目的   通过机器学习方法构建脓毒症谵妄患者30 d死亡的预测模型，并识别关键预测因子。方法   采用基于医疗信息集成重症监护数据库（Medical Information Mart for Intensive Care IV）的回顾性队列研究方法，boruta筛选重要特征，并通过决策树，K近邻，LightGBM，随机森林，支持向量机，XGBoost构建模型进行分析，通过ROC曲线下面积进行评估，利用F1分数、召回率、精确率、特异度、灵敏度和阳性预测值比较模型表现。结果  XGBoost模型在训练集和验证集中的ROC曲线下面积分别为0.906和0.762，表明该模型具有良好的预测能力，入院年龄、红细胞分布宽度和白细胞计数是最重要的预测因子。结论   基于机器学习的脓毒症谵妄患者预后预测模型展现出良好的预测效能，为临床早期干预提供了重要参考依据。

       Objective  To construct a  30-day mortality  prediction model for  patients with  sepsis-associated  delirium using machine learning methods and identify key predictive factors．Methods  A  retrospective cohort study was conducted based on the Medical Information Mart for Intensive Care IV database．Important features were selected using the Boruta algorithm，and models including Decision Tree，K-Nearest Neighbors，LightGBM，Random Forest，Support Vector Machine，and XGBoost were constructed and analyzed．Model performance was evaluated using the area under the reciver operater characteristic（ROC）curve（AUC），along with F1 score，recall，precision，specificity，sensitivity，and positive predictive value．Results  The XGBoost model demonstrated strong predictive performance，with AUC values of 0.906 in the training set and 0.762 in the test set．Key predictors identified included admission age，red blood cell distribution width，and white blood cell count．Conclusions  The machine learning-based prediction model for sepsis-associated delirium prognosis exhibits robust predictive efficacy，providing a valuable tool for early clinical intervention．

目的 探讨振幅整合脑电图（aEEG）联合头颅磁共振成像（cMRI）对早产儿矫正12月龄时神经发育的预测价值。方法 选取110例早产儿为研究对象,并在矫正12月龄时采用Gesell 发育量表评估发育商（DQ）,依据DQ分为Gesell 正常组（DQ≥85,n=83）、Gesell 异常组（DQ<85,n=27）。采集早产儿及母亲临床资料,对比两组出生后72 h内aEEG、矫正胎龄37周时cMRI检查指标差异。结果 两组早产儿及母亲基线资料比较差异无统计学意义（P>0.05）。相较于Gesell 正常组,Gesell 异常组双顶径（BPW）降低[（70.68±5.32）mm vs（66.54±3.69）mm],睡眠-觉醒周期（SWC）不成熟率（20.48% vs 85.19%）、aEEG异常率（30.12% vs 70.37%）、两半球间距（IHD）增高[（2.95±0.83） mm vs（3.56±0.72）mm]（P<0.05）。Pearson相关分析结果显示,DQ值与IHD呈负相关,DQ值与BPW呈正相关（r=-0.361、0.598,P<0.05）。二元Logistic回归分析结果显示,BPW增高是Gesell 异常的独立保护因素（P<0.05）,IHD增高、SWC不成熟及aEEG异常是Gesell 异常的独立危险因素（P<0.05）。结论 早产儿出生后72 h内aEEG异常、矫正胎龄37周时cMRI异常可能提示矫正12月龄时不良神经发育结局。

