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 examine the therapeutic effects and molecular mechanisms of nuclear receptor NR4A1 in alleviating postoperative ileus (POI) in a rat model.Methods:Twenty-four Sprague-Dawley rats were randomly(random number) divided into four groups ( n=6/group): sham-operated control, POI model, POI model + NR4A1 stimultior (Cytosporone B, 13 mg/kg), and POI model + NR4A1 antagonist (DIM-C-pPhCO2Me, 2 mg/kg). After 24 hours, intestinal tissues and serum were collected for analysis. We assessed: (1) histopathological changes, (2) intestinal motility via propulsion rate, (3) NR4A1 expression by immunohistochemistry, (4) epithelial apoptosis via TUNEL assay, (5) inflammatory cytokines (IL-6, IL-4) by ELISA, (6) tight junction protein (occludin) by Western blot, and (7) p38MAPK/NF-κB pathway activation through combined western blot and immunofluorescence analyses. Results:Compared with sham controls, POI model rats showed (all P<0.05): significantly reduced NR4A1 expression, severe mucosal damage, increased inflammatory infiltration, elevated epithelial apoptosis, decreased occludin expression, impaired intestinal motility, upregulated pro-inflammatory cytokines (IL-6, IL-4), and activated p38MAPK/NF-κB signaling. NR4A1 activation with Cytosporone B significantly reversed these pathological changes (all P<0.05), while NR4A1 inhibition exacerbated them. Conclusions:NR4A1 activation attenuates POI by suppressing p38MAPK/NF-κB-mediated inflammation and preserving intestinal barrier function, suggesting its potential as a therapeutic target for postoperative ileus.

Metabolic dysfunction-associated steatotic liver disease(MASLD)has become the most prevalent chronic liver disease worldwide,and China is facing a severe challenge of rapidly increasing MASLD burden.Beverages,as an important modifiable factor,have become a research focus for primary prevention and lifestyle management of MASLD.This article reviews beverage consumption trends,provides an in-depth analysis of the mechanisms and health effects of sugar-sweetened beverages,alcoholic drinks,coffee,and tea on MASLD,summarizes their potential pathogenic and protective pathways,and explores comprehensive strategies including beverage intervention,lifestyle coordination,functional beverage development,psychological and behavioral mechanism regulation,and targeted population prevention.The aim is to provide theoretical basis and practical guidance for the localized and precise prevention and control of MASLD.

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 experience and feeling of experiential health education for complications in middle-aged and elderly hypertensive patients,and to provide basis for health education model for hypertensive patients. Methods By objective sampling method,10 middle-aged and elderly hypertensive patients who received experiential health education for hypertension complications in Ruikang Hospital Affiliated to Guangxi University of Chinese Medicine from August to September 2023 were selected for semi-structured interviews,and the interview data were sorted out by Colaizzi seven-step analysis method. Results Middle-aged and elderly hypertension patients with complications of experiential health education experience can be summarized as two themes,seven subthemes,namely:the perceived benefits (improve the cognition of hypertension,complications of experience,behavior change and cognitive clarity,promote interpersonal communication),challenges (the lack of early cognitive,the limitations of traditional health education,body burden concerns). Conclusion Worry about long-term complications and lack of knowledge of disease management are common after receiving experiential health education on complications. Therefore,when designing the experiential health education program,clinical medical staff should fully consider the physiological and psychological characteristics of patients,provide personalized support,and gradually guide patients to adapt to the education process.

Objective To explore the experience and feeling of experiential health education for complications in middle-aged and elderly hypertensive patients,and to provide basis for health education model for hypertensive patients. Methods By objective sampling method,10 middle-aged and elderly hypertensive patients who received experiential health education for hypertension complications in Ruikang Hospital Affiliated to Guangxi University of Chinese Medicine from August to September 2023 were selected for semi-structured interviews,and the interview data were sorted out by Colaizzi seven-step analysis method. Results Middle-aged and elderly hypertension patients with complications of experiential health education experience can be summarized as two themes,seven subthemes,namely:the perceived benefits (improve the cognition of hypertension,complications of experience,behavior change and cognitive clarity,promote interpersonal communication),challenges (the lack of early cognitive,the limitations of traditional health education,body burden concerns). Conclusion Worry about long-term complications and lack of knowledge of disease management are common after receiving experiential health education on complications. Therefore,when designing the experiential health education program,clinical medical staff should fully consider the physiological and psychological characteristics of patients,provide personalized support,and gradually guide patients to adapt to the education process.

