Development and validation of a diagnostic prediction model for severe periventricular-intraventricular hemorrhage in newborns: insights from a retrospective analysis utilizing the MIMIC-III database

Abstract Objective: Periventricular-intraventricular hemorrhage is the most common type of intracranial bleeding in newborns, especially in the first 3 days after birth. Severe periventricular-intraventricular hemorrhage is considered a progression from mild periventricular-intraventricular hemorrhage and is often closely associated with severe neurological sequelae. However, no specific indicators are available to predict the progression from mild to severe periventricular-intraventricular in early admission. This study aims to establish an early diagnostic prediction model for severe PIVH. Method: This study was a retrospective cohort study with data collected from the MIMIC-III (v1.4) database. Laboratory and clinical data collected within the first 24 h of NICU admission have been used as variables for both univariate and multivariate logistic regression analyses to construct a nomogram-based early prediction model for severe periventricular-intraventricular hemorrhage and subsequently validated. Results: A predictive model was established and represented by a nomogram, it comprised three variables: output, lowest platelet count and use of vasoactive drugs within 24 h of NICU admission. The model's predictive performance showed by the calculated area under the curve was 0.792, indicating good discriminatory power. The calibration plot demonstrated good calibration between observed and predicted outcomes, and the Hosmer-Lemeshow test showed high consistency (p = 0.990). Internal validation showed the calculated area under a curve of 0.788. Conclusions: This severe PIVH predictive model, established by three easily obtainable indicators within the NICU, demonstrated good predictive ability. It offered a more user-friendly and convenient option for neonatologists.

A prediction model for coronary artery abnormalities in children with Kawasaki disease older than 5 years

Abstract Objective: Reliably prediction models for coronary artery abnormalities (CAA) in children aged > 5 years with Kawasaki disease (KD) are still lacking. This study aimed to develop a nomogram model for predicting CAA at 4 to 8 weeks of illness in children with KD older than 5 years. Methods: A total of 644 eligible children were randomly assigned to a training cohort (n = 450) and a validation cohort (n = 194). The least absolute shrinkage and selection operator (LASSO) analysis was used for optimal predictors selection, and multivariate logistic regression was used to develop a nomogram model based on the selected predictors. Area under the receiver operating characteristic curve (AUC), calibration curves, Hosmer-Lemeshow test, Brier score, and decision curve analysis (DCA) were used to assess model performance. Results: Neutrophil to lymphocyte ratio, intravenous immunoglobulin resistance, and maximum baseline z-score ≥ 2.5 were identified by LASSO as significant predictors. The model incorporating these variables showed good discrimination and calibration capacities in both training and validation cohorts. The AUC of the training cohort and validation cohort were 0.854 and 0.850, respectively. The DCA confirmed the clinical usefulness of the nomogram model. Conclusions: A novel nomogram model was established to accurately assess the risk of CAA at 4-8 weeks of onset among KD children older than 5 years, which may aid clinical decisionmaking.

Risk assessment of nosocomial infection in patients with multiple myeloma in the first hospitalization / 公共卫生与预防医学

Objective To assess the risk of nosocomial infection in patients with multiple myeloma during their first hospitalization. Methods Totally 480 patients with multiple myeloma who were hospitalized for the first time in department of hematology of West China Hospital, Sichuan University from August 2021 to August 2022 were included, and the nosocomial infection during treatment was statistically analyzed. The patients were divided into infected group and uninfected group. The independent influencing factors of nosocomial infection were analyzed and a prediction model was established. The reliability of the prediction model was analyzed by receiver operating characteristic curve (ROC). Results The incidence rate of nosocomial infection was 31.2% among 480 patients hospitalized for the first time. There were statistically significant differences in age, ISS staging, controlling nutritional status (CONUT) score, agranulocytosis, hemoglobin, and albumin between the infected group and the uninfected group (P<0.05). Logistic multivariate regression analysis showed that age, ISS staging, CONUT score, agranulocytosis, hemoglobin level, and albumin level were all independent correlated factors of nosocomial infection in patients with multiple myeloma hospitalized for the first time (P<0.05). The area under the ROC curve (AUC), sensitivity and specificity of multivariate logistic regression prediction model were 0.88 (95%CI: 0.840-0.920), 85.00% and 76.36%, respectively. Conclusion The incidence rate of nosocomial infection is high among patients with multiple myeloma in the first hospitalization. The prediction model established according to independent correlated factors of nosocomial infection has high predictive value on the occurrence of nosocomial infection.

A postoperative in-hospital mortality risk model for elderly patients undergoing cardiac valvular surgery based on LASSO-logistic regression / 中国胸心血管外科临床杂志

@#Objective     To evaluate the risk factors for postoperative in-hospital mortality in elderly patients receiving cardiac valvular surgery, and develop a new prediction models using the least absolute shrinkage and selection operator (LASSO)-logistic regression. Methods     The patients≥65 years who underwent cardiac valvular surgery from 2016 to 2018 were collected from the Chinese Cardiac Surgery Registry (CCSR). The patients who received the surgery from January 2016 to June 2018 were allocated to a training set, and the patients who received the surgery from July to December 2018 were allocated to a testing set. The risk factors for postoperative mortality were analyzed and a LASSO-logistic regression prediction model was developed and compared with the EuroSCOREⅡ. Results     A total of 7 163 patients were collected in this study, including 3 939 males and 3 224 females, with a mean age of 69.8±4.5 years. There were 5 774 patients in the training set and 1 389 patients in the testing set. Overall, the in-hospital mortality was 4.0% (290/7 163). The final LASSO-logistic regression model included 7 risk factors: age, preoperative left ventricular ejection fraction, combined coronary artery bypass grafting, creatinine clearance rate, cardiopulmonary bypass time, New York Heart Association cardiac classification. LASSO-logistic regression had a satisfying discrimination and calibration in both training [area under the curve (AUC)=0.785, 0.627] and testing cohorts (AUC=0.739, 0.642), which was superior to EuroSCOREⅡ. Conclusion     The mortality rate for elderly patients undergoing cardiac valvular surgery is relatively high. LASSO-logistic regression model can predict the risk of in-hospital mortality in elderly patients receiving cardiac valvular surgery.

