[Using Machine Learning to Investigate Factors Influencing the Efficacy of "Shoulder Tri-needles Therapy" in Treatment of Shoulder-hand Syndrome in 586 Stroke Patients].

OBJECTIVE: To analyze the factors influencing the therapeutic effect of "Shoulder Tri-needles therapy" in the treatment of shoulder-hand syndrome of stroke patients by using machine learning approach, so as to provide a feasibility for improving clinical efficacy. METHODS: A total of 586 stroke patients with shoulder-hand syndrome eligible for this study were involved in our machine learning experiments for classification of the influential factors. Their data including the age, gender, pulse condition, complexion, tongue quality, tongue coating, disease stage, body mass index (BMI), blood pressure, blood glucose, blood triglyceride, blood total cholesterol, smoking history, drinking history, and final outcomes were extracted from the medical record system (from Oct. of 2014 to Jan. of 2017 in the First Affiliated Hospital and Shenzhen Futian Hospital of Guangzhou University of Chinese Medicine). The single rule algorithm (1 R) was adopted to learn, followed by optimization with Repeated Incremental Pruning to Produce Error Reduction (RIPPER) algorithm, and C 5.0 decision tree algorithm. RESULTS: The accurate classification rates of 1 R, RIPPER and decision tree model were 87.37%(512/586), 95.90% (562/586), and 97.10% (569/586), respectively. The final outcomes of machine learning of this study showed that the disease stage (acute or recovery stage), complexion difference, tongue coating difference, blood pressure level, consumption of alcohol, BMI, and smoking habit were the most important factors influencing the therapeutic effect of "Shoulder Tri-needles" in the treatment of shoulder-hand syndrome of stroke patients. CONCLUSION: The disease stage, complexion and tongue identification, blood pressure level, alcohol drinking and smoking habits, and BMI are the principal factors affecting the therapeutic effect of "Shoulder Tri-needles therapy" in the treatment of shoulder-hand syndrome of stroke patients.

[A Meta-analysis of Effectiveness of Acupoint Catgut Embedding Therapy for Insomnia].

OBJECTIVE: To evaluate the effectiveness and superiority of acupoint catgut-embedding in the treatment of insomnia. METHODS: Randomized controlled trials (RCTs) for insomnia treated by acupoint implantation of catgut were included in the present study. We searched the related articles from 6 databases (PubMed, Google Scholar, CBM, CNKI, VIP and Wanfang) from the date of inception to March 19, 2017 by using keywords "catgut implantation at acupuncture point" or "catgut implantation at acupoint" and "insomnia" or "agrypnia" and "randomised (or randomized) clinical trial". Quality assessments were performed by two researchers independently using GRADE profile 3.6, followed by crosscheck. Data were analyzed using software Revman 5.3 and STATA 14.0. RESULTS: Twenty-two trials met the inclusion criteria were included. They recruited 1 714 cases of insomnia. GRADE grading suggests a low quality of these articles. Heterogeneous test (numerical test) showed χ2＝31.11, P＝0.07, I2＝32%. Gabriz chart and sensitivity analysis ultimately determined that these trials have smaller or no heterogenity. The effective rate of acupoint catgut embedding for insomnia was higher than that of the control group (OR＝ 3.77; 95% CI: 2.63－5.41; P<0.00001). CONCLUSION: Acupoint catgut embedding therapy has a positive role in clinical treatment of insomnia. But due to lower quality of current literature, more high-quality randomized controlled clinical trials are required.

[A Meta-analysis of the Effectiveness of Acupuncture in the Treatment of Epilepsy].

OBJECTIVE: To evaluate the efficacy and safety of acupuncture in the treatment of epilepsy. METHODS: We first collected research data about randomized control trials (RCTs) of acupuncture treatment of epilepsy from databases CNKI, CBM, VIP and Wanfang using key words "(acupuncture)", "(epilepsy)"or "(epilepsy)"or "(epilepsy)", and from PubMed, Google Scholar, and Cochrane Library using key words "acupuncture" "needling" "prod" "epilepsy" "epilepsies" or "seizure disorder" or "simple seizure" from the date of database construction to May 5, 2017. Then, two researchers extracted the study outcomes and evaluated the evidence qualification of the research data independently using GRADE profile 3.6 software and analyzed the primary outcome indexes using RevMan 5.3 and STATA 14.0. RESULTS: Eleven articles containing 827 cases were included in the Meta-analysis. We found that acupuncture or acupuncture in combination with other conventional drugs had a significantly better efficacy than conventional drugs in the treatment of epilepsy [OR=3.94, 95%CI (2.49, 6.24), Z=5.85, P<0.000 01]. There was a statistical heterogeneity (P=0.04, l2=60%), and the Meta-analysis was not feasible for the studies of acupuncture vs medication. Combination of acupuncture and Chinese traditional drugs was significantly better than simple Chinese traditional drugs [OR = 4.61, 95%CI (2.18, 9.74), Z=4.01, P<0.000 1], and combination of acupuncture and wes-tern medicines was obviously better than simple western medicines [OR=3.07, 95%CI(1.24, 7.65), Z=2.41, P=0.02] in the treatment of epilepsy. CONCLUSION: Acupuncture therapy may have a positive effect in the treatment of epilepsy but the conclusion needs further verification due to very fewer high-quality and well-designed RCTs found at the present.