OBJECTIVE To analyze the incidence of cyclosporine （CsA）-associated acute kidney injury （AKI） in hospitalized patients， identify influencing factors， and construct a risk prediction model. METHODS A single-center retrospective study was conducted， enrolling clinical data from hospitalized patients treated with CsA at the First Affiliated Hospital of Shandong First Medical University & Shandong Provincial Qianfoshan Hospital from January 2018 to July 2024. The patients were classified into AKI group and non-AKI group based on the occurrence of CsA-related AKI. Univariate analysis and multivariate Logistic regression analysis were used to identify independent risk factors for CsA-related AKI， and a risk prediction model was constructed and its performance was evaluated. RESULTS A total of 439 patients were included， of whom 54 developed CsA-related AKI， with an incidence rate of 12.30%. The occurrence of CsA-associated AKI was positively correlated with concurrent bacterial pulmonary infection， cytomegalovirus viremia， respiratory failure， renal insufficiency， gastrointestinal bleeding， and peripheral central venous catheterization （odds ratios of 763.750， 16.944， 41.933， 236.806， 17.537 and 212.789， respectively； P ＜0.05）； while uric acid， prealbumin， and calcium levels were negatively associated with it （odds ratios of 0.983， 0.967 and 0.058， respectively； P ＜0.05）. The prediction model constructed based on the above factors yielded a χ 2 value of 10.254 （ P ＞0.05） in the Hosmer-Lemeshow test. The average area under the curve （AUC） from 10-fold cross-validation was 0.885. The AUC of the receiver operating characteristic curve was 0.883， with a sensitivity of 84.3% and a specificity of 80.4%， respectively， at the optimal cutoff value of 0.1. CONCLUSIONS Six factors， including concurrent bacterial pulmonary infection and cytomegalovirus viremia， are positively associated with the occurrence of CsA-related AKI； while uric acid， prealbumin， and calcium levels are negatively associated. The Logistic regression model constructed based on these factors demonstrates good predictive performance and can assist clinic in conducting early risk assessment and personalized 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.

Objective:To determine the detection rate of myopia among primary and secondary school students in Hunan Province in 2022 and to analyze the influencing factors at both the school and individual levels, thereby providing a scientific basis for developing myopia prevention and control strategies.Methods:From October to November 2022, a multi-stage stratified cluster random sampling method was employed to select students from Year 4 of primary school to Year 3 of senior high school across 14 prefecture-level (autonomous prefecture) cities in Hunan Province for vision screening and questionnaire surveys. A multilevel regression model was utilized to analyze the influencing factors of myopia at both the school and individual levels.Results:A total of 189 343 primary and secondary school students were included in this study. The overall myopia detection rate was 55.56%, with a significantly higher prevalence observed in female students (60.49%) compared to males (51.03%) and in urban students (59.12%) versus those from rural areas (53.50%). A marked upward trend in myopia prevalence was identified with advancing grade levels (trend test χ2=16 246.13, P<0.001). Multilevel regression analysis revealed that at the individual level, female gender, higher grade level, parental myopia history, daily homework duration ≥2 hours after school, improper reading/writing postures, and taking breaks only after more than 15 minutes of near work were associated with an increased risk of myopia. Conversely, adequate sleep duration, outdoor activity ≥2 hours, and outdoor breaks during recess demonstrated protective effects. At the school level, non-compliant blackboard illumination uniformity emerged as a significant risk factor for myopia development. Conclusions:The detection rate of myopia among primary and secondary school students in Hunan Province remains relatively high and is associated with multiple factors at both the school and individual levels. Targeted interventions should be implemented at different levels to mitigate the risk of myopia.

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.