Invasiveness assessment by CT quantitative and qualitative features of lung cancers manifesting ground-glass nodules in 555 patients: A retrospective cohort study / 中国胸心血管外科临床杂志

@#Objective     To explore the correlation between the quantitative and qualitative features of CT images and the invasiveness of pulmonary ground-glass nodules, providing reference value for preoperative planning of patients with ground-glass nodules. Methods    The patients with ground-glass nodules who underwent surgical treatment and were diagnosed with pulmonary adenocarcinoma from September 2020 to July 2022 at the Third Affiliated Hospital of Kunming Medical University were collected. Based on the pathological diagnosis results, they were divided into two groups: a non-invasive adenocarcinoma group with in situ and minimally invasive adenocarcinoma, and an invasive adenocarcinoma group. Imaging features were collected, and a univariate logistic regression analysis was conducted on the clinical and imaging data of the patients. Variables with statistical difference were selected for multivariate logistic regression analysis to establish a predictive model of invasive adenocarcinoma based on independent risk factors. Finally, the sensitivity and specificity were calculated based on the Youden index. Results     A total of 555 patients were collected. The were 310 patients in the non-invasive adenocarcinoma group, including 235 females and 75 males, with a meadian age of 49 (43, 58) years, and 245 patients in the invasive adenocarcinoma group, including 163 females and 82 males, with a meadian age of 53 (46, 61) years. The binary logistic regression analysis showed that the maximum diameter (OR=4.707, 95%CI 2.060 to 10.758), consolidation/tumor ratio (CTR, OR=1.027, 95%CI 1.011 to 1.043), maximum CT value (OR=1.025, 95%CI 1.004 to 1.047), mean CT value (OR=1.035, 95%CI 1.008 to 1.063), spiculation sign (OR=2.055, 95%CI 1.148 to 3.679), and vascular convergence sign (OR=2.508, 95%CI 1.345 to 4.676) were independent risk factors for the occurrence of invasive adenocarcinoma (P<0.05). Based on the independent predictive factors, a predictive model of invasive adenocarcinoma was constructed. The formula for the model prediction was: Logit(P)=–1.293+1.549×maximum diameter of lesion+0.026×CTR+0.025×maximum CT value+0.034×mean CT value+0.72×spiculation sign+0.919×vascular convergence sign. The area under the receiver operating characteristic curve of the model was 0.910 (95%CI 0.885 to 0.934), indicating that the model had good discrimination ability. The calibration curve showed that the predictive model had good calibration, and the decision analysis curve showed that the model had good clinical utility. Conclusion     The predictive model combining quantitative and qualitative features of CT has a good predictive ability for the invasiveness of ground-glass nodules. Its predictive performance is higher than any single indicator.

Randomized Controlled Trial and Correlation Analysis of Gandouling Tablet in Treatment of Abnormal Lipid Metabolism of Wilson's Disease with Turbid Phlegm and Blood Stasis / 中国实验方剂学杂志

ObjectiveTo investigate the clinical efficacy of Gandouling tablet （GDL） on abnormal lipid metabolism in Wilson's disease （WD） and the correlation between the prediction model of hepatic steatosis and the related indexes of lipid metabolism in WD. MethodA total of 86 patients with abnormal lipid metabolism in WD were selected. The 24-hour urine copper， alanine aminotransferase （ALT）， aspartate aminotransferase （AST）， serum triglyceride （TG）， total cholesterol （TC）， apolipoprotein B （ApoB）， low density lipoprotein cholesterol （LDL-C）， bile acid （BA）， γ-glutamyl transferase （GGT）， prediction model of hepatic steatosis ［hepatic steatosis index （HSI） and Zhejiang University index （ZJU index）］， ultrasonic attenuation coefficient imaging （ATT）， and traditional Chinese medicine （TCM） syndrome score were statistically analyzed before treatment. Pearson correlation test was used to analyze the correlation between TG， TC， LDL-C， ApoB， ALT， AST， ALT/AST， BA， GGT， TCM syndrome score， ATT， and HIS and ZJU. The patients were divided into an observation group and a control group by random number table method， with 43 cases in each group. The observation group was treated with GDL combined with sodium dimercaptopropane sulfonate （DMPS）， while the control group was only treated with DMPS as a control. After six courses of treatment， 24-hour urine copper， TC， TG， LDL-C， ApoB， HSI， ZJU， ATT， TCM syndrome score， and clinical efficiency before and after treatment were observed and compared between the two groups. The correlation between HSI and ZJU and serum TC， TG， LDL-C， ApoB， ALT， AST， ALT/AST， BA， GGT， TCM syndrome scores， and ATT was analyzed. ResultPearson correlation analysis showed that serum TC （r = 0.811）， TG （r = 0.826）， LDL-C （r = 0.802）， ApoB （r = 0.820）， ALT （r = 0.497）， ALT/AST （r = 0.826）， TCM syndrome score （r = 0.716）， and ATT （r = 0.736） were positively correlated with HSI （P<0.01）， while AST， BA， and GGT had no significant correlation with HSI. TC （r = 0.718）， TG （r = 0.765）， LDL-C （r = 0.667）， ApoB （r = 0.699）， ALT/AST （r = 0.403）， TCM syndrome score （r = 0.666）， and ATT （r = 0.684） were positively correlated with ZJU （P<0.01）. ALT， AST， BA， and GGT had no significant correlation with ZJU. The total effective rate of the observation group was 86.05 （37/43）， and that of the control group was 72.09% （31/43）. The total effective rate of the observation group was higher than that of the control group （Z = -2.301， P<0.05）. After treatment， the 24-hour urine copper of the two groups increased significantly. The levels of TC， TG， LDL-C， and ApoB were significantly decreased， and the HSI， ZJU， and ATT were significantly decreased （P<0.01）. Compared with those in the control group after treatment， the above indexes improved better in the observation group （P<0.05， P<0.01）. ConclusionGDL can effectively improve the level of copper and lipid metabolism in patients with WD， with high clinical safety and good clinical application value. The prediction model of hepatic steatosis can effectively reflect the degree of abnormal lipid metabolism in WD.

