Alzheimer's disease (AD) remains a formidable challenge in modern healthcare, necessitating innovative approaches for its early detection and intervention. This study aimed to enhance the identification of individuals with mild cognitive impairment (MCI) at risk of developing AD. Leveraging advances in computational power and the extensive availability of healthcare data, we explored the potential of deep learning models for early prediction using medical claims data. We employed a bidirectional gated recurrent unit (BiGRU) deep learning model for predictive modeling of MCI progression across various prediction intervals, extending up to five years post-initial MCI diagnosis. The performance of the BiGRU model was rigorously compared with several machine-learning model baselines to evaluate its efficacy. Using a robust cross-validation methodology, the BiGRU emerged as the top-performing model, achieving an Area Under the Receiver Operating Characteristic Curve (AUC-ROC) of 0.833 (95% CI: 0.822, 0.843), an Area Under the Precision-Recall Curve (AUC-PR) of 0.856 (95% CI: 0.845, 0.867), and an F1-Score of 0.71 (95% CI: 0.694, 0.724) for a five-year prediction interval. The results indicate that BiGRU, utilizing longitudinal claims data, reliably predicts MCI-to-AD progression over a lengthy interval following the initial MCI diagnosis, offering clinicians a valuable tool for targeted risk identification and stratification.

Objective To investigate the risk factors of in-hospital mortality and establish a risk prediction model for patients receiving venoarterial extracorporeal membrane oxygenation(VA-ECMO).Methods We retrospectively collected the data of 302 patients receiving VA-ECMO in ICU of 3 hospitals in Guangdong Province between January,2015 and January,2022 using a convenience sampling method.The patients were divided into a derivation cohort(201 cases)and a validation cohort(101 cases).Univariate and multivariate logistic regression analyses were used to analyze the risk factors for in-hospital death of these patients,based on which a risk prediction model was established in the form of a nomogram.The receiver operator characteristic(ROC)curve,calibration curve and clinical decision curve were used to evaluate the discrimination ability,calibration and clinical validity of this model.Results The in-hospital mortality risk prediction model was established based the risk factors including hypertension(OR=3.694,95%CI:1.582-8.621),continuous renal replacement therapy(OR=9.661,95%CI:4.103-22.745),elevated Na2+ level(OR=1.048,95%CI:1.003-1.095)and increased hemoglobin level(OR=0.987,95%CI:0.977-0.998).In the derivation cohort,the area under the ROC curve(AUC)of this model was 0.829(95%CI:0.770-0.889),greater than those of the 4 single factors(all AUC<0.800),APACHE Ⅱ Score(AUC=0.777,95%CI:0.714-0.840)and the SOFA Score(AUC=0.721,95%CI:0.647-0.796).The results of internal validation showed that the AUC of the model was 0.774(95%CI:0.679-0.869),and the goodness of fit test showed a good fitting of this model(χ2=4.629,P>0.05).Conclusion The risk prediction model for in-hospital mortality of patients on VA-ECMO has good differentiation,calibration and clinical effectiveness and outperforms the commonly used disease severity scoring system,and thus can be used for assessing disease severity and prognostic risk level in critically ill patients.

Objective To investigate the risk factors of in-hospital mortality and establish a risk prediction model for patients receiving venoarterial extracorporeal membrane oxygenation(VA-ECMO).Methods We retrospectively collected the data of 302 patients receiving VA-ECMO in ICU of 3 hospitals in Guangdong Province between January,2015 and January,2022 using a convenience sampling method.The patients were divided into a derivation cohort(201 cases)and a validation cohort(101 cases).Univariate and multivariate logistic regression analyses were used to analyze the risk factors for in-hospital death of these patients,based on which a risk prediction model was established in the form of a nomogram.The receiver operator characteristic(ROC)curve,calibration curve and clinical decision curve were used to evaluate the discrimination ability,calibration and clinical validity of this model.Results The in-hospital mortality risk prediction model was established based the risk factors including hypertension(OR=3.694,95%CI:1.582-8.621),continuous renal replacement therapy(OR=9.661,95%CI:4.103-22.745),elevated Na2+ level(OR=1.048,95%CI:1.003-1.095)and increased hemoglobin level(OR=0.987,95%CI:0.977-0.998).In the derivation cohort,the area under the ROC curve(AUC)of this model was 0.829(95%CI:0.770-0.889),greater than those of the 4 single factors(all AUC<0.800),APACHE Ⅱ Score(AUC=0.777,95%CI:0.714-0.840)and the SOFA Score(AUC=0.721,95%CI:0.647-0.796).The results of internal validation showed that the AUC of the model was 0.774(95%CI:0.679-0.869),and the goodness of fit test showed a good fitting of this model(χ2=4.629,P>0.05).Conclusion The risk prediction model for in-hospital mortality of patients on VA-ECMO has good differentiation,calibration and clinical effectiveness and outperforms the commonly used disease severity scoring system,and thus can be used for assessing disease severity and prognostic risk level in critically ill patients.

