Objective To explore the application effect of multimodal somatosensory exercise based on artificial intelligence technology in home rehabilitation exercise for elderly patients with chronic obstructive pulmonary dis-ease(COPD),so as to promote COPD patients to participate in home rehabilitation exercise.Methods Using the convenient sampling method,80 elderly patients with COPD admitted to the Department of Respiratory Medicine of a tertiary A hospital in Urumqi from November 2023 to February 2024 were selected as the research subjects.Ac-cording to the random number table method,they were divided into a control group and an experimental group,with 40 cases in each group.The control group adopted the traditional exercise training method,and the experimental group adopted the multi-modal somatosensory movement based on artificial intelligence technology for exercise in-tervention,with 5 times a week,and the intervention was implemented for 12 weeks.The pulmonary function index,modified Medical Research Council scale score,physical fitness level,Chronic Obstructive Pulmonary Disease As-sessment Test scale score and exercise compliance of the 2 groups were compared before intervention and 12 weeks after intervention.Results 77 patients completed the study,with 39 in the experimental group and 38 in the control group.The forced vital capacity,forced expiratory volume in one second,forced expiratory volume in one second to forced vital capacity ratio,physical fitness level and exercise compliance of the experimental group were higher than those of the control group,while the modified British Medical Research Council scale score and Chron-ic Obstructive Pulmonary Disease Assessment Test score were lower than those of the control group.The differences were statistically significant(P＜0.05).Conclusion Somatosensory exercise based on artificial intelligence technology can improve the lung function of the patients with COPD,improve the exercise compliance and physical fitness in-dicators of elderly patients and improve the quality of life of the patients.

Objective:To strengthen the management of low-value consumables in public hospitals by introducing the Supply Processing Distribution(SPD)management model,and to explore refined operational management strategies and path optimization for low-value consumables.Methods:The SPD management model was introduced,and the entire process of hospital consumables was refinedly managed using third-party supply chain information management platforms,visualized tertiary department warehouses,Radio Frequency Identification(RFID)technology and intelligent cabinet systems,Unique Device Identification(UDI)coding,"four-code integration"and other supporting technologies.Results:Based on the analysis of the current situation in the target Hospital,specific measures related to the management of low-value consumables were introduced after the introduction of the SPD model.Conclusion:It provides a reference and guidance for the hospital's medical consumables management department to promote refined management of medical consumables under the SPD model.

Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Objective To explore the application effect of multimodal somatosensory exercise based on artificial intelligence technology in home rehabilitation exercise for elderly patients with chronic obstructive pulmonary dis-ease(COPD),so as to promote COPD patients to participate in home rehabilitation exercise.Methods Using the convenient sampling method,80 elderly patients with COPD admitted to the Department of Respiratory Medicine of a tertiary A hospital in Urumqi from November 2023 to February 2024 were selected as the research subjects.Ac-cording to the random number table method,they were divided into a control group and an experimental group,with 40 cases in each group.The control group adopted the traditional exercise training method,and the experimental group adopted the multi-modal somatosensory movement based on artificial intelligence technology for exercise in-tervention,with 5 times a week,and the intervention was implemented for 12 weeks.The pulmonary function index,modified Medical Research Council scale score,physical fitness level,Chronic Obstructive Pulmonary Disease As-sessment Test scale score and exercise compliance of the 2 groups were compared before intervention and 12 weeks after intervention.Results 77 patients completed the study,with 39 in the experimental group and 38 in the control group.The forced vital capacity,forced expiratory volume in one second,forced expiratory volume in one second to forced vital capacity ratio,physical fitness level and exercise compliance of the experimental group were higher than those of the control group,while the modified British Medical Research Council scale score and Chron-ic Obstructive Pulmonary Disease Assessment Test score were lower than those of the control group.The differences were statistically significant(P＜0.05).Conclusion Somatosensory exercise based on artificial intelligence technology can improve the lung function of the patients with COPD,improve the exercise compliance and physical fitness in-dicators of elderly patients and improve the quality of life of the patients.