Establishment and verification of a prognostic nomogram for survival of tongue squa-mous cell carcinoma patients who underwent cervical dissection / 北京大学学报(医学版)

Objective:To evaluate the prognostic significance of inflammatory biomarkers,prognostic nutritional index and clinicopathological characteristics in tongue squamous cell carcinoma(TSCC)patients who underwent cervical dissection.Methods:The retrospective cohort study consisted of 297 patients undergoing tumor resection for TSCC between January 2017 and July 2018.The study population was divided into the training set and validation set by 7:3 randomly.The peripheral blood indices of interest were preoperative neutrophil-to-lymphocyte ratio(NLR),lymphocyte-to-monocyte ratio(LMR),platelet-to-lymphocyte ratio(PLR),systemic immune-inflammation index(SII),systemic inflammation score(SIS)and prognostic nutritional index(PNI).Kaplan-Meier survival analysis and multivariable Cox regression analysis were used to evaluate independent prognostic factors for overall survival(OS)and disease-specific survival(DSS).The nomogram's accuracy was internally validated using concordance index,receiver operating characteristic(ROC)curve,area under the curve(AUC),calibration plot and decision curve analysis.Results:According to the univariate Cox regression analysis,clinical TNM stage,clinical T category,clinical N category,differentiation grade,depth of invasion(DOI),tumor size and pre-treatment PNI were the prognostic factors of TSCC.Multivariate Cox regression analysis revealed that pre-treatment PNI,clinical N category,DOI and tumor size were independent prognostic factors for OS or DSS(P＜0.05).Positive neck nodal status(N≥1),PNI≤50.65 and DOI＞2.4 cm were associated with the poorer 5-year OS,while a positive neck nodal status(N≥1),PNI≤50.65 and tumor size＞3.4 cm were associated with poorer 5-year DSS.The concordance index of the nomograms based on independent prognostic factors was 0.708(95％CI,0.625-0.791)for OS and 0.717(95％CI,0.600-0.834)for DSS.The C-indexes for external validation of OS and DSS were 0.659(95％CI,0.550-0.767)and 0.780(95％CI,0.669-0.890),respectively.The 1-,3-and 5-year time-dependent ROC analyses(AUC=0.66,0.71 and 0.72,and AUC=0.68,0.77 and 0.79,respec-tively)of the nomogram for the OS and DSS pronounced robust discriminative ability of the model.The calibration curves showed good agreement between the predicted and actual observations of OS and DSS,while the decision curve confirmed its pronounced application value.Conclusion:Pre-treatment PNI,clinical N category,DOI and tumor size can potentially be used to predict OS and DSS of patients with TSCC.The prognostic nomogram based on these variables exhibited good accurary in predicting OS and DSS in patients with TSCC who underwent cervical dissection.They are effective tools for predicting sur-vival and helps to choose appropriate treatment strategies to improve the prognosis.

Establishment and validation of nomogram of cancer specific survival of patients with hepatocellular carcinoma with negative alpha fetoprotein based on SEER Database / 吉林大学学报(医学版)

Objective:To discuss the factors related to the prognosis in the alpha fetoprotein(AFP)negative hepatocellular carcinoma(HCC)patients,and to construct the nomogram for predicting the survival time of the patients.Methods:The retrospective analysis on data of 2 064 cases of AFP negative HCC patients extracted from the Surveillance,Epidemiology,and End Results(SEER)Database was conducted,and all the patients were divided into training cohort and internal validation cohort at a ratio of 7∶3,and 101 AFP negative HCC patients from the Integrated Traditional Chinese and Western Medicine Hospital in Hunan Province were regarded as the external validation cohort.The univariate Cox regression analysis results were incorporated into the multivariate analysis,and the independent risk factors for the AFP negative HCC patients were obtained by multivariate Cox analysis to build a cancer specific survival(CSS)prognosis nomogram for the AFP negative HCC patients.The predictive efficacy and clinical utility of the nomogram were evaluated by time-dependent receiver operating characteristic curve(ROC),calibration plots,and decision curve analysis(DCA).The total score obtained from the nomogram was used for the risk stratification to compare the degree of risk discrimination between the nomogram and the American Joint Committee on Cancer(AJCC)staging system.Results:Ten independent risk factors were selected by multivariate Cox regression analysis to construct 3-year,4-year,and 5-year CSS prognostic nomograms for the AFP negative HCC patients,including the patient's age,pathological grade,surgical status,radiotherapy status,chemotherapy status,lung metastasis status,tumor size,tumor T stage,tumor M stage,and marital status.The area under curve(AUC)for the 3-year,4-year,and 5-year time-dependent ROC in the training cohort were 0.807(95%CI:0.786-0.828),0.804(95%CI:0.782-0.826),and 0.813(95%CI:0.790-0.835),respectively.In the internal validation cohort,they were 0.776(95%CI:0.743-0.810),0.772(95%CI:0.737-0.808),and 0.789(95%CI:0.752-0.826),and in the external validation cohort,they were 0.773(95%CI:0.677-0.868),0.746(95%CI:0.620-0.872),and 0.736(95%CI:0.577-0.895).The calibration plots verified that the nomogram fitted well with the perfect line.The DCA curve revealed that the net benefit of the nomogram was significatly higer than that of the AJCC staging system at certain probability thresholds compared with AJCC staging,the nomogram had a better ability to identify high-risk individuals.Conclusion:The serum AFP expression is one of the prognostic markers for the HCC patients.For those patients with AFP negative expression in serum,different considerations should be taken.The nomogram model based on multiple risk factors is a promising clinical tool for assessing the CSS in the AFP negative HCC patients.

