Risk factors and survival prediction model establishment for prognosis in patients with radical resection of gallbladder cancer

BACKGROUND Gallbladder cancer(GBC)is the most common malignant tumor of the biliary system,and is often undetected until advanced stages,making curative surgery unfeasible for many patients.Curative surgery remains the only option for long-term survival.Accurate postsurgical prognosis is crucial for effective treatment planning.tumor-node-metastasis staging,which focuses on tumor infiltration,lymph node metastasis,and distant metastasis,limits the accuracy of prognosis.Nomograms offer a more comprehensive and personalized approach by visually analyzing a broader range of prognostic factors,enhancing the precision of treatment planning for patients with GBC.AIM A retrospective study analyzed the clinical and pathological data of 93 patients who underwent radical surgery for GBC at Peking University People's Hospital from January 2015 to December 2020.Kaplan-Meier analysis was used to calculate the 1-,2-and 3-year survival rates.The log-rank test was used to evaluate factors impacting prognosis,with survival curves plotted for significant variables.Single-factor analysis revealed statistically significant differences,and multivariate Cox regression identified independent prognostic factors.A nomogram was developed and validated with receiver operating characteristic curves and calibration curves.Among 93 patients who underwent radical surgery for GBC,30 patients survived,accounting for 32.26%of the sample,with a median survival time of 38 months.The 1-year,2-year,and 3-year survival rates were 83.87%,68.82%,and 53.57%,respectively.Univariate analysis revealed that carbohydrate antigen 19-9 expre-ssion,T stage,lymph node metastasis,histological differentiation,surgical margins,and invasion of the liver,ex-trahepatic bile duct,nerves,and vessels(P≤0.001)significantly impacted patient prognosis after curative surgery.Multivariate Cox regression identified lymph node metastasis(P=0.03),histological differentiation(P<0.05),nerve invasion(P=0.036),and extrahepatic bile duct invasion(P=0.014)as independent risk factors.A nomogram model with a concordance index of 0.838 was developed.Internal validation confirmed the model's consistency in predicting the 1-year,2-year,and 3-year survival rates.CONCLUSION Lymph node metastasis,tumor differentiation,extrahepatic bile duct invasion,and perineural invasion are independent risk factors.A nomogram based on these factors can be used to personalize and improve treatment strategies.

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。

Risk factors of concurrent urinary sepsis in patients with diabetes mellitus comorbid with upper urinary tract calculi

BACKGROUND Urinary sepsis is frequently seen in patients with diabetes mellitus(DM)complicated with upper urinary tract calculi(UUTCs).Currently,the known risk factors of urinary sepsis are not uniform.AIM To analyze the risk factors of concurrent urinary sepsis in patients with DM complicated with UUTCs by logistic regression.METHODS We retrospectively analyzed 384 patients with DM complicated with UUTCs treated in People’s Hospital of Jincheng between February 2018 and May 2022.The patients were screened according to the inclusion and exclusion criteria,and 204 patients were enrolled.The patients were assigned to an occurrence group(n=78)and a nonoccurrence group(n=126).Logistic regression was adopted to analyze the risk factors for urinary sepsis,and a risk prediction model was established.RESULTS Gender,age,history of lumbago and abdominal pain,operation time,urine leukocytes(U-LEU)and urine glucose(U-GLU)were independent risk factors for patients with concurrent urinary sepsis(P<0.05).Risk score=0.794×gender+0.941×age+0.901×history of lumbago and abdominal pain-1.071×operation time+1.972×U-LEU+1.541×U-GLU.The occurrence group had notably higher risk scores than the nonoccurrence group(P<0.0001).The area under the curve of risk score for forecasting concurrent urinary sepsis in patients was 0.801,with specificity of 73.07%,sensitivity of 79.36%and Youden index of 52.44%.CONCLUSION Sex,age,history of lumbar and abdominal pain,operation time,ULEU and UGLU are independent risk factors for urogenic sepsis in diabetic patients with UUTC.