Objective To evaluate the predictive value of amplitude-integrated electroencephalogram combined with cranial magnetic resonance on neurodevelopment for preterm infants at corrected age of 12 months．Methods A total of 110 preterm infants were selected as study subjects,and Gesell developmental scale was used to evaluate developmental quotient（DQ）at corrected age of 12 months．According to DQ,they were divided into normal Gesell group（DQ≥85,n=83）and abnormal Gesell group（DQ<85,n=27）．Clinical data of preterm infants and their mothers were collected,and the differences of amplitude-integrated electroencephalogram and cranial MRI（cMRI）were compared between two groups．Results There was no significant difference in baseline data between two groups（P>0.05）．Compared with the normal Gesell group,the biparirtal width（BPW）in the abnormal Gesell group was decreased（70.68±5.32mm vs 66.54±3.69mm）,the immaturity rate of sleep-wake cycle（SWC）（20.48% vs 85.19%）,the abnormal rate of aEEG（30.12% vs 70.37%）,and（IHD）（2.95±0.83mm vs 3.56±0.72mm）were increased（P<0.05）．The results of Pearson correlation analysis showed that DQ was negatively correlated with IHD,and DQ was positively correlated with BPW（r=-0.361、0.598,P<0.05）．Binary Logistic regression analysis showed that increased BPW was an independent protective factor for abnormal Gesell（P<0.05）,and increased IHD,immature SWC and abnormal aEEG were independent risk factors for abnormal Gesell（P<0.05）．Conclusions Abnormal aEEG within 72h after birth and abnormal cMRI at corrected age of 37 weeks may lead to adverse neurodevelopmental outcomes at corrected age of 12 months．

目的 应用FRAX^®工具评估广州社区中老年人发生骨质疏松性骨折的风险。方法 回顾性研究1 140例广州社区中老年人的临床资料,应用FRAX^®工具计算未来10年发生主要骨质疏松性骨折及髋部骨折的风险,分析不同危险因素与骨折风险的关系。结果 广州社区中老年人群10年内发生主要骨质疏松性骨折概率为(4.2±3.6)%,髋部骨折概率为(1.3±2.4)%。主要骨质疏松性骨折风险及髋部骨折风险、OSTA值均随着年龄增长而增加。多因素回归分析结果显示: 年龄、性别、既往骨折、继发性骨质疏松、股骨颈T值、跌倒对主要部位骨折及髋部骨折风险具有独立性预测意义。结论 FRAX^®工具可用于评估广州社区中老年人骨质疏松性骨折风险,建议在社区中老年人健康体检时应用FRAX^®工具进行骨折风险评估。

Objective To predict the osteoporotic fracture risk in senile people in Guangzhou communities by FRAX,the fracture risk assessment tool published by WHO. Methods Clinical data of 1140 cases were collected for the retrospective analysis. The FRAX tool was uesed to calculate the 10-year probability of a major osteoporotic and hip fracture.The relationship between different risk factors and the fracture risk predicted by FRAX was analyzed. Results The 10-year probability of major osteoporotic fractures was (4.2±3.6)%, and the 10-year probability of hip fractures was (1.3±2.4)%.The 10-year probability of the major osteoporotic and hip fracture increased with age.Multivariate regression analysis showed that age,gender,previous fracture,secondary osteoporosis,T-score of femoral neck BMD and fall were independent predictors of the 10-year probability of major osteoporotic fracture and hip fracture. Conclusion The FRAX tool may be effectively applied to assess the fracture risk of senile population in Guangzhou communities.We recommedated that FRAX-tool should be included in routine health check-up.

目的 探讨白蛋白-胆红素（ALBI）联合中性粒细胞与淋巴细胞比值（NLR）预测肝硬化合并食管胃底静脉曲张破裂出血（EGVB）的临床价值。方法 回顾性分析2021年1月—2022年12月肇庆市第一人民医院消化内科收治的80例肝硬化合并EGVB患者的临床资料,通过电话及门诊、再入院对其进行为期1年的随访,根据随访结果,将其分为2组,即存活组（n=69）与死亡组（n=11）,分析导致患者死亡的危险因素,并评估ALBI联合NLR预测肝硬化合并EGVB患者死亡的临床价值。结果 死亡组的年龄60岁以上、腹水和肝性脑病者占比,总胆红素（TBiL）、NLR、凝血酶原时间（PT）、谷丙转氨酶（ALT）水平及ALBI评分均高于存活组（均P<0.05）,而血红蛋白（HGB）、白蛋白（ALB）及血钠水平均低于存活组（均P<0.05）;Logtisic回归分析显示,年龄60岁以上、腹水、肝性脑病和TBiL、NLR水平升高及ALBI分级为3级是肝硬化合并EGVB患者死亡的危险因素（均P<0.05）;ALBI联合NLR预测肝硬化合并EGVB患者预后的准确率及灵敏度高于单一诊断,漏诊率低于单一诊断（P<0.05）。结论 肝硬化合并EGVB患者可见ALBI评分及NLR水平升高,而以上两种指标是患者死亡的危险因素,将其联合检测可评估患者预后,预测其死亡风险。