Construction of unplanned offline prediction model for IHD two-stage citrate anticoagulation / 重庆医学

Objective To study the risk factors of two-stage citrate anticoagulation in intermittent he-modialysis(IHD)and to establish an unplanned offline prediction model.Methods A retrospective analysis was conducted to include 34 patients and 118 times of treatment with two-stage citrate anticoagulation for IHD in the hospital from January 2019 to February 2023.According to whether the treatment did not reach the treatment time due to the coagulation of the extracorporeal circulation pipeline,118 treatments were divid-ed into the planned units(n=111)and the unplanned units(n=7).Univariate and multivariate logistic re-gression analysis were used to analyze the risk factors of unplanned weaning,and a risk prediction model was established.The receiver operating characteristic(ROC)curve was used to analyze the predictive value of the regression model.Results Univariate analysis showed that there were statistically significant differences in hematocrit(HCT),platelet count(PLT),activated partial thromboplastin time(APTT),and treatment mode between the planned and unplanned units(P<0.05).Multivariate logistic regression analysis showed that HCT and APTT were independent influencing factors for unplanned weaning(P<0.05).The HCT level was represented by A,the APTT level was represented by B,and the prediction model was:Logit(P)=1.304+ 0.206×A-0.378×B.The area under the ROC curve(AUC)of the prediction model was 0.912(95%CI:0.825-0.995,P<0.001),the maximum Youden index was 0.782,the cut off value was 0.113,the sensitivity was 85.7%,and the specificity was 92.5%.Conclusion The prediction model established by multivariate logistic regression analy-sis can make a preliminary judgment on whether coagulation occurs in two-stage IHD treatment.

Construction of risk prediction model for predicting death or readmission in acute heart failure patients during vulnerable phase based on machine learning / 陆军军医大学学报

Objective To construct risk prediction models of death or readmission in patients with acute heart failure(AHF)during the vulnerable phase based on machine learning algorithms and screen the optimal model.Methods A total of 651 AHF patients with admitted to Department of Cardiology of the Second Affiliated Hospital of Army Medical University from October 2019 to July 2021 were included.The clinical data consisting of admission vital signs,comorbidities and laboratory results were collected from electronic medical records.The composite endpoint was defined as all-cause death or readmission for worsening heart failure within 3 months after discharge.The patients were divided into a training set(521 patients)and a test set(130 patients)in a ratio of 8:2 through the simple random sampling.Six machine learning models were developed,including logistic regression(LR),random forest(RF),decision tree(DT),light gradient boosting machine(LGBM),extreme gradient boosting(XGBoost)and neural networks(NN).Receiver operating characteristic(ROC)curve and decision curve analysis(DCA)were used to evaluate the predictive performance and clinical benefit of the models.Shapley additive explanation(SHAP)was used to explain and evaluate the effect of different clinical characteristics on the models.Results A total of 651 AHF patients were included,of whom 203 patients(31.2%)died or were readmitted during the vulnerable phase.ROC curve analysis showed that the AUC values of the LR,RF,DT,LGBM,XGBoost and NN model were 0.707,0.756,0.616,0.677,0.768 and 0.681,respectively.The XGBoost model had the highest AUC value.DCA showed that the XGBoost model exhibited greater clinical net benefit compared with other models,with the best predictive performance.SHAP algorithm analysis showed that the clinical features that had the greatest impact on the output of the model were serum uric acid,D-dimer,mean arterial pressure,B-type natriuretic peptide,left atrial diameter,body mass index,and New York Heart Association(NYHA)classification.Conclusion The XGBoost model has the best predictive performance in predicting the risk of death or readmission of AHF patients during the vulnerable phase.

Construction of predictive model for early allograft dysfunction after liver transplantation / 陆军军医大学学报

Objective To analyze the factors related to early allograft dysfunction(EAD)after liver transplantation and to construct a predictive model.Methods A total of 375 patients who underwent liver transplantation in our hospital from December 2008 to December 2021 were collected,including 90 patients with EAD and 266 patients without EAD.Thirty items of baseline data for the 2 groups were compared and analyzed.Aftergrouping in a ratio of 7∶3,univariate and multivariate logistic regression analyses were used in the training set to evaluate the factors related to EAD and construct a nomogram.Receiver operating characteristic(ROC)curve,decision curve analysis(DCA),sensitivity,specificity,positive predictive value,negative predictive value,Kappa value and other indicators were used to evaluate the model performance.Results The incidence of EAD after liver transplantation was 24%.Multivariate logistic regression analysis showed that preoperative tumor recurrence history(OR=3.15,95%CI:1.28～7.77,P=0.013)and operation time(OR=1.22,95%CI:1.04～1.42,P=0.015)were related to the occurrence of EAD after surgery.After predicting the outcome according to the cut-off point of 0.519 identified by the Youden index,the model performance in the both training set and validation set was acceptable.DCA suggested the model has good clinical applicability.Conclusion The risk factors for EAD after liver transplantation are preoperative tumor recurrence history and operation time,and the established model has predictive effect on prognosis.

