Machine learning-based model to predict composite thromboembolic events among Chinese elderly patients with atrial fibrillation.

OBJECTIVE: Accurate prediction of survival prognosis is helpful to guide clinical decision-making. The aim of this study was to develop a model using machine learning techniques to predict the occurrence of composite thromboembolic events (CTEs) in elderly patients with atrial fibrillation(AF). These events encompass newly diagnosed cerebral ischemia events, cardiovascular events, pulmonary embolism, and lower extremity arterial embolism. METHODS: This retrospective study included 6,079 elderly hospitalized patients (≥ 75 years old) with AF admitted to the People's Liberation Army General Hospital in China from January 2010 to June 2022. Random forest imputation was used for handling missing data. In the descriptive statistics section, patients were divided into two groups based on the occurrence of CTEs, and differences between the two groups were analyzed using chi-square tests for categorical variables and rank-sum tests for continuous variables. In the machine learning section, the patients were randomly divided into a training dataset (n = 4,225) and a validation dataset (n = 1,824) in a 7:3 ratio. Four machine learning models (logistic regression, decision tree, random forest, XGBoost) were trained on the training dataset and validated on the validation dataset. RESULTS: The incidence of composite thromboembolic events was 19.53%. The Least Absolute Shrinkage and Selection Operator (LASSO) method, using 5-fold cross-validation, was applied to the training dataset and identified a total of 18 features that exhibited a significant association with the occurrence of CTEs. The random forest model outperformed other models in terms of area under the curve (ACC: 0.9144, SEN: 0.7725, SPE: 0.9489, AUC: 0.927, 95% CI: 0.9105-0.9443). The random forest model also showed good clinical validity based on the clinical decision curve. The Shapley Additive exPlanations (SHAP) showed that the top five features associated with the model were history of ischemic stroke, high triglyceride (TG), high total cholesterol (TC), high plasma D-dimer, age. CONCLUSIONS: This study proposes an accurate model to stratify patients with a high risk of CTEs. The random forest model has good performance. History of ischemic stroke, age, high TG, high TC and high plasma D-Dimer may be correlated with CTEs.

Prediction of 30-day in-hospital mortality in older UGIB patients using a simplified risk score and comparison with AIMS65 score.

BACKGROUND: Upper gastrointestinal bleeding (UGIB) in older patients is associated with substantial in-hospital morbidity and mortality. This study aimed to develop and validate a simplified risk score for predicting 30-day in-hospital mortality in this population. METHODS: A retrospective analysis was conducted on data from 1899 UGIB patients aged ≥ 65 years admitted to a single medical center between January 2010 and December 2019. An additional cohort of 330 patients admitted from January 2020 to October 2021 was used for external validation. Variable selection was performed using five distinct methods, and models were generated using generalized linear models, random forest, support vector machine, and k-nearest neighbors approaches. The developed score, "ABCAP," incorporated Albumin < 30 g/L, Blood Urea Nitrogen (BUN) > 7.5 mmol/L, Cancer presence, Altered mental status, and Pulse rate > 100/min, each assigned a score of 1. Internal and external validation procedures compared the ABCAP score with the AIMS65 score. RESULTS: In internal validation, the ABCAP score demonstrated robust predictive capability with an area under the curve (AUC) of 0.878 (95% CI: 0.824-0.932), which was significantly better than the AIMS65 score (AUC: 0.827, 95% CI: 0.751-0.904), as revealed by the DeLong test (p = 0.048). External validation of the ABCAP score resulted in an AUC of 0.799 (95% CI: 0.709-0.889), while the AIMS65 score yielded an AUC of 0.743 (95% CI: 0.647-0.838), with no significant difference between the two scores based on the DeLong test (p = 0.16). However, the ABCAP score at the 3-5 score level demonstrated superior performance in identifying high-risk patients compared to the AIMS65 score. This score exhibited consistent predictive accuracy across variceal and non-variceal UGIB subgroups. CONCLUSIONS: The ABCAP score incorporates easily obtained clinical variables and demonstrates promising predictive ability for 30-day in-hospital mortality in older UGIB patients. It allows effective mortality risk stratification and showed slightly better performance than the AIMS65 score. Further cohort validation is required to confirm generalizability.

Poor sleep is responsible for the impaired nocturnal blood pressure dipping in elderly hypertensive: A cross-sectional study of elderly.

