To set up a logistic regression prediction model for hepatotoxicity of Chinese herbal medicines based on the efficacy of Chinese herbal medicines

In our previous research,a logistic regression prediction model for hepatotoxicity of Chinese herbal medicines based on the four properties,five flavors and channel tropism has been successfully established.However,could Chinese herbal medicines efficacy also be applied to predict the hepatotoxicity of Chinese herbal medicines?Therefore,a logistic regression prediction model for hepatotoxicity of Chinese herbal medicines based on Chinese herbal medicines efficacy has been tentatively set up to study the correlations of hepatotoxic and nonhepatotoxic Chinese herbal medicines with efficacy by using a chi-square test for two-way unordered categorical data.Logistic regression prediction model was established and the accuracy of the prediction by this model was evaluated.It has been found that the hepatotoxicity and nonhepatotoxicity of Chinese herbal medicines were weakly related to the efficacy,and the coefficient was 0.295.There were 20 variables from Chinese herbal medicines efficacy analyzed with unconditional logistic regression,and 6 variables,rectifying Qi and relieving pain,clearing heat and disinhibiting dampness,invigorating blood and stopping pain,invigorating blood and relieving swelling,killing worms and relieving fright were chosen to establish the logistic regression prediction model,with the optimal cutoff value being 0.250.Dissipating cold and relieving pain(DCRP),clearing heat and disinhibiting dampness,invigorating blood and relieving pain(IBRP),invigorating blood and relieving swelling,killing worms,and relieving fright were the variables to affect the hepatotoxicity and the established logistic regression prediction model had predictive power for hepatotoxicity of Chinese herbal medicines to a certain degree.

基于Logistic回归和支持向量机的早发性结直肠癌风险预测模型

目的:通过Logis tic回归和支持向量机(SVM)探究早发性结直肠癌(EOCRC)和晚发性结直肠癌(LOCRC)的危险因素,建立针对不同年龄段人群的风险预测模型并比较预测效果。方法:选择2012—2022年诊断为结直肠癌患者,记录人口学特征、临床表现、既往史、家族史、生活方式、体格检查、实验室检查及病理诊断,分别建立风险预测模型,比较两模型的ROC曲线下面积(AUROC)、准确率、精确率、召回率、F1分数。结果:综合两模型结果,EOCRC风险与出现消化道出血、腹胀腹痛、大便习惯改变等临床表现、体重减轻、肿瘤标志物升高具有较强的正相关性,与婚姻状况、阑尾切除史、糖尿病史、血脂异常病史、结直肠癌家族史也存在较弱的正相关;LOCRC风险与婚姻状况、出现临床表现、体重减轻、血脂异常、肿瘤标志物升高具有较强的正相关性,与年龄、吸烟、阑尾切除史、结直肠癌家族史也存在一定的正相关性。两模型的AUROC、准确率、F1分数相差不大,但Logistic回归模型的精确率更高而SVM模型的召回率更高。结论:EOCRC和LOCRC的危险因素不完全相同,婚姻状况、吸烟、血脂异常、肿瘤家族史在EOCRC中的贡献低于在LOCRC中的贡献。相较Logistic回归,SVM能发现更多的结直肠癌危险因素,能尽可能多的找出结直肠癌的可能患者。

Investigation of contemporary college students’mental health status and construction of a risk prediction model