Hypertensive disorder of pregnancy (HDP) involves two major public health issues: mother-infant safety and prevention and controlling major chronic disease. HDP poses a serious threat to maternal and neonatal safety, and it is one of the leading causes of maternal and perinatal morbidity and mortality worldwide, as well as an important risk factor for long-term cardiovascular disease (CVD). In order to explore effective strategies to prevent and control the source of CVD and reduce its risk, we have established a cohort of HDPs in Shenzhen for the primordial prevention of CVD. The construction of the HDP cohort has already achieved preliminary progress till now. A total of 2 239 HDP women have been recruited in the HDP cohort. We have established a cohort data management platform and Biobank. The follow-up and assessment of postpartum cardiovascular metabolic risk in this cohort has also been launched. Our efforts will help explore the pathophysiological mechanism of HDP, especially the pathogenesis and precision phenotyping, prediction, and prevention of pre-eclampsia, which, therefore, may reduce the risk of adverse pregnancy outcomes, and provide a bridge to linking HDP and maternal-neonatal cardiovascular, metabolic risk to promote the cardiovascular health of mothers and their infants.

AIM:To investigate the influence of Jiedu hugan granule on the inflammatory factor and tight junction protein of small intestine in rats with immunological liver injury.METHODS:Fifty SD rats were randomly divided into control group,model group,low,middle and high experimental group of Jiedu hugan granule (2.7,5.4,and 10.8 g/kg).All the groups excepted the control group received intraperitoneal injections of 0.5 mL pig serum for each to establish immunological liver injury model.The experimental group was irrigated ltime/d,continuous dosing for 14 d.The liver tissue and small intestinal tissue pathological changes were observed by HE staining,the serum alanine aminotransferase (ALT),aspartate aminotransferase (AST) and lactate dehydrogenase (LDH) were detected,and the expression of liver tissue TNF-α and small intestine tissue occludin-5 were detected by immunohistochemical method.RESULTS:The model group liver tissue showed accumulation of fat cells,liver cells enlargement,disorganized liver and associated with inflammatory cells infiltration;the experimental group liver cell morphological ruled,hepatic cords in alignment and inflammatory cells infiltration significantly decrease.The model group small intestinal mucosa villi showed atrophy,fall off of epithelial cell,edema,large number of inflammatory cells infiltration;the experimental group showed closelyknitted small intestinal mucosa villi,relieve edema,and no obvious infiltration of inflammatory cells.The levels of ALT,AST,LDH and TNF-α in experimental group were statistically lower than the model group,and the levels were statistically reduce with the dose of jiedu hugan granule increased.The levels of occludin-5 in experimental group were statistically highter than those of the model group,and the levels of occludin-5 were statistically increase with the dose of Jiedu hugan granule increased,the differences were statistically significant (P ＜ 0.05).CONCLUSION:Jiedu hugan granule can improve the organizational structure of liver and small intestine,protect the damage of liver,reduce inflammation,and maintain small intestine mucosal barrier function.

Objective To investigate the reasons of repeated hospitalizations in school-age children with diabetes,and to explore the related interventions.Methods Based on purposive sampling,three endocrinologists from a Children's Hospital in Tianjin and the family members of 10 school-age children with diabetes were recruited into the study. A semi-structured depth interview was used to investigate the influence factors of the participants' compliance,acquisition of diabetes knowledge,and children's self-management. Claizzi phenomenological seven-step analysis was used to analyze data.Results Both the environmental factors and participants' attitudes would affect their compliance. The reasons of repeated hospitalizations included:insufficient knowledge and awareness of diabetes;lack of public education and concern;poor diet-control after discharge from hospital,inaccurate dose.Conclusions Intensive public education can be implemented through the internet to improve both knowledge and awareness of diabetes. Related health education should be strengthened to the children patients and their caregivers.