OBJECTIVES: The detection rate of scoliosis among school-aged children has been rising annually, varying by region, and has become a major public health concern affecting both physical and mental health. Its onset is multifactorial, and early screening combined with targeted interventions can alter disease progression. This study aims to investigate the prevalence and influencing factors of scoliosis among primary and secondary school students in Hunan Province, providing scientific evidence for targeted prevention strategies. METHODS: A stratified, randomized cluster sampling method was used to select 281 401 students from 14 prefecture-level cities in Hunan Province for scoliosis screening, physical examination, and questionnaire survey. The chi-square test was used for group comparisons, and trend chi-square test analyzed differences in screening positive rate by age. A multilevel regression model was applied to identify influencing factors, and ArcGIS was used to visualize spatial distribution patterns of scoliosis. RESULTS: The overall screening positive rate for scoliosis among Hunan students was 1.61%. Urban areas had a significantly higher rate than rural counties (2.81% vs 0.98%; P<0.01). The rate was equal between boys and girls (1.61% each). Underweight students had a higher rate than those with normal weight, overweight, or obesity (P<0.01). Stratified by age, urban students aged 6-18 years consistently showed higher positive rates than rural peers (P<0.001). No significant gender differences were observed at most ages (all P>0.05), except at age 11, where the females had a higher rate (1.28% vs 1.02%; P=0.048). After age 11, underweight students exhibited significantly higher positive rates than those with normal or higher BMI(all P<0.05). Across all groups, urban/rural, male/female, underweight/normal/overweight/obese, the scoliosis rate increased with age. By region, the screening positive rate ranged from 0.38% to 3.36%, with the top three being Chenzhou (3.36%), Xiangtan (2.78%), and Hengyang (2.71%), while the lowest was Xiangxi Tujia and Miao Autonomous Prefecture (0.38%). Multilevel regression analysis revealed that age (OR=1.160, 95% CI 1.135 to 1.186) and urban residence (OR=2.497, 95% CI 1.946 to 3.205) were positively associated with scoliosis risk (both P<0.01). Conversely, female gender (OR=0.931, 95% CI 0.874 to 0.993), normal nutritional status (OR=0.751, 95% CI 0.671 to 0.840), overweight (OR=0.513, 95% CI 0.447 to 0.590), obesity (OR=0.418, 95% CI 0.358 to 0.489), and engaging in ≥ 60 minutes of moderate-to-vigorous physical activity 2 to 4 days (OR=0.928, 95% CI 0.865 to 0.996) or 5 to 7 days per week (OR=0.912, 95% CI 0.833 to 0.998) were negatively associated with scoliosis risk (all P<0.05). CONCLUSIONS The prevalence of scoliosis among primary and secondary school students in Hunan Province is relatively high and is significantly associated with age, gender, urban-rural status, nutritional condition, and physical activity frequency. Targeted interventions and enhanced monitoring in high-risk regions and populations are essential to prevent and control scoliosis.
Humans ; Scoliosis/epidemiology* ; Male ; Female ; Adolescent ; China/epidemiology* ; Prevalence ; Child ; Students/statistics & numerical data* ; Rural Population/statistics & numerical data* ; Urban Population/statistics & numerical data* ; Surveys and Questionnaires ; Risk Factors ; Thinness/epidemiology*

The in-depth research of artificial intelligence in the medical field has greatly improved the workflow and diagnostic ability of diagnostic radiology.This article focuses on artificial intelligence technology in the field of interventional medicine,and enumerates its potential application scenarios,including improving image analysis capabilities to assist diagnosis and predict treatment response.It also describes the challenges that need to be overcome for practical application.Finally,with the continuous development of artificial intelligence in interventional medicine,artificial intelligence will further optimize the channels of interventional medicine and bring revolutionary changes to the clinical practice of interventional medicine.

Objective:To determine the detection rate of myopia among primary and secondary school students in Hunan Province in 2022 and to analyze the influencing factors at both the school and individual levels, thereby providing a scientific basis for developing myopia prevention and control strategies.Methods:From October to November 2022, a multi-stage stratified cluster random sampling method was employed to select students from Year 4 of primary school to Year 3 of senior high school across 14 prefecture-level (autonomous prefecture) cities in Hunan Province for vision screening and questionnaire surveys. A multilevel regression model was utilized to analyze the influencing factors of myopia at both the school and individual levels.Results:A total of 189 343 primary and secondary school students were included in this study. The overall myopia detection rate was 55.56%, with a significantly higher prevalence observed in female students (60.49%) compared to males (51.03%) and in urban students (59.12%) versus those from rural areas (53.50%). A marked upward trend in myopia prevalence was identified with advancing grade levels (trend test χ2=16 246.13, P<0.001). Multilevel regression analysis revealed that at the individual level, female gender, higher grade level, parental myopia history, daily homework duration ≥2 hours after school, improper reading/writing postures, and taking breaks only after more than 15 minutes of near work were associated with an increased risk of myopia. Conversely, adequate sleep duration, outdoor activity ≥2 hours, and outdoor breaks during recess demonstrated protective effects. At the school level, non-compliant blackboard illumination uniformity emerged as a significant risk factor for myopia development. Conclusions:The detection rate of myopia among primary and secondary school students in Hunan Province remains relatively high and is associated with multiple factors at both the school and individual levels. Targeted interventions should be implemented at different levels to mitigate the risk of myopia.