Liver regeneration following injury aids the restoration of liver mass and the recovery of liver function. In the present study we investigated the contribution of megakaryocytic leukemia 1 (MKL1), a transcriptional modulator, to liver regeneration. We report that both MKL1 expression and its nuclear translocation correlated with hepatocyte proliferation in cell and animal models of liver regeneration and in liver failure patients. Mice with MKL1 deletion exhibited defective regenerative response in the liver. Transcriptomic analysis revealed that MKL1 interacted with E2F1 to program pro-regenerative transcription. MAPKAPK2 mediated phosphorylation primed MKL1 for its interaction with E2F1. Of interest, phospholipase d2 promoted MKL1 nuclear accumulation and liver regeneration by catalyzing production of phosphatidic acid (PA). PA administration stimulated hepatocyte proliferation and enhanced survival in a MKL1-dependent manner in a pre-clinical model of liver failure. Finally, PA levels was detected to be positively correlated with expression of pro-regenerative genes and inversely correlated with liver injury in liver failure patients. In conclusion, our data reveal a novel mechanism whereby MKL1 contributes to liver regeneration. Screening for small-molecule compounds boosting MKL1 activity may be considered as a reasonable approach to treat acute liver failure.

Objective To investigate the efficacy of transcranial direct current stimulation(tDCS)on sleep disorder in patients with Parkinson's disease(PD).Methods From July 2021 to July 2023,patients with PD and sleep disorders in the Department of Neurosurgery of the Second People's Hospital of Guangdong Province were selected.The enrolled patients were divided into sham stimulation group(n=28)and true stimulation group(tDCS)(n=29)according to the inclusion and exclusion criteria.MDS-UPDRS,PDSS and other rating scales were used to evaluate the patients.Before and after tDCS treatment,MS-11 was used for intelligent sleep monitor-ing.The baseline and improvement of sleep disorders in the two groups before and after treatment were analyzed.Results Before tDCS treatment,there was no significant difference in general conditions and scale scores between the two groups(P＞0.05).There was no significant difference in polysomnographic monitoring results between the two groups before treatment(P＞0.05).Compared with pre-treatment,there was no significant difference in sleep monitoring results in the sham stimulation group(P＞0.05),while the sleep duration and sleep efficiency signifi-cantly increased,the nighttime awakening duration,nighttime awakening frequency,MDS-UPDRS-Ⅲ score,and LEDD dose significantly decreased in the true stimulation group,with statistical significance(P＜0.05).Conclusion Pharmacological treatment combined with tDCS treatment is effective for sleep disorders and motor function in patients with PD,which could increase the sleep duration and sleep efficiency of PD patients with sleep disorders to a certain extent,reduce the nighttime awakening duration and frequency,thereby improving the fatigue symp-toms during the daytime,and improving the efficacy of conventional pharmacological treatment for PD.

BACKGROUND: Studies have shown that the incidence and severity of corona virus disease 2019 (COVID-19) in patients with lung cancer are higher than those in healthy people. At present, the main anti-tumor treatments for lung cancer include surgery, immunotherapy, chemotherapy, radiotherapy, targeted therapy and anti-angiogenesis therapy. While the effects of different anti-tumor treatments on the occurrence and severity of COVID-19 pneumonia are not uniform. Therefore, we aimed to describe clinical characteristics and antitumor therapy of patients with lung cancer and COVID-19 pneumonia, and examined risk factors for severity in this population. METHODS: From December 1, 2022 to February 15, 2023, a retrospective study was conducted in 217 patients diagnosed with COVID-19 and pathologically confirmed lung cancer in the Jinling Hospital. We collected data about patients' clinical features, antitumor treatment regimen within 6 months, and the diagnosis and treatment of COVID-19. Risk factors for occurrence and severity of COVID-19 pneumonia were identified by univariable and multivariable Logistic regression models. RESULTS: (1) Among the 217 patients included, 51 (23.5%) developed COVID-19 pneumonia, of which 42 (82.4%) were classified as medium and 9 (17.6%) were classified as severe; (2) Univariate and multivariate analysis revealed overweight (OR=2.405, 95%CI: 1.095-5.286) and intrapulmonary focal radiotherapy (OR=2.977, 95%CI: 1.071-8.274) are risk factors for increasing occurrence of COVID-19 pneumonia, while other therapies are not; (3) Chronic obstructive pulmonary disease (COPD) history (OR=7.600, 95%CI: 1.430-40.387) was more likely to develop severe pneumonia and anti-tumor therapies such as intrapulmonary focal radiotherapy, chemotherapy, targeted therapy and immunotherapy did not increase severity. CONCLUSIONS Intrapulmonary focal radiation therapy within 6 months increased the incidence of COVID-19 pneumonia, but did not increase the severity. However, there was no safety concern for chemotherapy, targeted therapy, surgery and immunotherapy.
Humans ; COVID-19 ; Retrospective Studies ; Lung Neoplasms/drug therapy* ; Incidence ; Pneumonia/etiology*