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。

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Logistic回归模型及ROC曲线的糖尿病足溃疡复发的危险因素分析

目的基于Logistic回归模型及ROC曲线的糖尿病足溃疡(DFU)复发的危险因素分析。方法回顾性选取2018年9月—2019年9月本院收治的92例初发2型糖尿病(T2DM)足溃疡患者,根据3年内足溃疡复发情况分为非复发组51例与复发组41例,行DFU患者足溃疡复发的单因素分析,多因素Logistic模型研究DFU患者足溃疡复发的危险因素,Spearman检验分析各指标与DFU患者足溃疡复发的相关性,受试者工作特征曲线(ROC)评价模型诊断效能。结果92例DFU患者随访3年,复发41例,复发率为44.57%。单因素分析显示,两组体质量指数(BMI)、性别、心脑血管疾病病史占比、高血压病史占比、住院时间、发病至就诊时间、ALB、TBIL、Scr、HbA1c、TG、HDL、TC、LDL差异无统计学意义(P>0.05);与非复发组比较,复发组年龄、T2DM病程、糖尿病周围神经病变(DPN)占比、下肢外周动脉病变(PAD)占比、吸烟史占比、创面位于胼胝占比明显升高,TBIL水平明显降低(均P<0.05)。多因素分析显示,年龄增大、T2DM病程长、合并DPN、合并PAD、有吸烟史、创面位于胼胝及血清TBIL水平降低为DFU患者足溃疡复发的危险因素(P<0.05)。Spearman检验提示,DFU患者足溃疡复发与年龄、T2DM病程、DPN、PAD、吸烟史、创面位于胼胝呈正相关,TBIL水平明显降低呈负相关(均P<0.05)。以unite(七变量综合)、年龄、T2DM病程、TBIL、DPN、PAD、吸烟、创面位于胼胝为检验变量绘制ROC曲线,结果显示,unite的AUC值为0.834,分别大于年龄(0.632)、T2DM病程(0.619)、TBIL(0.645)、DPN(0.684)、PAD(0.662)、吸烟(0.640)、创面位于胼胝(0.677),提示7项指标联合应用于评估DFU患者足溃疡复发的效能明显优于单一指标(P<0.05)。结论年龄增大、T2DM病程长、合并DPN、合并PAD、有吸烟史、创面位于胼胝、血清TBIL水平降低为DFU患者足溃疡复发的危险因素,如发现上述情况应高度警惕DFU患者足溃疡复发风险,并尽早干预。

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。

决策树联合Logistic回归模型探讨骨科清洁手术术后切口感染病原菌特点及危险因素

目的探讨我院骨科清洁手术切口感染的病原菌特点及危险因素。方法收集2018年1月-2020年12月在我院骨科行清洁手术的2264例患者资料,分析切口感染的病原菌特点,并分别建立决策树CHAID模型和Logistic回归模型,分析切口感染的影响因素,更全面地探讨导致切口感染的危险因素。结果手术后有31例(1.37%)患者发生切口感染,感染患者切口分泌物中共培养出致病菌15株,其中革兰阳性球菌10株,革兰阴性杆菌5株。决策树CHAID模型分析结果显示,手术时间>2 h、术前抗菌药物使用时间≥10 d以及既往有手术经历均是切口感染的危险因素,并且术前抗菌药物使用时间≥10 d的患者术后感染的风险最高;Logistic回归结果显示,合并糖尿病、手术时间>2 h、术前抗菌药物使用时间≥10 d以及既往有手术经历是感染发生的独立危险因素。结论通过分析切口感染的病原菌,并且利用决策树CHAID模型与Logistic回归相结合,从不同方面描述影响术后切口感染发生的因素及其作用,为制定骨科手术切口感染的预防和治疗策略提供充分的实践依据,降低了院内的感染率。