BACKGROUND Due to academic pressure,social relations,and the change of adapting to independent life,college students are under high levels of pressure.Therefore,it is very important to study the mental health problems of college students.Developing a predictive model that can detect early warning signals of college students’mental health risks can help support early intervention and improve overall well-being.AIM To investigate college students’present psychological well-being,identify the contributing factors to its decline,and construct a predictive nomogram model.METHODS We analyzed the psychological health status of 40874 university students in selected universities in Hubei Province,China from March 1 to 15,2022,using online questionnaires and random sampling.Factors influencing their mental health were also analyzed using the logistic regression approach,and R4.2.3 software was employed to develop a nomogram model for risk prediction.RESULTS We randomly selected 918 valid data and found that 11.3%of college students had psychological problems.The results of the general data survey showed that the mental health problems of doctoral students were more prominent than those of junior college students,and the mental health of students from rural areas was more likely to be abnormal than that of urban students.In addition,students who had experienced significant life events and divorced parents were more likely to have an abnormal status.The abnormal group exhibited significantly higher Patient Health Questionnaire-9(PHQ-9)and Generalized Anxiety Disorder-7 scores than the healthy group,with these differences being statistically significant(P<0.05).The nomogram prediction model drawn by multivariate analysis includ-ed six predictors:The place of origin,whether they were single children,whether there were significant life events,parents’marital status,regular exercise,intimate friends,and the PHQ-9 score.The training set demonstrated an area under the receiver operating characteristic(ROC)curve(AUC)of 0.972[95%confidence interval(CI):0.947-0.997],a specificity of 0.888 and a sensitivity of 0.972.Similarly,the validation set had a ROC AUC of 0.979(95%CI:0.955-1.000),with a specificity of 0.942 and a sensitivity of 0.939.The H-L deviation test result was χ^(2)=32.476,P=0.000007,suggesting that the model calibration was good.CONCLUSION In this study,nearly 11.3%of contemporary college students had psychological problems,the risk factors include students from rural areas,divorced parents,non-single children,infrequent exercise,and significant life events.

Dynamic Statistical Models for Corporate Failure Prediction in Italy

Different models have been proposed in corporate finance literature for predicting the risk of firm＇s bankruptcy and insolvency. In spite of the large amount of empirical findings, significant issues are still unsolved. In this paper, the authors developed dynamic statistical models for bankruptcy prediction of Italian firms in the industrial sector by using financial indicators. The model specification has been obtained via different variable selection techniques, and the predictive accuracy of the proposed default risk models has been evaluated at various horizons by means of different accuracy measures. The reached results give evidence that dynamic models have a better performance in any of the considered scenarios.

An Early Warning Model of Financial Distress Prediction Based on Logistic-AHP-BP Neural Network Model

Ever since the appearance of"Implementation Measures for Suspending and Terminating the Listing of Loss-making Companies"in 2001,the delisting system has emerged.However,the proportion of delisted companies in China has never exceeded 1% each year.The number of delisted companies in the security market is far less than the number of companies with financial distress.The capital market lacks a good delisting system and investors lack risk identification capabilities.Financial risk is directly related to delisting risk.Therefore,an early warning model of financial distress prediction for China.s stock market can provide guidance to stakeholders such as listed companies and capital markets.This paper first explains the immature delisting system of China.s capital market and the overall high risk of listed companies.financial distress.Then,the paper further elaborates previous research on financial distress prediction model of listed companies and analyzes the advantages and disadvantages of different models.This paper chooses the Analytic Hierarchy Process(AHP)to screen out the main factors that affect the risk of financial distress.The main factors are included in Logistic regression model and BP neural network model for predicting financial distress of listed companies.The overall effect of two models are assessed and compared.Finally,this paper proposes policy implications according to empirical results.

随机森林模型和Logistic回归模型预测非计划再手术发生风险的效能比较

目的比较随机森林模型和Logistic回归模型预测非计划再手术发生风险的效能。方法在手术麻醉系统中筛选一次住院期间申请2次手术的患者信息。提取所有非计划再次手术患者(n=219)作为研究组,对应科室的计划再次手术患者(n=14311)作为对照组。运用随机森林模型和Logistic回归模型建立非计划再手术预测模型。采用受试者工作特征曲线下面积评价两种模型的预测效能。结果(1)Logistic回归分析结果显示,前次术中输血、罹患恶性肿瘤、合并疾病数量、前次手术切口愈合等级、前次手术级别、前次手术时长、前次手术切口类别是非计划再手术发生的影响因素(P<0.05)。Logistic回归预测模型的曲线下面积为0.922,灵敏度、特异度、准确率分别为92.59%、79.11%、79.28%。(2)随机森林模型特征变量的重要性排序结果显示,前次手术切口类别、前次术中输血、前次手术级别、前次手术切口愈合等级、合并疾病数量、罹患恶性肿瘤等变量的重要性更靠前。随机森林预测模型的曲线下面积为0.866,灵敏度、特异度、准确率分别为80.00%、93.33%、86.66%。Logistic回归预测模型曲线下面积大于随机森林预测模型,但差异无统计学意义(P>0.05)。结论综合使用Logistic回归模型和随机森林模型,并将二者分析结果互为补充,可从各个方面预测非计划再次手术的风险因素,能获得更好的预测效能。