【Objective】 To investigate the risk factors of red blood cell transfusion frequency (fRBCT) toward newborns with very/extremely low birth weight (V/ELBW) who experienced <32 weeks of gestational age and were complicated with neonatal respiratory distress syndrome (NRDS), and to explore related complications and predictive indicators that can arise from increased fRBCT, so as to provide safe and scientific blood transfusion recommendations for children with NRDS. 【Methods】 A total of 585 cases of V/ELBW NRDS newborns who experienced <32 weeks of gestational age between January 2016 and December 2020 were retrospectively collected. They were divided into three groups according to the fRBCT throughout their hospitalization[fRBCT = 0(n = 97), 1 ≤fRBCT≤2(n = 253), and fRBCT≥3(n= 235) ]. Clinical data and laboratory parameters of all three groups were compared to identify the risk factors of increased blood transfusion frequency toward V/ELBW NRDS newborns. 【Results】 Statistically significant differences in gestational age (week) (30.72±1.84 vs 29.87±1.66 vs 28.29±1.46), birth weight(g) (1 366.19± 128.12 vs 1 265.20± 163.98 vs 1 081.73± 196.06), hemoglobin level(g/L) (172.37±19.98 vs 161.96±21.41 vs 154.33±24.61) and hematocrit ratio(%) (50.46±5.74 vs 47.69±5.55 vs 45.46±6.84) at admission, as well as duration of hospital stay(d) (40 vs 51 vs 68), non-invasive ventilation(d) (6 vs 11.01 vs 24.56) and intravenous nutrition (IVN) (d) (16.73 vs 22.37 vs 30.74) were found among all three groups (all P<0.05) . Duration of invasive ventilation in Group fRBCT ≥3 (7.66 days) were significantly higher than those in Group fRBCT = 0 and Group 1 ≤fRBCT≤2, showing statistically significant differences (P<0.05). Pairwise comparison of the incidences of hematosepsis (1%, 1/97 vs 4%, 10/253 vs 9.4%, 22/235 ), retinopathy of prematurity (ROP) (16.5%, 16/97 vs 17%, 43/253 vs 46.8%, 110/235) and bronchopulmonary dysplasia (BPD) (4.1%, 4/97 vs 19%, 48/253 vs 59.1%, 139/235) among the three groups demonstrated statistically significant differences (P<0.05). The incidence of neonatal necrotizing enterocolitis (NEC) in Group fRBCT≥3 (26.8%, 63/235) also showed statistically significant differences in relation to Group fRBCT = 0 (P<0.05). Multivariate logistic regression analysis also proved that duration of hospital stay, invasive ventilation and IVN were independent risk factors for Group fRBCT≥ 3 (OR= 1.048, 1.073, and 1.030; all P<0.05). The receiver operating characteristic (ROC) curves indicated that duration of hospital stay, invasive ventilation and IVN made better predictors for Group fRBCT≥3. Areas under the ROC curves were 0.841, 0.766 and 0.716, while the corresponding cutoff values were respectively >57 days, >2.75 days and >23.75 days. 【Conclusion】 Increased fRBCT may complicate V/ELBW NRDS newborns who experienced <32 weeks of gestational age with NEC, hematosepsis, BPD and ROP. Duration of hospital stay, invasive ventilation and IVN are relatively effective predictive indicators for whether such cases have undergone ≥3 red blood cell transfusions throughout their hospitalization.