Objective To predict the risk of in-hospital death in patients with chronic heart failure(CHF)complicated by lung infections using interpretable machine learning.Methods The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database.According to the pathogen type,the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups,and their risks of in-hospital death were compared using Kaplan-Meier survival curves.Univariate analysis and LASSO regression were used to select the features for constructing LR,AdaBoost,XGBoost,and LightGBM models,and their performance was compared in terms of accuracy,precision,F1 value,and AUC.External validation of the models was performed using the data from eICU-CRD database.SHAP algorithm was applied for interpretive analysis of XGBoost model.Results Among the 4 constructed models,the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set.In the external test set,the XGBoost model had an AUC of 0.691(95%CI:0.654-0.720)in bacterial pneumonia group and an AUC of 0.725(95%CI:0.577-0.782)in non-bacterial pneumonia group,and showed better predictive ability and stability than the other models.Conclusion The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections.The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.

Objective To predict the risk of in-hospital death in patients with chronic heart failure(CHF)complicated by lung infections using interpretable machine learning.Methods The clinical data of 1415 patients diagnosed with CHF complicated by lung infections were obtained from the MIMIC-IV database.According to the pathogen type,the patients were categorized into bacterial pneumonia and non-bacterial pneumonia groups,and their risks of in-hospital death were compared using Kaplan-Meier survival curves.Univariate analysis and LASSO regression were used to select the features for constructing LR,AdaBoost,XGBoost,and LightGBM models,and their performance was compared in terms of accuracy,precision,F1 value,and AUC.External validation of the models was performed using the data from eICU-CRD database.SHAP algorithm was applied for interpretive analysis of XGBoost model.Results Among the 4 constructed models,the XGBoost model showed the highest accuracy and F1 value for predicting the risk of in-hospital death in CHF patients with lung infections in the training set.In the external test set,the XGBoost model had an AUC of 0.691(95%CI:0.654-0.720)in bacterial pneumonia group and an AUC of 0.725(95%CI:0.577-0.782)in non-bacterial pneumonia group,and showed better predictive ability and stability than the other models.Conclusion The overall performance of the XGBoost model is superior to the other 3 models for predicting the risk of in-hospital death in CHF patients with lung infections.The SHAP algorithm provides a clear interpretation of the model to facilitate decision-making in clinical settings.

Objective To investigate the effectiveness of music therapy on patients with post-stroke aphasia.Methods Randomized controlled trials of music therapy for patients with post-stroke aphasia were systematically searched from 9 databases,such as CNKI,WanFang,PubMed,etc.The search time was from the inception of databases to July 2023.The literature was screened and extracted by 2 researchers according to the inclusion criteria,and the quality of the literature was assessed using Cochrane Manual 5.1.0.Revman 5.3 software was used for meta-analysis.Results We selected 22 studies comprising 827 participants comparing with control conditions.The meta-analysis demonstrated that music therapy significantly improved spontaneous speech[SMD=0.60,95％CI(0.40～0.80),P＜0.01],listening comprehension[SMD=0.49,95％CI(0.32～0.67),P＜0.0 1],repetition[SMD=0.77,95％CI(0.60～0.94),P＜0.01],naming[SMD=0.54,95％CI(0.29～0.78),P＜0.01],communication ability[SMD=0.40,95％CI(0.02～0.78),P＜0.01],depression[SMD=-0.75,95％CI(-1.10～-0.40),P＜0.01],but had no significant effect on the severity of aphasia[SMD=0.82,95％CI(-0.26,1.90),P=0.14].Conclusion Music therapy significantly improved language expres-sion and understanding ability,but there was no clear evidence for the improvement of aphasia severity.

The COVID-19 pandemic caused by the novel SARS-CoV-2 virus has caused havoc across the entire world. Even though several COVID-19 vaccines are currently in distribution worldwide, with others in the pipeline, treatment modalities lag behind. Accordingly, researchers have been working hard to understand the nature of the virus, its mutant strains, and the pathogenesis of the disease in order to uncover possible drug targets and effective therapeutic agents. As the research continues, we now know the genome structure, epidemiological and clinical features, and pathogenic mechanism of SARS-CoV-2. Here, we summarized the potential therapeutic targets involved in the life cycle of the virus. On the basis of these targets, small-molecule prophylactic and therapeutic agents have been or are being developed for prevention and treatment of SARS-CoV-2 infection.