Factors affecting nosocomial death in elderly patients with COVID-19 and construction of a risk predictive model / 基础医学与临床

Objective To study the factors affecting hospital death in elderly patients with novel coronavirus infec-tion/disease 2019(COVID-19),and to build a risk prediction model.Methods According to the diagnostic criteria of Diagnosis and Treatment Protocol for COVID-19 Infection(Trial 10th Edition).Totally 775 elderly patients(≥60 years old)diagnosed as COVID-19 infection in the emergency department and fever clinic of the First Hospital of Changsha were selected as the research objects.General data and serum biomarkers of patients were collected.After treatment,the patients'data were divided into survival group and hospital death group.Binary Logistic regres-sion was used to screen the independent influencing factors of death,and ROC curve was used to analyze the pre-dictive value of related indicators on hospital death.Results After treatment,712 patients(91.9%)survived and 63 patients(8.3%)died in hospital.Binary Logistic regression analysis showed that:≥90 years old[OR=5.065,95%CI(1.427,17.974)],type 2 diabetes mellitus[OR= 3.757,95%CI(1.649,8.559)],COPD[OR= 5.625,95%CI(2.357,13.421)],monocyte ratio[OR=0.908,95%CI(0.857,0.963)],plasma fibringen[OR=1.376,95%CI(1.053,1.800)]and lactate dehydrogenase[OR=1.005,95%CI(1.001,o1.008)]were independent factors of in-hospital death(P＜0.05).The predictive value of diabetes mellitus+COPD+age+monocyte ratio+plasma fibrinogen+lactate dehydrogenase was proved in hospital death from COVID-19 infected patients:the area under the curve(AUC)was 0.883(95%CI:0.827,0.940,P＜0.001),the critical value≥0.710 suggested the risk of death in hospital,the specificity was 0.851,the sensitivity was 0.857.Conclusions The hospital mortality of the elderly after COVID-19 infection is higher and closely related to type 2 diabetes,COPD,monocyte ratio,plasma fibrinogen and lactate dehydrogenase.

The nomogram based on preoperative inflammatory biomarkers used for predicting the prognosis of HCC patients treated with transcatheter arterial chemoembolization:its construction and validation / 介入放射学杂志

Objective To construct and validate a predictive model based on preoperative inflammatory biomarkers,and to evaluate its ability in predicting the prognosis of patients with unresectable hepatocellular carcinoma(HCC)after receiving transcatheter arterial chemoembolization(TACE).Methods A total of 544 patients with HCC,who received TACE as the initial treatment at six medical institutions between January 2007 and December 2020,were retrospectively collected.The patients were divided into training cohort(n=376)and validation cohort(n=168).LASSO algorithm and Cox regression analysis were used to screen out the independent influencing factors and to make modelling.The model was validated based on the discrimination,calibration and clinical applicability,and the Kaplan-Meier risk stratification curves were plotted to determine the prognostic differences between groups.The likelihood ratio chi-square value,R2 value,akaike information criterion(AIC)value,C-index and AUROC value of the model were calculated to determine its accuracy and efficiency.Results The training cohort and validation cohort had 376 participants and 168 participants respectively.Multivariate analysis indicated that BCLC,tumor size,number of tumor lesions,neutrophil and prognostic nutritional index(PNI)were the independent influencing factors for postoperative overall survival(OS),with all P being＜0.05;the BCLC grade,tumor size,number of tumor lesions,NLR,PNI and PS score were the independent influencing factors for progression-free survival(PFS),with all P being＜0.05.The C-indexes of the OS and PFS models were 0.735(95％ CI=0.708-0.762)and 0.736(95％ CI=0.711-0.761)respectively,and the external validation was 0.721(95％ CI=0.680-0.762)and 0.693(95％ CI=0.656-0.730)respectively.Ideal discrimination ability of the nomogram was exhibited in time-dependent C-index,time-dependent ROC,and time-dependent AUC.The calibration curves significantly coincided with the ideal standard lines,indicating that the model had high stability and low over-fitting level.Decision curve analysis revealed that there was a wider range of threshold probabilities and it could augment net benefits.The Kaplan-Meier curves for risk stratification indicated that the prognosis of patients varied dramatically between risk categories(P＜0.000 1).The Kaplan-Meier curves for risk stratification indicated that the prognosis of patients varied dramatically among different risk groups(P＜0.000 1).The likelihood ratio chi-square value,R2 value,AIC value,C-index and AUROC value of the model were better than those of other models commonly used in clinical practice.Conclusion The newly-developed prognostic nomogram based on preoperative inflammatory indicators has excellent accuracy as well as excellent prediction effect in predicting the prognosis of patients with unresectable HCC after receiving TACE,therefore,it can be used as an effective tool for guiding individualized treatment and for predicting prognosis.(J Intervent Radiol,2024,33:245-258)

Construction and efficacy evaluation of a short-term prognostic model for emergency patients with acute ischemic cerebral stroke / 中华急诊医学杂志

