Turning to critical illness is a common stage of various diseases and injuries before death. Patients usually have complex health conditions, while the treatment process involves a wide range of content, along with high requirements for doctor′s professionalism and multi-specialty teamwork, as well as a great demand for time-sensitive treatments. However, this is not matched with critical care professionals and the current state of medical care in China. Telemedicine, which shortens the distance of medical professionals and the gap of disease diagnosis and treatments in various regions through electronic information, can effectively solve the current problem. Therefore, there is an urgent need to develop a standardized, high-quality visualization telemedicine round system .Therefore, experts have been organized to search domestic and foreign literature on telemedicine round for critically ill patients and to form this consensus based on clinical experiences so as to further improve the level of critical care treatments in regions.

Objective:To explore the interrelationship between brain functional networks and features in functional magnetic resonance imaging(fMRI)of patients with Alzheimer's disease(AD),and to construct mixed-function networks(MFN),and apply them in machine learning classification models to improve the accuracy of AD classification.Methods:102 AD patients and 227 healthy subjects in the Alzheimer's Neuroimaging Initiative(ADNI)dataset were retrospectively analyzed.The partial correlation brain network of the blood oxygen level dependent(BOLD)signal was calculated and fused with low-frequency wave amplitude(ALFF),fractional low-frequency wave amplitude(fALFF)and local consistency(ReHo)features to construct MFN.Network topology parameters were extracted,and a variety of machine learning classification models were constructed based on MFN topological parameters,accuracy,precision,recall and area under the curve(AUC)were used to evaluate the predictive efficiency of the models.Results:By constructed MFN and calculated intra group to inter group ratio(IIGR),35 features could be obtained from ALFF,fALFF and ReHo feature topological parameter analysis,after rank sum test and FDR correction,there were statistical differences among 28 features(P＜0.05).The classification results show that,all the five classifiers have high classification performance on the test data set.The accuracy,precision and recall rates of random forest(RF),adaptive lifting algorithm(AdaBoost),guided aggregation algorithm(Bagging)and support vector machine(SVM)were all 99.7％,and the AUC values were up to 100％,99.5％,99.1％and 99.5％,respectively.The accuracy(98.5％),precision(98.5％),recall(98.5％),and AUC(99.1％)of the multi-layer perceptron(MLP)were slightly lower than other models,but remained excellent.It was worth noting that RF has the highest AUC value of all models at 100.0％,while Bagging has the lowest AUC value(99.1％)in the integrated approach.The results of performance comparison show that,MFN classification model can significantly improve the recognition and classification of AD disease,and greatly improve the performance of various indicators of the classifier.The results showed that,MFN classification model was superior to intelligent classification based fusion,DBN-based multitask learning,PVT-TSVM,unsupervised learning and clustering,SVM and SVM of degree 3 polynomial kernel function in key indicators such as accuracy(99.13％),AUC(99.42％),recall rate(99.46％)and specificity(99.42％)with plasma proteins,machine learning algorithms.It was further proved that MFN classification model has good generalization ability and robustness in AD disease classification.Conclusion:The AD classification model constructed based on brain mixed function network topology parameters and machine learning can improve the accuracy of AD classification.

Objective:To explore the interrelationship between brain functional networks and features in functional magnetic resonance imaging(fMRI)of patients with Alzheimer's disease(AD),and to construct mixed-function networks(MFN),and apply them in machine learning classification models to improve the accuracy of AD classification.Methods:102 AD patients and 227 healthy subjects in the Alzheimer's Neuroimaging Initiative(ADNI)dataset were retrospectively analyzed.The partial correlation brain network of the blood oxygen level dependent(BOLD)signal was calculated and fused with low-frequency wave amplitude(ALFF),fractional low-frequency wave amplitude(fALFF)and local consistency(ReHo)features to construct MFN.Network topology parameters were extracted,and a variety of machine learning classification models were constructed based on MFN topological parameters,accuracy,precision,recall and area under the curve(AUC)were used to evaluate the predictive efficiency of the models.Results:By constructed MFN and calculated intra group to inter group ratio(IIGR),35 features could be obtained from ALFF,fALFF and ReHo feature topological parameter analysis,after rank sum test and FDR correction,there were statistical differences among 28 features(P＜0.05).The classification results show that,all the five classifiers have high classification performance on the test data set.The accuracy,precision and recall rates of random forest(RF),adaptive lifting algorithm(AdaBoost),guided aggregation algorithm(Bagging)and support vector machine(SVM)were all 99.7％,and the AUC values were up to 100％,99.5％,99.1％and 99.5％,respectively.The accuracy(98.5％),precision(98.5％),recall(98.5％),and AUC(99.1％)of the multi-layer perceptron(MLP)were slightly lower than other models,but remained excellent.It was worth noting that RF has the highest AUC value of all models at 100.0％,while Bagging has the lowest AUC value(99.1％)in the integrated approach.The results of performance comparison show that,MFN classification model can significantly improve the recognition and classification of AD disease,and greatly improve the performance of various indicators of the classifier.The results showed that,MFN classification model was superior to intelligent classification based fusion,DBN-based multitask learning,PVT-TSVM,unsupervised learning and clustering,SVM and SVM of degree 3 polynomial kernel function in key indicators such as accuracy(99.13％),AUC(99.42％),recall rate(99.46％)and specificity(99.42％)with plasma proteins,machine learning algorithms.It was further proved that MFN classification model has good generalization ability and robustness in AD disease classification.Conclusion:The AD classification model constructed based on brain mixed function network topology parameters and machine learning can improve the accuracy of AD classification.

