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 explore the effectiveness of a hospital-to-home transitional health management program for caregivers of children with severe encephalitis,aiming to provide a reference for optimizing transitional care models for these patients.Methods A convenience sampling method was used to select 84 children with severe encephalitis and their caregivers admitted to the neurology department of a tertiary hospital in Zhengzhou between March 2023 and June 2024.According to the admission time,they were divided into an experimental group and a control group,with 42 cases in each group.The experimental group received a hospital-to-home transitional health management program in addition to routine care,while the control group received standard care and discharge instructions.Differences in caregivers' perceived benefits,caregiver burden,disease management ability,and post-intervention outcomes of the children were compared between the 2 groups before and after the intervention.Results All 42 participants in both groups completed the study.After the intervention,the experimental group reported higher perceived benefits of(91.29±9.76)compared to(84.81±12.86)in the control group,lower caregiver burden of(48.55±7.15)compared to(54.71±11.23)in the control group,greater disease management ability of(41.83±4.97)than(37.79±5.23)in the control group,and lower difficulty in disease management of(31.52±7.82)compared to(34.55±3.96)in the control group,with all differences being statistically significant(P＜0.05).No statistically significant difference was found in the prognosis of the children between the 2 groups(P=0.500).Conclusion The hospital-to-home transitional health management program can effectively enhance caregivers'perceived benefits and disease management capabilities,reduce their caregiving burden,and provide scientific evidence for optimizing transitional care for children with severe encephalitis.

To investigate body composition and associated factors in adolescents undergoing long-term regular sports training.

Xiaoaiping (XAP) Injection demonstrates the anti-prostate cancer (PCa) effects, yet the underlying mechanism remains unclear. This study aims to investigate the impact of XAP on PCa and elucidate its mechanism of action. PCa cell proliferation was evaluated using a cell counting kit-8 (CCK-8) assay. Cell apoptosis was assessed through Hoechst staining and Western blotting assays. Proteomics technology was employed to identify key molecules and significant signaling pathways modulated by XAP in PCa cells. To further validate potential key genes and important pathways, a series of assays were conducted, including acridine orange (AO) staining, transmission electron microscopy, and immunofluorescence assays. The molecular mechanism of XAP against PCa in vivo was examined using a PC3 xenograft mouse model. Results demonstrated that XAP significantly inhibited cell proliferation in multiple PCa cell lines. In C4-2 and prostate cancer cell line-3 (PC3) cells, XAP induced cellular apoptosis, evidenced by reduced B-cell lymphoma 2 (Bcl-2) levels and elevated Bcl-2-associated X (Bax) levels. Proteomic, immunofluorescence, and quantitative reverse transcription-polymerase chain reaction (qRT-PCR) investigations revealed a strong correlation between forkhead box O3a (FoxO3a) autophagic degradation and the anti-PCa action of XAP. XAP hindered autophagy by reducing the expression levels of autophagy-related protein 5 (Atg5)/autophagy-related protein 12 (Atg12) and enhancing FoxO3a expression and nuclear translocation. Furthermore, XAP exhibited potent anti-PCa action in PC3 xenograft mice and triggered FoxO3a nuclear translocation in tumor tissue. These findings suggest that XAP induces PCa apoptosis via inhibition of FoxO3a autophagic degradation, potentially offering a novel perspective on XAP injection as an effective anticancer therapy for PCa.
Male ; Humans ; Prostatic Neoplasms/physiopathology* ; Autophagy/drug effects* ; Animals ; Drugs, Chinese Herbal/pharmacology* ; Proteomics ; Mice ; Apoptosis/drug effects* ; Cell Line, Tumor ; Cell Proliferation/drug effects* ; Forkhead Box Protein O3/genetics* ; Xenograft Model Antitumor Assays ; Mice, Nude ; Mice, Inbred BALB C