Development and application of hepatocellular carcinoma risk prediction model based on clinical characteristics and liver related indexes

BACKGROUND Hepatocellular carcinoma(HCC)is difficult to diagnose with poor therapeutic effect,high recurrence rate and has a low survival rate.The survival of patients with HCC is closely related to the stage of diagnosis.At present,no specific serolo-gical indicator or method to predict HCC,early diagnosis of HCC remains a challenge,especially in China,where the situation is more severe.AIM To identify risk factors associated with HCC and establish a risk prediction model based on clinical characteristics and liver-related indicators.METHODS The clinical data of patients in the Affiliated Hospital of North Sichuan Medical College from 2016 to 2020 were collected,using a retrospective study method.The results of needle biopsy or surgical pathology were used as the grouping criteria for the experimental group and the control group in this study.Based on the time of admission,the cases were divided into training cohort(n=1739)and validation cohort(n=467).Using HCC as a dependent variable,the research indicators were incorporated into logistic univariate and multivariate analysis.An HCC risk prediction model,which was called NSMC-HCC model,was then established in training cohort and verified in validation cohort.RESULTS Logistic univariate analysis showed that,gender,age,alpha-fetoprotein,and protein induced by vitamin K absence or antagonist-II,gamma-glutamyl transferase,aspartate aminotransferase and hepatitis B surface antigen were risk factors for HCC,alanine aminotransferase,total bilirubin and total bile acid were protective factors for HCC.When the cut-off value of the NSMC-HCC model joint prediction was 0.22,the area under receiver operating characteristic curve(AUC)of NSMC-HCC model in HCC diagnosis was 0.960,with sensitivity 94.40%and specificity 95.35%in training cohort,and AUC was 0.966,with sensitivity 90.00%and specificity 94.20%in validation cohort.In early-stage HCC diagnosis,the AUC of NSMC-HCC model was 0.946,with sensitivity 85.93%and specificity 93.62%in training cohort,and AUC was 0.947,with sensitivity 89.10%and specificity 98.49%in validation cohort.CONCLUSION The newly NSMC-HCC model was an effective risk prediction model in HCC and early-stage HCC diagnosis.

基于Lasso-Logistic回归模型的胃癌影响因素分析

目的探究胃癌影响因素并构建临床预测模型。方法收集2020年12月~2023年10月就诊于上海中医药大学附属普陀医院及上海中医药大学附属曙光医院的1000例胃肿瘤患者的临床资料,经数据清洗剔除异常值后,分为胃息肉组(n=487)和胃癌组(n=479)。采用非参数检验筛选出有意义的指标,Lasso回归筛选具有非0系数的胃癌相关特征因素,逐步Logistic回归分析筛选出具有显著相关的因素,构建Lasso-Logistic回归模型,并绘制受试者工作特征(receiver operator characteristic,ROC)曲线计算曲线下面积(area under the curve,AUC)及混淆矩阵评估模型效能。结果多因素Logistic回归分析结果显示,年龄、白细胞计数(white blood cell,WBC)、单核细胞(monocyte,M)计数、谷丙转氨酶(alanine amiontransferase,ALT)、糖类抗原724(cancer antigen 724,CA724)、糖类抗原242(cancer antigen 242,CA242)、糖类抗原50(cancer antigen 50,CA50)、癌胚抗原(carcinoembryonic antigen,CEA)是胃癌的独立影响因素。基于多因素Logistic回归分析结果构建胃癌的风险预测列线图模型,测试集的AUC为0.91,精准率为100%,召回率为100%,验证集的AUC为0.93,精准率为93.63%,召回率为74.1%,模型预测效果良好。结论本研究构建8个胃癌常见预测因子,且Lasso-Logistic回归预测模型具有较好区分度,临床可基于患者体检报告,完成胃癌早期筛查。