Objective To investigate the clinical value of albumin-bilirubin（ALBI）combined with neutrophil lymphocyte ratio（NLR）in predicting liver cirrhosis complicated with esophageal and gastric varices bleeding（EGVB）．Methods The clinical data of 80 patients with liver cirrhosis complicated with EGVB admitted to the Department of Gastroenterology of the First People's Hospital of Zhaoqing from January 2021 to December 2022 were retrospectively analyzed．They were followed up for one year by telephone,outpatient service and readmission．According to the follow-up results,they were divided into the survival group（n=69）and the death group（n=11）．The risk factors leading to the death of patients were analyzed and evaluated．Results The proportion of age over 60,ascites and hepatic encephalopathy,the levels of TBiL,NLR,PT,ALT and ALBI in the death group were higher（P<0.05）,while the levels of HGB,ALB and blood sodium were lower（P<0.05）．Logistics analysis showed that age over 60,ascites,hepatic encephalopathy,NLR and ALBI grade 3 were independent risk factors for the death（P<0.05）．The accuracy and sensitivity of ALBI combined with NLR in predicting their prognosis were significantly higher than that of single diagnosis,and the missed diagnosis rate was lower（P<0.05）．Conclusions ALBI scores and NLR levels significantly increase in patients with liver cirrhosis complicated with EGVB,and the above two indexes are risk factors for the death,and the combination of them can evaluate the prognosis of patients and predict the death risk．

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 探讨肝脏衰弱程度联合肝功能分级预测肝硬化患者肝病复合不良事件的价值,作为识别和干预不良结局的依据。方法 选择2022年12月—2023年12月医院接收的肝硬化患者80例进行研究,随访6个月观察患者不良事件发生情况,将出现2个及以上肝病并发症的肝病复合不良事件患者25例作为观察组,将出现1个肝病并发症或未出现并发症的患者55例作为对照组,比较两组患者的基本资料、实验室指标、营养指标、体力活动水平、肝脏衰弱指数（LFI）、肝功能Child-Turcotte-Pugh（CTP）评分,采用单因素和多因素Cox回归分析评估肝硬化患者肝病复合不良事件的危险因素,使用受试者工作特征（ROC）曲线下面积评估LFI联合CTP评分预测肝硬化患者肝病复合不良事件的价值。结果 观察组年龄、丙氨酸氨基转移酶（ALT）高于对照组,红细胞计数（RBC）、血红蛋白（Hb）、血肌酐（Scr）、总胆红素（TBIL）、步速、小腿围低于对照组（t分别为4.235、6.500、3.826、3.989、4.289、8.878、2.474,均P<0.05）。观察组营养风险48.00%、LFI≥4.5分52.00%、CTP分级B/C级76.00%高于对照组18.18%、14.55%、27.27%（χ²分别为7.664、12.454、16.699,均P<0.05）。单因素Cox回归分析显示年龄、ALT、营养风险、LFI≥4.5分、CTP分级B/C级、RBC、Scr、TBIL、Hb、步速、小腿围为肝硬化患者发生肝病复合不良事件的危险因素（HR分别为2.251、1.578、1.626、1.981、1.715、1.428、1.443、1.419、1.336、1.332、1.254,均P<0.05）。多因素Cox回归分析显示年龄、营养风险、LFI≥4.5分、CTP分级B/C级为肝硬化患者发生肝病复合不良事件的独立危险因素（HR分别为2.275、1.746、2.025、1.895,P均<0.05）。ROC曲线结果显示LFI、CTP、LFI联合CTP预测肝硬化患者肝病复合不良事件的AUC分别为0.82、0.79、0.88（P<0.05）。结论 年龄、肝脏衰弱、CTP分级B/C级、营养风险为肝硬化患者肝病复合不良事件的危险因素,肝脏衰弱程度联合肝功能分级预测肝硬化患者肝病复合不良事件具有更高的效能。