Objective To explore the effectiveness of a hospital-to-home transitional health management program for caregivers of children with severe encephalitis,aiming to provide a reference for optimizing transitional care models for these patients.Methods A convenience sampling method was used to select 84 children with severe encephalitis and their caregivers admitted to the neurology department of a tertiary hospital in Zhengzhou between March 2023 and June 2024.According to the admission time,they were divided into an experimental group and a control group,with 42 cases in each group.The experimental group received a hospital-to-home transitional health management program in addition to routine care,while the control group received standard care and discharge instructions.Differences in caregivers' perceived benefits,caregiver burden,disease management ability,and post-intervention outcomes of the children were compared between the 2 groups before and after the intervention.Results All 42 participants in both groups completed the study.After the intervention,the experimental group reported higher perceived benefits of(91.29±9.76)compared to(84.81±12.86)in the control group,lower caregiver burden of(48.55±7.15)compared to(54.71±11.23)in the control group,greater disease management ability of(41.83±4.97)than(37.79±5.23)in the control group,and lower difficulty in disease management of(31.52±7.82)compared to(34.55±3.96)in the control group,with all differences being statistically significant(P＜0.05).No statistically significant difference was found in the prognosis of the children between the 2 groups(P=0.500).Conclusion The hospital-to-home transitional health management program can effectively enhance caregivers'perceived benefits and disease management capabilities,reduce their caregiving burden,and provide scientific evidence for optimizing transitional care for children with severe encephalitis.

Objective To analyze the clinical characteristics associated with prenatal diagnosis of FBN 1 gene mutations in a family.This study explores the correlation between gene mutations and their corresponding clini-cal phenotypes,emphasizing the significance of prenatal diagnosis in providing a foundation for subsequent follow-up and intervention.Methods Genomic DNA was extracted from the amniotic fluid of the fetus and the peripheral blood of the parents for trio-whole exome sequencing.The candidate variant identified was subsequently validated using Sanger sequencing.Results The pedigree comprised four generations and nine family members,with four individuals exhibiting slender limbs and toes.Among these,three showed congenital lens dislocation or subluxation.No abnormalities in the cardiovascular system were observed.Genetic testing of symptomatic individuals revealed a heterozygous mutation(c.6158G>T)in the FBN 1 gene.Conclusions The FBN 1 c.6158G>T(p.C2053F)muta-tion was identified as the pathogenic variant responsible for the condition in this family,exhibiting autosomal domi-nant inheritance.To our knowledge,this is the first reported case of the FBN 1 c.6158G>T(p.C2053F)mutation in China.Prenatal diagnosis can facilitate early confirmation of the condition and provide a foundation for subsequent in-terventions and follow-up care.

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 analyze the clinical characteristics associated with prenatal diagnosis of FBN 1 gene mutations in a family.This study explores the correlation between gene mutations and their corresponding clini-cal phenotypes,emphasizing the significance of prenatal diagnosis in providing a foundation for subsequent follow-up and intervention.Methods Genomic DNA was extracted from the amniotic fluid of the fetus and the peripheral blood of the parents for trio-whole exome sequencing.The candidate variant identified was subsequently validated using Sanger sequencing.Results The pedigree comprised four generations and nine family members,with four individuals exhibiting slender limbs and toes.Among these,three showed congenital lens dislocation or subluxation.No abnormalities in the cardiovascular system were observed.Genetic testing of symptomatic individuals revealed a heterozygous mutation(c.6158G>T)in the FBN 1 gene.Conclusions The FBN 1 c.6158G>T(p.C2053F)muta-tion was identified as the pathogenic variant responsible for the condition in this family,exhibiting autosomal domi-nant inheritance.To our knowledge,this is the first reported case of the FBN 1 c.6158G>T(p.C2053F)mutation in China.Prenatal diagnosis can facilitate early confirmation of the condition and provide a foundation for subsequent in-terventions and follow-up care.