随机森林模型和Logistic回归模型预测髋部骨折患者住院时间延长的效能比较

背景:髋部骨折发生率与日俱增,由于此类人群身体状况较差,常需要长时间住院,而住院时间延长导致床位流通率下降和经济负担增加。目前针对髋部骨折延迟出院的预测模型较少,此次研究旨在寻找针对髋部骨折延迟出院的最佳模型,指导临床决策。目的:探究髋部骨折患者住院时间延长的危险因素,建立两种不同的风险预测模型,获得最佳风险预测工具,为临床干预及管理提供参考。方法:回顾性分析2019年1月至2021年12月天津市天津医院收治的老年髋部骨折患者683例,将全部患者按7∶3比例随机分成建模组(479例)和验证组(204例),以住院时间的第75百分位数为分界点(>28 d),分为住院时间延长组和正常组。基于建模组采用SPSS和R软件进行单因素分析和多因素Logistic回归分析和变量重要性排序筛选最佳预测变量,构建列线图及随机森林模型。基于验证组通过ROC曲线下面积、准确度、灵敏度、特异度、阳性预测值和阴性预测值评价并比较两种模型的预测效能。结果与结论:(1)Logistic回归分析显示,骨牵引、肺炎、再骨折、多发性创伤、静脉血栓、肺感染和年龄校正Charlson合并症指数(ageadjusted Charlson Comorbidity Index,ACCI)是髋部骨折患者住院时间延迟的危险因素。(2)随机森林模型根据基尼指数减少平均值排序显示,年龄、骨牵引、手术类型、ACCI、肺炎是前5个指标,对延迟出院的预测有重要影响。(3)Logistic回归模型和随机森林预测模型的ROC曲线下面积、准确度、灵敏度、特异度、阳性预测值、阴性预测值分别为0.774(95%CI:0.696-0.853)和0.708(95%CI:0.627-0.789)、60.78%和90.85%、80.39%和23.53%、50.82%和78.09%、86.01%和46.15%,结果显示Logistic模型具有较好的预测效能。(4)上述结果证实,Logistics回归模型和随机森林模型对髋部骨折患者住院时间延长均具有较高的预测价值,这对临床医护人员及时识别高危患者并采取有效干预措施降低髋部骨折患者住院时间具有重要意义。

基于Logistic回归模型分析急性类鼻疽脓毒症患者预后不良的危险因素

目的基于Logistic回归模型分析急性类鼻疽脓毒症患者预后不良的危险因素。方法前瞻性选取2020年11月至2021年11月海南医学院第一附属医院收治的急性类鼻疽脓毒症患者109例,均按照标准规程对患者进行抗生素治疗。分析急性类鼻疽脓毒症的临床特征,并根据预后将其分为预后良好组(n=51)和预后不良组(n=58)。比较两组患者一般资料,单因素及多因素Logistic回归模型分析急性类鼻疽脓毒症患者预后不良的危险因素,并根据分析结果构建预后预测模型,绘制受试者工作特征(ROC)曲线,分析该预后预测模型的预测价值。结果畏寒高热、咳嗽咳痰、感染指标升高为急性类鼻疽脓毒症主要临床特征。预后良好组与预后不良组年龄、职业、居住地、体重、饮酒史、长期使用糖皮质激素情况、免疫抑制剂使用情况、合并糖尿病、合并慢性乙型肝炎比较,差异均有统计学意义(P<0.05)。多因素Logistic回归模型显示,年龄、职业、体重、饮酒史、长期使用糖皮质激素情况、免疫抑制剂使用情况、合并糖尿病、合并慢性乙型肝炎结果与急性类鼻疽脓毒症预后不良相关(P<0.05)。根据危险因素构建预后预测模型,并进行ROC曲线分析,结果显示该模型预测急性类鼻疽脓毒症预后不良的ROC曲线下面积为0.850,敏感度为90.00%,特异度为70.00%。结论Logistic回归模型显示,老年、务农、体弱、酗酒、长期使用糖皮质激素和免疫抑制剂、合并糖尿病、合并慢性乙型肝炎是急性类鼻疽脓毒症患者预后不良的主要相关因素,上述指标联合临床特征可为急性类鼻疽脓毒症的早期识别、及时治疗、改善预后提供参考。

A Nomogram Model for Prediction of Mortality Risk of Patients with Dangerous Upper Gastrointestinal Bleeding:A Two-center Retrospective Study

Objective:This study aimed to establish a nomogram model to predict the mortality risk of patients with dangerous upper gastrointestinal bleeding(DUGIB),and identify high-risk patients who require emergent therapy.Methods:From January 2020 to April 2022,the clinical data of 256 DUGIB patients who received treatments in the intensive care unit(ICU)were retrospectively collected from Renmin Hospital of Wuhan University(n=179)and the Eastern Campus of Renmin Hospital of Wuhan University(n=77).The 179 patients were treated as the training cohort,and 77 patients as the validation cohort.Logistic regression analysis was used to calculate the independent risk factors,and R packages were used to construct the nomogram model.The prediction accuracy and identification ability were evaluated by the receiver operating characteristic(ROC)curve,C index and calibration curve.The nomogram model was also simultaneously externally validated.Decision curve analysis(DCA)was then used to demonstrate the clinical value of the model.Results:Logistic regression analysis showed that hematemesis,urea nitrogen level,emergency endoscopy,AIMS65,Glasgow Blatchford score and Rockall score were all independent risk factors for DUGIB.The ROC curve analysis indicated the area under curve(AUC)of the training cohort was 0.980(95%CI:0.962-0.997),while the AUC of the validation cohort was 0.790(95%CI:0.685-0.895).The calibration curves were tested for Hosmer-Lemeshow goodness of fit for both training and validation cohorts(P=0.778,P=0.516).Conclusion:The developed nomogram is an effective tool for risk stratification,early identification and intervention for DUGIB patients.