Objective To explore the value of predicting liver disease complex adverse events in patients with liver cirrhosis by combining the degree of liver frailty with liver function grading,as a basis for identifying and intervening in adverse outcomes．Methods A study was conducted on 80 patients with liver cirrhosis admitted to the hospital from December 2022 to December 2023． Patients were followed up for six months to observe the occurrence of adverse events．Twenty-five patients with liver disease complex adverse events with two or more liver disease complications were selected as the observation group,and 55 patients with one or no liver disease complication were selected as the control group．The basic information,laboratory indicators,nutritional indicators,physical activity levels,liver frailty index（LFI）,Child Turcotte Pugh（CTP）scores,univariate and multivariate Cox regression analysis were used to evaluate the risk factors for liver disease complex adverse events in liver cirrhosis patients．The value of combining LFI and CTP score in predicting liver disease complex adverse events in patients with liver cirrhosis was assessed by Receiver Operating Characteristic（ROC）curve area．Results The age,alanine aminotransferase（ALT）,red blood cell count（RBC）,hemoglobin（Hb）,serum creatinine（Scr）,total bilirubin（TBIL）,walking speed,and calf circumference of the observation group were higher than those of the control group（t=4.235,6.500,3.826,3.989,4.289,8.878,2.474,all P<0.05）．The nutritional risk of the observation group was 48.00%,LFI score≥4.5 was 52.00%,CTP grade B/C was 76.00%,which was higher than that of the control group at 18.18%,14.55%,and 27.27%（χ²=7.664,12.454,16.699,all P<0.05）．Univariate Cox regression analysis showed age,ALT,nutritional risk,LFI ≥ 4.5,CTP grade B/C,RBC,Scr,TBIL,Hb,step speed and calf circumference were risk factors for the occurrence of liver disease complex adverse events in patients with liver cirrhosis（HR values=2.251,1.578,1.626,1.981,1.715,1.428,1.443,1.419,1.336,1.332,1.254,all P<0.05）．Multivariate Cox regression analysis showed that age,nutritional risk,LFI ≥ 4.5,and CTP grade B/C were independent risk factors for liver disease complex adverse events in patients with liver cirrhosis（HR values=2.275,1.746,2.025,1.895,all P<0.05）．The ROC curve results showed that the AUC of LFI,CTP,and LFI combined with CTP in predicting liver disease composite adverse events in patients with liver cirrhosis were 0.82,0.79,and 0.88,respectively（P<0.05）．Conclusions Age,liver frailty,CTP grade B/C,and nutritional risk are risk factors for liver disease complex adverse events in patients with liver cirrhosis．The combination of LFI and liver function grade has higher efficacy in predicting liver disease complex adverse events in patients with liver cirrhosis．

目的 构建并验证主动脉夹层B型（TBAD）患者急性期预后的列线图预测模型,帮助临床医生在急性期内更准确地评估TBAD患者的死亡风险,并制定更合适的治疗策略。方法 回顾性分析从重症监护医学信息数据库v2.2 中提取的399例 TBAD患者的人口学资料和临床资料,结局为TBAD患者急性期（≤14 d）内死亡。先采用最小绝对收缩选择算法回归筛选特征变量,再采用多因素分析确定独立预后因素,并据此构建预测模型。通过受试者工作特征曲线、校准曲线、决策曲线分析（DCA）评价列线图预测模型的性能和临床适用性。结果 APS Ⅲ评分、二氧化碳总量、红细胞分布宽度为TBAD患者14 d内死亡的独立预测因素。列线图预测模型在内部验证中的受试者工作特征曲线下面积为0.776（95% CI：0.691 ~ 0.860）,Hosmer-Lemeshow 检验P=0.604,校准曲线和标准曲线高度重合,表明该模型具有良好的区分度和校准度。同时,DCA曲线显示,预测模型在大部分的阈值概率范围内提供了显著的净收益。结论 本研究基于APS Ⅲ评分、二氧化碳总量、红细胞分布宽度构建的列线图预测模型可以较准确地预测TBAD患者14 d内的死亡风险,有助于临床医生制定更合适的个体化治疗策略。

