Amid the global wave of digital economy, China's medical artificial intelligence applications are rapidly advancing through technological innovation and policy support, while facing multifaceted evaluation and regulatory challenges. The dynamic algorithm evolution undermines the consistency of assessment criteria, multimodal systems lack unified evaluation metrics, and conflicts persist between data sharing and privacy protection. To address these issues, the China National Health Development Research Center has established a value assessment framework for artificial intelligence medical technologies, formulated the country's first technical guideline for clinical evaluation, and validated their practicality through scenario-based pilot studies. Furthermore, this paper proposes introducing a "regulatory sandbox" model to test technical compliance in controlled environments, thereby balancing innovation incentives with risk governance.
Artificial Intelligence/legislation & jurisprudence* ; China ; Humans ; Algorithms

This consensus will introduce the characteristics of fillers used in the surgical cavities of domestic nasal surgery patients based on relevant literature and expert opinions. It will also provide recommendations for the selection of cavity fillers for different nasal diseases, with chronic sinusitis as a representative example.
Humans ; Nasal Cavity/surgery* ; Nasal Surgical Procedures ; China ; Consensus ; Sinusitis/surgery* ; Dermal Fillers

AIM To investigate the clinical effects of Mahuang Fuzi Xixin Decoction combined with non-immunosuppressive treatment on patients with focal segmental glomerulosclerosis due to Spleen-Kidney Yang Deficiency.METHODS Sixty patients were randomly assigned into control group(30 cases)for 24-week intervention of non-immunosuppressive treatment,and observation group(30 cases)for 24-week intervention of both Mahuang Fuzi Xixin Decoction and non-immunosuppressive treatment.The changes in clinical effects,TCM syndrome effects,TCM syndrome score,24 h UTP,ALB,eGFR,Nephrin,Podocin and safety indices were detected.RESULTS The observation group demonstrated higher total effective rate and TCM syndrome effective rate than the control group(P＜0.05).After the treatment,the two groups displayed decreased TCM syndrome score,24 h UTP,Nephrin,Podocin(P＜0.05),and increased ALB(P＜0.05),especially for the observation group(P＜0.05).No obvious adverse reactions occured in the two groups.CONCLUSION For the patients with focal segmental glomerulosclerosis due to Spleen-Kidney Yang Deficiency,Mahuang Fuzi Xixin Decoction combined with non-immunosuppressive treatment can improve TCM syndromes,whose action mechanism may be contribute to the alleviation of podocyte injury.

Objective:To predict mechanical complications (MC) following spinal deformity surgery for adult spine deformity (ASD) using machine learning models, identify key risk factors, and develop a visualizable tool for individualized risk assessment.Methods:Clinical and radiological data from 525 patients with ASD who underwent surgery in our hospital between January 2017 and December 2021 were collected. Patients were randomly assigned to a training set (70%) and a test set (30%) for model development. The cohort included 88 males and 437 females, with a mean age of 42.2±18.1 years. Variables included demographic data, comorbidities, local and systemic radiological parameters, paraspinal muscle fat infiltration (FI), and vertebral bone quality (VBQ) scores. Multiple machine learning algorithms: Random Forest (RF), Gaussian Naive Bayes (GNB), Light GBM, Support Vector Machine (SVM), XGBoost (XGB), and Logistic Regression (LR) were trained and evaluated. Model performance was compared using the receiver operating characteristic curve (ROC) and precision-recall curve (PRC). SHAP (Shapley Additive Explanations) was used to rank risk factors, while LIME (Local Interpretable Model-Agnostic Explanations) was applied to visualize MC risk in individual cases.Results:Of the 525 patients, 135 (25.7%) developed postoperative MC. Among these, 80 (59.3%) experienced proximal junction kyphosis or failure (PJK/PJF), 7 (5.2%) had distal junction kyphosis or failure (DJK/DJF), 28 (20.7%) sustained rod fractures, and 29 (21.5%) showed significant loss of correction. In the validation cohort, the RF model achieved the highest area under the curve (AUC=0.80), followed by GNB (0.77), XGB (0.76), LR (0.74), LightGBM (0.73), and SVM (0.66). The RF model also demonstrated the best PRC value (0.58), highest sensitivity (0.65), and lowest Brier score (0.20). GNB, Light GBM, and LR models achieved the highest accuracy (0.78 each), while LightGBM exhibited the highest specificity (0.93). SHAP analysis identified higher preoperative VBQ scores, larger T 1 pelvic angle (TPA), and higher paraspinal muscle FI as the main risk factors for MC. Based on the RF model, a LIME-based tool was successfully constructed for individualized MC risk estimation. Conclusion:The RF model demonstrated the best overall predictive performance for MC. A machine learning-based prediction model has the potential to provide valuable guidance for surgical decision-making in ASD patients.