Turning to critical illness is a common stage of various diseases and injuries before death. Patients usually have complex health conditions, while the treatment process involves a wide range of content, along with high requirements for doctor′s professionalism and multi-specialty teamwork, as well as a great demand for time-sensitive treatments. However, this is not matched with critical care professionals and the current state of medical care in China. Telemedicine, which shortens the distance of medical professionals and the gap of disease diagnosis and treatments in various regions through electronic information, can effectively solve the current problem. Therefore, there is an urgent need to develop a standardized, high-quality visualization telemedicine round system .Therefore, experts have been organized to search domestic and foreign literature on telemedicine round for critically ill patients and to form this consensus based on clinical experiences so as to further improve the level of critical care treatments in regions.

Objective To analyze the characteristics of adult body composition and obesity status of three ethnic groups:Ewenki,Daur and Mongolian Buryat.Methods The bioelectrical impedance analysis(BIA)was used to measure 18 body composition components in three adults ethnic groups:245(male 124,female 121)Ewenki,207(male 90,female 117)Daur,and 181(male 74,female 107)Mongolian Buryat.The data were processed using Excel 2016 and SPSS 24.0 statistical software.Results The result of correlation analysis showed that visceral fat level was significantly and positively correlated with age(P＜0.01).Stature,total body muscle mass,estimated bone mass and trunk muscle mass were all significantly and negatively correlated with age(P＜0.01)in males and females of the three ethnic groups.The percent body fat,percent left upper limb fat and percent trunk fat were positively correlated with age in Ewenki males(P＜0.05 or P＜0.01)and the percent body fat,body mass index(BMI),percent limb fat and percent trunk fat were positively correlated with age in Ewenki females(P＜0.05 or P＜0.01).Body weight,BMI,percent left upper limb fat,left upper limb muscle mass,bilateral lower limb fat and muscle mass were all negatively correlated with age in Daur males(P＜0.05 or P＜0.01).Body weight,upper limb muscle mass and left lower limb muscle mass were negatively correlated with age(P＜0.05 or P＜0.01)in Mongolian Buryat males and percent trunk fat was positively correlated with age(P＜0.05)in Mongolian Buryat females.Comparison between ethnic groups showed that most of the body composition index values of the Ewenki and Mongolian Buryat divisions were closest to each other,and the body fat content was higher than that of the Daur.BMI,percent body fat and visceral fat level were all manifested in the Mongolian Buryat Department＞Ewenki＞Daur.Cluster analysis showed that Ewenki,Daur and Mongolian Buryat were closer to the northern groups and further from the southern groups.Conclusion The Ewenki is most similar to the Mongolian Buryat in body composition characteristics all three ethnic groups has a more serious obesity problem.

Objective To explore the common features of Chinese ethnic groups.Methods Eight body indexes of 62 ethnic groups in China were analyzed.Results The cluster analysis showed that 52 males and 59 females ethnic groups were grouped into the mixed group dominated by the northern ethnic group and the mixed group dominated by the southern ethnic group.Eight Han ethnic groups were grouped into each group,but no Han group was aggregated.The result of body index classification showed that the main body types of Chinese male population were long trunk,middle chest,wide shoulder,wide pelvis and middle leg.Middle body,wide chest,wide shoulder,wide pelvis and middle leg were the main body types of Chinese female population.This showed that the characteristics of Chinese ethnic groups had obvious consistency.The consistency of Chinese group features was related to its close origin.It should be said that Han nationality played an important role in the process of communication and integration of various ethnic groups in China.In the history of the Han nationality,there had been many large-scale population migration.The southern movement of the northern ethnic minorities into the northern Han and the southward movement of the northern Han into the south promoted the formation of the Southern Han,which made the southern Han and the northern Han had similar body features,and also promoted the southern ethnic minorities into the southern Han.In addition,the Han nationality who moved into minority areas also gradually integrated into minority areas.Conclusion There are obvious commonalities in Chinese ethnic groups.

