Objective To construct a machine learning prediction model for diabetic kidney disease(DKD)in type 2 diabetes mellitus(T2DM)patients in the plain-sand and loess hilly areas of Gansu Province,and analyze the interpretability of the model.Methods A multi-stage stratified random sampling method was used to collect the data of T2DM patients in the two areas.After key feature screening,eight ML prediction models were constructed for the risk of DKD in the two areas.The receiver operating characteristic(ROC)curve,accuracy and F1 index were used to evaluate the model,and Shapley additive explanation(SHAP)algorithm was used for model interpretation.Results A total of 1599 patients with T2DM were enrolled in this study.After feature screening,ten variables were selected for model construction in the plain-sand areas.Among the eight models,the gradient boosting decision tree(GBDT)model had the highest prediction efficiency.The area under the curve(AUC)of the test dataset was 0.972,the accuracy was 0.949,and the F1 index was 0.884.In the loess hilly region,12 variables were included in the model,and the best model was the random forest(RF).The AUC of the test set was 0.966,the accuracy was 0.951,and the F1 index was 0.861.SHAP analysis showed that in addition to serum creatinine,age,LDL-C,HbA1c,DM duration,serum uric acid and urinary microalbumin were also closely related to the high risk of DKD.Conclusions The GBDT and RF models have good predictive efficiency for the occurrence of DKD in the two areas,which can be used for the screening of DKD high-risk populations and the in-depth exploration of potential risk factors in the two areas.

With the increasingly stringent requirements of international standards for the stability of clinical samples,there has been a significant rise in clinical laboratories'demand for sample stability research.To ensure the accuracy of laboratory test results,conducting research and verification work related to sample stability has become particularly urgent.However,there is currently a lack of unified standards for clinical sample stability studies both domestically and internationally.In order to better promote the resach and validation of sample stability in clinical laboratroy projects,this review summarized the latest progress in sample stability research methods by reviewing relevant literature and guidelines.It recommends referencing guidance from international organizations in clinical sample stability studies,such as the cress checklist for reporting stability studies and the"recommendations for the design of stability studies for clinical samples"issued by the European Federation of Clinical Chemistry and Laboratory Medicine(EFLM).Laboratories should select either continuous experimental design or discrete experimental design based on their practical circumstances when conducting such research.

In recent years, 7-tesla high-resolution magnetic resonance imaging (7 T HR-MRI) has demonstrated significant advantages in evaluating intracranial atherosclerotic plaques due to its ultrahigh signal-to-noise ratio and submillimeter isotropic spatial resolution. This cutting-edge technique enables precise visualization of plaque microstructures, including morphological characteristics and compositional features. Moreover, it allows noninvasive in vivo imaging of small intracranial vessels and provides clear delineation of the anatomical relationship between perforating artery ostia and their parent arteries. Although not yet widely adopted in clinical practice, 7 T HR-MRI shows promising potential for plaque vulnerability assessment, stroke mechanism elucidation, and therapeutic monitoring. This review summarizes recent advancements in 7 T MRI applications for intracranial atherosclerotic disease, aiming to provide novel insights for precision medicine in clinical practice.

Objective:To evaluate the association between postoperative delirium (POD) and preoperative frailty in elderly patients undergoing knee or hip arthroplasty.Methods:This nested case-control study utilized medical records from elderly patients who underwent knee or hip arthroplasty under combined spinal-epidural anesthesia at Qingdao Municipal Hospital between September 2021 and May 2023. Participants were divided into 2 groups based on clinically diagnosed POD: POD group ( n=53) and non-POD group ( n=256). Univariate analysis was conducted on suspected influencing factors, and logistic regression analysis was utilized to identify the risk factors for POD. Receiver operating characteristic and clinical decision curves were plotted to evaluate the predictive performance of these risk factors for POD. Mediation analysis was performed, and a clinically applicable nomogram was constructed to achieve visual prediction of outcomes. Results:There were statistically significant differences in age, preoperative frailty, body mass index, American Society of Anesthesiologists Physical Status classification, Memorial Delirium Assessment Scale scores, and concentrations of Aβ 42, Aβ 40, phosphorylated tau protein (p-tau protein) and tau protein, Aβ 42/tau ratio and Aβ 42/p-tau ratio in cerebrospinal fluid (CSF) between non-POD group and POD group ( P<0.05). Preoperative frailty was a risk factor for POD ( P<0.05). Mediation analysis revealed that the association between preoperative frailty and POD was mediated by CSF tau protein concentrations. The area under the receiver operating characteristic curve of preoperative frailty and CSF biomarker concentrations in predicting POD was 0.974 ( P<0.05). The clinical decision curve demonstrated that the model combining the preoperative frailty and CSF biomarker concentrations predicted a higher net benefit ( P<0.05). The clinical decision curve showed that the model combining preoperative frailty and CSF biomarker concentrations predicted a higher net benefit. Conclusions:Preoperative frailty is a risk factor for POD in elderly patients undergoing knee or hip arthroplasty, and its combination with CSF biomarker concentrations can effectively predict the occurrence of POD. CSF tau concentration mediates the association between preoperative frailty and development of POD.

