Comparison of external treatment of Acupuncture and moxibustion and intervention of Chinese and Western Medicine on postoperative pain of hemorrhoids:A systematic review and meta-analysis

Background To evaluate the clinical efficacy and safety of acupuncture and moxibustion in the treatment of postoperative pain of hemorrhoids compared with traditional Chinese medicine and western medicine.Methods CNKI,PubMed,Cochrane Library,Science Direct,Wan Fang,VIP,CBM,WOS,Bailian Yun Library and other databases were systematically retrieved from January 1,2017 to October 31,2022 for clinical randomized controlled trials of acupuncture versus traditional Chinese medicine and Western medicine for postoperative pain in hemorrhoids.The two evaluators independently retrieved,sifted through literature and extracted data for inclusion in a randomized controlled trial of acupuncture for the treatment of hemorrhoid pain that matched the study.Literature quality assessment was performed using RevMan5.4 for meta-analysis.Results A total of 540 related literature articles were retrieved,of which 139 were from CNKI,104 from Wan Fang,26 from VIP,7 from PubMed,9 from Cochrane Library,35 from WOS,173 from CMB,1 from Science Direct and 46 from the Bailian Yun Library,Screening resulted in inclusion of 10 RCTs including 870 patients.Meta analysis showed no statistically significant difference between the degree of pain in 2 hours[MD=-0.01,95%CI(-0.23,0.24),P=0.95].And it showed that the total effective rate of the two groups was[RR=1.14,95%CI(1.06,1.24),P=0.001],intervention for 2 days pain degree was[MD=0.41,95%CI(0.13,0.69),P=0.004],the length of hospital stay was[SMD=1.10,95%CI(0.73,1.48),P<0.00001],the incidence of adverse reaction was[RR=0.15,95%CI(0.03,0.79),P=0.03],the difference was statistically significant(P<0.05).Conclusion Drug treatment is effective quickly,analgesia effect is better than acupuncture in early treatment,but the effect is not lasting.Acupuncture treatment is slow to start but the effects of acupuncture will gradually become apparent at a later stage.However,due to the poor quality of collection,multicenter,large sample size and double-blind randomized controlled trials are still needed.

Battle damage assessment based on an improved Kullback-Leibler divergence sparse autoencoder

为解决深度学习网络中隐藏层节点数难以确定的问题,文中提出一种改进的KL(Kullback-Leibler)散度稀疏自动编码机,并将该方法应用到战斗损伤评估中。该方法能够自动筛选出对数据重建贡献大的隐层特征,舍弃贡献小的隐层特征,从而优化网络结构。在网络预测精度不受影响的前提下,该方法自动筛选隐层特征,提升了计算速度。基于UCI(University of California,Irvine)数据集和BDA(battle damage assessment)战争破坏数据的实验表明,该方法优于其他数据驱动的方法。改进的KL稀疏自动编码机回归网络在保证预测精度的前提下,能提升网络的训练和预测速度,并自动筛选隐层有效特征,优化隐层节点数,优化网络结构。