The wheeled mobile robot(WMR)was introduced in terms of concept,development route and application progress in medical service support in the world.The advantages and disadvantages of the WMRs from some countries were analyzed,and the key technologies of WMR were described.It's pointed out the WMR would be enhanced in obstacle-crossing ability,battlefield sensing and information interaction and endurance.[Chinese Medical Equipment Journal,2024,45(3):86-94]

Objective To observe the value of artificial intelligence(AI)models based on non-contrast chest CT for measuring bone mineral density(BMD).Methods Totally 380 subjects who underwent both non-contrast chest CT and quantitative CT(QCT)BMD examination were retrospectively enrolled and divided into training set(n=304)and test set(n=76)at a ratio of 8∶2.The mean BMD of L1-L3 vertebrae were measured based on QCT.Spongy bones of T5-T10 vertebrae were segmented as RO1,radiomics(Rad)features were extracted,and machine learning(ML),Rad and deep learning(DL)models were constructed for classification of osteoporosis(OP)and evaluating BMD,respectively.Receiver operating characteristic curves were drawn,and area under the curves(AUC)were calculated to evaluate the efficacy of each model for classification of OP.Bland-Altman analysis and Pearson correlation analysis were performed to explore the consistency and correlation of each model with QCT for measuring BMD.Results Among ML and Rad models,MLBagging OP and RadBagging-OP had the best performances for classification of OP.In test set,AUC of MLBagging-OP,RadBagging-op and DLOP for classification of OP was 0.943,0.944 and 0.947,respectively,with no significant difference(all P＞0.05).BMD obtained with all the above models had good consistency with those measured with QCT(most of the differences were within the range of(x)±1.96s),which were highly positively correlated(r=0.910-0.974,all P＜0.001).Conclusion AI models based on non-contrast chest CT had high efficacy for classification of OP,and good consistency of BMD measurements were found between AI models and QCT.

Objective To explore the influence of regional differences on the body composition of the Miao nationality. Methods The bioelectrical impedance method was used to measure 17 body composition indexes of 357 adults of Miao Nationality in Guizhou (162 males and 195 females) and 471 adults of Miao Nationality in Western Hu'nan (210 males and 261 females). The correlation analysis between body composition and age, One-Way ANOVA and principal component analysis were carried out. Results The visceral fat grade and trunk fat percentage of Miao men in Guizhou and Miao in Western Hu'nan were positively correlated with age, and total muscle mass and trunk muscle mass were negatively correlated with age. The visceral fat grade and trunk fat rate of Miao women in the two regions were positively correlated with age, and the presumed bone mass and trunk muscle mass were negatively correlated with age. The index values of weight, muscle mass, estimated bone mass, water content, visceral fat grade, limb and trunk muscle mass in Guizhou Miao and Miao men in Western Hu'nan were all larger than women, and the body fat rate, limb and trunk fat mass were all smaller than women. The body fat percentages, limbs and trunk fat percentages of Guizhou Miao men and women were similar to those of Xiangxi Miao, and the muscle mass, limbs and trunk muscle mass were less than that of Xiangxi Miao. Conclusion There are obvious regional differences in muscle mass between the Miao nationality in Guizhou and the Miao nationality in Western Hu'nan.

BACKGROUND: The benefits of healthy lifestyles are well recognized. However, the extent to which improving unhealthy lifestyles reduces cardiovascular disease (CVD) risk needs to be discussed. We evaluated the impact of lifestyle improvement on CVD incidence using data from the China-PAR project (Prediction for Atherosclerotic Cardiovascular Disease Risk in China). METHODS: A total of 12,588 participants free of CVD were followed up for three visits after the baseline examination. Changes in four lifestyle factors (LFs) (smoking, diet, physical activity, and alcohol consumption) were assessed through questionnaires from the baseline to the first follow-up visit. Cox proportional hazard models were used to estimate hazard ratios (HRs) and corresponding 95% confidence intervals (CIs). The risk advancement periods (RAPs: the age difference between exposed and unexposed participants reaching the same incident CVD risk) and population-attributable risk percentage (PAR%) were also calculated. RESULTS: A total of 909 incident CVD cases occurred over a median follow-up of 11.14 years. Compared with maintaining 0-1 healthy LFs, maintaining 3-4 healthy LFs was associated with a 40% risk reduction of incident CVD (HR = 0.60, 95% CI: 0.45-0.79) and delayed CVD risk by 6.31 years (RAP: -6.31 [-9.92, -2.70] years). The PAR% of maintaining 3-4 unhealthy LFs was 22.0% compared to maintaining 0-1 unhealthy LFs. Besides, compared with maintaining two healthy LFs, improving healthy LFs from 2 to 3-4 was associated with a 23% lower risk of CVD (HR = 0.77, 95% CI: 0.60-0.98). CONCLUSIONS Long-term sustenance of healthy lifestyles or improving unhealthy lifestyles can reduce and delay CVD risk.