Objective:To establish a 14-day prognosis model for emergency patients with acute ischemic cerebral stroke and evaluate its predictive efficacy.Methods:A prospective cohort study was conducted. Patients with acute ischemic stroke admitted to the emergency department of Beijing Bo’ai Hospital within 72 hours of onset from October 2018 to December 2020 were enrolled. Univariate and multivariate logistic regression analysis were used to screen the risk factors of poor prognosis. The ROC curve was drawn to determine the cut-off value of continuous variables and discretise data with reference to clinical practice. The corresponding scores were set up according to the β regression coefficient of each variable, and the clinical scale prediction model of short-term prognosis of acute cerebral infarction was established. Patients with ischemic stroke in the hospital from January to December 2021 were selected as the internal validation, to verify the constructed predictive model.Results:A total of 321 patients were included in the study, including 223 in the training set and 98 in the internal validation set. Multivariate logistic regression analysis showed that age, hypersensitive C-reactive protein, prealbumin (PA), infarct volume, Frailty Screening Questionnaire (FSQ) and National Institute of Health Stroke Scale (NIHSS) were independent risk factors for poor short-term prognosis of acute cerebral infarction. The total score of the clinical prediction scoring system for short-term prognosis of acute cerebral infarction in the emergency department was 15 points, including age ≥74 years (1 point), PA ≤373 mg/L (2 points), large artery atherosclerosis (1 point), cardiogenic embolism (2 points), infarct volume ≥ 2.18 cm 3 (2 points), FSQ ≥3 points (1 point), NIHSS ≥4 points (6 points); The area under the ROC curve (AUC) of the scoring system for predicting short-term poor prognosis of acute cerebral infarction was 0.927 (95% CI: 0.894-0.960). The optimal cut-off value was ≥5 points, and the sensitivity and specificity were 0.770 and 0.976, respectively. In the internal validation set, the scoring system had similar predictive value for poor outcomes (AUC=0.892, 95% CI:0.827-0.957). Conclusion:The scoring system for short-term prognosis prediction of acute ischemic cerebral infarction has good diagnostic efficacy, and could guide clinicians to judge the prognosis of emergency patients in the early stage.

Predictive model for extubation delay undergoing non-emergency major surgery based on random forest algorithm / 临床麻醉学杂志

Objective To construct and validate a clinical prediction model for delayed extubation undergoing non-emergency major surgery based on the random forest algorithm.Methods Clinical data of 7 528 patients undergoing non-emergency major surgery under general anesthesia from January 2018 to De-cember 2022 were retrospectively collected.The patients were divided into two groups according to whether extubation was performed within 2 hours after surgery:non-delayed extubation group(≤2 hours)and de-layed extubation group(＞2 hours).All the patients were randomly divided into a training set and a valida-tion set in a ratio of 7 ∶ 3.The predictive factors for delayed extubation after surgery were screened through LASSO regression and Logistic regression.The random forest model was established and verified by random forest algorithm.Results There were 123 patients(1.6%)experienced delayed extubation after surgery.ASA physical status,department,intraoperative use of flurbiprofen ester,dexmedetomidine,glucocorticoid,hypocalcemia,severe anemia,intraoperative blood transfusion,and airway spasm were identified as inde-pendent predictive factors for delayed extubation.The area under curve(AUC)value of the random forest prediction model in the validation set was0.751(95%CI0.742-0.778),and the sensitivity was98.1%,and the specificity was 41.9%.Conclusion The predictive model of delayed extubation undergoing non-e-mergency major surgery based on random forest algorithm has a good predictive value,which may be helpful to prevent delayed extubation undergoing non-emergency major surgery.

Analysis of risk factors of postoperative venous thromboembolism in patients with gastric cancer and establishment of prediction model / 临床外科杂志

Objective To explore the related risk factors of postoperative venous thromboembolism(VTE)in patients with gastric cancer,establish a prediction model and verify the predictive value of the model.Methods 160 gastric cancer patients who underwent radical surgery at the First Affiliated Hospital of Hainan Medical College from January 2019 to June 2021 were included as the modeling group,167 cases as validation group.Their clinicopathological data were collected.All modeling group patients were divided into VTE group and N-VTE group according to the occurrence of VTE within 6 months after operation.The clinicopathological factors of the two groups were analyzed by univariate analysis.Then,the statistically significant indexes in the univariate analysis were substituted into the multivariate logistic regression model for multivariate analysis to obtain the independent risk factors affecting the postoperative VTE of patients with gastric cancer.The independent risk factors obtained based on the results of multivariate analysis were combined p Value,assign scores to independent risk factors according to the principle of nomogram,construct the nomogram model,draw the nomogram with R software,internal and external validation of nomogram model with Bootstrap method and calibration curve,calculate the discrimination evaluation Index C index,and evaluate the calibration ability of the prediction model through goodness of fit(H-L).Results 160 modeling group patients with gastric cancer underwent radical gastrectomy.According to the occurrence of VTE within 6 months after operation,they were divided into VTE group(23 cases)(14.38％)and N-VTE group(137 cases)(85.62％).Multivariate analysis showed that the age of 60 years old,the diameter of the lesion was more than 5 cm,the stage of diabetes,the TNM/T stage was 3-4,and the lymph node metastasis was the independent risk factors affecting the postoperative VTE of patients with gastric cancer(P＜0.05).Construct nomogram:P=1/(1+e-x),X=1.885 × Age(≥ 60 years=1,＜60 years=0)+2.051 × Diabetes mellitus(=1,no=0)+2.646 × Lesion diameter(≥ 5 cm=1,＜5 cm=0)+2.952 × TNM/T stage(stage 1-2=0,stage 3-4=1)+0.694 × Lymph node metastasis(yes=1,no=0)-0.436.The C index of nomogram model was 847(95％CI:0.784-0.932)and 0.832(95％CI:0.772-0.910).H-L test showed that the predicted value of postoperative VTE in patients with gastric cancer was in good agreement with the actual value(P＞0.05).Conclusion A nomogram model for predicting the risk of postoperative VTE in patients with gastric cancer was established.It was verified that the model can accurately predict the risk of postoperative VTE in patients with gastric cancer.