Objective:To investigate the relationship between lean lipid accumulation product (LAP) and metabolic associated fatty liver disease (MAFLD).Methods:This cross-sectional study consecutively enrolled 1 990 adult subjects who underwent health examinations at the Second Affiliated Hospital of Xi′an Jiaotong University between June 2021 and May 2023. All recruited participants had a body mass index (BMI)<23 kg/m2. Data collection included general information, physical examination, serum biochemical parameter measurements, and liver ultrasonography. Participants were divided into four groups (Q1-Q4) according to quartiles value of LAP from low to high. The differences of biochemical parameters and the prevalence of lean MAFLD were compared among the groups. Logistic regression, restricted cubic spline (RCS) and receiver operating characteristic (ROC) curve analysis were used to explore the relationship between LAP and lean MAFLD and assess the diagnostic predictive value of LAP for lean MAFLD.Results:A total of 1990 participants were selected, and the detection rate of lean MAFLD was 4.97% (99 cases). The detection rate of lean MAFLD showed a significant increasing trend from Q1 to Q4 groups ( P<0.001) and respectively was 0.40%, 0.81%, 4.01% and 14.70%. The average age, male proportion, BMI and waist circumference significantly increased in a dose-response manner from Q1 to Q4 (all P<0.001). Indirect bilirubin, alanine aminotransferase, aspartate aminotransferase, γ-glutamyltranspeptidase, alkaline phosphatase, total cholesterol, triglycerides, low-density lipoprotein, serum uric acid, fasting blood glucose, fatty liver index, fibrosis-4 index and every metabolic syndrome component in groups Q2 to Q4 were significantly higher than in the Q1 group, while high-density lipoprotein levels gradually decreased (all P<0.05). RCS showed that the risk of lean MAFLD rose significantly with the increase of LAP ( P<0.005), presenting a nonlinear relationship between them ( P for nonlinear<0.001). Logistic regression analysis revealed that after adjusting other confounding factors, the risk of lean MAFLD in the Q4 group remained 4.75 times higher than that in the Q1 group (95% CI: 11.22-31.69, P<0.05). ROC curve demonstrated that LAP had a better predictive value for lean MAFLD than BMI and waist circumference, with area under the curve of 0.839, critical value of 19.59, diagnostic sensitivity of 82.8% and specificity of 75.1%. Conclusions:Elevated LAP is independently and positively correlated with the risk of lean MAFLD, and its predictive efficacy is significant superior to traditional obesity indicators.

Objective To construct a quality control model for cervical liquid-based thin cell smears using two different artificial intelligence(AI)techniques and to compare the total use of the two methods to improve the level of quality control of cervical liquid-based thin cell smears through the assistance of hybrid AI.Methods In this study,105 cervical liquid-based thin cell smear samples were used.Convolutional neural network(CNN)algorithm and Transformer network algorithm were used as specific AI algorithms in the AI model.The labeled features included the number of cells in the slice,excessive red blood cells,excessive inflammatory cells,and air bubbles.The smear samples were pre-processed and digitized by smear,followed by image segmentation and feature extraction.Using the labeled feature data,machine learning models were trained and optimized.Statistical AI and physician QC results were analyzed by calculating KAPPA index,sensitivity,specificity,area under the curve(AUC),and other indexes for AI QC results.Results CNN algorithm QC results in normal smear,inflammatory background and bloody background were significantly different from the expert review QC results(P＜0.001).Transformer algorithm QC results were similar to the expert review results,with no statistical difference(P＞0.05).General practitioner QC results were statistically different from the expert review QC results in normal smear detection rate and bloody background(P＜0.001).CNN algorithm Kappa value was 0.567,which had medium consistency with expert review results.Transformer algorithm Kappa value was 0.890,with the best consistency with expert review results.General practitioner Kappa value was 0.675,which had better consistency with expert review results.Using the expert review results as a reference standard,the predictive efficacy of the Transformer algorithm and the general practitioners' QC results was evaluated,and the predictive efficacy of the Transformer algorithm was higher than that of the general practitioners in detecting hemorrhagic backgrounds and normal smears(inflammatory backgrounds:AUC=1.000;normal smears:AUC=0.768)(hemorrhagic backgrounds:AUC=0.849;normal smears:AUC=0.849;normal smear:AUC=0.500).Conclusion In this study,we found that the Transformer algorithm was effective in improving the quality control of cervical liquid-based thin-layer cell smears by assisting doctors to perform smear quality control scoring and improving the efficiency and accuracy of smear sample quality control.It can be used as a new quality control method for cervical cancer cytological screening and has potential clinical applications.

