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.

目的 基于网络药理学方法预测银杏叶治疗心肌缺血的潜在靶点及信号通路。方法 利用 TCMSP 平台筛选生物利用度(OB)≥ 30% 和类药性(DL)≥ 0.18 的活性成分及作用靶点。利用GeneCards和OMIM数据库检索心肌缺血疾病相关靶点,并提取药物成分和心肌缺血疾病的共有靶点作为关键靶点。通过在线TRING平台构建PPI网络,并采用Cytoscape 软件构建可视化的“化合物-靶点-通路”网络,进一步进行GO 功能富集分析和KEGG通路富集分析。结果 筛选得到 27种潜在的药效成分,2 164个化合物靶点,531个心肌缺血相关靶基因。两者取交集后获得疾病-类药活性成分40个共同靶点,PPI 蛋白互作网络自由度较高的节点依次为:IL6、VEGFA、CASP3、MAPK8、MYC、NOS3。GO 功能富集分析得到42个 GO 条目,KEGG 通路富集分析得到42条信号通路。结论 银杏叶治疗心肌缺血主要GO 能力富集在半胱氨酸肽链内切酶活性,内肽酶活力,激活转录因子结合,DNA结合转录激活剂活性,RNA聚合酶II特异性等功能,调控TNF信号通路,糖尿病并发症的年龄愤怒信号, 细胞凋亡,PI3K-Akt信号通路等信号,进一步达到对心肌缺血疾病的治疗。

Objective To predict the potential targets and signal pathways of ginkgo leaf in the treatment of myocardial ischemia based on network pharmacology. Methods The active components and targets of bioavailability (OB) ≥ 30% and drug-like (DL) ≥ 0.18 were screened by TCMSP platform.The related targets of myocardial ischemic diseases were searched by GeneCards and OMIM database, the components and the common targets of myocardial ischemic diseases were extracted as the key targets. To build the PPI network through the online STRING platform, a visual “compound-target-pathway” network was constructed to further analyze the functional enrichment of GO and the enrichment of KEGG pathway. Results 27 potential active components, 2 164 compound targets and 531 myocardial ischemia related target genes were screened. After the intersection of the two, 40 common targets of disease-class active components were obtained. The nodes with higher degree of freedom of PPI protein interaction network were IL6、VEGFA、CASP3、MAPK8、MYC and NOS3.42 entries were obtained by GO functional enrichment analysis and 42 signal pathways were obtained by KEGG pathway enrichment analysis. Conclusion Ginkgo leaf may be a target of cysteine-type endopeptidase activity,endopeptidase activity,activating transcription factor binding,DNA-binding transcription activator activity, RNA polymerase II-specific function. TNF signaling pathway, AGE-RAGE signaling pathway in diabetic complications, apoptosis, PI3K-Akt signaling pathway were regualted to achieve the treatment of myocardial ischemia disease.

  目的   基于SEER数据库分析三阴性乳腺癌（TNBC）的预后，并建立Cox回归临床预测模型且进行内部验证。方法   使用SEER*Stat软件（8.4.2版）筛选2010—2015年诊断为TNBC的病例，进行单因素和Cox多因素回归以及向后逐步回归分析，明确与生存相关的独立危险因素，构建预测TNBC患者3年和5年癌症特异生存（CSS）率的Nomogram图，并用受试者工作特征曲线，Harrell’s一致性指数，临床预测模型校准曲线以及决策曲线对该模型进行评估及内部验证，以评估该模型的临床预测效能。结果   共筛选出符合纳入标准的TNBC患者5 564例，按照7∶3的比例随机拆分为训练集（n=3 894）和验证集（n=1 670）。通过单因素，多因素分析显示TNM分期、放射治疗、化学治疗以及手术和其他治疗的先后顺序是与TNBC患者CSS显著相关的独立危险因素（P＜0.05）。利用上述预后相关因素建立Nomogram图模型。训练集的C-index为0.731（95%CI：0.712~0.749），验证集的C-index为0.719（95%CI：0.688~0.749），训练集和验证集3年和5年生存ROC曲线的曲线下面积均＞0.7，区分度较好，且校准曲线拟合良好。结论  TNM分期、放射治疗、化学治疗以及手术和其他治疗的先后顺序是TNBC的独立预后因素，基于此建立的Nomogram图临床预测模型区分度、准确度以及临床适用性较好，能较好地预测TNBC患者的生存预后。

