OBJECTIVE To upgrade the drug traceability code management system for a pediatric hospital under the “payment by code” background， aiming to comprehensively enhance traceability integrity， efficiency， and compliance. METHODS Taking Xiamen Children’s Hospital as the implementation setting， a before-and-after control design was adopted to construct an intelligent drug traceability code management system through systematic upgrades involving the technology platform， core mechanisms， and coordination with medical insurance. Key interventions included： upgrading a traceability code management platform and designing a dynamic code pool； innovating differentiated traceability mechanisms for routine， split-dose， and special drugs； establishing a tiered early-warning and emergency response system； and constructing a data coordination and quality control system. The drug traceability code upload rate served as the primary outcome. Process indicators such as the root causes distribution of failed uploads and the duration of medication returns， and a comprehensive outcome （the number of insurance-flagged abnormal prescriptions） were also analyzed. The data between the baseline period （April 2025） and the observation period （June-August 2025） were compared and evaluated. RESULTS After the upgrade， the overall upload rate of drug traceability codes increased from 9.21% （baseline） to 99.86% （August 2025）. The upload rate of traceability codes in previously unmanaged areas， such as the inpatient pharmacy and pharmacy intravenous admixture services， soared from 0 to nearly 100%. The proportion of non-uploads due to system issues fell from 66.44% （June 2025） to 2.62% （August Additionally， the number of insurance-flagged） abnormal prescriptions dropped sharply from 2 275.00 in the first “payment by code” policy month （July 2025） to 212.00 by the end of the observation period （August 2025）， a 90.70% decrease. CONCLUSIONS The developed management system effectively addresses complex scenario challenges such as high-frequency drug splitting. It significantly enhances traceability code upload performance and ensures a high degree of compliance with medical insurance data requirements. These outcomes contribute to proactive risk mitigation against insurance claim denials and demonstrate a concurrent optimization of pharmacy operations.

The implantation of left ventricular assist device (LVAD) has significantly improved the quality of life for patients with end-stage heart failure. However, it is associated with the risk of complications, with unplanned readmissions gaining increasing attention. This article reviews the influencing factors, prediction methods and models, and intervention measures for unplanned readmissions in LVAD patients, aiming to provide scientific guidance for clinical practice, assist healthcare professionals in accurately assessing patients' conditions, and develop rational care plans.

Objective To aim at using machine learning algorithms to predict the risk of neonatal intensive care unit(ICU)mortality,providing clinicians with an early diagnosis and risk assessment tool to assist in decision-making.Methods Clinical data of preterm infants from the paediatric intensive care database retrospectively were collected.By using least absolute shrinkage and selection operator(LASSO)regression analysis and multivariate Logistic regression analysis,key clinical characteristics affecting preterm infant prognosis were screened.The study was balanced the data by using the synthetic minority oversampling technique,combined seven machine learning models to build a predictive model and evaluate its performance.The Shapley additive explanations(SHAP)was used for model interpretation.Results A total of 923 preterm infants were finally included,survival group comprised 886 infants,and death group comprised 37 infants.A total of 38 clinical characteristics were collected.LASSO screening identified 8 variables significantly associated with neonatal ICU mortality,including lactate,respiratory rate,chloride concentration,neutrophils,and red blood cell distribution width etc.Multivariate Logistic regression analysis revealed that lactate and respiratory rate were independent predictors of neonatal ICU outcomes.Internal testing and external validation showed that light gradient boosting machine model outperformed other models in terms of accuracy and precision etc.indicators.SHAP analysis indicated that respiratory rate and lactate levels had the largest predictive contribution to the risk of preterm infants mortality.Conclusion This study provides reliable tools for early identification and intervention in the prognosis of preterm infants,emphasizing the importance of key indicators.

