Objective To construct a nomogram prediction model for predicting hemoglobin A1c(HbA1c)failure in type 2 diabetes mellitus(T2DM)patients.Methods A total of 936 inpatients with T2DM admitted to the Department of Endocrinology of the Affiliated Hospital of Shandong Second Medical University from January 2021 to January 2022 were selected as the research objects and divided into the non-standard group(HbA1c≥7%,n=801)and the standard group(HbA1c<7%,n=135).Univariate analysis was used to screen the related factors of HbA1c failure.Logistic regression multivariate model was used to analyze the influencing factors of HbA1c failure in T2DM patients.The R language was used to construct a nomogram,and the area under the receiver operating characteristic(ROC)curve(AUC)was used to evaluate the predictive ability of the model.The C-index and Hosmer-Lemeshow test were used to evaluate the discrimination and calibration of the model.Results There were statistically significant differences in triglyceride(TG),low-density lipoprotein cholesterol,direct bilirubin,urinary albumin/creatinine ratio(UACR),self-monitoring of blood glucose(SMBG),meat and vegetable pairing,hot pot,whole grain and animal viscera consumption between the two groups(P<0.05).Logistic regression analysis showed that TG(OR 1.699,95%CI 1.298～2.222),UACR(OR 1.003,95%CI 1.001～1.005),SMGB(OR 0.480,95%CI 0.313～0.735),more meat and less vegetables(OR 1.432,95%CI 1.062～1.931)were the influencing factors of HbA1c failure.The AUC of the nomogram prediction model based on the influencing factors was 0.711,with C-index 0.710(95%CI 0.663～0.758)and good calibration(χ2=11.185,P=0.191).Conclusions The nomogram prediction model for HbA1c failure in T2DM patients established based on TG,UACR,SMGB,meat and vegetarian mix has good discrimination and calibration,which can provide certain reference value for warning of poor blood glucose control.

Objective To analyze the disease burden of chronic kidney diseases (CKD) attributed to high body mass index (BMI) in China from 1992 to 2021 and predict the disease burden for the next decade, and to provide evidence for the prevention and treatment of CKD. Methods Using the Global Burden of Disease (GBD) database and the Joinpoint model, the average annual percentage rate change (AAPC) of the mortality rate and disability-adjusted life year (DALY) rate was calculated to describe and analyze the CKD disease burden attributed to high BMI in China from 1992 to 2021. The ARIMA model was employed to predict and analyze the change trend of the CKD disease burden. Results From 1992 to 2021, the mortality rate and DALY rate attributed to high BMI-induced chronic kidney disease showed an upward trend. Compared to 1992, the attributed number of deaths increased by 324.38%, and DALYs increased by 268.56%; the mortality rate increased by 64.00%, and the DALY rate grew by 51.62%. From 1992 to 2021, the mortality rate and DALY rate for males were lower than those for females, but the growth rate for males exceeded that of females. From 1992 to 2021, the mortality rate and DALY rate of chronic kidney disease attributed to high BMI in China increased with age. The average annual change rate of chronic kidney disease attributed to high BMI in China from 1992 to 2021 (mortality rate: 1.40 per 100,000 (95% CI: 1.04–1.76), DALY rate: 1.43 per 100 000 (95% CI: 1.17–1.70)) was higher than thHuaiyin Normal University, Huai'anher social demographic index (SDI) regions. The ARIMA model predicted that the age-standardized mortality rate increased from 2.91 per 100 000 in 2022 to 3.05 per 100 000 in 2026, and the age-standardized DALY rate increased from 69.65 per 100 000 in 2022 to 73.58 per 100 000 in 2026. Conclusion Chronic kidney disease attributed to high BMI in China is on the rise, and it will continue to grow in the future. The focus of CKD prevention and control should be on males and the elderly, while active measures should be taken to reduce the occurrence and progression of chronic kidney disease.

