Objective The abnormal ankle-brachial index ( ABI) is associated with the incidence of cardiocerebral vascular diseases, but little is known about its relationship with cerebral microbleeds (CMB).This study aimed to investigate the correlation be-tween ABI≤0.9 and different distribution patterns of CMB . Methods We enrolled 187 patients with acute lacunar infarction , inclu-ding 115 non-CMB cases and 72 CMB cases (20 strictly lobar, 24 strictly deep, and 28 lobar and deep).We analyzed the differences between the two groups and the association of abnormal ABI with the occurrence and distribution of CMB by logistic regression analysis . Results ABI≤0.9 was found in 57 (30.5%) of the patients, with a significantly higher incidence rate in the CMB group than in the non-CMB group (43.1%vs 22.6%, P=0.003).The level of ABI was negatively correlated with the number of CMBs (r=-0.211, P=0.006).Multivariate logistic regression analysis after adjusted for confounders indicated that ABI ≤0.9 was significantly associated with the presence of CMB (OR=2.363;95%CI:1.181-4.729), deep CMB (OR=3.434;95%CI:1.283-9.187), and lobar and deep CMB ( OR=2.837;95%CI:1.098-7.333) in patients with ischemic cerebrovascular disease . Conclusion Decreased ABI is a risk factor of CMB, particularly deep CMB, in patients with ischemic stroke.

Objective To investigate the risk factors for reduced renal function in patients with ischemic stroke.Methods The medical records of patients with ischemic stroke were analyzed retrospectively.They were divided into normal renal function group and reduced renalfunction group.Reduced renal function was defined as estimated glomerular filtration rate (eGFR) ＜60 ml/(min·1.73 m2).Multivariate logistic regression analysis was used to identify the risk factors for reduced renal function in patients with ischemic stroke.Results A total of 805 patients with ischemic stroke were enrolled in the study.8.8％ of patients had a reduced renal function.There was no significant differences in the proportion of patients with mild and moderate neurological deficit between the reduced renal function group and the normal renal function group (all P ＞ 0.05),however,the proportion of patients with severe neurological deficit was significantly higher than that in the normal renal function group (8.4％vs.2.6％,x2 =5.573,P =0.017).The proportion of small artery occlusion in the reduced renal function group was sigaificantly higher than that in the normal renal function group (66.2％ vs.46.5％,x2 =9.962,P =0.002),and the proportion of large artery atherosclerosis was significantly lower than that in the normal renal function group (19.7％ vs.43.5％,x2 =15.045,P =0.000).Multivariate logistic regression analysis indicated that old age (odds ratio [ OR] 3.301,95％ confidence interval [ CI],1.575 to 6.918; P=0.002) was the most important independent risk factor for reduced renal function,then was female (OR,2.291,95％ CI 1.355to 3.872; P=0.002) and hyperlipidemia (OR,2.527,95％ CI 1.095 to 5.831; P=0.030).Conclusions Reduced renal function in patients with ischemic stroke is strongly associated with old age,female,and hyperlipidemia.

OBJECTIVE: To analyze the risk factors of in-hospital death in patients with sepsis in the intensive care unit (ICU) based on machine learning, and to construct a predictive model, and to explore the predictive value of the predictive model. METHODS: The clinical data of patients with sepsis who were hospitalized in the ICU of the Affiliated Hospital of Jining Medical University from April 2015 to April 2021 were retrospectively analyzed,including demographic information, vital signs, complications, laboratory examination indicators, diagnosis, treatment, etc. Patients were divided into death group and survival group according to whether in-hospital death occurred. The cases in the dataset (70%) were randomly selected as the training set for building the model, and the remaining 30% of the cases were used as the validation set. Based on seven machine learning models including logistic regression (LR), K-nearest neighbor (KNN), support vector machine (SVM), decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost) and artificial neural network (ANN), a prediction model for in-hospital mortality of sepsis patients was constructed. The receiver operator characteristic curve (ROC curve), calibration curve and decision curve analysis (DCA) were used to evaluate the predictive performance of the seven models from the aspects of identification, calibration and clinical application, respectively. In addition, the predictive model based on machine learning was compared with the sequential organ failure assessment (SOFA) and acute physiology and chronic health evaluation II (APACHE II) models. RESULTS: A total of 741 patients with sepsis were included, of which 390 were discharged after improvement, 351 died in hospital, and the in-hospital mortality was 47.4%. There were significant differences in gender, age, APACHE II score, SOFA score, Glasgow coma score (GCS), heart rate, oxygen index (PaO₂/FiO₂), mechanical ventilation ratio, mechanical ventilation time, proportion of norepinephrine (NE) used, maximum NE, lactic acid (Lac), activated partial thromboplastin time (APTT), albumin (ALB), serum creatinine (SCr), blood urea nitrogen (BUN), blood uric acid (BUA), pH value, base excess (BE), and K⁺ between the death group and the survival group. ROC curve analysis showed that the area under the curve (AUC) of RF, XGBoost, LR, ANN, DT, SVM, KNN models, SOFA score, and APACHE II score for predicting in-hospital mortality of sepsis patients were 0.871, 0.846, 0.751, 0.747, 0.677, 0.657, 0.555, 0.749 and 0.760, respectively. Among all the models, the RF model had the highest precision (0.750), accuracy (0.785), recall (0.773), and F1 score (0.761), and best discrimination. The calibration curve showed that the RF model performed best among the seven machine learning models. DCA curve showed that the RF model exhibited greater net benefit as well as threshold probability compared to other models, indicating that the RF model was the best model with good clinical utility. CONCLUSIONS The machine learning model can be used as a reliable tool for predicting in-hospital mortality in sepsis patients. RF models has the best predictive performance, which is helpful for clinicians to identify high-risk patients and implement early intervention to reduce mortality.
Humans ; Hospital Mortality ; Retrospective Studies ; ROC Curve ; Prognosis ; Sepsis/diagnosis* ; Intensive Care Units