Objective: To investigate the impact of blood pressure and age on arterial stiffness in general population. Methods: Participants who took part in 2010, 2012 and 2014 Kailuan health examination were included. Data of brachial ankle pulse wave velocity (baPWV) examination were analyzed. According to the WHO criteria of age, participants were divided into 3 age groups: 18-44 years group (n=11 608), 45-59 years group (n=12 757), above 60 years group (n=5 002). Participants were further divided into hypertension group and non-hypertension group according to the diagnostic criteria for hypertension (2010 Chinese guidelines for the managemengt of hypertension). Multiple linear regression analysis was used to analyze the association between systolic blood pressure (SBP) with baPWV in the total participants and then stratified by age groups. Multivariate logistic regression model was used to analyze the influence of blood pressure on arterial stiffness (baPWV≥1 400 cm/s) of various groups. Results: (1)The baseline characteristics of all participants: 35 350 participants completed 2010, 2012 and 2014 Kailuan examinations and took part in baPWV examination. 2 237 participants without blood pressure measurement values were excluded, 1 569 participants with history of peripheral artery disease were excluded, we also excluded 1 016 participants with history of cardiac-cerebral vascular disease. Data from 29 367 participants were analyzed. The age was (48.0±12.4) years old, 21 305 were males (72.5%). (2) Distribution of baPWV in various age groups: baPWV increased with aging. In non-hypertension population, baPWV in 18-44 years group, 45-59 years group, above 60 years group were as follows: 1 299.3, 1 428.7 and 1 704.6 cm/s, respectively. For hypertension participants, the respective values of baPWV were: 1 498.4, 1 640.7 and 1 921.4 cm/s. BaPWV was significantly higher in hypertension group than non-hypertension group of respective age groups (P<0.05). (3) Multiple linear regression analysis defined risk factors of baPWV: Multivariate linear regression analysis showed that baPWV was positively correlated with SBP(t=39.30, P<0.001), and same results were found in the sub-age groups (t-value was 37.72, 27.30, 9.15, all P<0.001, respectively) after adjustment for other confounding factors, including age, sex, pulse pressure(PP), body mass index (BMI), fasting blood glucose (FBG), total cholesterol (TC), smoking, drinking, physical exercise, antihypertensive medications, lipid-lowering medication. (4) Multivariate logistic regression analysis of baPWV-related factors: After adjustment for other confounding factors, including age, sex, PP, BMI, FBG, TC, smoking, drinking, physical exercise, antihypertensive medication, lipid-lowering medication, multivariate logistic regression analysis showed that risks for increased arterial stiffness in hypertension group were higher than those in non-hypertension group, the OR in participants with hypertension was 2.54 (2.35-2.74) in the total participants, and same results were also found in sub-age groups, the ORs were 3.22(2.86-3.63), 2.48(2.23-2.76), and 1.91(1.42-2.56), respectively, in each sub-age group. Conclusion SBP is positively related to arterial stiffness in different age groups, and hypertension is a risk factor for increased arterial stiffness in different age groups. Clinical Trial Registry Chinese Clinical Trial Registry, ChiCTR-TNC-11001489.

Objective: To study the risk factors for prevalence of acute myocardial infarction (AMI) in young and middle-aged population. Methods: A prospective cohort study was conducted in 110100 subjects at the age of (18-98) years who received physical examination in Kailuan Group from 2012-06 to 2014-10. Based on the limitations of male≤53 years and female≤63 years, a total of 62367 subjects were enrolled in our study. The subjects were followed-up for 2 years by the end point event of AMI to analyze the risk factors ofAMI occurrence. Results: According to AMI occurrence at the follow-up period, the subjects were divided into 2 groups: AMI group, n=56 and Control group, n=62152. Compared with Control group, AMI group had increased BMI, SBP, DBP and elevated blood levels of LDL-C, TG; AMI group also showed the higher ratios of subjects with the history of diabetes and taking anti-hypertension medication. Cox proportional hazard regression analysis indicated that age (RR=1.37), male (RR=60.54), LDL-C (RR=1.12), and TG (RR=5.93) were the risk factors forAMI occurrence in young and middle-aged population, allP<0.05. Conclusion: Age, male gender, blood levels of LDL-C, and TG were the risk factors for AMI occurrence in young and middle-aged population.

OBJECTIVE:To analyze the risk factors of adverse reaction in children induced by Azithromycin for injection. METHODS:Data and medication of 428 children used Azithromycin for injection were retrospectively collected,and logistic re-gression method was used to analyze the risk factors of adverse reactions that likely to occur. RESULTS:In the 428 children,98 re-ported adverse reactions with incidence of 22.9%,among which,53 showed gastrointestinal adverse reactions (12.4%),22 showed pain in injection site(5.1%),12 showed phlebitis(2.8%),4 showed pruritus(0.9%),2 showed rash(0.5%),3 showed liver function abnormalities(0.7%),1 showed thrombocytopenia(0.2%)and 1 showed drowsiness(0.2%). According to adverse reactions diagnostic criteria,24 were sure,23 were very likely and 51 were possible. Logistic regression analysis showed younger age [OR=0.811,95% CI(0.754,0.842),P=0.000] and long duration [OR=0.1.357,95% CI(1.212,1.519),P=0.000] might the rick factors that caused adverse reactions. CONCLUSIONS:Younger age and long duration are the possible rick factors that caused adverse reactions in children after intravenous administration of azithromycin,close observation and controlling duration should be noticed to reduce the incidence of adverse reactions in children medication.

