algorithm, prune the itemsets which do not meet the constraint conditions firstly, design a constraint based frequent closed itemsets mining algorithm, which was used on the clinical dataset of TCM to confirm the effectiveness of the method and the clinical significance of the mining results. Results: Based on the Charm algorithm, a constraint based frequent closed itemsets mining algorithm was proposed. The results of the method for mining frequent closed itemsets from data of symptom, diagnosis and herbs were consistent with the relevant theories of TCM.Conclusion: The combination of constraint conditions and frequent closed itemsets mining methods can effectively reduce the mining space. Using constraint based frequent closed itemsets mining methods to mine the combination rules between symptoms, diagnosis, and herbs in TCM clinical data maybe helpful for assisting clinical diagnosis and treatment.