基于logistic回归模型分析骨科手术部位感染的影响因素

目的总结骨科手术部位感染现状,探讨骨科手术部位感染的影响因素。方法收集江苏省盐城市第三人民医院2022年1月至2023年12月骨科手术部位感染病例作为感染组,共41例,按照1∶1的比例,随机抽取同科室2022年1月至2023年12月年龄相近(±10岁)、性别相同未发生手术部位感染的41例病例作为非感染组,分析骨科手术部位感染病原菌分布情况并基于二分类logistic回归模型分析骨科手术部位感染的影响因素。结果本研究共纳入41例手术部位感染患者,术后1~3 d发生手术部位感染10例(24.39%),术后4~6 d发生手术部位感染12例(29.27%),术后7~9 d发生手术部位感染5例(12.20%),术后10~30 d发生手术部位感染10例(24.39%),术后31~90 d发生手术部位感染4例(9.76%)。感染组检出40株病原菌,主要为革兰氏阳性球菌(31株,77.50%),最常见的为金黄色葡萄球菌(19株,47.50%),其次为凝固酶阴性葡萄球菌(7株,17.50%)。两组糖尿病史、体重指数(BMI)、术前纤维蛋白原、手术持续时间、手术引流比较,差异有统计学意义(P<0.05)。logistic回归分析显示,患者BMI(OR=1.231,95%CI:1.049~1.445,P=0.011)是骨科手术部位感染的独立危险因素。BMI作为手术部位感染的独立危险因素,其临界值为25.37 kg/m2。结论骨科手术患者中,肥胖患者更易发生手术部位感染,建议进一步强化肥胖患者的围手术期管理,以减少手术部位感染的发生。

普外科术中低体温发生情况Logistics回归分析及预测模型构建

目的探讨普外科术中低体温发生的风险因素,构建并验证术中低体温发生的风险预测模型。方法选取2020年12月至2022年12月在本院接受普外科手术的117例患者作为观察对象。收集患者临床资料,根据患者术中是否发生低体温将其分为发生低体温组(A组)和未发生低体温组(B组)。Logistic回归分析影响患者普外科术中发生低体温的危险因素,并建立风险预测模型,受试者工作特征曲线(ROC)检测该模型的预测效能。结果117例患者中发生低体温31例(26.49%),未发生低体温86例(73.50%)。两组患者在年龄、体重指数、手术方式、ASA分级、术中输液量、手术室温、手术时间等方面比较,差异具有统计学意义(P<0.05)。Logistic回归分析结果显示,年龄≥65岁、术中输液量≥1000 mL、麻醉时间≥4 h、手术室温<23℃是普外科术中发生低体温的危险因素(P<0.05)。独立危险因素纳入Logistic回归分析并建立预测模型,模型预测概率P=1/[1+e(-1.020+0.874)×(年龄)+1.114×(术中输液量)+1.556×(手术室温)+1.453×(麻醉时间)]。ROC曲线检验该模型预测效能,结果显示ROC曲线下面积(AUC)=0.754(P<0.05);Hosmer-Lemeshow拟合优度检验显示,χ^(2)=1.001,P=0.998。结论患者年龄、术中输液量、麻醉时间、手术室温是普外科患者术中发生低体温的独立危险因素,Logistic风险预测模型拟合效度好,具有较高预测价值。

基于Logistic回归的老年髋部骨折患者术后尿道感染风险预测模型构建与应用

目的探讨老年髋部骨折患者术后尿道感染风险因素,并以此构建老年髋部骨折术后患者尿道感染风险预测模型,并应用于老年髋部骨折围手术期。方法选取我院骨科2019年1月至2023年5月收治的老年髋部骨折患者1012例作为研究对象,其中发生术后尿道感染者111例。通过单因素分析初步筛选出老年骨科患者尿道感染的危险因素,综合考虑临床经验,将相关危险因素纳入多因素Logistic回归分析,并根据结果建立Logistic模型。结果纳入单因素、多因素Logistic回归分析模型分析,经筛选后发现,影响术后尿道感染的独立危险因素有低蛋白血症、电解质失衡、肺炎、糖尿病4项(P<0.05)。检测发现,预测模型在老年髋部骨折患者诊断中的敏感度、特异度各为83.78%,90.77%。结论低蛋白血症、电解质失衡、肺炎、糖尿病均是影响老年髋部骨折患者术后尿道感染风险的因素。基于本文列线图模型构建的老年髋部骨折尿道感染预测模型有良好的预测能力与准确性。