Objective Investigate the expression level of discs large homolog associated protein 5(DLGAP5)in oral squamous cell carcinoma(OSCC)and analyze its effects on cell proliferation,migration,invasion capacity,and the Warburg effect.Methods Bioinformatics analysis was performed to identify the potential therapeutic targets for OSCC.A total of 72 OSCC tissue samples and 40 adjacent non-cancerous tissue samples collected in the First Affiliated Hospital of Shihezi University from 2013 to 2024 were included,and the clinical pathological and prognostic data were collected from patients.Immunohistochemistry assay was applied to detect the protein expression of DLGAP5,and its association with clinical pathological features was analyzed.Kaplan-Meier survival curve was plotted for survival analysis,and Cox regression model was employed to analyze the prognostic factors.The expression of DLGAP5 at mRNA and protein levels was detected in HOK,SCC-9,SCC-15,SCC-25,and CAL-27 cell lines with RT-qPCR and Western blotting,respectively.Four small interfering RNAs(siRNAs)were designed to target the DLGAP5 sequence,and then based on the transfection efficiency,the sequence with optimal silencing effect was selected for subsequent functional studies.After DLGAP5 was silenced in the CAL-27 and SCC-15 cells,Western blotting was applied to detect the expression of hexokinase 2(HK2)and enolase 1(ENO1),CCK-8,scratch healing and Transwell assays were conducted to assess cell proliferation,migration,and invasion capabilities,and glucose,lactate,and ATP detection kits were utilized to determine the glycolytic metabolic levels in OSCC cells.Results Bioinformatics analysis indicates that DLGAP5 is a potential key therapeutic target for OSCC.Experimental validation demonstrated that DLGAP5 was highly expressed in both OSCC tissues and cells(P<0.05).Analysis of clinical pathology and prognostic data revealed that DLGAP5 expression level was significantly correlated with tumor TNM stage,lymph node metastasis,and differentiation grade in OSCC patients,and high DLGAP5 expression was associated with poor prognosis(P<0.05).DLGAP5 silencing resulted in significantly reduced expression of HK2 and ENO1,markedly decreased levels of glycolytic metabolites(P<0.05),and notably declined cell proliferation,migration,and invasion capabilities(P<0.05).Conclusion DLGAP5 is highly expressed in OSCC.Silencing DLGAP5 may inhibit OSCC cell proliferation,migration,and invasion by indirectly regulating the Warburg effect,and the molecule is associated with poor prognosis in the OSCC patients.

Objective:To strengthen the management of low-value consumables in public hospitals by introducing the Supply Processing Distribution(SPD)management model,and to explore refined operational management strategies and path optimization for low-value consumables.Methods:The SPD management model was introduced,and the entire process of hospital consumables was refinedly managed using third-party supply chain information management platforms,visualized tertiary department warehouses,Radio Frequency Identification(RFID)technology and intelligent cabinet systems,Unique Device Identification(UDI)coding,"four-code integration"and other supporting technologies.Results:Based on the analysis of the current situation in the target Hospital,specific measures related to the management of low-value consumables were introduced after the introduction of the SPD model.Conclusion:It provides a reference and guidance for the hospital's medical consumables management department to promote refined management of medical consumables under the SPD model.