Objective To develop and verify a nomogram for predicting acute phase outcomes in patients with type B aortic dissection（TBAD）,enabling clinicians to more precisely evaluate mortality risk in TBAD patients during the acute stage and to devise better treatment plans．Methods This retrospective study analyzed demographic and clinical data of 399 TBAD patients from the Medical Information Mart for Intensive Care IV v2.2,focusing on mortality within 14 days of the acute phase in TBAD patients． Initially,the Least Absolute Shrinkage and Selection Operator regression was employed for feature variable selection,and then multivariate analysis was used to identify independent prognostic factors for constructing the predictive model．The nomogram predictive model's effectiveness and clinical applicability were assessed via the Receiver Operating Characteristic curve,calibration curve,and Decision Curve Analysis（DCA）．Results Acute Physidogy Score Ⅲ score,total carbon dioxide,and red blood cell distribution width emerged as independent predictors of 14-day mortality in TBAD patients．The internal validation of the nomogram predictive model showed an area under the curve of 0.776（95%CI：0.691-0.860）,with a Hosmer-Lemeshow test P-value of 0.604． The close alignment of the calibration and standard curves suggested the model's strong discriminative power and calibration． Furthermore,the DCA curve revealed that the predictive model offered substantial net benefits within a wide range of threshold probabilities．Conclusions This study's nomogram,developed using APS Ⅲ score,total carbon dioxide,and red blood cell distribution width,accurately predicts the 14-day mortality risk in TBAD patients,assisting clinicians in creating better personalized treatment plans．

目的 分析产后出血预测评分与产妇凝血指标的相关性,以及出血预测评分对阴道分娩产后出血的预测效能。方法 采用回顾性研究,纳入2021年1月—2022年12月河南科技大学第二附属医院收治的136例阴道分娩产妇,根据产后出血情况,将合并产后出血的36例患者列为病例组,其余100例列为对照组,比较两组患者的产后出血预测评分及凝血指标,经Spearman相关性系数验证产后出血预测评分结果与凝血指标的相关性,依据实际出血情况,验证产后出血预测评分、各凝血指标对产后出血的预测效能。结果 病例组患者的产后出血预测评分为（7.33±2.46）分,D-二聚体（D-D）为（2.62±0.41）mg/L,均高于对照组[（6.14±2.06）分、（2.17±0.45）mg/L],纤维蛋白原（FIB）为（4.42±1.25）g/L,低于对照组（5.23±1.16）g/L;活化部分凝血活酶时间（APTT）为（37.44±10.25）s,凝血酶原时间（PT）为（15.45±4.12）s,凝血酶时间（TT）为（16.77±4.25）s,均高于对照组[（30.11±10.12）s、（12.49±4.11）s、（13.34±4.18）s],差异具有统计学意义（P<0.05）。经Spearman相关性系数分析,产后出血预测评分与经阴道分娩产妇的D-D、APTT、PT、TT呈正相关,与FIB呈负相关。通过绘制受试者工作特征曲线（ROC）后得知,产后出血预测评分及凝血指标对产后出血均有一定预测价值,但产后出血预测评分的AUC值大于各凝血指标。结论 产后出血预测评分与产妇凝血功能指标呈正相关,将产后出血预测评分与凝血指标检测相结合能实现对产后出血的早期识别及诊断。

Objective To analyze the correlation between postpartum bleeding prediction score and maternal blood coagulation index and the prediction efficiency of postpartum bleeding in vaginal delivery．Methods This is a retrospective study．The cases were included from January 2021 to December 2022．The subjects of the study were 136 vaginal delivery mothers． According to the delivery situation,36 patients with postpartum bleeding were included in the case group,and the rest 100 patients were included in the control group．The postpartum bleeding prediction score and coagulation indicators of the two groups were compared．The correlation between postpartum bleeding prediction score and coagulation indicators was verified by Spearman correlation coefficient．According to the actual bleeding situation,verify the predictive score for postpartum bleeding and the diagnostic efficacy of various coagulation indicators on postpartum bleeding．Results According to the test,the predictive score for postpartum bleeding in the case group was（7.33±2.46）,D-dimer（D-D）was（2.62±0.41）mg/L,which were higher than those in the control group [（6.14±2.06）,（2.17±0.45）mg/L]．Fibrinogen（FIB）was（4.42±1.25）g/L,lower than the control group（5.23±1.16）g/L,activated partial thromboplastin time（APTT）was（37.44±10.25）s,prothrombin time（PT）was（15.45±4.12）s,and thrombin time（TT）was（16.77±4.25）s．Compared with the control group [（30.11±10.12）s,（12.49±4.11）s,and（13.34±4.18）s）],the above indicators were all higher（P<0.05）．Through Spearman correlation coefficient analysis,the predictive score of postpartum bleeding was positively correlated with the D-D,APTT,PT,TT,negatively correlated with the FIB of the parturient who delivered through vagina．After drawing the ROC curve,it was found that both the postpartum hemorrhage prediction score and coagulation indicators had certain predictive value for postpartum hemorrhage,but the AUC value of the postpartum hemorrhage prediction score was greater than each coagulation indicator．Conclusions The prediction score of postpartum bleeding is positively correlated with the coagulation function indicators of the parturient,combining the score and indicators can achieve early identification and diagnosis of postpartum bleeding．