基于Lasso-Logistic回归分析构建中青年急性LHI静脉溶栓后出血转化预测模型

目的基于Lasso-Logistic回归分析中青年急性大面积脑梗死(LHI)患者静脉溶栓后出血转化(HT)的影响因素,并建立列线图预测模型。方法选取2022年5月—2023年10月首都医科大学宣武医院行阿替普酶静脉溶栓治疗的中青年急性LHI患者495例,溶栓后24 h是否发生HT分为HT组、非HT组。比较两组临床资料,通过Lasso-Logistic回归分析HT发生的影响因素,根据回归分析筛查出的指标构建列线图预测模型,并评价列线图预测模型的临床应用价值。结果495例中青年急性LHI患者中HT发生率为25.66%(127/495);HT组年龄、房颤占比、糖尿病占比、发病至溶栓时间(ONT)3.0~4.5 h占比、溶栓前美国国立卫生研究院卒中量表(NIHSS)评分、血清C反应蛋白(CRP)、降钙素原(PCT)、中性粒细胞/淋巴细胞比值(NLR)、基质金属蛋白酶-9(MMP-9)、脂蛋白相关磷脂酶A2(Lp-PLA2)、可溶性凝集素样氧化低密度脂蛋白受体-1(sLOX-1)水平高于非HT组,外周血血小板、尿酸水平低于非HT组(P<0.05);房颤、糖尿病、ONT、溶栓前NIHSS评分、外周血血小板、尿酸水平、血清NLR、MMP-9、Lp-PLA2、sLOX-1水平均是静脉溶栓治疗后HT发生的影响因素(P<0.05);列线图预测模型预测HT发生的AUC为0.893(95%CI:0.862~0.925),敏感度、特异度分别为83.65%、88.42%,该模型校准度良好,且具有明显的正向净收益。结论房颤、糖尿病、ONT、溶栓前NIHSS评分、外周血血小板、尿酸水平、血清NLR、MMP-9、Lp-PLA2、sLOX-1水平均是中青年急性LHI患者阿替普酶静脉溶栓治疗后发生HT的影响因素,依据上述影响因素建立列线图预测模型,该模型对静脉溶栓治疗后HT发生具有一定预测价值及临床实用性,临床可依据该模型筛选早期HT发生高危患者,并采取个体化治疗措施,以降低HT发生风险。

Correction:Establishment of a prediction model for prehospital return of spontaneous circulation in out-of-hospital patients with cardiac arrest

This is an erratum to an already published paper named“Establishment of a prediction model for prehospital return of spontaneous circulation in out-ofhospital patients with cardiac arrest”.We found errors in the affiliated institution of the authors.We apologize for our unintentional mistake.Please note,these changes do not affect our results.

基于Logistic回归模型的头孢类药物引起静脉炎危险因素分析

目的:探讨基于Logistic回归模型的头孢类药物引起静脉炎危险因素。方法:选取345例输注头孢类药物的住院患者为研究对象,根据是否发生静脉炎分为研究组(n=27)和对照组(n=318)。比较两组患者一般资料、头孢类药物用药情况,分析头孢类药物引起静脉炎的相关因素。结果:研究组中,患者静脉炎1级4例,2级16例,3级7例,经对症治疗后所有患者均转归有效,无严重后遗症发生。单因素分析结果显示,两组患者年龄、药物过敏史、用药时间、滴注速度均有统计学差异(P<0.05);多因素Logistic回归结果显示,合并药物过敏史、用药时间≥7 d是头孢类药物引起静脉炎的独立危险因素(P<0.05)。结论:合并药物过敏史、头孢类药物用药时间≥7 d可能会增加患者静脉炎发生风险;因此,临床应用头孢类药物时,应重点关注既往存在药物过敏史及用药时间过长的患者,规范使用,减少静脉炎的发生。