Construction and Validation of A Prediction Model for Pulmonary Nodule Nature Based on Clinicopathological Features,Imaging and Serum Biomarkers / 现代检验医学杂志

Objective The study aimed to construct and validate a predictive model for pulmonary nodules(PN)nature based on clinicopa-thological features,imaging,and serum biomarkers,so as to provide scientificdecision-making for early diagnosis and treatment of lung cancer.Methods A retrospective was performed on 816 PN patients with definited pathological diagnosis who received surgical resection analysisor lung biopsy in the Department of Thoracic Surgery and Oncology of Shenzhen Traditional Chinese Medicine Hospital from January 2019 to February 2023.Among them,113 cases that did not meet the inclusion criteria were excluded,and the remaining 703 cases were included in the study.The study based on the clinicopathologic features(age,gender,smoking history,smoking cessation history and family history of cancer),chest imaging(maximum diameter of nodule,location of lesion,clear border,Lobulation,spiculation,vascular convergence sign,vacuole,calcification,air bronchial sign,emphysema,nodule type and pleural indentation,nodule number)and serum carcinoembryonic antigen(CEA),cytokeratin 19 fragment(CYFRA21-1),squamous cell carcinoma antigen(SCCA)in patients with PN.These cases were randomly divided into a modeling group(n=552,237 benign,315 malignant)and a validation group(n=151,85 benign,66 malignant).First,univariate analysis was performed to screen for statistically significant predictors of nodules nature.Then,multivariate regression analysis was performed to screen for independent predictors of nodules nature.Finally,the prediction model of PN nature was constructed by logistic regression analysis.Subsequently,the validation group data were entered into the proposed model and Mayo clinic(Mayo)model,veterans affairs(VA)model,Brock University(Brock)model,Peking University(PKU)model and Guangzhou Medical University(GZMU)model,respectively.PN malignancy probability was calculated.The receiver operating characteristic(ROC)curves were plotted.The diagnostic efficiency of each model was compared according to the area under the curve(AUC).Results There were statistically significant variables including age,family history of cancer,maximum nodule diameter,nodule type,upper lobe of lung,calcification,vascular convergence sign,lobulation,clear border,spiculation,and serum CEA,SCCA,CYFRA21-1 using univariate analysis.Multiple regression analysis showed that age,CEA,clear border,CYFRA21-1,SCCA,upper lobe of lung,maximum nodule diameter,family history of cancer,spiculation and nodule type were independent predictors of PN nature.The prediction model equation constructed in this study is as follows:f(x)= ex/(1+ex),X=(-6.318 8+0.020 8×Age+0.527 4×CEA-0.928 4×clear border+0.294 6×Cyfra21-1+0.294×maximum nodule diameter+1.220 1×family history of cancer +0.573 2×upper lobe of lung +0.064 8×SCCA +1.461 5×Spiculation +1.497 6×nodule type).The AUC(0.799 vs 0.659,0.650)of the proposed model was significantly higher compared with Mayo model and VA model,and there were statistically significant differences(Z=3.029,2.638,P=0.003,0.008).However,compared with Brock model,PKU model and GZMU model,the differences of AUC(0.799 vs 0.762,0.773,0.769)were not statistically significant(Z=1.063,0.686,0.757,P=0.288,0.493,0.449).Conclusion The prediction model for PN nature established in this study is accurate and reliable,which can help clinics with early diagnosis and early intervention,and this prediction model deserves to be popularized.

Construction and Validation of Prediction Model of Gestational Diabetes Mellitus Based on Multivariate Regression Analysis in the First Trimester of Pregnancy / 现代检验医学杂志