Risk factors for Parkinson disease and the path analysis: One-to-one paired design

BACKGROUND： Parkinson disease （PD） results from the reduce of neurotransmitter dopamine that transmits intracellular information in brain caused by some reasons, then leads to the dynamic disequilibrium with another neurotransmitter of acetylcholine which is relatively hyperactive. The main causes for PD are still unclear. OBJECTIVE： To screen out the risk factors of PD by means of univariate analysis and multivariate Logistic regression analysis, and investigate the manner of actions between various factors and PD, so as to provide clues for the etiological study of PD. DESIGN： A paired design, Logistic regression analysis, path analysis. SETTING： Department of Scientific Research, Shandong Institute of Physical Education. PARTICIPANTS： Totally 157 PD patients were selected from the Department of Neurology, Qilu Hospital of Shandong University from November 2001 to October 2002. Inclusive criteria： PD was diagnosed according to the standard set by the Fourth National Seminar on Extrapyramidal Disease, Parkinsonian syndromes caused by stroke, carbon monoxide poisoning, encephalitis, drugs, etc. were excluded. Another 157 patients treated in the same department at the same period were selected as the control group, they were the same in sex as those in the patient group, within 3 years older or younger than those in the patient group, and without PD or other extrapyramidal diseases. METHODS： （1） The general conditions were investigated in all the subjects, including general conditions, social behavioral factor, environmental factor, genetic factor, life events, and previous disease; There were 12 main variables, including educational level, family history, mental labour, contact to insecticides, living place before school-age, smoking index, drinking index, tea-drinking index, history of brain trauma, history of cardiovascular disease, history of diabetes mellitus, and history of depression. （2） SAS6.12 software and SPSS 10.0 software were used in the conditional Logistic regression analysis and path analysis respectively. MAIN OUTCOME MEASURES： The results of 12-variable univariate and multivariate analyses; Correlation between main variables and PD; Effects of the factors. RESULTS： All the subjects were involved in the analysis of results. （1） The results of Logistic regression analysis showed that family history, mental labour, insecticides, drinking index and history of depression all had significant positive correlations with PD （univariate analysis： OR=1.405- 5.429, P 〈 0.05- 0.01; multivariate analysis： OR=2.029- 6.754, P 〈 0.05- 0.01）, whereas smoking had significant negative correlations with PD [univariate analysis： odd ratio （OR）=0.765, P 〈 0.05; multivariate analysis： OR =0.489, P 〈 0.01]. （2） The path analysis showed that family history, mental labour, insecticides, smoking, drinking and history of depression had direct effects on PD occurrence [（path coefficient= - 0.218 to 0.204, P 〈 0.05 -0.01）]; Insecticides could cause PD indirectly on the basis of family history （genetic susceptibility） （path coefficient=0.946, P 〈 0.01）; Insecticides could also cause PD by drinking （path coefficient=0.165, P 〈 0.01） Drinking could cause PD indirectly on the basis of family history （path coefficient=0.043, P 〈 0.01 ）. CONCLUSION： The main risk factors of PD are family history, history of depression, drinking, mental labour and insecticides, whereas the protective factor is smoking. PD attack has genetic susceptibility, insecticides and drinking can cause PD on the basis of PD family history. The risk of PD can be decreased by reducing the occasion for contacting the environmental risk factors.

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.