BACKGROUND:Early identification of patients requiring ventilator support will be beneficial for the outcomes of botulism.The present study aimed to establish a new scoring system to predict mechanical ventilation(MV)for botulism patients. METHODS:A single-center retrospective study was conducted to identify risk factors associated with MV in botulism patients from 2007 to 2022.Univariate analysis and multivariate logistic regression analysis were used to screen out risk factors for constructing a prognostic scoring system.The area under the receiver operating characteristic(ROC)curve was calculated. RESULTS:A total of 153 patients with botulism(66 males and 87 females,with an average age of 43 years)were included.Of these,49 patients(32.0%)required MV,including 21(13.7%)with invasive ventilation and 28(18.3%)with non-invasive ventilation.Multivariate analysis revealed that botulinum toxin type,pneumonia,incubation period,degree of hypoxia,and severity of muscle involvement were independent risk factors for MV.These risk factors were incorporated into a multivariate logistic regression analysis to establish a prognostic scoring system.Each risk factor was scored by allocating a weight based on its regression coefficient and rounded to whole numbers for practical utilization([botulinum toxin type A:1],[pneumonia:2],[incubation period≤1 day:2],[hypoxia<90%:2],[severity of muscle involvement:grade II,3;grade III,7;grade IV,11]).The scoring system achieved an area under the ROC curve of 0.82(95%CI 0.75-0.89,P<0.001).At the optimal threshold of 9,the scoring system achieved a sensitivity of 83.7%and a specificity of 70.2%. CONCLUSION:Our study identified botulinum toxin type,pneumonia,incubation period,degree of hypoxia,and severity of muscle involvement as independent risk factors for MV in botulism patients.A score≥9 in our scoring system is associated with a higher likelihood of requiring MV in botulism patients.This scoring system needs to be validated externally before it can be applied in clinical settings.

End-stage liver diseases,such as cirrhosis and liver cancer caused by hepatitis B,are often combined with hepatic encephalopathy(HE);ammonia poisoning is posited as one of its main pathogenesis mechanisms.Ammonia is closely related to autophagy,but the molecular mechanism of ammonia's regulatory effect on autophagy in HE remains unclear.Sialylation is an essential form of glycosylation.In the nervous system,abnormal sialylation affects various physiological processes,such as neural development and synapse formation.ST3 β-galactoside α2,3-sialyltransferase 6(ST3GAL6)is one of the significant glycosyltransferases responsible for adding α2,3-linked sialic acid to substrates and generating glycan structures.We found that the expression of ST3GAL6 was upregulated in the brains of mice with HE and in astrocytes after ammonia induction,and the expression levels of α2,3-sialylated glycans and autophagy-related proteins microtubule-associated protein light chain 3(LC3)and Beclin-1 were upregulated in ammonia-induced astrocytes.These findings suggest that ST3GAL6 is related to autophagy in HE.Therefore,we aimed to determine the regulatory relationship between ST3GAL6 and autophagy.We found that silencing ST3GAL6 and blocking or degrading α2,3-sialylated glycans by way of Maackia amurensis lectin-Ⅱ(MAL-Ⅱ)and neuraminidase can inhibit autophagy.In addition,silencing the expression of ST3GAL6 can downregulate the expression of heat shock protein β8(HSPB8)and Bcl2-associated athanogene 3(BAG3).Notably,the overexpression of HSPB8 partially restored the reduced autophagy levels caused by silencing ST3GAL6 expression.Our results indicate that ST3GAL6 regulates autophagy through the HSPB8-BAG3 complex.

Objective:To evaluate the application effect of the nurse-led catheter extraction assessment model for children in PICU.Methods:From January to May 2020, 100 children with short-term catheter in PICU of Guangzhou Women and Children Medical Center were selected by convenient sampling method as the experimental group, the need for urethral catheter indwelling was assessed daily using an evidence-based assessment scale in PICU children, and the unnecessary indwelling catheters were removed timely, and 109 children with indwelling urethral catheters from August to December 2019 were collected as the control group, the catheter was removed by the nurse on medical advice, recorded and compared days of indwelling of catheters, the incidence of patients with catheter-associated urinary tract infection , resetting of catheters and the length of stay in ICU between the two groups.Results:The median and interquartile spacing of the days with indwelling catheter were 5.0 (6.0) days in the experimental group and 6.0 (6.0) days in the control group ( Z=-2.01, P<0.05) . In the experimental group, the incidence of catheter-associated urinary tract infection was 1.000 percent (1/100), and in the control group, the incidence of catheter-associated urinary tract infection was 1.835 percent (2/109); in the experimental group, 2 cases of urethral catheter were reset, and in the control group, 2 cases of urethral catheter were reset; the median and interquartile spacing of the length of stay in ICU was 6.5 (7.0) days in the experimental group and 7.0 (8.0) days in the control group. The differences of the above three indexes between the two groups were statistically significant ( χ2=0.26, 0.01, Z=-0.96, all P>0.05). Conclusions:The nurse-led catheter extraction assessment model for children can effectively shorten the catheter indwelling days for children in PICU, which has certain clinical practice significance for reducing the incidence of catheter-associated urinary tract infection.