OBJECTIVE: This study was aimed to assess whether sleep disorder was associated with an increased risk of less nocturnal blood pressure (BP) dipping in elderly patients with hypertension. METHODS: Cases were 1006 patients, aged >60 years, who were admitted to hospital with diagnosed hypertension during 2016-2017, and were divided into three groups with the systolic nocturnal BP dipping of 10%, and 0% as the cut-off value. The patients' sleep was evaluated by Pittsburgh sleep quality index (PSQI). RESULTS: Compared to non-dipper BP rhythm patients (n = 382) and dipper BP rhythm patients (n = 132), reverse dipper patients (n = 492) exhibited higher PSQI score and had higher scores on six components with the exception of use sleep drug (p < 0.05). Multivariate logistic regression indicated that poor sleep, which was defined as high score of PSQI or its seven components, was associated with prevalence of reverse dipper in elderly hypertensive (odds ratio (OR) = 1.17, (95% confidence interval (CI), 1.13-1.21, p < 0.05) after adjusting for risk factors of hypertension. Multiple linear regression analysis showed that there was a significant negative correlation between PSQI score (include its seven components) and nocturnal BP dipping value after adjusting for risk factors of hypertension (ß = -0.584, p < 0.001). CONCLUSIONS: In elderly patients with hypertension, poor sleep quality individuals were more prone to reverse dipper BP rhythm. Even adjusting for the effect of known risk factors of hypertension, poor sleep may contribute to attenuated BP dipping in elderly hypertensive.

Cyclic RGD functionalized PLGA nanoparticles loaded with noncovalent complex of indocyanine green with urokinase for synergistic thrombolysis.

Thrombotic diseases have the characteristics of long latency period, rapid onset, and high mortality rate, which seriously threaten people's life and health. The aim of this research is to fabricate a novel indocyanine green complex of urokinase (ICG@uPA) and employ the amphiphilic PEG-PLGA polymer to deliver the complex as an enzyme-phototherapeutic synergistic thrombolysis platform. The noncovalent indocyanine green (ICG) complex of urokinase (ICG@uPA) was prepared via supramolecular self-assembly and then encapsulated into cRGD decorated polymeric nanoparticles (cRGD-ICG-uPA NPs) by double-emulsion solvent evaporation method. Then the nanoparticles (NPs) were characterized in terms of particle size, optical properties, in vitro release, etc. The targeting and thrombolytic effect of the nanoparticles were studied both in vitro and in vivo. ICG@uPA and cRGD-ICG-uPA NPs displayed significantly higher photostability and laser energy conversion efficiency than free ICG. Concomitantly, the NPs exhibited selective binding affinity to the activated platelets and specific accumulation in the mouse mesenteric vessel thrombus. Significant thrombolysis was achieved in vivo by photo-assisted synergistic therapy with reduced dose and systemic bleeding risk of uPA. Our results prove that the functional PLGA nanoparticle loaded with the ICG@uPA offers a novel option for effective and safe thrombolytic treatment.

Protective Effect of Xinmailong Injection on Rats With Myocardial Infarction.

This study aimed to investigate the protective effect of Xinmailong injection on rats with myocardial infarction. Thirty-six rats were induced myocardial infarction by operation, and six underwent sham operation. The myocardial infarction rats were randomly divided into three groups, 12 in each, and administered intraperitoneal injection of Xinmailong 5 mg/(kg·d), sodium creatine phosphate 80 mg/(kg·d), or normal saline as control respectively for 14 days. When the treatments were completed, the hemodynamic parameters of the rats were observed, and blood samples were taken to examine blood routine, blood coagulation index, liver and kidney function, inflammatory index, myocardial marker, thrombo-elastography, and other indicators. The morphology of cardiomyocytes was observed through light microscopy, and the microstructure of the myocardial cells was observed under electron microscope. No significant difference was found in blood routine, liver and kidney function, and blood coagulation index between the Xinmailong and sodium creatine phosphate groups compared with the saline control group. However, the inflammatory index and levels of myocardial markers were significantly decreased, and cardiac function was significantly improved. In terms of the morphology of myocardial cells, the Xinmailong group was similar to the sodium creatine phosphate group, the myocardial cell membrane was protected, and myocardial cell damage was reduced. In conclusion, Xinmailong is safe and had anti-inflammatory, heart-improving, and myocardial-protective effects. Its effectiveness is not inferior to that of sodium creatine phosphate.

Evaluation of homocysteine in the diagnosis and prognosis of coronary slow flow syndrome.

Aim: To identify the exact molecular markers related to coronary slow flow syndrome (CSFS) and its prognosis. Patients & methods: Data from 54 patients with CSFS diagnosed by coronary angiography and 101 normal control patients were collected and analyzed. Results: Logistic regression analysis confirmed that homocysteine (Hcy; odds ratio: 1.107; 95% CI: 1.018-1.205; p = 0.018) was associated with CSFS. Receiver-operating characteristic curve analysis identified an Hcy value of 17.1 µmol/l as an effective cut-off point for predicting CSFS. Cox survival analysis showed a relationship between high admission Hcy level (odds ratio: 1.19; 95% CI = 1.05-1.34; p = 0.005) and recurrent angina. Conclusion: Our results showed positive correlations of Hcy with CSFS and cardiac events.