With the increasingly stringent requirements of international standards for the stability of clinical samples,there has been a significant rise in clinical laboratories'demand for sample stability research.To ensure the accuracy of laboratory test results,conducting research and verification work related to sample stability has become particularly urgent.However,there is currently a lack of unified standards for clinical sample stability studies both domestically and internationally.In order to better promote the resach and validation of sample stability in clinical laboratroy projects,this review summarized the latest progress in sample stability research methods by reviewing relevant literature and guidelines.It recommends referencing guidance from international organizations in clinical sample stability studies,such as the cress checklist for reporting stability studies and the"recommendations for the design of stability studies for clinical samples"issued by the European Federation of Clinical Chemistry and Laboratory Medicine(EFLM).Laboratories should select either continuous experimental design or discrete experimental design based on their practical circumstances when conducting such research.

Objective:To evaluate the association between postoperative delirium (POD) and preoperative frailty in elderly patients undergoing knee or hip arthroplasty.Methods:This nested case-control study utilized medical records from elderly patients who underwent knee or hip arthroplasty under combined spinal-epidural anesthesia at Qingdao Municipal Hospital between September 2021 and May 2023. Participants were divided into 2 groups based on clinically diagnosed POD: POD group ( n=53) and non-POD group ( n=256). Univariate analysis was conducted on suspected influencing factors, and logistic regression analysis was utilized to identify the risk factors for POD. Receiver operating characteristic and clinical decision curves were plotted to evaluate the predictive performance of these risk factors for POD. Mediation analysis was performed, and a clinically applicable nomogram was constructed to achieve visual prediction of outcomes. Results:There were statistically significant differences in age, preoperative frailty, body mass index, American Society of Anesthesiologists Physical Status classification, Memorial Delirium Assessment Scale scores, and concentrations of Aβ 42, Aβ 40, phosphorylated tau protein (p-tau protein) and tau protein, Aβ 42/tau ratio and Aβ 42/p-tau ratio in cerebrospinal fluid (CSF) between non-POD group and POD group ( P<0.05). Preoperative frailty was a risk factor for POD ( P<0.05). Mediation analysis revealed that the association between preoperative frailty and POD was mediated by CSF tau protein concentrations. The area under the receiver operating characteristic curve of preoperative frailty and CSF biomarker concentrations in predicting POD was 0.974 ( P<0.05). The clinical decision curve demonstrated that the model combining the preoperative frailty and CSF biomarker concentrations predicted a higher net benefit ( P<0.05). The clinical decision curve showed that the model combining preoperative frailty and CSF biomarker concentrations predicted a higher net benefit. Conclusions:Preoperative frailty is a risk factor for POD in elderly patients undergoing knee or hip arthroplasty, and its combination with CSF biomarker concentrations can effectively predict the occurrence of POD. CSF tau concentration mediates the association between preoperative frailty and development of POD.

