Objective Heart failure(HF)complicated by acute kidney injury(AKI)significantly impacts patient outcomes,and it is crucial to make early predictions of short-term mortality.This study is focused on developing an interpretable machine learning model to enhance early prediction accuracy in such clinical scenarios.Methods This retrospective cohort study utilized data from the Medical Information Mart for Intensive Care Ⅳ(MIMIC-Ⅳ,version 2.0)database.Data from the first 24 hours after admission to the ICU were extracted and divided into a training set(70％)and a validation set(30％).We utilized the SHapley Additive exPlanation(SHAP)method to interpret the workings of an extreme gradient boosting(XGBoost)model and identify key prognostic factors.The XGBoost model's predictive ability was evaluated against three other machine learning models using the area under the curve(AUC)metric,and its interpretation was enhanced using the SHAP method.Results The study included 8 028 patients with HF complicated by AKI.The XGBoost model outperformed the other models,achieving an AUC of 0.93(95％confidence interval[CI]:0.78-0.94;accuracy=0.89),while neural network model showed the worst performance(AUC=0.79,95％CI:0.77-0.82;accuracy=0.82).Decision curve analysis showed the superior net benefit of the XGBoost model within the 9％to 60％threshold probabilities.SHAP analysis was performed to identify the top 20 predictors,with age(mean SHAP value 1.29)and Glasgow Coma Scale score(mean SHAP value 1.24)emerging as significant factors.Conclusions Our interpretable model offers an enhanced ability to predict mortality risk in HF patients with AKI in ICUs.This model can be used to assist in formulating effective treatment plans and optimizing resource allocation.

Alzheimer's disease(AD)is a highly destructive neurodegenerative disorder,and due to its complex pathology and insuffi-cient treatment,it is urgent to explore new targets that can directly address the root cause of the disease.In recent years,numerous stud-ies have shown that triggering receptor expressed on myeloid cells 2(TREM2)in microglial cells has the function of delaying the pro-gression of AD,and its abnormality plays a key role in the development and progression of AD,with a potential of being used as a target for the treatment of AD.This article reviews the biological characteristics of TREM2 and discusses its important role in the three major pathological features of AD and its potential as a target for AD treatment,in order to deepen the understanding of the role of TREM2 in AD and provide a theoretical reference for exploring new targets for AD treatment in the future.

Cannabis is a traditional industrial crop that has been used for thousands of years for medicines， foods， and textiles. Due to its active components， cannabis has attracted extensive attention in the pharmaceutical industry at home and abroad. Currently， 55 countries around the world have legalized medical marijuana， and two provinces in China， Yunnan and Heilongjiang， can legally cultivate and process industrial hemp. However， the low content of cannabidiol （CBD） in industrial hemp is not conducive to subsequent development and research. Based on this， the author took medicinal cannabis， defined by CHEN Shilin′s team as tetrahydrocannabinol （THC） content<0.3% and high CBD content， as the research object， and reviewed four aspects of the active ingredients of medicinal cannabis， the isolation and purification technology of CBD， the development and application of cannabinoid-related products and the breeding methods of medicinal cannabis. Through combing， it is suggested that subsequent research should focus on excavation of genes of CBD synthesis， molecular breeding of evolutionary cannabis by gene editing technology， development of green extraction process， discovery of more active ingredients， and high yield of CBD through synthetic biology and cell-free system， with a view to provide reference for the development and application of medicinal cannabis in China.

Abstract The popularization of the use of electronic has become a global trend, and children are exposed to devices at younger ages. A large proportion of children and adolescents spend on screen time more than 2 h which is recommended in most guidelines. The paper reviews possible effects of screen time on physical and mental health, as well as mental disorders in children and adolescents. It is found that excessive screen time showed negative impacts on mental health, including depression, anxiety, mood disorder, social adaptational problems, behavioral disorders, self injurious behaviors, and health risk behaviors. Much attention has been paid on the association between excessive screen time and mental health of children and adolescents, while possible mechanisms and influencing factors are lacking. Effective intervention studies are needed to provide a basis for child and adolescent health promotion.