OBJECTIVE: To observe the therapeutic effect of electroacupuncture at acupoints of liver meridian in patients with diminished ovarian reserve (DOR) of liver depression. METHODS: A total of 62 patients with DOR of liver depression were randomly divided into an electroacupuncture group (31 cases, 1 case discontinued) and a western medication group (31 cases, 1 case was eliminated). Electroacupuncture was applied at bilateral Taichong (LR 3), Ligou (LR 5), Ququan (LR 8), Jimai (LR 12) in the electroacupuncture group, with continuous wave, in frequency of 2 Hz and current of 0.5-1.0 mA, 30 min each time, once every other day, 3 times a week. Femoston was taken orally in the western medication group, oral estradiol tablets were taken for the first 14 days, followed by oral estradiol/progesterone complex tablets for the rest 14 days, 1 tablet a day. Both groups were treated for 3 consecutive menstrual cycles. Before and after treatment, the scores of TCM syndrome, self-rating anxiety scale (SAS) and self-rating depression scale (SDS) were observed, serum levels of follicle stimulating hormone (FSH) and anti-Müllerian hormone (AMH) were detected, and antral follicle count (AFC), peak systolic velocity (PSV) and resistance index (RI) of ovarian artery were measured by color Doppler ultrasound in the two groups, and the clinical efficacy was evaluated after treatment. RESULTS: After treatment, the scores of primary symptom and secondary symptom, as well as the total scores of TCM syndrome were decreased compared with those before treatment (P<0.01), the scores of SAS and SDS, as well as the serum FSH levels and RI of ovarian artery were decreased compared with those before treatment (P<0.01), while the serum AMH levels, AFC and PSV of ovarian artery were increased compared with those before treatment (P<0.05, P<0.01) in the two groups. After treatment, in the electroacupuncture group, the primary symptom score of TCM syndrome was higher than that in the western medication group (P<0.01), the secondary symptom score of TCM syndrome and the scores of SAS and SDS were lower than those in the western medication group (P<0.05, P<0.01). The total effective rate was 70.0% (21/30) in the electroacupuncture group and 73.3% (22/30) in the western medication group respectively, there was no significant difference in the total effective rate between the two groups (P>0.05). CONCLUSION Electroacupuncture at acupoints of liver meridian can effectively improve the clinical symptoms, anxiety and depression, regulate the serum sex hormone levels, increase AFC and improve ovarian blood supply in DOR patients of liver depression.
Humans ; Female ; Electroacupuncture ; Adult ; Acupuncture Points ; Meridians ; Ovarian Reserve ; Young Adult ; Liver Diseases/physiopathology* ; Liver/metabolism* ; Ovary/physiopathology* ; Treatment Outcome ; Depression/therapy*

Aim To explore the correlation between carotid atherosclerosis(CAS)and neutrophil/lymphocyte ratio(NLR)in patients with early morning hypertension,and to construct a line chart model to predict the risk of CAS in patients with hypertension in the morning.Methods 255 patients with early morning hypertension hospitalized in the Affiliated Hospital of Chengde Medical College from October 2019 to November 2022 were collected,and their basic data,blood routine and blood biochemical indexes were collected.All selected patients need to improve 24-hour ambulatory blood pressure monitoring and carotid artery color ultrasound detection.According to the presence or absence of CAS,all selected patients were divided into morning hypertension with CAS group(n=197)and morning hypertension without CAS group(n=58).Multivariate Logistic regression analysis was used to explore the risk factors of early morning hypertension with CAS,and to construct and verify an individual line chart model to predict the risk of early morning hypertension pa-tients with CAS.Results The age,NLR,neutrophils(NE),monocytes(MO),white blood cell(WBC),total cho-lesterol(TC),triglyceride(TG)and low density lipoprotein cholesterol(LDLC)increased in the early morning hyperten-sion with CAS group compared with those in the morning hypertension group without CAS,while the HDLC decreased(P＜0.05).The results of multivariate Logistic regression analysis showed that the age,NLR and TC were higher in the early morning hypertension with CAS group than those in the early morning hypertension without CAS group,while HDLC was lower;Age,NLR and TC were independent risk factors of early morning hypertension with CAS,while HDLC was inde-pendent protective factors of morning hypertension with CAS.Based on the results of multivariate Logistic regression anal-ysis,an individualized line chart model for predicting early morning hypertension with CAS was constructed.The area un-der the ROC curve of the line chart model was 0.853(95％CI:0.802-0.904,P＜0.01).The result of Hosmer Leme-show fit test was x2=1.665(P＞0.05).Conclusions There was a positive correlation between NLR and morning hy-pertension with CAS,and NLR was an independent risk factor for morning hypertension with CAS.The individualized line chart model based on age,NLR,TC and HDLC can effectively predict the risk of hypertension with CAS in the early morn-ing,which provides a theoretical basis for early detection and prevention of atherosclerosis.