Analysis of treatment effect of acupuncture on cervical spondylosis and neck pain with the data mining technology under deep learning

This study was to explore the value of data mining model in evaluating the treatment effect of acupuncture on patients with cervical spondylosis (CS) and neck pain. A total of 270 patients with CS and neck pain recruited in the acupuncture clinic of Shanxi Provincial People’s Hospital were selected as the research objects in this study and were divided into an acupuncture needle group (group A), an acupoint latent acupuncture group (group B), and a puncture bloodletting group (group C) randomly, with 90 cases in each group. The Northwick Park Questionnaire (NPQ), McGill Pain Questionnaire (MPQ), and Role-Physical (RP), Physiological Function (PF), General Health (GH), and Body Pain (BP) of all patients were recorded before treatment, at the completion of the fifth acupuncture, at the end of treatment, one-month follow-up, two-month follow-up, and three-month follow-up to analyse the clinical treatment effect. Based on the artificial neural network (ANN) algorithm, a curative effect evaluation method and data mining model was further established to compare the accuracy rate of data processing by different data models, and the data processed by the data mining model were compared with the clinical data to analyse the feasibility of the data mining model. The test results found that the NPQ and MPQ values of patients in group B were significantly lower than those in groups A and C (P < 0.05). At the end of treatment, the PF and BP values of patients in groups B and C were significantly higher than those of group A (P < 0.05). The RP value of patients in group B was significantly higher than that in groups A and C after treatment and during follow-up (P < 0.05). The GH value of patients in group B was significantly higher than that in groups A and C (P < 0.05). The clinical treatment efficiency in group B was significantly higher than that in the other two groups (P < 0.05). Different sample sizes of decision tree (DT-1), clustering algorithm (CA-1), and support vector machines (SVM-1) had no effect on the accuracy rate of efficacy judgement of the model. Moreover, the accuracy rate of DT-2, CA-2, and SVM-2 using the neighbourhood learning algorithm increased as increase of the sample size. The correct rate of treatment efficiency judgement of the SVM model and the data mining model reached the maximum value of 81.48% and 82.64%, respectively. It suggested that the data mining model based on the ANN algorithm could accurately estimate and evaluate the overall efficacy data of patients with CS and neck pain.