    Objective  To analyze the prognosis of triple negative breast cancer（TNBC）based on the SEER database，and to establish a Cox regression clinical prediction model with internal validation．Methods  Cases diagnosed with TNBC from 2010 to 2015 were screened using SEER*Stat software（version 8.4.2），and univariate and Cox multifactorial  regression as well as backward stepwise regression analyses were performed to identify the independent risk factors associated with survival，and to construct a clinical prediction model for predicting the three- and five-year cancer specific survival（CSV）of TNBC patients．Survival（CSS）rates of TNBC patients at 3 and 5 years，and the model was evaluated and internally validated using the ROC curve，Harrell’s consistency index（C-index），clinical prediction model calibration curve，and decision-making curve（DCA curve）to assess the predictive efficacy of the model for clinical prediction．Results  A total of 5 564 TNBC patients meeting the inclusion criteria were screened and randomly split into a training set（n=3 894）and a validation set（n=1 670）according to a 7∶3 ratio．By univariate，multivariate analysis showed that T-stage，N-stage，M-stage，radiotherapy，chemotherapy，and the sequence of surgery and other treatments were independent risk factors significantly associated with CSS in TNBC patients．The above prognostic-related factors were utilized to build a Nomogram plot model．The C-index was 0.731（95%CI：0.712-0.749）for the training set and 0.719（95%CI：0.688-0.749）for the validation set，and the areas under the curves of the 3- and 5-year survival ROC curves of both the training and validation sets were ＞0.7，which was a good differentiation，and the calibration curves were well-fitted．Conclusions  T-stage，N-stage，M-stage，radiotherapy，chemotherapy，and the  sequence of  surgery and other treatments are independent prognostic factors for TNBC，and the Nomogram clinical prediction model based on this has good differentiation，accuracy，and clinical utility，and can better predict the survival prognosis of TNBC patients．

       目的   基于Nomogram初步构建膝骨关节炎（KOA）患者术前衰弱的风险预测模型。方法   便利选取172例于2021年12月—2022年8月在广州市某三甲医院关节外科接受择期膝关节置换术的KOA患者为研究对象，依据衰弱的发生与否分为衰弱组（n=111）和非衰弱组（n=61），通过单因素分析筛选变量，纳入Logistic回归分析，并构建列线图模型。结果   单因素分析结果显示年龄、BMI、膝关节疼痛年限、合并症、抑郁、焦虑、疼痛、睡眠障碍、营养状况等在不同组间比较差异存在统计学的意义（P＜0.05）。多因素Logistic回归分析表明，BMI异常（OR=3.360）、膝关节疼痛年限＞5年（OR=14.188）、抑郁（OR=5.608）、睡眠障碍（OR=25.480）是KOA患者术前衰弱的独立危险因素（P＜0.05）。基于此，建立了预测膝骨关节炎患者术前衰弱风险的列线图预测模型。结果显示C-index为0.915，校正曲线接近理想曲线，ROC曲线下面积（AUC）为0.919（95%CI：0.878~0.961），可见该预测模型具有较好的区分度和准确度。结论   根据BMI、膝关节疼痛年限、抑郁以及睡眠障碍这四个独立危险因素，可以准确地预测膝骨关节炎患者术前衰弱的风险。

    Objective  To develop a nomogram for predicting the risk of preoperative frailty in knee osteoarthritis patients．Methods  A convenience sample of 172 patients who underwent elective knee arthroplasty at a Grade-A hospital in Guangzhou from December 2021 to August 2022 was selected．The patients were divided into two groups based on the presence of preoperative frailty：frailty group（n=111）and non-frailty group（n=61）．The variables with statistical differences were screened by univariate analysis for multivariate logistic regression analysis，and the nomogram prediction model was established．Results  Univariate analysis identified significant differences between the groups in age，BMI，years of knee pain，complications，depression，anxiety，pain，sleep disturbance，and nutrition（P＜0.05）．Multivariate logistic regression showed that abnormal BMI（OR=3.360），years of knee pain ＞ 5（OR=14.188），depression（OR=5.608），and sleep disorders（OR=25.480）were independent  risk factors for preoperative frailty in knee osteoarthritis patients（P＜0.05）．Based on these findings，a nomogram prediction model was established．Model verification results demonstrated that the nomogram had good differentiation and accuracy in predicting the risk of preoperative frailty，with a C-index of 0.915，an area under the ROC curve of 0.919（95% CI：0.878~0.961），and a calibration curve slope close to 1．Conclusions  The nomogram，based on four independent risk factors（BMI，years of knee pain，depression，and sleep disturbance），effectively predicts the risk of preoperative frailty in knee osteoarthritis patients．