Traditional Chinese medicine (TCM) is an ancient medical system distinctive and effective in treating cancer, depression, coronavirus disease 2019 (COVID-19), and other diseases. However, the relatively abstract diagnostic methods of TCM lack objective measurement, and the complex mechanisms of action are difficult to comprehend, which hinders the application and internationalization of TCM. Recently, while breakthroughs have been made in utilizing methods such as network pharmacology and virtual screening for TCM research, the rise of machine learning (ML) has significantly enhanced their integration with TCM. This article introduces representative methodological cases in quality control, mechanism research, diagnosis, and treatment processes of TCM, revealing the potential applications of ML technology in TCM. Furthermore, the challenges faced by ML in TCM applications are summarized, and future directions are discussed.

Spine fracture and dislocation are common traumatic spinal conditions that often require surgical intervention due to compromised spinal stability. Surgical approaches include anterior, posterior, and combined anterior-posterior spinal procedures. According to the specific surgical requirements, patients may be placed in the prone position or repositioned between prone and supine positions during surgery. Intraoperative repositioning has become an essential step in patient positioning. However, during repositioning, patients with spinal fracture and dislocation are at increased risk for complications such as hemodynamic instability, nerve injury, and pressure injuries to the skin and soft tissue. Notably, due to the instability of the spinal cord, even minor manipulations can further exacerbate the damage, potentially leading to severe outcomes like paraplegia. Although the current clinical guidelines provide instructive recommendations for standard position, there remains no specific protocols for intraoperative repositioning in patients with spine fracture and dislocation. With a concern for the lack of clinical studies on positioning techniques, risk prevention, and operational norms for special patients, no applicable guidelines or standards are available. A consensus was required to provide clinical reference, meet the requirements of surgical treatment, and minimize the safety risks of patients caused by improper placement of positions. Professional Committee of Operating Room Nursing of Shaanxi Nursing Association organized experts in nursing management and operating room nursing from major hospitals across China to formulate Expert consensus on intraoperative repositioning for patients with spinal fracture and dislocation ( version 2025). The consensus provides 11 recommendations covering pre-repositioning preparation, intraoperative maneuvers, and post-repositioning observation, aiming to provide references for clinical standardization of the intraoperative repositioning process and protection of patients′ safety.

Spine fracture and dislocation are common traumatic spinal conditions that often require surgical intervention due to compromised spinal stability. Surgical approaches include anterior, posterior, and combined anterior-posterior spinal procedures. According to the specific surgical requirements, patients may be placed in the prone position or repositioned between prone and supine positions during surgery. Intraoperative repositioning has become an essential step in patient positioning. However, during repositioning, patients with spinal fracture and dislocation are at increased risk for complications such as hemodynamic instability, nerve injury, and pressure injuries to the skin and soft tissue. Notably, due to the instability of the spinal cord, even minor manipulations can further exacerbate the damage, potentially leading to severe outcomes like paraplegia. Although the current clinical guidelines provide instructive recommendations for standard position, there remains no specific protocols for intraoperative repositioning in patients with spine fracture and dislocation. With a concern for the lack of clinical studies on positioning techniques, risk prevention, and operational norms for special patients, no applicable guidelines or standards are available. A consensus was required to provide clinical reference, meet the requirements of surgical treatment, and minimize the safety risks of patients caused by improper placement of positions. Professional Committee of Operating Room Nursing of Shaanxi Nursing Association organized experts in nursing management and operating room nursing from major hospitals across China to formulate Expert consensus on intraoperative repositioning for patients with spinal fracture and dislocation ( version 2025). The consensus provides 11 recommendations covering pre-repositioning preparation, intraoperative maneuvers, and post-repositioning observation, aiming to provide references for clinical standardization of the intraoperative repositioning process and protection of patients′ safety.