Objective To explore the risk factors of gestational diabetes mellitus(GDM)in the first trimester(12～13+6 weeks)of pregnancy,build a prediction model and verify it.Methods 433 singleton pregnant women delivered in the First People's Hospital of Shanghai from January 2020 to December 2020 were selected.They were divided into GDM group(n=188)pregnant women and non-GDM group(n=245)pregnant women according to a 75g glucose tolerance test results at 24～28 weeks of gestation.The electrochemiluminescence method measured serum biochemical indexes in early pregnancy,and glycosylated hemoglobinAlc was measured by ion exchange high-performance liquid chromatography.Using logistic regression analysis to screen the risk factors of GDM and construct a predictive model,draw the subject's work characteristic curve to analyze the model's predictive value.Ninety-five pregnant women who underwent prenatal examinations at Shanghai First People's Hospital from January 2021 to June 2021 were selected to validate the model's effectiveness.Results Compared with the non-GDM group,the level of body mass index(BMI)(23.41±11.17 kg/m2 vs 21.18±2.88 kg/m2),gamma-glutamyl transpeptidase(γ-GGT)(16.61±10.62 U/L vs 14.00±8.35 U/L),triacylglycerol(TG)(1.90±0.58 mmol/L vs 1.57±0.55 mmol/L),glycosylated hemoglobinAlc(HbAlc)(5.25%±0.47%vs 5.07±0.34%),fasting blood glucose(FBG)(4.68±0.47 mmol/L vs 4.36±0.36 mmol/L),LDL/HDL(1.53±0.49 vs 1.41±0.50),TG/HDL(2.93±0.59 vs 2.71±0.58),and TC/HDL(1.19±0.49 vs 0.95±0.45)in GDM group was increased,and the level of highdensity lipoprotein-cholesterol(HDL)(1.69±0.39 mmol/L vs 1.77±0.41 mmol/L)was decreased,the differences were statistically significant(t=2.613,2.818,5.874,4.582,17.701,2.458,3.815,5.310,-2.187,all P＜0.05).Logistic regression analysis showed that pre-pregnancy BMI,FBG,HbAlc,TG,and TC/HDL were all independent risk factors for predicting gestational diabetes(Waldχ2=4.48～35.549,all P＜0.05).The prediction model constructed based on the selected risk factors was as follows:Logit(P)=-20.562+0.085(BMI)+1.921(FBG)+1.57(HbAlc)+2.248(TG)-2.302(TC/HDL).The model predicts that the area under the curve of GDM was 0.800(95%CI:0.757～0.842),the optimal cutoff value was 0.352,and the sensitivity and specificity were 80.00%and 66.00%,respectively.Ninety-five pregnant women validated the model,and its sensitivity,specificity,and accuracy were 84.50%,91.00%,and 85.30%,respectively.Conclusion The prediction model constructed by BMI combined with FBG,HbAlc,TG and TC/HDL in the first trimester(12～13+6 weeks)of pregnancy has a high predictive value for GDM.

Establishment of a Predictive Model for Induced Abortion Failure in Term Sin-gle Pregnancy Pregnant Women / 实用妇产科杂志

Objective:To analyze the influencing factors of failed induction of labor(IOL)in full-term singleton pregnant women,and to establish a prediction model for failed IOL.Methods:This study retrospectively analyzed the clinical data of 1483 pregnant women with full-term singleton of IOL in the Department of Obstetrics and Gy-necology,Heping Branch of General Hospital of Northern War Zone from January 1,2019 to December 31,2019.According to the outcome of IOL,the pregnant women were divided into the successful group(1108 cases)and the failed group(375 cases)of IOL.The influencing factors of failed IOL were screened to establish the prediction model through multivariate Logistic regression analysis.The receiver operating characteristic(ROC)curves and Hosmer-Lemeshow test were used to assess the predictive performance and fitting degree of the model.Results:Multivariate Logistic regression analysis showed that there were risk factors for failed IOL(OR>1,P<0.05),in-cluding elderly primiparous delivery,with no history of vaginal delivery,education level≤12 years,gestational age<40 weeks,pre-pregnancy overweight or obesity,excessive gestational weight gain,height<160 cm,cervical Bishop score before IOL<4 points,neonatal weight≥3750 g,combined IOL,suspected fetal distress,and the time from IOL to onset of labor≥24 hours,and height≥165 cm,IOL with dinoprostol suppositories were protective fac-tors for failed IOL(OR<1,P<0.05).Antepartum factors and antepartum factors combined with intrapartum fac-tors were separately used to establish model for predicting failed IOL.The area under the ROC curve(AUC)were 0.914 and 0.940,and the Youden index were 0.660 and 0.733,respectively.The prediction accuracy were 87.5%and 88.9%,respectively.Conclusions:This study screened the significant influencing factors of failed IOL,providing a theoretical basis for clinical measures to improve the success rate of IOL and constructing a pre-diction model of failed IOL,which is helpful for obstetricians and pregnant women to decide the mode of delivery together,and ensure the safety of mother and baby;on the other hand,it aims to enhance everyone′s awareness of pregnancy health care and improve the vaginal delivery rate.

Construction and validation of predictive model for the risk of stigma in enterostomy patients / 中国实用护理杂志

Objective:To explore the influencing factors of stigma and to construct a nomogram model for stigma perceptionin enterostomy patients. The basis for prevention of stigmatization in enterostomy patients.Methods:This was a prospective survey. By convenient sampling, 300 with enterostomy patients from the stoma clinic of the Sixth Medical Center of PLA General Hospital from March 2022 to July 2023 were investigated. Univariate analysis and logistic regression were explored the risk factors of stigma.R 4.2.2 software was constructed a nomogram to achieve the visualization display. Using receiver operating characteristic curve, Hosmer-Leme show test and calibration curves tested model predictive performance.Results:Totally 284 valid questionnaires were ultimately collected, including 161 males and 123 females. There were 21 cases aged 20-40, 117 cases aged 41-60, and 146 cases aged 60 and above. The incidence of stigma among 284 patients was 69.37% (197/284). Predictive model was constructed and validated based on six risk factors: fecal status ( OR=0.63, 95% CI 0.42-0.95), level of accept from spouse ( OR=0.56, 95% CI 0.34-0.94), body image change ( OR=0.51, 95% CI 0.28-0.91), effectiveness of WeChat platform ( OR=0.31, 95% CI 0.13-0.78), support from friends ( OR=0.34, 95% CI 0.14-0.82), confidence diet ( OR=0.37, 95% CI 0.19-0.71). The area under the ROC curve of the modeling group was 0.837, with a sensitivity of 0.923 and a specificity of 0.649. The area under the ROC curve of the validation group was 0.841, with a sensitivity of 0.846 and a specificity of 0.740. Conclusions:This study had a good prediction effect in constructing a model. The model can provide reference for medical staff to quickly identify the risk of stigma and in a timely manner take preventive management measuresin enterostomy patients.