基于宏、中、微观对冠心病血瘀证前证相关因素的二元logistic回归分析

目的基于中医状态学宏、中、微观健康状态表征参数体系探讨冠心病血瘀证前证发展过程中的相关保护/危险因素。方法收集湖南中医药大学各附属医院就诊于心内科门诊及住院部冠心病待查对象253例,按照宏观、中观、微观3个维度制定调查问卷,对采集的参数用Python软件进行分类整理,将患者诊断为冠心病血瘀证前证(150例)和冠心病血瘀证(100例),用频次分析、χ^(2)检验及Logistic回归等方法进行统计分析。结果(1)单因素分析结果显示:年龄、BMI、吸烟史、饮酒史、高血压史、糖尿病史、月平均高温、空气质量、季节、职业类型、社会环境、冠脉造影狭窄、舒张压、收缩压、肌酐、尿酸、总胆固醇等指标在冠心病血瘀证前证和冠心病血瘀证之间存在差异,差异均有统计学意义(P<0.05)。(2)二元Logistic回归分析显示:年龄、BMI、饮酒史、职业类型、冠脉造影狭窄、舒张压、肌酐、暗红舌是其独立危险因素。建立预测模型:P=1/[1+exp(16.522-1.427×年龄-0.975×BMI-3.55×饮酒史+1.982×月平均高温+0.709×季节-1.827×职业类型-1.1×冠脉造影狭窄-0.072×舒张压-0.076×肌酐+2.398×头晕-4.108×暗红舌+4.169×脉涩)],模型预测率为90.5%。结论冠心病血瘀证logistic回归模型与临床诊断良好,为冠心病已病与未病之间的状态探索奠定基础,为亚健康理论提供重要的基础数据。

基于过采样Logistic回归模型的互联网贷款违约预测研究

在持续增长的居民贷款消费需求刺激下,互联网贷款业务的规模呈现出持续快速扩张的发展态势,发挥机器学习模型在个贷违约预测的作用,控制和防范互联网贷款违约风险,具有十分重要的意义。通过对不同数据集的样本特征进行详细分析,构建个人信用风险评估指标体系,利用具有普适性特征和可解释性特征的Logistic回归模型对个贷违约进行预测。针对原始数据集存在不平衡样本的问题,分别采用过采样和欠采样的重抽样方法获得平衡样本集,调整正则化惩罚力度,选择最优结果的参数来进行建模,得到模型预测结果。最后对如何防范互联网贷款违约风险提出了相关建议。

Logistic回归与决策树模型对大面积急性岛叶梗死患者预后的预测价值

目的探讨Logistic回归模型和决策树模型对大面积急性岛叶梗死预后不良的预测价值。方法回顾性分析2019年1月—2022年12月收治的大面积急性岛叶梗死100例的临床资料,根据发病3个月后改良Rankin量表分为预后良好组和预后不良组。统计2组临床资料、实验室指标、疾病史等基线资料。构建Logistic回归模型、决策树模型分析预后不良影响因素。绘制受试者工作特征(ROC)曲线分析2种模型对预后不良的预测效能。结果发病3个月后失访3例,预后不良发生率为39.18%(38/97),预后良好率为60.82%(59/97)。Logistic回归分析显示,年龄、房颤、基线肌钙蛋白T(cTnT)、鸢尾素、闭锁蛋白(Occludin)是预后不良影响因素(P<0.01);决策树模型分析显示,年龄、房颤、基线cTnT及Occludin是预后不良影响因素;决策树模型预测预后不良的曲线下面积大于Logistic回归模型。结论年龄、房颤、基线cTnT、Occludin是大面积急性岛叶梗死患者预后不良影响因素,基于上述因素构建Logistic回归模型和决策树模型均具有良好应用价值,应结合2种模型优点,为临床诊治提供新思路。