A new urine analysis core module based on high performance 32-bit microprocessor and high precision color sensor was presented. A novel optical structure and a specific circuit were applied to improve measurement precision and temperature was used to compensate for results in this core module. The information of urine test peice, such as all original data and color RGB value, reflectivity, semi-quantitative level, etc. can be output. The results showed that the measuring precision was about 95% or above with ideal stability and reliability using this presented core module, which can be conveniently applied in various urine analyzers, and can greatly decrease the cost of urine analyzers in development and production.
Color ; Equipment Design ; Microcomputers ; Reproducibility of Results ; Temperature ; Urinalysis ; instrumentation ; methods

Objective To evaluate the predictive value of eight scoring systems (Acute Physiology and Chronic Health Evaluation Ⅱ [APACHE Ⅱ] and APACHE Ⅲ,Improved Edinburgh-Scandinavian Scale [CSS],U.S.National Institutes of Health Stroke Scale [NIHSS],Activity of Daily Living [ADL] scale,Glasgow Coma Scale [GCS],Previous History of Disease Scale and Concomitant Disease Scale) in severity and outcomes of patients with acute ischemic stroke by using discriminant analysis,and to establish their mathematical models to predict the status of early death of stroke patients.Methods Three hundred and ninety-nine patients with acute ischemic stroke,admitted to our hospital from January 2008 to December 2012,were chosen in our study; these patients were tested with APACHE Ⅱ,APACHE Ⅲ,CSS,NIHSS,ADL,GCS,Previous History of Disease Scale and Concomitant Disease Scale within 24 h of admission.All of them were divided into two groups according to groups of survival (n=278) or death (n=121) one month after disease onset.Discriminant analysis was performed on all the data and the predictive values of these eight scales in the prognosis were analyzed.Results Patients from group of death had significantly higher scores of APACHE Ⅱ,APACHE Ⅲ,CSS,NIHSS and Concomitant Disease Scale,and statistically lower scores of ADL and GCS scores than those from group of survival (P＜0.05).Cluster analysis showed that CSS and NIHSS,and APACHE Ⅱ and APACHE Ⅲ,respectively,belong to clusters,which enjoyed higher predictive values than other scales.The areas under receiver operator characteristic (ROC) curves were 0.808,0.818,0.796 and 0.794 of APACHE Ⅱ,APACHE Ⅲ,CSS and NIHSS scores,respectively,enjoying good definition; Discriminant analysis was used to analyze the eight scoring systems and mathematical models were established to predict the outcomes of stroke patients,enjoying more than 80％ of coincidence rate.Conclusion APACHE Ⅱ,APACHE Ⅲ,CSS and NIHSS are superior to the other four score systems in evaluating severity of stroke patients,whose mathematical models,having more than 80％ of accuracy rate.

ObjectiveTo investigate the current status of hope in maintenance hemodialysis patients and analyze its influential factor,in order to provide reference for effective intervention.MethodsA total of 182 maintenance hemodialysis patients were recruited from 3 dialysis centers in Guangzhou and were investigated with the self-designed questionnaire,dialysis symptom Index,the Herth hope scale,simplified coping scale and social support scale.The data were analyzed by single-factor and multiple-factor analysis.ResultsThe average score of hope in maintenance hemodialysis patients was 31.83 ±3.69,and 87.91％ of patients got a moderate hope level.The average scores of present of symptom distress,degree of distress,active coping style,passive coping style and social support were 13.44 ± 5.63,35.27 ± 18.51,2.15 ± 0.28,1.56 ± 0.33 and 42.24 ± 4.09 respectively.Multiple linear regression indicated that symptoms presence,the symptoms distress degree,the passive coping style were the risk factors of hope level and the standard regression coefficient were - 0.098,- 0.424,- 0.104,P =0.047 ～ 0.000.The social support and the active coping style were the protective factors of hope level and the standard regression coefficient were 0.183,0.226,P=0.000.And they explained 96.2％ of the variance.ConclusionThe level of hope in maintenance hemodialysis patients is moderate.Symptom distress,the coping style and social support are factors influencing hope level of patients.