论著

支持向量机和Logistic回归在GDM风险预测中的应用

Application of support vector machine and logistic regression in risk prediction of GDM

:23-27
 
目的 探讨两种不同机器学习算法在妊娠期糖尿病(gestational diabetes mellitus,GDM)风险预测中的应用。方法 选取2019年7月—2020年8月在广州市妇女儿童医疗中心及广东省计划生育专科医院进行产前检查的孕早期妇女520例,其中妊娠期糖尿病孕妇200例,随机抽取同期正常孕妇320例,收集孕妇的一般资料和孕早期(8~12周)的生化指标、血常规和凝血功能等检测资料。利用这些分析变量建立支持向量机(SVM)和Logistic回归(LR)预测模型。根据模型预测能力和模型实用性,如准确率、精确率、真阳性(TP)率、假阳性(FP)率、召回率、F测度、受试者工作特征曲线(ROC)进行效果评价。结果 两种预测模型的分类准确率总体为86%。SVM模型在真阳性(TP)率、假阳性(FP)率、召回率、F测度、受试者工作特征曲线(ROC)方面优于LR模型。结论 在分类与预测方面,支持向量机算法比Logistic回归模型更具有实用价值。
Objective To explore the application of two different machine learning algorithms in the risk prediction of gestational diabetes mellitus (GDM). Methods A total of 520 pregnant women with gestational diabetes mellitus were selected from Women and Children's Medical Center and Guangdong Family Planning Hospital from July 2019 to August 2020, including 200 cases of gestational diabetes mellitus, and 320 normal pregnant women in the same period. The general information of pregnant women and the detection data of biochemical indexes, blood routine test and coagulation function in early pregnancy (8~12 weeks) were collected. Support vector machine (SVM) and logistic regression (LR) prediction models were established by using these analysis variables. According to the predictive ability and practicability of the model, something like accuracy rate, precision ratio, true positive (TP) rate, false positive (FP) rate, recall rate, F-measure and receiver operating characteristic curve (ROC) were evaluated. Results The classification accuracy of the two models was 86%. SVM model is better than LR model in TPrate, FPrate, recall rate, F measure and ROC. Conclusion Support vector machine is more practical than logistic regression model in classification and prediction.
论著

Milligan-Morgan术后出现胃肠道症状危险因素Logistic回归分析

Logistic regression analysis of risk factors for gastrointestinal symptoms after Milligan-Morgan operation

:81-84
 
目的 回顾分析我医院近8年混合痔行Milligan-Morgan术式治疗的患者的临床病历资料,探索术后出现胃肠道症状的危险因素。方法 选取我医院2012年1月—2019年6年期间行Milligan-Morgan术式治疗的混合痔患者1 221例,分成术后胃肠道症状组和未出现胃肠道症状组,比较两组间的差异,分析其相关危险因素。结果 1 221例混合痔患者中出现胃肠道症状的为168例,发生率为13.8%(168/1 221);单因素分析结果显示,高血压、全麻麻醉方式是术后出现胃肠道症状的相关因素,差异有统计学意义;多因素Logistic回归分析结果显示,高血压、全麻麻醉方式是术后出现胃肠道症状的独立危险因素。结论 混合痔患者行Milligan-Morgan术式治疗出现胃肠道症状率较高;围手术期控制患者血压,以及慎重选择全麻麻醉方式可能有效减少胃肠道症状发生率。
Objective To explored the risk factors of gastrointestinal symptoms after operation by retrospectively analyzing the clinical records of patients with mixed hemorrhoids treated by Milligan-Morgan operation in our hospital in recent 8 years. Methods 1 221 patients with mixed hemorrhoids treated by Milligan-Morgan operation in our hospital from January 2012 to June 2016 were divided into two groups: the group with digestive tract symptoms after operation and the group without digestive tract symptoms. The differences between the two groups were compared and the related risk factors were analyzed. Results Among 1 221 patients with mixed hemorrhoids, 168 had gastrointestinal symptoms, whose incidence was 13.8%(168/1 221). Univariate analysis showed that hypertension and general anesthesia were the related factors of gastrointestinal symptoms after operation, and the difference was statistically significant. Multivariate logistic regression analysis showed that hypertension and general anesthesia were the independent risk factors. Conclusion Milligan-Morgan operation for mixed hemorrhoids has a high incidence of digestive tract symptoms. Perioperative blood pressure control and careful selection of general anesthesia may effectively reduce the incidence of digestive tract symptoms.
论著

剖宫产术后切口脂肪液化危险因素Logistic回归分析

Logistic regression analysis of risk factors for incision fat liquefaction after cesarean section