Objective To systematically evaluate the risk prediction models for anastomotic leakage (AL) in patients with esophageal cancer after surgery. Methods A computer-based search of PubMed, EMbase, Web of Science, Cochrane Library, Chinese Medical Journal Full-text Database, VIP, Wanfang, SinoMed and CNKI was conducted to collect studies on postoperative AL risk prediction model for esophageal cancer from their inception to October 1st, 2023. PROBAST tool was employed to evaluate the bias risk and applicability of the model, and Stata 15 software was utilized for meta-analysis. Results A total of 19 literatures were included covering 25 AL risk prediction models and 7373 patients. The area under the receiver operating characteristic curve (AUC) was 0.670-0.960. Among them, 23 prediction models had a good prediction performance (AUC>0.7); 13 models were tested for calibration of the model; 1 model was externally validated, and 10 models were internally validated. Meta-analysis showed that hypoproteinemia (OR=9.362), postoperative pulmonary complications (OR=7.427), poor incision healing (OR=5.330), anastomosis type (OR=2.965), preoperative history of thoracoabdominal surgery (OR=3.181), preoperative diabetes mellitus (OR=2.445), preoperative cardiovascular disease (OR=3.260), preoperative neoadjuvant therapy (OR=2.977), preoperative respiratory disease (OR=4.744), surgery method (OR=4.312), American Society of Anesthesiologists score (OR=2.424) were predictors for AL after esophageal cancer surgery. Conclusion At present, the prediction model of AL risk in patients with esophageal cancer after surgery is in the development stage, and the overall research quality needs to be improved.

Objective To evaluate the effect of glucocorticoid(GC)treatment on the prognosis of patients with severe viral pneumonia,and to screen for related influencing factors and optimal beneficiary groups,providing reference for clinical medication decisions.Methods Based on the MIMIC-Ⅳ database,eligible patients with severe viral pneumonia were screened and divided into GC group and non GC group.Baseline differences were balanced using propensity score matching(PSM).Kaplan-Meier survival curves were used to analyze the cumulative survival rate of two groups of patients at 30 d,and Cox regression models were used to evaluate the association between GC use and the 30 d mortality risk in patients.Results A total of 518 severe viral pneumonia patients were included,including 43 in the GC group and 475 in the non-GC group.After PSM,there were 43 cases in the GC group and 86 cases in the non-GC group.The Kaplan-Meier survival curves showed that the 30 d cumulative survival rate of patients in the GC group was significantly higher than that in the non-GC group(P＜0.05).The results of multivariate Cox regression analysis showed that GC treatment significantly reduced the 30 d mortality risk[HR=0.35,95％CI(0.154,0.793),P=0.012],especially for patients older than 54 years,receiving mechanical ventilation,and with acute kidney injury.GC use,age＞54 years,and acute kidney injury were independent predictors of patient mortality risk(C-index=0.718 1).Subgroup analysis showed that for specific indications(age＞54 years,mechanical ventilation,no myocardial infarction,no hypertension,no hyperlipidemia,no heart failure,complicated by acute kidney failure),GC use could effectively reduce the 30 d mortality risk.Conclusion GC could effectively improve the prognosis of severe viral pneumonia patients,but individualized patient characteristics and treatment risks need to be considered comprehensively to optimize the medication regimen.

Objective To evaluate the effect of glucocorticoid(GC)treatment on the prognosis of patients with severe viral pneumonia,and to screen for related influencing factors and optimal beneficiary groups,providing reference for clinical medication decisions.Methods Based on the MIMIC-Ⅳ database,eligible patients with severe viral pneumonia were screened and divided into GC group and non GC group.Baseline differences were balanced using propensity score matching(PSM).Kaplan-Meier survival curves were used to analyze the cumulative survival rate of two groups of patients at 30 d,and Cox regression models were used to evaluate the association between GC use and the 30 d mortality risk in patients.Results A total of 518 severe viral pneumonia patients were included,including 43 in the GC group and 475 in the non-GC group.After PSM,there were 43 cases in the GC group and 86 cases in the non-GC group.The Kaplan-Meier survival curves showed that the 30 d cumulative survival rate of patients in the GC group was significantly higher than that in the non-GC group(P＜0.05).The results of multivariate Cox regression analysis showed that GC treatment significantly reduced the 30 d mortality risk[HR=0.35,95％CI(0.154,0.793),P=0.012],especially for patients older than 54 years,receiving mechanical ventilation,and with acute kidney injury.GC use,age＞54 years,and acute kidney injury were independent predictors of patient mortality risk(C-index=0.718 1).Subgroup analysis showed that for specific indications(age＞54 years,mechanical ventilation,no myocardial infarction,no hypertension,no hyperlipidemia,no heart failure,complicated by acute kidney failure),GC use could effectively reduce the 30 d mortality risk.Conclusion GC could effectively improve the prognosis of severe viral pneumonia patients,but individualized patient characteristics and treatment risks need to be considered comprehensively to optimize the medication regimen.