Objective To construct a machine learning prediction model for diabetic kidney disease(DKD)in type 2 diabetes mellitus(T2DM)patients in the plain-sand and loess hilly areas of Gansu Province,and analyze the interpretability of the model.Methods A multi-stage stratified random sampling method was used to collect the data of T2DM patients in the two areas.After key feature screening,eight ML prediction models were constructed for the risk of DKD in the two areas.The receiver operating characteristic(ROC)curve,accuracy and F1 index were used to evaluate the model,and Shapley additive explanation(SHAP)algorithm was used for model interpretation.Results A total of 1599 patients with T2DM were enrolled in this study.After feature screening,ten variables were selected for model construction in the plain-sand areas.Among the eight models,the gradient boosting decision tree(GBDT)model had the highest prediction efficiency.The area under the curve(AUC)of the test dataset was 0.972,the accuracy was 0.949,and the F1 index was 0.884.In the loess hilly region,12 variables were included in the model,and the best model was the random forest(RF).The AUC of the test set was 0.966,the accuracy was 0.951,and the F1 index was 0.861.SHAP analysis showed that in addition to serum creatinine,age,LDL-C,HbA1c,DM duration,serum uric acid and urinary microalbumin were also closely related to the high risk of DKD.Conclusions The GBDT and RF models have good predictive efficiency for the occurrence of DKD in the two areas,which can be used for the screening of DKD high-risk populations and the in-depth exploration of potential risk factors in the two areas.

In recent years, 7-tesla high-resolution magnetic resonance imaging (7 T HR-MRI) has demonstrated significant advantages in evaluating intracranial atherosclerotic plaques due to its ultrahigh signal-to-noise ratio and submillimeter isotropic spatial resolution. This cutting-edge technique enables precise visualization of plaque microstructures, including morphological characteristics and compositional features. Moreover, it allows noninvasive in vivo imaging of small intracranial vessels and provides clear delineation of the anatomical relationship between perforating artery ostia and their parent arteries. Although not yet widely adopted in clinical practice, 7 T HR-MRI shows promising potential for plaque vulnerability assessment, stroke mechanism elucidation, and therapeutic monitoring. This review summarizes recent advancements in 7 T MRI applications for intracranial atherosclerotic disease, aiming to provide novel insights for precision medicine in clinical practice.

Red blood cells(RBCs)are the primary mediators of oxygen transport in the human body,and their function is mainly achieved through conformational changes of hemoglobin(Hb).Hb is a tetramer composed of four subunits,with HbA being the predominant Hb in healthy adults,existing in two forms:tense state(T state)and relaxed state(R state).Endogenous regulators of Hb conformation include 2,3-diphosphoglyceric acid,carbon dioxide,protons,and chloride ions,while exogenous regulators include inositol hexaphosphate,inositol tripyrophosphate,benzabate,urea derivative L35,and vanillin,each with different mechanisms of action.The application of Hb conformational regulators provides new insights into the study of hypoxia oxygen supply issues and the treatment of sickle cell disease.

Objective To investigate the prevalence of insomnia in college students and analyze the correlation between insomnia and perceived stress. Methods A cluster sampling method was used to investigate the prevalence of insomnia and stress levels in 3702 college students using Insomnia Severity Index (ISI) and Perceived Stress Scale-10 (PSS-10). Results Insomnia was detected in 31.4％ of the college students, and the symptoms were more severe in male students (t=2.047, P=0.041) and in those with poorer family economic conditions (F=20.423, P<0.001). Insomnia was positively correlated with perceived stress, perceived distress, and perceived coping ability, with correlation coefficients of 0.42, 0.38, and 0.31, respectively (P<0.001). The students with higher levels of perceived stress had higher insomnia scores (F=203.03, P<0.001) and higher detection rate of insomnia (x2=359.784, P<0.001), and those with moderate or severe insomnia also had higher levels of perceived stress (F=293.569, P<0.001). The types of perceived stress among college students included incontrollable (15.3％), nervous (8.3％), vulnerable (23.0％) and the relaxed types (53.5％). The incontrollable type was associated with the highest insomnia scores, followed by the nervous type and susceptible type, and the relaxed type had the lowest insomnia scores (F=185.969, P<0.001). The prevalence rates of insomnia in students with the 4 types of perceived stress were 57.3％, 43.3％, 39.3％, and 18.7％, respectively (x2=368.876, P<0.001). Conclusion There is a close correlation between perceived stress and insomnia, and identification of the high-risk population for insomnia from the perspectives of perceived stress level and perceived stress type can facilitate the management and prevention of insomnia.