:102-106
 
目的 回顾分析我医院近9年产妇行剖宫产术治疗的患者的住院病历资料,探索术后出现切口脂肪液化的危险因素。方法 选取我医院2011年1月—2019年8月期间行剖宫产术治疗的产妇患者1 018例,分成术后切口脂肪液化组和甲级愈合组,比较2组间的差异,分析其相关危险因素。结果 1 018例产妇患者中出现切口脂肪液化的为34例,发生率为3.34%(34/1 018);单因素分析结果显示,糖尿病、体质指数超重、7 cm以上切口长度是术后出现切口脂肪液化的相关因素,差异有统计学意义;多因素Logistic回归分析结果显示,糖尿病、体质指数超重、7 cm以上切口长度是术后出现切口脂肪液化的独立危险因素。结论 产妇患者行剖宫产术治疗出现切口脂肪液化率较高;围手术期控制患者血糖,以及孕期控制体质指数、缩小剖宫产手术切口长度可能有效地减少切口脂肪液化发生率。
Objective To retrospectively analyze the medical records of patients undergoing cesarean section in our hospital in recent 9 years, and explore the risk factors of incision fat liquefaction after operation. Methods 1 018 patients undergoing cesarean section in our hospital from January 2011 to August 2019 were divided into two groups: incision fat liquefaction group and grade A healing group. The differences between the two groups were compared and the risk factors were analyzed. Results Among 1 018 parturients, 34 had incision fat liquefaction, and the incidence was 3.34% (34/1018). Univariate analysis showed that diabetes mellitus, overweight body mass index and incision length of more than 7 cm were risk factors for incision fat liquefaction after operation, and the difference was statistically significant. Multivariate logistic regression analysis showed that diabetes mellitus, overweight body mass index and incision length over 7 cm were independent risk factors for incision fat liquefaction. Conclusion The incision fat liquefaction rate is higher in patients undergoing cesarean section. Controlling blood sugar level, body mass index during pregnancy and shortening the length of incision during perioperative period may effectively reduce the incidence of incision fat liquefaction.
临床诊疗

外科Ⅲ类手术切口术后感染危险因素Logistic回归分析

Logistic regression analysis of risk factors for infection of type Ⅲ incision

:76-79
 
目的 研究和分析外科Ⅲ类手术切口术后感染的危险因素,达到进一步预防外科Ⅲ类手术切口术后感染的目的。方法 研究对象为我科2014年1月—2016年12月普外科的1 816例Ⅲ类手术切口患者,以术后是否发生切口感染为因变量,以性别、年龄、是否切口贴用医用薄膜、切口是否碘伏冲洗等相关因素为自变量,进行Logistic回归分析,统计分析外科Ⅲ类手术切口术后发生感染的危险因素。结果 1 816例外科Ⅲ类手术切口中,术后发生切口感染有218例,切口感染率为12%。单因素分析显示,8项影响因素与Ⅲ类手术切口术后感染具有相关性(P﹤0.01),对具有统计学意义的8影响因素进行多因素Logistic回归分析,结果显示手术切皮前应用薄膜保护切口、术后切口碘伏冲洗及合理应用抗生素为切口感染保护因素(P﹤0.01),而患者年龄、全麻、急诊手术、输血及住院时间为切口感染独立危险因素(P﹤0.01)。结论 手术皮肤切开前应用医用薄膜、关腹后碘伏冲洗伤口对降低Ⅲ类手术切口术后感染发生率有一定效果,值得临床推广。
Objective: To research and analyze the risk factor which lead to type Ⅲ operation incision infection,and prevent the incision infection.Methods: The clinical data of 1816 typeⅢoperation incision patients from the general surgery department during 2001-2016,With incision infection serving as a dependent variable, gender, age, using medical films, rinsing the incision with iodophor after the abdomen closing and other factors as independent variables, single factor analysis and logistic regression analysis were used to identify risk factor for typeⅢoperation incisions.Results: From 1816 typeⅢoperation incision patients,218 patients suffered from incision infection with a infection rate of 12%,Single factor analysis showed that 8 factors had significant effects on infection of type Ⅲ operation incision(P<0.01). Logistic regression analysis showed that there were 8 related factors out of 9 factors,and age,anesthesia,blood transfusion,the days of hospitalization and emergency surgery were possible independent risk factors of incision infection(P<0.01), and the critical pathway,using medical films,rinsing the incision with iodophor after the abdomen closing,reasonable use of antibiotics were protective factors against incision infection(P<0.01),while age,anesthesia,blood transfusion,the days of hospitalization and emergency surgery were possible independent risk factors of incision infection(P<0.01).Conclusion: Using medical films before the skin incising, rinsing the incision with iodophor after the abdomen closing can reduce the rate of incision infection postoperation, it is worthy of clinical promotion.
出版者信息








《广州医药》公众号