Objective:To explore the association of blood and urinary cadmium levels with lipid profile levels and dyslipidemia in Chinese adults aged 18 to 79 years.Methods:Based on the China National Human Biomonitoring (CNHBM) program, a cross-sectional survey was conducted from 2017 to 2018 using a multi-stage stratified random sampling method, including a total of 10 713 adults aged 18 to 79 years. Data was obtained through questionnaires, physical examinations, biological sample collection, and laboratory testing. Multiple linear mixed effect model (MLMM) and generalized linear mixed effect model (GLMM) were used to analyze the association of blood and creatinine-corrected urinary cadmium levels with lipid profile levels as well as dyslipidemia among adults.Results:The age of 10 713 participants was (47.23±0.24) years, with 5 372 males accounting for 61.3% of the national population. The weighted mean±standard error (SE) of total cholesterol (TC), triglycerides (TG), low-density lipoprotein cholesterol (LDL-C), and high-density lipoprotein cholesterol (HDL-C) was (5.21±0.03), (1.86±0.03), (2.96±0.03), and (1.43±0.01) mmol/L, respectively. The prevalence rate of hypercholesterolemia, hypertriglyceridemia, mixed hyperlipidemia, low HDL-C, and high LDL-C was 16.0%, 21.6%, 6.6%, 13.5%, and 10.0%, respectively. MLMM showed that, after adjusting for relevant confounders, log-transformed blood cadmium levels were positively associated with increased levels of TC, TG and LDL-C ( P<0.05). When blood cadmium levels were categorized into quartiles, compared to the lowest exposure group ( Q1), participants in the highest blood cadmium exposure group ( Q4) had increases of 0.19 (95% CI: 0.06, 0.32) mmol/L in TC and 0.25 (95% CI: 0.08, 0.43) mmol/L in TG. GLMM indicated that, after adjusting for confounders, higher blood cadmium exposure levels were associated with increased risks of hypercholesterolemia, hypertriglyceridemia, mixed hyperlipidemia, and high LDL-C ( P<0.05). Further analysis by quartiles showed that, compared to the blood cadmium Q1 exposure group, the OR value (95% CI) for the Q4 group was 1.53 (1.12, 2.08) for hypercholesterolemia, 1.54 (1.09, 2.17) for hypertriglyceridemia, 2.24 (1.47, 3.40) for mixed hyperlipidemia, and 1.49 (1.07, 2.09) for high LDL-C. Conclusion:The cadmium internal exposure levels are associated with blood lipid profile levels as well as the incidence of dyslipidemia in Chinese adults aged 18 to 79.

Porcine hemagglutinating encephalomyelitis virus(PHEV)is one of the coronaviruses susceptible to swine populations.The non-structural protein 2(NS2)encoded by its genome is fre-quently deleted during the epidemic transmission of the virus,but its biological significance re-mains unclear.In order to explore the structure and function of the NS2 protein,this study utilized platforms such as ProtParam,TMHMM,NetPhos3.1,and ExPASy to analyze its physicochemical properties,spatial structure,genetic evolution,and post-translational modification characteristics.Meanwhile,the NS2 protein was expressed in eukaryotes and transcriptome sequencing was per-formed to clarify the biological processes it participates in.The results showed that the NS2 protein consists of 233 amino acids,with a molecular weight of 26.735 kDa,and a half-life of approximately 30 hours in mammals.It includes 13 phosphorylation sites,2 N-glycosylation sites,and 1 O-glyco-sylation site,with no signal peptide and strong hydrophilicity.The a-helix accounts for the highest proportion in NS2(43.78％),followed by random coils(36.05％).The homology of the NS2 pro-tein between the epidemic strains PHEV-CC14 and PHEV-JL/2008 in Northeast China is 99.57％.The NS2 protein is widely involved in the regulation of nerve-related functions,such as axon guid-ance and synaptic development.This study preliminarily clarified the biological function of the NS2 protein,providing a new perspective for understanding the pathogenic mechanism of PHEV.

