OBJECTIVE:Nowadays,machine learning algorithms are gradually being applied to predict stroke and cardiovascular disease.Compared with traditional regression models,machine learning can learn from data to achieve high prediction accuracy by exploring the flexible relationship between a large number of predictive features and outcome variables,providing a new method for the formulation of individualized treatment and rehabilitation programs.This study aims to systematically evaluate stroke functional recovery and prognosis prediction models based on machine learning,comprehensively assessing their predictive performance and clinical application potential to provide references for the development,application,and promotion of related predictive models.METHODS:This review was conducted following the PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses)guidelines.Relevant literature on stroke prognosis prediction using machine learning methods was selected by searching PubMed,EMbase,Web of Science Core Collection,CNKI,WanFang,and the China Biomedical Literature Database,with the search period from January 1,2014,to July 1,2024.Two researchers independently screened the literature and extracted data based on inclusion and exclusion criteria,using the Prediction model Risk Of Bias ASsessment Tool(PROBAST)to assess model quality.RESULTS:(1)A total of 3 126 articles were obtained in the preliminary search.After screening and exclusion,18 articles were finally included.150 prediction models were constructed using 13 machine learning methods.The three most frequently used methods are Logistic Regression,Random Forest,and Extreme Gradient Boosting(XGBoost).Only one study was externally validated.Eight studies reported how the missing data were handled.(2)In terms of outcome indicators,8 studies used the combination of clinical data and imaging data to build models,9 studies only used clinical data to build models,and 1 study only used imaging data to build models.(3)Each of the 18 studies gave the most important characteristics of the study,with the most mentioned being the National Institute of Health Stroke Scale and age.All studies reported area under curve values ranging from 0.74 to 0.96,with the highest area under curve being 0.96.The overall risk of bias in all models was high.The high risk of bias in the field of model analysis was the main reason for the high risk of overall bias in all models.(4)The results of meta-analysis showed that age and National Institute of Health Stroke Scale score had significant influence on stroke prognosis,with age[MD=8.49,95％CI(6.24,10.75),P＜0.01]and National Institute of Health Stroke Scale score[MD=4.78,95％CI(2.56,7.00),P＜0.01].CONCLUSION:This study systematically evaluated the predictive model of functional recovery and prognosis of stroke based on machine learning,and all the models have good predictive potential.However,future studies should increase the sample size of the included model,adopt prospective studies,and add external validation of the model to improve the stability and prediction accuracy of the model,control the risk of bias,and contribute to the validation and promotion of the model in practical clinical applications.At the same time,the interpolation of missing values is more transparent and accurate.Although existing machine learning models show good predictive performance,it is also important to focus on the functionality and usability of the model,and the inclusion of features will reduce ease of use.We should develop easy to use model interfaces and user-friendly clinical tools to enable medical staff to better apply the model for clinical decision.

BACKGROUND:Understanding the characteristics and influencing factors of the gut microbiota in athletes can help determine the optimal gut microbial composition for relevant sport events.Further investigation in this area could provide important insights for improving athletic performance and recovery as well as developing personalized nutrition prescriptions.OBJECTIVE:To summarize the characteristics of gut microbiota in athletes,and to elucidate the important factors influencing the gut microbiota characteristics of athletes from the perspectives of exercise training and dietary intake.METHODS:A literature search was conducted using the PubMed,ScienceDirect,CNKI,WanFang and VIP databases for publications from 2004 to 2024.The search terms included"microbiota,microbiome,athlete,exercise,training,diet,nutrition,dietary fiber,protein,ketogenic,fat"in English and Chinese.After excluding studies of poor quality and irrelevant content,a total of 65 articles were included for review and analysis.RESULTS AND CONCLUSION:(1)The gut microbiota of elite athletes differs from that of the general population,characterized by increased α-diversity,elevated Firmicutes/Bacteroidetes ratio,increased abundance of beneficial bacteria,and enrichment of functional pathways contributing to athletic performance.(2)The type of sport and training load are closely related to the species structure and functional expression of the gut microbiota in athletes.(3)The bidirectional communication between the host and gut microbiota mediated by metabolites is an important mechanism by which exercise influences the gut microbiota.(4)Phase training typically induces adaptive changes in the gut microbiota,and alterations in the structure or function of the microbiota have lasting effects.(5)The type,quantity,and combination of macronutrients intake can significantly influence the structure and function of the gut microbiota,and interact synergistically or antagonistically with exercise training.(6)In the future,it is important to continue the exploration of the gut microbiota in athletes,clarify causal relationships,and establish new targets for exercise training interventions.

