Identification of Predominant Diseases and Clinical Applications of Acupotomy Using Data Mining

The purpose of this study is to use data mining (DM) to find out the main diseases of acupotomy and their regularity in clinical practice. To meet the objective, we establish an acupotomy database with sufficient cases, and then take 3-Gram enhanced Naive Bayesian (NB) classification model as the dominant data analysis method. By comparing several mainstream classification algorithms, it is found that the NB model enhanced by 3-Gram shows significant advantages in the identification of dominant diseases in acupotomy. The results show that the model can effectively identify the dominant diseases of acupotomy, such as cervical spondylosis and lumbar disc herniation, and provide strong data support for clinical decision-making. The performance of the model in different feature dimensions is also assessed, and the effectiveness of 3-Gram features in improving the performance of the model is verified. The research reveals the clinical application characteristics of acupotomy, and also provides a new idea for the application of DM technology in the field of traditional Chinese medicine.