Objective:To investigate the relationship between lean lipid accumulation product (LAP) and metabolic associated fatty liver disease (MAFLD).Methods:This cross-sectional study consecutively enrolled 1 990 adult subjects who underwent health examinations at the Second Affiliated Hospital of Xi′an Jiaotong University between June 2021 and May 2023. All recruited participants had a body mass index (BMI)<23 kg/m2. Data collection included general information, physical examination, serum biochemical parameter measurements, and liver ultrasonography. Participants were divided into four groups (Q1-Q4) according to quartiles value of LAP from low to high. The differences of biochemical parameters and the prevalence of lean MAFLD were compared among the groups. Logistic regression, restricted cubic spline (RCS) and receiver operating characteristic (ROC) curve analysis were used to explore the relationship between LAP and lean MAFLD and assess the diagnostic predictive value of LAP for lean MAFLD.Results:A total of 1990 participants were selected, and the detection rate of lean MAFLD was 4.97% (99 cases). The detection rate of lean MAFLD showed a significant increasing trend from Q1 to Q4 groups ( P<0.001) and respectively was 0.40%, 0.81%, 4.01% and 14.70%. The average age, male proportion, BMI and waist circumference significantly increased in a dose-response manner from Q1 to Q4 (all P<0.001). Indirect bilirubin, alanine aminotransferase, aspartate aminotransferase, γ-glutamyltranspeptidase, alkaline phosphatase, total cholesterol, triglycerides, low-density lipoprotein, serum uric acid, fasting blood glucose, fatty liver index, fibrosis-4 index and every metabolic syndrome component in groups Q2 to Q4 were significantly higher than in the Q1 group, while high-density lipoprotein levels gradually decreased (all P<0.05). RCS showed that the risk of lean MAFLD rose significantly with the increase of LAP ( P<0.005), presenting a nonlinear relationship between them ( P for nonlinear<0.001). Logistic regression analysis revealed that after adjusting other confounding factors, the risk of lean MAFLD in the Q4 group remained 4.75 times higher than that in the Q1 group (95% CI: 11.22-31.69, P<0.05). ROC curve demonstrated that LAP had a better predictive value for lean MAFLD than BMI and waist circumference, with area under the curve of 0.839, critical value of 19.59, diagnostic sensitivity of 82.8% and specificity of 75.1%. Conclusions:Elevated LAP is independently and positively correlated with the risk of lean MAFLD, and its predictive efficacy is significant superior to traditional obesity indicators.

Objective To explore and validate the application value of a deep learning model based on the Huawei Cloud ModelArts platform in the diagnosis of atypical cervical cells in liquid-based cytology(LBC)and to evaluate its assistive effect for pathologists with different diagnostic experiences.Methods We retrospectively analyzed 1 044 cervical cytology specimens from Dongguan People's Hospital in 2020.The artifical intelligence(AI)-assisted diagnostic system developed on the Huawei Cloud ModelArts platform was compared with junior,intermediate,and senior pathologists for diagnosis.Sensitivity,specificity,precision,recall,and area under the receiver operating characteristic curve(AUC)were calculated to assess the diagnostic performance of the Al system and its assistive effect for pathologists with different levels of experience.The McNemar test was used to compare the differences between the Al system and manual diagnosis.P＜0.05 was considered statistically significant.Results For the 1 044 cervical exfoliated cytology specimens,the sensitivity and specificity of the AI system in detecting atypical cells was 98.96％and 89.15％,both of which were higher than those of junior doctors(81.95％and 91.81％,respectively).The overall diagnostic accuracy of the Al system was 93.68％,which was significantly higher than that of junior doctors(87.26％,P＜0.001).Al assistance could significantly improve junior doctors'ability to detect atypical cells,with the sensitivity and specificity increasing from 80.1％to 96.5％and from 85.6％to 92.3％,respectively.Conclusion The AI-assisted cervical cytology diagnostic system developed in this study demonstrated superior performance,particularly in significantly improving the diagnostic level of junior pathologists,showing promising clinical application prospects.