OBJECTIVE:Nowadays,machine learning algorithms are gradually being applied to predict stroke and cardiovascular disease.Compared with traditional regression models,machine learning can learn from data to achieve high prediction accuracy by exploring the flexible relationship between a large number of predictive features and outcome variables,providing a new method for the formulation of individualized treatment and rehabilitation programs.This study aims to systematically evaluate stroke functional recovery and prognosis prediction models based on machine learning,comprehensively assessing their predictive performance and clinical application potential to provide references for the development,application,and promotion of related predictive models.METHODS:This review was conducted following the PRISMA(Preferred Reporting Items for Systematic Reviews and Meta-Analyses)guidelines.Relevant literature on stroke prognosis prediction using machine learning methods was selected by searching PubMed,EMbase,Web of Science Core Collection,CNKI,WanFang,and the China Biomedical Literature Database,with the search period from January 1,2014,to July 1,2024.Two researchers independently screened the literature and extracted data based on inclusion and exclusion criteria,using the Prediction model Risk Of Bias ASsessment Tool(PROBAST)to assess model quality.RESULTS:(1)A total of 3 126 articles were obtained in the preliminary search.After screening and exclusion,18 articles were finally included.150 prediction models were constructed using 13 machine learning methods.The three most frequently used methods are Logistic Regression,Random Forest,and Extreme Gradient Boosting(XGBoost).Only one study was externally validated.Eight studies reported how the missing data were handled.(2)In terms of outcome indicators,8 studies used the combination of clinical data and imaging data to build models,9 studies only used clinical data to build models,and 1 study only used imaging data to build models.(3)Each of the 18 studies gave the most important characteristics of the study,with the most mentioned being the National Institute of Health Stroke Scale and age.All studies reported area under curve values ranging from 0.74 to 0.96,with the highest area under curve being 0.96.The overall risk of bias in all models was high.The high risk of bias in the field of model analysis was the main reason for the high risk of overall bias in all models.(4)The results of meta-analysis showed that age and National Institute of Health Stroke Scale score had significant influence on stroke prognosis,with age[MD=8.49,95％CI(6.24,10.75),P＜0.01]and National Institute of Health Stroke Scale score[MD=4.78,95％CI(2.56,7.00),P＜0.01].CONCLUSION:This study systematically evaluated the predictive model of functional recovery and prognosis of stroke based on machine learning,and all the models have good predictive potential.However,future studies should increase the sample size of the included model,adopt prospective studies,and add external validation of the model to improve the stability and prediction accuracy of the model,control the risk of bias,and contribute to the validation and promotion of the model in practical clinical applications.At the same time,the interpolation of missing values is more transparent and accurate.Although existing machine learning models show good predictive performance,it is also important to focus on the functionality and usability of the model,and the inclusion of features will reduce ease of use.We should develop easy to use model interfaces and user-friendly clinical tools to enable medical staff to better apply the model for clinical decision.

BACKGROUND:Understanding the characteristics and influencing factors of the gut microbiota in athletes can help determine the optimal gut microbial composition for relevant sport events.Further investigation in this area could provide important insights for improving athletic performance and recovery as well as developing personalized nutrition prescriptions.OBJECTIVE:To summarize the characteristics of gut microbiota in athletes,and to elucidate the important factors influencing the gut microbiota characteristics of athletes from the perspectives of exercise training and dietary intake.METHODS:A literature search was conducted using the PubMed,ScienceDirect,CNKI,WanFang and VIP databases for publications from 2004 to 2024.The search terms included"microbiota,microbiome,athlete,exercise,training,diet,nutrition,dietary fiber,protein,ketogenic,fat"in English and Chinese.After excluding studies of poor quality and irrelevant content,a total of 65 articles were included for review and analysis.RESULTS AND CONCLUSION:(1)The gut microbiota of elite athletes differs from that of the general population,characterized by increased α-diversity,elevated Firmicutes/Bacteroidetes ratio,increased abundance of beneficial bacteria,and enrichment of functional pathways contributing to athletic performance.(2)The type of sport and training load are closely related to the species structure and functional expression of the gut microbiota in athletes.(3)The bidirectional communication between the host and gut microbiota mediated by metabolites is an important mechanism by which exercise influences the gut microbiota.(4)Phase training typically induces adaptive changes in the gut microbiota,and alterations in the structure or function of the microbiota have lasting effects.(5)The type,quantity,and combination of macronutrients intake can significantly influence the structure and function of the gut microbiota,and interact synergistically or antagonistically with exercise training.(6)In the future,it is important to continue the exploration of the gut microbiota in athletes,clarify causal relationships,and establish new targets for exercise training interventions.