Objective To aim at using machine learning algorithms to predict the risk of neonatal intensive care unit(ICU)mortality,providing clinicians with an early diagnosis and risk assessment tool to assist in decision-making.Methods Clinical data of preterm infants from the paediatric intensive care database retrospectively were collected.By using least absolute shrinkage and selection operator(LASSO)regression analysis and multivariate Logistic regression analysis,key clinical characteristics affecting preterm infant prognosis were screened.The study was balanced the data by using the synthetic minority oversampling technique,combined seven machine learning models to build a predictive model and evaluate its performance.The Shapley additive explanations(SHAP)was used for model interpretation.Results A total of 923 preterm infants were finally included,survival group comprised 886 infants,and death group comprised 37 infants.A total of 38 clinical characteristics were collected.LASSO screening identified 8 variables significantly associated with neonatal ICU mortality,including lactate,respiratory rate,chloride concentration,neutrophils,and red blood cell distribution width etc.Multivariate Logistic regression analysis revealed that lactate and respiratory rate were independent predictors of neonatal ICU outcomes.Internal testing and external validation showed that light gradient boosting machine model outperformed other models in terms of accuracy and precision etc.indicators.SHAP analysis indicated that respiratory rate and lactate levels had the largest predictive contribution to the risk of preterm infants mortality.Conclusion This study provides reliable tools for early identification and intervention in the prognosis of preterm infants,emphasizing the importance of key indicators.

Objective To systematically review the risk prediction models for postoperative pancreatic fistula(POPF)after pancreaticoduodenectomy(PD),and to provide a reference for the clinical screening and application of POPF-related risk models.Methods This study was conducted according to the PRISMA guidelines,with a PROSPERO registration number of CRD42023437672.PubMed,Scopus,Embase,Web of Science,the Cochrane Library,CNKI,VIP,Wanfang Data,China Medical Journal Full-text Database,and CBM were searched for studies on establishing risk prediction models for POPF after PD published up to April 26,2024.The PROBAST tool was used to assess the quality of articles,and RevMan 5.4 and MedCalc were used to perform the Meta-analysis.Results A total of 36 studies were included,involving 20 119 in total,and the incidence rate of POPF after PD was 7.4%—47.8%.A total of 55 risk prediction models were established in the 36 articles,with an area under the receiver operating characteristic curve(AUC)of 0.690-0.952,among which 52 models had an AUC of>0.7.The quality assessment of the articles showed high risk of bias and good applicability.MedCalc was used to perform a statistical analysis of AUC values,and the results showed a pooled AUC of 0.833(95%confidence interval:0.808-0.857).The Meta-analysis showed that body mass index,amylase in drainage fluid on the first day after surgery,preoperative serum albumin,pancreatic duct diameter,pancreatic texture,fat score,tumor location,blood loss,sex,time of operation,main pancreatic duct index,and pancreatic CT value were predictive factors for POPF(all P<0.05).Conclusion The risk prediction models for POPF after PD is still in the exploratory stage.There is a lack of calibration methods and internal validation for most prediction models,and only the univariate analysis is used to for the screening of variables,which leads to the high risk of bias.In the future,it is necessary to improve the methods for model establishment,so as to develop risk prediction models with a higher prediction accuracy.