OBJECTIVE: To construct a prediction model for the clinical effect of eye acupuncture combined with rehabilitation therapy on ischemic stroke based on interpretable machine learning. METHODS: From January 1st, 2020 to October 1st, 2024, the clinical data of 470 patients with ischemic stroke were collected in the the Second Department of Encephalopathy Rehabilitation of the Affiliated Hospital of Liaoning University of TCM. The modified Barthel index (MBI) score before and after treatment was used to divide the patients into an effect group (291 cases) and a non-effect group (179 cases). Random forest and recursive feature elimination with cross-validation were combined to screen the predictors of the therapeutic effect of patients. Seven representative machine learning models with different principles were established according to the screening results. The predictive effect of the best model was evaluated by receiver operating characteristics (ROC), calibration, and clinical decision-making (DCA) curves. Finally, the Shapley additive explanation (SHAP) framework was used to interpret the prediction results of the best model. RESULT: ①All the machine learning models presented the area under curve (AUC) to be above 85%. Of these models, the random forest model showed the best prediction ability, with AUC of 0.96 and the precision of 0.87. ②The prediction probability of calibration curve and the actual probability showed a good prediction consistency. ③The net benefit rate of DCA curve in the range of 0.1 to 1.0 was higher than the risk threshold, indicating a good effect of model. ④SHAP explained the characteristic values of variables that affected the prediction effect of the model, meaning, more days of treatment, lower MBI score before treatment, lower level of fibrinogen, shorter days of onset and younger age. These values demonstrated the better effect of eye acupuncture rehabilitation therapy. CONCLUSION The rehabilitation effect prediction model constructed in this study presents a good performance, which is conductive to assisting doctors in formulating targeted personalized rehabilitation programs, and identifying the benefit groups of eye acupuncture combined with rehabilitation therapy and finding the advantageous groups with clinical effect. It provides more ideas for the treatment of ischemic stroke with eye acupuncture combined with rehabilitation therapy.
Humans ; Acupuncture Therapy ; Machine Learning ; Male ; Female ; Middle Aged ; Ischemic Stroke/rehabilitation* ; Aged ; Stroke Rehabilitation ; Adult ; Eye

Ras homolog gene family member A(RhoA)is a small GTPase protein.Rho-associated coiled-coil forming protein kinase(ROCK)can be activated during the occurrence and development of ischemic stroke.RhoA/ROCK signaling pathway is an important regulatory factor in the pathological process of ischemic stroke,and regulation of this signaling pathway has become a research focus in promoting neuronal recovery and improving cerebral ischemia/reperfusion injury after ischemic stroke.However,only Fasudil is currently available as a RhoA/ROCK inhibitor.The rest is still in the stage of research and development or clinical trials,and has broad research prospects.In this paper,the regulatory role and mechanism of RhoA/ROCK signaling pathway in ischemic stroke were analyzed,and the application of inhibitors and regulatory drugs were described,aiming to provide new ideas for the prevention and treatment of ischemic stroke.

Objective: Based on physical activity (PA) and sedentary behavior (SB) variables on weekdays and weekends, the study aims to cluster the physical activities inside and outside kindergartens and to explore the cluster characteristics of different children using physical fitness indicators, so as to provide new strategies and methods for early childhood education and health. Methods: From March to June 2019, 291 children aged 3-6 years from 6 kindergartens in Nanchang were recruited by a stratified cluster random sampling method. The ActiGraph GT3X-BT triaxial accelerometer was used to measure and analyze the PA and SB levels inside and outside the kindergarten. A twostep clustering algorithm model was employed for cluster analysis. Physical fitness were measured and evaluated according to the "National Physical Fitness Measurement Standard Manual (Preschool Section)". Differences in physical fitness among different clusters of children were compared, and the cluster characteristics of different children were analyzed. Results: The clustering algorithm model indicated that based on six indicators, including PA and SB inside the kindergarten on weekdays, and PA and SB outside the kindergarten on both weekdays and weekends, children could be divided into three categories:active inside (high PA, low SB inside), active outside (high PA outside), and inactive (low PA, high SB both inside and outside). The average silhouette coefficient of the model was 0.3, indicating good clustering results. Both the active inside and active outside children showed significantly higher PA inside on weekdays, PA outside on weekdays and weekends, daily low intensity physical activity (LPA) and moderate-to-vigorous physical activity (MVPA) than the inactive children ( F=157.91, 80.79 , 95.86, 95.52, 124.74, P <0.05). After adjusting for gender and age, the physical fitness scores of both active outside ( 19.03 ±0.47) and active inside (19.11±0.40) were significantly higher than those of the inactive children (17.94±0.31). Additionally, active inside children (3.91±0.14) also showed significantly better performance in continuous double-leg jumps, compared to inactive children (3.45±0.11) ( P <0.05). Conclusion Children active inside and those active outside perform well in PA. Future research should focus on the proportion of structured and unstructured PA time to enhance the overall physical fitness of children.

OBJECTIVETo study the effect of iodine supplementation on infant mortality and growth in Xinjiang.

METHODSUrine iodine, height and head circumference (HC) of children aged 5 years in two townships was measured before and yearly after iodine supplementation of irrigation water. Height and HC were expressed as Z scores (United States children used as the reference group). Neonatal and infant mortality rates were obtained from official records in three counties from 1988 to 1999, and analyzed by a logistic regression model.

RESULTSThe odds ratio of infant mortality decreased 56.49% and neonatal mortality 65.71% respectively after iodination; there was no significant difference in the odds ratio of infant or neonatal mortality between experimental and control areas without iodination. In Langru township, the mean height of 5 year-old children increased from 95 cm in 1992 to 106.9 cm in 1998 - 1999, and HC from 48.4 cm to 50.5 cm. Median urine iodine increased from <10 to 176 micro g/L. In Bakechi township, mean height increased from 91 cm in 1993 to 106.5 cm in 1998 - 1999, HC from 48.7 to 49.6 cm, and median urine iodine from 39 to 138 micro g/L.

CONCLUSIONIn Xinjiang, adequate iodine treatment markedly decreased infant and neonatal mortality, and largely preventing stunting of height and HC in children.

Adolescent ; Adult ; Animals ; Body Height ; drug effects ; Child ; Child Development ; drug effects ; Child, Preschool ; Female ; Humans ; Infant ; Infant Mortality ; trends ; Iodine ; analysis ; pharmacology ; urine ; Logistic Models ; Male ; Odds Ratio ; Plants ; chemistry ; Soil ; analysis ; Thyroid Gland ; chemistry ; Time Factors ; Water ; chemistry