Traditional Chinese medicine(TCM)is an ancient medical system distinctive and effective in treating cancer,depression,coronavirus disease 2019(COVID-19),and other diseases.However,the relatively abstract diagnostic methods of TCM lack objective measurement,and the complex mechanisms of action are difficult to comprehend,which hinders the application and internationalization of TCM.Recently,while breakthroughs have been made in utilizing methods such as network pharmacology and virtual screening for TCM research,the rise of machine learning(ML)has significantly enhanced their inte-gration with TCM.This article introduces representative methodological cases in quality control,mechanism research,diagnosis,and treatment processes of TCM,revealing the potential applications of ML technology in TCM.Furthermore,the challenges faced by ML in TCM applications are summarized,and future directions are discussed.

Objective To construct a nomogram prediction model for predicting hemoglobin A1c(HbA1c)failure in type 2 diabetes mellitus(T2DM)patients.Methods A total of 936 inpatients with T2DM admitted to the Department of Endocrinology of the Affiliated Hospital of Shandong Second Medical University from January 2021 to January 2022 were selected as the research objects and divided into the non-standard group(HbA1c≥7%,n=801)and the standard group(HbA1c<7%,n=135).Univariate analysis was used to screen the related factors of HbA1c failure.Logistic regression multivariate model was used to analyze the influencing factors of HbA1c failure in T2DM patients.The R language was used to construct a nomogram,and the area under the receiver operating characteristic(ROC)curve(AUC)was used to evaluate the predictive ability of the model.The C-index and Hosmer-Lemeshow test were used to evaluate the discrimination and calibration of the model.Results There were statistically significant differences in triglyceride(TG),low-density lipoprotein cholesterol,direct bilirubin,urinary albumin/creatinine ratio(UACR),self-monitoring of blood glucose(SMBG),meat and vegetable pairing,hot pot,whole grain and animal viscera consumption between the two groups(P<0.05).Logistic regression analysis showed that TG(OR 1.699,95%CI 1.298～2.222),UACR(OR 1.003,95%CI 1.001～1.005),SMGB(OR 0.480,95%CI 0.313～0.735),more meat and less vegetables(OR 1.432,95%CI 1.062～1.931)were the influencing factors of HbA1c failure.The AUC of the nomogram prediction model based on the influencing factors was 0.711,with C-index 0.710(95%CI 0.663～0.758)and good calibration(χ2=11.185,P=0.191).Conclusions The nomogram prediction model for HbA1c failure in T2DM patients established based on TG,UACR,SMGB,meat and vegetarian mix has good discrimination and calibration,which can provide certain reference value for warning of poor blood glucose control.

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 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.

Purpose To evaluate the classification criteria of triple negative breast cancer(TNBC)based on histomorphol-ogy and immunohistochemistry(IHC),and to provide theoreti-cal basis for the classification and treatment of TNBCs.Methods TNBC subtyping was performed according to the histomorphologi-cal characteristics and the expression of immune markers AR,CD8 and FOXC1,and the clinicopathological features and prog-nostic differences were compared.Results Among 93 cases of TNBC,there were 23 cases(24.7％)of luminal androgen re-ceptor subtypes,24 cases(25.8％)of immunomodulatory type,39 cases(42.0％)of basal immunosuppressive type,and 7 ca-ses(7.5％)of mesenchymal type.There were significant differ-ences in the clinicopathological features of subtypes,including pT stage(P=0.030),histological grade(P＜0.001),intersti-tial lymphocyte infiltration pattern(P＜0.001),expression of PD-L1(P＜0.001),and HER2-low(P=0.024).There was no significant difference in disease-free survival among the sub-types(P＞0.05).Univariate survival analysis showed there was significant difference in disease-free survival among the subtypes at pT1 stage(P=0.011),and other clinicopathological features were not independent prognostic factors.Conclusion The clini-copathological characteristics of TNBC subtypes are different,which are expected to be an alternative choice for complex gene expression profile analysis and to provide theoretical basis for subtypic therapy and targeted therapy.