基于Logistic模型分析输尿管上段结石微创手术后发生结石逃逸的危险因素

目的基于Logistic模型分析输尿管上段结石微创手术后发生结石逃逸的危险因素。方法回顾性选取2020年8月至2022年8月琼海市人民医院收治的123例输尿管上段结石患者,均行输尿管钬激光碎石术,根据结石逃逸情况分为未逃逸组(n=88)与逃逸组(n=35),行结石逃逸的单因素分析,多因素Logistic模型研究患者结石逃逸的影响因素,Spearman检验进行相关性分析,受试者工作特征(ROC)曲线评价模型诊断效能。结果2组年龄、体重指数、性别、饮酒史占比、吸烟史占比、脑血管疾病病史占比、冠心病病史占比、糖尿病病史占比、高血压病史占比、结石大小、结石数目差异均无统计学意义(P>0.05)。与未逃逸组比较,逃逸组术前肾积水轻中度占比、术中未使用输尿管管路封堵器占比、术中泵注0.9%氯化钠溶液压力值≥200 mmHg占比明显增高,差异均有统计学意义(P<0.05)。多因素Logistic模型显示,术前肾积水处于轻中度、输尿管管路封堵器术中未使用情况、术中泵注0.9%氯化钠溶液压力值≥200 mmHg为患者结石逃逸发生的危险因素(P<0.05)。Spearman检验数据提示,患者结石逃逸与术中泵注0.9%氯化钠溶液压力值呈正相关(P<0.05),与输尿管管路封堵器术中使用情况、术前肾积水程度呈负相关(P<0.05)。绘制ROC曲线显示,unite(三变量综合)的AUC值为0.960,分别大于术中泵注0.9%氯化钠溶液压力值(0.855)、输尿管管路封堵器术中使用情况(0.763)、术前肾积水程度(0.769),提示三项指标联合应用于评估患者结石逃逸的效能明显优于单一指标(P<0.05)。结论术前肾积水处于轻中度、输尿管管路封堵器术中未使用情况、术中泵注0.9%氯化钠溶液压力值≥200 mmHg为患者结石逃逸发生的危险因素,如发现上述情况应高度警惕患者发生结石逃逸的风险,并尽早干预。

创伤性脑出血术后并发迟发性脑出血患者不良预后风险的Logistic回归模型构建

目的探讨创伤性脑出血术后并发迟发性脑出血患者不良预后的相关影响因素,并构建其Logistic回归预测模型。方法选取2018年5月-2022年1月创伤性脑出血术后并发迟发性脑出血后预后良好患者77例(良好组)及预后不良患者77例(不良组),比较两组临床资料;采用多因素Logistic回归方程分析迟发性脑出血患者预后的相关影响因素,采用受试者工作特征(ROC)曲线及曲线下面积(AUC)分析各相关影响因素单独及所构建Logistic回归模型预测预后的价值。结果不良组脑疝、心电图异常改变多于良好组,维生素B1注射液使用、术前GCS评分、血小板低于良好组(P<0.05);脑疝患者不良预后风险是无脑疝患者的15.318倍,使用维生素B1注射液患者不良预后风险是未使用者的0.505倍,心电图异常改变患者不良预后风险是无异常改变患者的14.700倍,术前GCS评分、血小板均是预后相关保护因素,其对应OR值分别为0.388、0.191(P<0.05);Logistic回归模型:Logit(P)=7.199+2.729×脑疝-0.684×维生素B1注射液+2.688×心电图异常改变-0.946×术前GCS评分-1.655×血小板;Logistic回归模型预测不良预后的AUC为0.890,大于单独的相关影响因素[脑疝(0.558)、维生素B1注射液(0.662)、心电图异常改变(0.584)、术前GCS评分(0.808)、血小板(0.701)]。结论脑疝、维生素B1注射液、心电图异常改变、术前GCS评分、血小板与创伤性脑出血术后并发迟发性脑出血患者预后相关,基于各相关因素构建的模型有望成为预测预后一个可靠方法,为临床管理、治疗提供参考。