Objective:To construct a transcultural nursing competency framework for master of nursing specialist, providing reference for the cultivation and evaluation of transcultural nursing competency for master of nursing specialist.Methods:From December 2022 to March 2023, based on the cultural awareness, cultural skill, cultural knowledge, cultural encounter and cultural desire (ASKED) model of cultural competency and the group discussion, a preliminary pool of transcultural nursing competency elements for master of nursing specialist was formed using literature analysis, questionnaire survey, and semi-structured interviews. From April to July 2023, purposive sampling was used to select 20 nursing experts from universities and their affiliated hospitals in seven provinces, autonomous regions, and municipalities including Guangdong Province, Guangxi Zhuang Autonomous Region, Beijing City, Zhejiang Province, Hebei Province, Hunan Province, and Shaanxi Province as consultant experts. The transcultural nursing competency framework for master of nursing specialist was established using the Delphi method.Results:A total of 17 experts completed two rounds of consultation. The positive coefficients of the two rounds of expert consultation were 85.00% (17/20) and 100.00% (17/17), respectively. The authority coefficients of the two rounds of consultant experts were 0.826 and 0.878, respectively. The Kendall harmony coefficients for the first and second level elements in the second round of expert consultation were 0.302 ( P<0.01) and 0.304 ( P<0.01). After two rounds of expert consultations, a transcultural nursing competency framework for master of nursing specialist was established, which included five first-level elements of cultural awareness, cultural attitude, cultural knowledge, cultural skills, and cultural interaction, as well as 21 second-level elements. Conclusions:The transcultural nursing competency framework for master of nursing specialist is scientific and reliable, which can provide reference for formulating transcultural nursing competency standards for master of nursing specialist and lay a foundation for improving their cross-cultural nursing competency.

Objective:To summarize the clinical phenotype and genetic characteristics of a case of autosomal dominant mental retardation-42 (MRD42) caused by GNB1 gene mutation. Methods:The clinical and genetic data of a case of MRD42 caused by a GNB1 gene missense mutation diagnosed in the Department of Neurology, Children′s Hospital Affiliated to Zhengzhou University in March 2023 were retrospectively analyzed. The child was followed-up, the child′s data were summarized, and related literature was reviewed. Results:The patient is a 6-month-old female infant, who was admitted to hospital because of "developmental delay for 3 months, intermittent convulsions for 1 month". The clinical manifestations included generalized tonic-clonic seizures, focal seizures, intellectual disability, delayed language and motor development. Long-term video electroencephalogram showed slightly slower background activity, bilateral occipital spike and wave discharges, multispike and wave complexes during sleep. Three focal onset seizures were captured. Cranial magnetic resonance imaging suggested that the subarachnoid space of the bilateral frontotemporal areas was slightly wide. Chromosome karyotype and copy number variation analysis showed no abnormality. The results of whole exon sequencing showed a de novo heterozygous missense mutation in the GNB1 gene [NM_002074:c.155(exon5)G>A;p.Arg52Gln], which had not been reported. The seizure was effectively controlled by function rehabilitation training and anti-epileptic drug therapy. Conclusions:MRD42 is a rare autosomal dominant disorder caused by mutation in the GNB1 gene. The clinical manifestations include infantile-onset seizures, mental retardation, speech and motor development delay, etc. The de novo heterozygous missense mutation in the GNB1 gene c.155G>A(p.Arg52Gln) is the genetic cause of the proband.

Background::Growth differentiation factor-15 (GDF-15) is a stress response protein and is related to cardiovascular diseases (CVD). This study aimed to investigate the association between GDF-15 and pre-eclampsia (PE).Method::The study involved 299 pregnant women, out of which 236 had normal pregnancies, while 63 participants had PE. Maternal serum levels of GDF-15 were measured by using enzyme-linked immunosorbent assay kits and then translated into multiple of median (MOM) to avoid the influence of gestational week at blood sampling. Logistic models were performed to estimate the association between GDF-15 MOM and PE, presenting as odd ratios (ORs) and 95% confidence intervals (CIs).Results::MOM of GDF-15 in PE participants was higher compared with controls (1.588 vs. 1.000, p < 0.001). In the logistic model, pregnant women with higher MOM of GDF-15 (>1) had a 4.74-fold (95% CI= 2.23-10.08, p < 0.001) increased risk of PE, adjusted by age, preconceptional body mass index, gravidity, and parity. Conclusions::These results demonstrated that higher levels of serum GDF-15 were associated with PE. GDF-15 may serve as a biomarker for diagnosing PE.