胶质瘤是颅内最常见的原发性恶性肿瘤,其分级对患者治疗方式的选择和预后至关重要。尽管目前组织病理学仍是其最为可靠的分级手段,但需通过有创性手术以获取组织样本,存在一定的风险。相较之下,磁共振成像（MRI）作为一种非侵入性影像诊断工具,在胶质瘤分级中发挥着不可或缺的作用。然而,传统MRI评估受限于医师个体主观性强和可重复性差的问题,一定程度上影响了准确的分级结果。近年来,影像组学技术的崭露头角为解决上述难题开辟了新视角,通过高通量提取影像数据特征捕捉并量化肿瘤的影像学表现,避免因主观因素而导致的不确定性,协助医师更准确地评估肿瘤的恶性程度。本文对近五年来MRI影像组学在胶质瘤术前分级预测方面的相关研究进行了简要综述,旨在为相关领域研究者提供有益的参考和借鉴,以推动MRI影像组学在临床实践中的应用。

Glioma is the most common primary malignant brain tumor,and its grading is crucial for treatment decisions and prognosis．Currently,histopathology remains the gold standard for grading,but it requires invasive procedures and carries inherent risks．In contrast,magnetic resonance imaging（MRI）,a non-invasive diagnostic tool,plays an indispensable role in glioma grading．However,traditional MRI assessment is hampered by interobserver subjectivity and limited repeatability,which compromise grading accuracy．In recent years,radiomics,a burgeoning field,has offered a promising solution to address these challenges．By extracting high-dimensional imaging data features,radiomics enables the quantification of tumor radiological characteristics and elimination of subjectivity-related discrepancies．This technology assists clinicians in more precisely assessing the malignancy of gliomas．This article summarizes relevant studies in the past five years on the application of MRI radiomics in preoperative glioma grading,aiming to provide valuable insights and guidance to researchers in the field and promote the clinician implementation of MRI radiomics．

目的 分析常规炎性指标与进展性脑梗死（PCI）患者病灶损害程度的关联,及其对预后水平的预测效能。方法 采用回顾性研究,纳入2021年6月—2023年2月平顶山市第二人民医院收治的100例PCI患者,根据入院时神经功能缺损评分（NIHSS）结果,将NIHSS评分≥21分的30例患者列为重度组,将NIHSS评分15~20分的35例患者列为中度组,将NIHSS评分<15分的35例患者列为轻度组,比较三组患者的神经功能血清学指标及炎症指标,经Pearson相关性分析炎症指标与神经功能血清学指标的相关性;根据是否发生不良预后将入组患者分为预后良好组和预后不良组,比较两组患者各炎症指标及改良Rakin量表（mRS）评分间的差异,并通过绘制受试者操作特征（ROC）曲线、曲线下面积（AUC）评估炎症指标对PCI患者预后水平的预测效能。结果 重度组患者的C-反应蛋白（CRP）、白细胞介素-6（IL-6）、肿瘤坏死因子-α（TNF-α）分别为（26.44±5.18）mg/L、（95.28±10.46）ng/L、（45.24±10.31）pg/mL,均高于中度组[（23.12±5.46）mg/L、（90.44±10.17）ng/L、（40.25±10.18）pg/mL],轻度组[（20.28±5.33）mg/L、（84.33±10.27）ng/L、（35.62±8.45）pg/mL],差异具有统计学意义（P<0.05）。重度组的神经元特异性烯醇化酶（NSE）、S100钙结合蛋白β（S100β）分别为（25.45±5.69）μg/L、（60.45±10.31）ng/mL,均高于中度组[（22.18±5.36）μg/L、（55.27±10.46）ng/mL],轻度组[（19.44±5.37）μg/L、（50.49±10.25）ng/mL],差异具有统计学意义（P<0.05）。经Pearson相关性分析,PCI患者的CRP、IL-6、TNF-α等常见炎性指标水平与NSE、S100β等神经功能血清学指标水平正相关（P<0.05）。经检测,预后不良组的CRP、IL-6、TNF-α、mRS分别为（26.62±5.31）mg/L、（96.77±10.24）ng/L、（47.25±10.33）pg/mL、（4.24±1.33）分,均高于预后良好组[（23.75±5.44）mg/L、（91.25±10.37）ng/L、（41.12±10.44）pg/mL,（3.36±0.27）分],差异具有统计学意义（P<0.05）。经ROC曲线验证,CRP、IL-6、TNF-α等常见炎性指标水平越高,PCI患者的mRS评分越高（AUC均>0.85）。结论 CRP、IL-6、TNF-α等常见炎性指标会随PCI患者脑神经功能损伤程度加剧而不断升高,与病灶损害程度正相关;通过检测上述炎性指标能实现对患者不良预后的早期预测。