决策树及Logistic回归模型在活动性肺结核预测中的应用

目的采用决策树模型与Logistic回归模型分析活动性肺结核(active tuberculosis,ATB)的危险因素,为ATB的预防控制提供参考依据。方法实验组为2021年3月至2023年3月昆明市第三人民医院收治的200例活动性肺结核患者,对照组为同期200例健康体检者,建立Logistic回归和决策树ATB风险预测模型,并在是否基于Logistic回归结果条件下建立决策树分析模型(决策树1和决策树2),用受试者工作曲线评价3种模型的预测效果。结果Logistic回归结果显示AAT、IL-4、IL-6、IL-17、IFN-γ是发生ATB的危险因素,CD+4为保护因素,决策树1分析结果显示CRP为根节点,其后分别以IL-1、IL-6、CD+4、IL-17、AGP、IFN-γ作为子节点,决策树2分析结果显示IL-6作为根节点,其后是AAT、IL-4、IL-17作为子节点。建立的风险预测模型显示,Logistic回归的AUC为0.887,决策树模型的AUC分别为0.900(决策树1)和0.857(决策树2)。3组模型的AUC比较结果显示,决策树1的AUC优于决策树2(95%CI:0.0019~0.0841,P<0.05),但与Logistic回归模型比较,差异无统计学意义(95%CI:0.0265~0.0522,P=0.526)。结论Logistic模型和决策树1模型在预测ATB危险因素时均有一定的应用价值,建议将2种模型结合使用,以便更好地为ATB的防治提供参考价值。

俯卧位通气相关面部压力性损伤危险因素分析及最佳建模方法选择

背景面部压力性损伤是俯卧位通气患者常见并发症,创面局部暴露可增加全身感染风险,影响俯卧位通气治疗效果,甚至造成局部组织永久性功能损害。探讨其危险因素并构建预测模型对于预防俯卧位通气相关面部压力性损伤具有重要临床意义。目的探讨俯卧位通气相关面部压力性损伤的危险因素及其最佳建模方法。方法选择2020年6月—2023年3月入住新疆医科大学第一附属医院重症医学科的159例接受俯卧位通气的患者为研究对象,根据是否发生面部压力性损伤分为压力性损伤组(n=22)和非压力性损伤组(n=137),收集患者的一般信息、疾病诊断、治疗措施、实验室检查。分别使用逐步Logistic回归模型、全变量Logistic回归模型及Lasso-Logistic回归模型筛选面部压力性损伤危险因素并建立预测模型,应用受试者工作特征曲线下面积(AUC)评价模型区分度;应用赤池信息准则(AIC)、贝叶斯信息准则(BIC)及校准曲线评价模型校准度;应用决策曲线评价模型临床应用价值。通过比较三种Logistic回归模型预测效能和临床应用差异选择最佳建模方法。结果逐步Logistic回归模型结果显示,面部压力性损伤的影响因素为年龄(OR=39.041)、糖尿病(OR=7.256)和单次俯卧位通气时间(OR=6.705);全变量Logistic回归模型结果显示,面部压力性损伤的影响因素为年龄(OR=26.882)、糖尿病(OR=1.770)、ICU住院时间(OR=2.610)和单次俯卧位通气时间(OR=5.340);Lasso-Logistic回归结果显示,面部压力性损伤的影响因素为年龄(OR=38.256)、糖尿病(OR=1.094)、单次俯卧位通气时间(OR=5.738)和Richmond躁动镇静评分(OR=1.179)。Lasso-Logistic回归模型预测俯卧位通气相关面部压力性损伤的AUC、灵敏度和特异度分别为0.855、0.959和0.750,优于逐步和全变量Logistic回归模型;AIC和BIC分别为44.634和55.745,低于逐步和全变量Logistic回归模型;校准曲线显示Lasso-Logistic回归模型预测概率与实际概率拟合效果最佳。决策曲线显示Lasso-Logistic回归模型获得临床收益对应风险阈值为0.01~0.98,优于逐步和全变量Logistic回归模型。结论年龄、糖尿病、单次俯卧位通气时长和Richmond躁动镇静评分是俯卧位通气相关面部压力性损伤的危险因素,Lasso-Logistic回归模型预测效能和临床应用价值优于逐步Logistic回归模型和全变量Logistic回归模型,是最佳建模方法。

Understanding Credit Risk in Internet Consumer Finance:An Empirical Analysis with a Focus on the Young Generation

In recent years,internet finance has garnered increasing attention from the public.Online lending,emerging within the framework of Internet finance as a pivotal component,has witnessed substantial growth.While online credit,within the realm of Internet finance,presents numerous advantages over traditional lending,it concurrently exposes a plethora of credit risk issues.This study aims to facilitate the effective utilization of online credit tools by the young generation within the context of Internet finance.Additionally,it seeks to ensure the overall stability of the Internet finance environment and mitigate risks for the youth.Given the significance of understanding credit risk management for college students in the age of internet finance,this paper adopts the logistic model to evaluate credit risk in internet consumer finance and provides pertinent recommendations from the perspective of the young generation.