209例老年慢性心力衰竭患者远期预后的影响因素Logistic回归分析

目的209例老年慢性心力衰竭患者远期预后的影响因素Logistic回归分析。方法对2017年1月—2018年12月上海市浦东新区老年医院209例老年慢性心力衰竭患者作为研究对象进行研究,回顾性收集患者临床资料。比较所有患者临床资料、远期预后情况,采用Logistic回归分析法分析老年慢性心力衰竭患者远期预后不良的影响因素,建立预测模型,并绘制受试者工作特征(ROC)曲线分析预测模型对老年慢性心力衰竭患者远期预后不良的预测价值。结果209例老年慢性心力衰竭患者,随访5年期间,70例患者死亡,发生率为33.49%(70/209)。较预后良好组,预后不良组美国纽约心脏病协会(NYHA)心功能分级为Ⅳ级的患者占比、血清肌肉生长抑制素(MSTN)、肌肉环指蛋白-1(MuRF-1)、N-末端B型利钠肽原(NT-proBNP)、直接胆红素(DBIL)、间接胆红素(IBIL)、总胆红素(TBIL)水平均更高;左室射血分数(LVEF)则更低(P<0.05)。Logistic回归分析结果显示,NYHA心功能分级为Ⅳ级、血清MSTN、MuRF-1、NT-proBNP、DBIL、IBIL、TBIL水平异常偏高均为老年慢性心力衰竭患者远期预后不良的影响因素,差异有统计学意义(OR=1.579,1.505,1.480,1.531,1.439,1.374,1.401,P<0.05)。将上述因素纳入预测模型:Logit(P)=-8.122+NYHA心功能分级×0.457+血清MSTN水平×0.409+血清MuRF-1水平×0.392+血清NT-proBNP水平×0.426+血清DBIL水平×0.364+血清IBIL水平×0.318+血清TBIL水平×0.337+LVEF×0.226。按照预测模型绘制预测老年慢性心力衰竭患者远期预后不良发生的ROC曲线,结果显示,当Logit(P)>7.635时,曲线下面积(AUC)为0.858,95%CI为0.8030.902,χ^(2)为13.381,诊断敏感度为77.14%、特异度为79.14%。结论老年慢性心力衰竭患者远期预后不良的影响因素主要为NYHA心功能分级为Ⅳ级、血清MSTN、MuRF-1、NT-proBNP、DBIL、IBIL、TBIL水平异常偏高,在影响因素基础上构建的预测模型具有良好的预测价值,临床可据此对高危人群应采取针对性的防治措施,以改善老年慢性心力衰竭患者远期预后。

XGBoost模型与Logistic回归模型预测儿童TBTB合并MPP的价值

目的比较XGBoost模型和Logistic回归模型在预测儿童气管支气管结核(TBTB)合并肺炎支原体肺炎(MPP)中的效能。方法收集2018年6月至2023年1月入院治疗的212例MPP患儿临床资料,根据是否合并TBTB将其分为合并组(n=42)与肺炎组(n=170)。通过XGBoost和Logistic回归构建儿童TBTB合并MPP的临床预测模型,采用受试者工作特征(ROC)曲线绘制两个模型在预测儿童TBTB合并MPP中的预测价值;采用Delong检验确定两个模型曲线下面积的差异。结果XGBoost模型筛选符合情况的相关变量为地区、咳嗽时间、发热史、咳嗽史、SIRI、WBC、湿罗音、SII,多因素Logistic回归分析发现,地区、发热史、咳嗽史、咳嗽时间、WBC是儿童TBTB合并MPP的独立危险因素(P<0.05),XGBoost曲线下面积为0.996,而Logistic回归模型曲线下面积仅为0.851。Delong检验发现,XGBoost模型预测效能高于Logistic回归模型,差异有统计学意义(P<0.01)。结论XGBoost模型优于Logistic回归模型,可作为诊断儿童TBTB合并MPP的有效工具。

基于二元Logistic回归模型分析机器人辅助子宫内膜癌术后并发症危险因素

目的:探索基于二元Logistics回归模型分析机器人辅助子宫内膜癌患者术后并发症的危险因素。方法:回顾性分析2021年5月—2022年5月在空军军医大学第一附属医院收治的96例子宫内膜癌患者的临床资料,根据手术方式不同将所有患者分为常规组(n=47)和机器人组(n=49),并比较两组患者并发症发生率。同时,经二元Logistic回归模型分析影响术后并发症的危险因素。结果:机器人组术后并发症发生率低于常规组(6.12%Vs 31.91%,P<0.05)。经二元Logistic回归模型分析,年龄>60岁、BMI>24 kg/m^(2)、术中出血量>200 ml、有贫血史、常规手术是影响患者术后出现并发症的独立危险因素(P<0.05)。利用Bootstrap法内验证,预测模型AUC为0.818,特异性71.8%,灵敏性77.8%,95%CI 0.720~0.917。结论:影响机器人辅助子宫内膜癌术后并发症的主要因素为贫血史、手术时间、BMI、年龄、手术方式,针对合并此类危险因素的患者需采用相应的干预措施,从而降低患者术后并发症,改善预后。