Background::Growth differentiation factor-15 (GDF-15) is a stress response protein and is related to cardiovascular diseases (CVD). This study aimed to investigate the association between GDF-15 and pre-eclampsia (PE).Method::The study involved 299 pregnant women, out of which 236 had normal pregnancies, while 63 participants had PE. Maternal serum levels of GDF-15 were measured by using enzyme-linked immunosorbent assay kits and then translated into multiple of median (MOM) to avoid the influence of gestational week at blood sampling. Logistic models were performed to estimate the association between GDF-15 MOM and PE, presenting as odd ratios (ORs) and 95% confidence intervals (CIs).Results::MOM of GDF-15 in PE participants was higher compared with controls (1.588 vs. 1.000, p < 0.001). In the logistic model, pregnant women with higher MOM of GDF-15 (>1) had a 4.74-fold (95% CI= 2.23-10.08, p < 0.001) increased risk of PE, adjusted by age, preconceptional body mass index, gravidity, and parity. Conclusions::These results demonstrated that higher levels of serum GDF-15 were associated with PE. GDF-15 may serve as a biomarker for diagnosing PE.

Objective To explore the association between iron metabolism indexes and the risk of gestational diabetes mellitus(GDM)in pregnant women with advanced age.Methods A total of 292 pregnant women,whose age were≥35 years old and gave birth in Taicang First People's Hospital from April 2021 to April 2023,were retrospectively included and divided into GDM group and non-GDM group.The differences of iron metabolism indexes[serum ferritin(SF),serum iron(SI)and hemoglobin(Hb)]measured from the 20 to 24 weeks of gestation were compared between the two groups.Multivariable Logistic regression model was used to explore the association of SF,SI and Hb with GDM.Based on the data of single nucleotide polymorphism from IEU OpenGWAS(http://gwas.mr-cieu.ac.uk/)and FinnGen datasets,two samples Mendelian randomization analysis were conducted to explore the causal relationship between iron metabolism indexes and GDM by using the methods of Inverse Variance Weighted(IVW).Results In the maximally ad-justed multi-factor logistic models,the statistically significant association between SF measured from 20 to 24 weeks of gestation and the risk of GDM was found[odds ratio(95％confident interval)=1.02(1.01-1.04),P=0.001].The association between Hb and GDM was marginally significant[odds ratio(95％confident interval)=1.04(1.00-1.07),P=0.044],but no association between SI and GDM reached statistical significance.However,Mendelian randomization analysis showed there was no significant evidence for causal association between SF,Hb and GDM.Conclusion SF examined at 20 to 24 weeks of gestation could be used as a biomarker of GDM in the pregnant women with advanced age,but no evidence supported the causal association between SF and GDM.

Objective:To explore the correlation between frailty and foot care behavior in elderly patients with high-risk diabetic foot.Methods:From January to June 2022, 220 patients with high-risk diabetic foot who were admitted to the Department of Endocrinology and Department of Geriatrics of Xuanwu Hospital of Capital Medical University were selected by convenience sampling as the research object. The patients were investigated with the General Information Questionnaire, Gavin's Weighted Scale for Diabetic Foot Risk Factors for Progression to Ulceration, the Chinese version of the Frail Scale and the Foot Care Behavior Questionnaire for Diabetic Patients. Spearman correlation analysis was used to explore the correlation between frailty and foot care behavior in elderly patients with high-risk diabetic foot. Multiple linear regression was used to analyze the influencing factors of foot care behavior in elderly patients with high-risk diabetic foot. A total of 220 questionnaires were distributed, and 210 valid questionnaires were collected, with an effective response rate of 95.45% (210/220) .Results:The standardized score of the Foot Care Behavior Questionnaire for Diabetic Patients among 210 elderly patients with high-risk diabetic foot was (56.65±11.27), which was in the middle to low level. Among them, 126 patients (60.00%) were at a low level, and 80 patients (38.10%) were at a middle level. The incidence of frailty in 210 elderly patients with high-risk diabetic foot was 27.14% (57/210). The results of correlation analysis showed that the frailty score of elderly patients with high-risk diabetic foot were negatively correlated with the scores of the foot and footwear examination, foot cleaning and maintenance, footwear selection, and the total score of Foot Care Behavior Questionnaire for Diabetic Patients ( P<0.05). The results of multiple linear regression analysis showed that gender, frailty, foot risk classification and living conditions were the influencing factors of foot care behavior in elderly patients with high-risk diabetic foot ( P<0.05) . Conclusions:The foot care behavior of elderly patients with high-risk diabetic foot needs to be improved. The higher the degree of frailty, the lower the level of foot care behavior. Medical and nursing staff should formulate targeted intervention measures according to the characteristics of patients to improve or delay the progression of patients' frailty, thereby improving their foot care behavior and preventing the occurrence of diabetic foot.