Objective To analyze the correlation between routine inflammatory indicators and the degree of lesion damage in progressive cerebral infarction（PCI） patients,as well as predictive efficacy of indicators on prognosis levels．Methods This is a retrospective study,with case enrollment from June 2021 to February 2023．The study subjects were 100 PCI patients．Based on the NIHSS score at admission,30 patients with a NIHSS score ≥ 21 were classified as the severe group,35 patients with a NIHSS score of 15~20 were classified as the moderate group,and 35 patients with a NIHSS score <15 were classified as the mild group．The neurological function serological and inflammatory indicators of the three groups of patients were compared．The correlation between inflammatory indicators and neurological serological indicators was verified by Pearson correlation coefficient．According to the occurrence of adverse prognosis,enrolled patients were divided into good prognosis group and poor prognosis group．The differences in inflammatory indicators and mRS scores between the two groups were compared,and the predictive power of inflammatory indicators on the prognosis level of PCI patients was evaluated by plotting ROC and observing AUC．Results After testing,the levels of CRP,IL-6 and TNF in the severe group were（26.44±5.18）mg/L,（95.28±10.46）ng/L and（45.24±10.31）pg/mL,respectively,higher than those in the moderate group[（23.12±5.46）mg/L,（90.44±10.17）ng/L and（40.25±10.18）pg/mL]and the mild group[（20.28±5.33）mg/L,（84.33±10.27）ng/L and（35.62±8.45）pg/mL]（P<0.05）．NSE and S100β in the severe group were（25.45±5.69）μg/L and（60.45±10.31）ng/mL,all higher than those in the moderate group[（22.18±5.36）μg/L,（55.27±10.46）ng/mL]and mild group[（19.44±5.37）μg/L,（50.49±10.25）ng/mL]（P<0.05）．According to Pearson correlation coefficient test,CRP,IL-6,TNF-α and mRS in PCI patients positively correlated with NSE,S100β（P<0.05）．After testing,CRP,IL-6,TNF-α and mRS in the group with poor prognosis were（26.62±5.31）mg/L,（96.77±10.24）ng/L,（47.25±10.33）pg/mL and（4.24±1.33）scores,respectively,which were higher than those in the group with good prognosis[（23.75±5.44）mg/L,（91.25±10.37）ng/L,（41.12±10.44）pg/mL and（3.36±0.27）scores]（P<0.05）．Verified by ROC curve,the higher the levels of CRP,IL-6 and TNF- α,the higher the mRS scores of PCI patients（AUC>0.85）．Conclusions Common inflammatory indicators such as CRP,IL-6 and TNF- α of PCI will continue to increase with the severity of brain nerve function damage in patients,and are positively correlated with the degree of lesions damage．By detecting the aforementioned inflammatory indicators,early prediction of poor prognosis can be achieved for patients．