Porcine hemagglutinating encephalomyelitis virus(PHEV)is one of the coronaviruses susceptible to swine populations.The non-structural protein 2(NS2)encoded by its genome is fre-quently deleted during the epidemic transmission of the virus,but its biological significance re-mains unclear.In order to explore the structure and function of the NS2 protein,this study utilized platforms such as ProtParam,TMHMM,NetPhos3.1,and ExPASy to analyze its physicochemical properties,spatial structure,genetic evolution,and post-translational modification characteristics.Meanwhile,the NS2 protein was expressed in eukaryotes and transcriptome sequencing was per-formed to clarify the biological processes it participates in.The results showed that the NS2 protein consists of 233 amino acids,with a molecular weight of 26.735 kDa,and a half-life of approximately 30 hours in mammals.It includes 13 phosphorylation sites,2 N-glycosylation sites,and 1 O-glyco-sylation site,with no signal peptide and strong hydrophilicity.The a-helix accounts for the highest proportion in NS2(43.78％),followed by random coils(36.05％).The homology of the NS2 pro-tein between the epidemic strains PHEV-CC14 and PHEV-JL/2008 in Northeast China is 99.57％.The NS2 protein is widely involved in the regulation of nerve-related functions,such as axon guid-ance and synaptic development.This study preliminarily clarified the biological function of the NS2 protein,providing a new perspective for understanding the pathogenic mechanism of PHEV.

Objective:To predict mechanical complications (MC) following spinal deformity surgery for adult spine deformity (ASD) using machine learning models, identify key risk factors, and develop a visualizable tool for individualized risk assessment.Methods:Clinical and radiological data from 525 patients with ASD who underwent surgery in our hospital between January 2017 and December 2021 were collected. Patients were randomly assigned to a training set (70%) and a test set (30%) for model development. The cohort included 88 males and 437 females, with a mean age of 42.2±18.1 years. Variables included demographic data, comorbidities, local and systemic radiological parameters, paraspinal muscle fat infiltration (FI), and vertebral bone quality (VBQ) scores. Multiple machine learning algorithms: Random Forest (RF), Gaussian Naive Bayes (GNB), Light GBM, Support Vector Machine (SVM), XGBoost (XGB), and Logistic Regression (LR) were trained and evaluated. Model performance was compared using the receiver operating characteristic curve (ROC) and precision-recall curve (PRC). SHAP (Shapley Additive Explanations) was used to rank risk factors, while LIME (Local Interpretable Model-Agnostic Explanations) was applied to visualize MC risk in individual cases.Results:Of the 525 patients, 135 (25.7%) developed postoperative MC. Among these, 80 (59.3%) experienced proximal junction kyphosis or failure (PJK/PJF), 7 (5.2%) had distal junction kyphosis or failure (DJK/DJF), 28 (20.7%) sustained rod fractures, and 29 (21.5%) showed significant loss of correction. In the validation cohort, the RF model achieved the highest area under the curve (AUC=0.80), followed by GNB (0.77), XGB (0.76), LR (0.74), LightGBM (0.73), and SVM (0.66). The RF model also demonstrated the best PRC value (0.58), highest sensitivity (0.65), and lowest Brier score (0.20). GNB, Light GBM, and LR models achieved the highest accuracy (0.78 each), while LightGBM exhibited the highest specificity (0.93). SHAP analysis identified higher preoperative VBQ scores, larger T 1 pelvic angle (TPA), and higher paraspinal muscle FI as the main risk factors for MC. Based on the RF model, a LIME-based tool was successfully constructed for individualized MC risk estimation. Conclusion:The RF model demonstrated the best overall predictive performance for MC. A machine learning-based prediction model has the potential to provide valuable guidance for surgical decision-making in ASD patients.

Objective:To explore the association of blood and urinary cadmium levels with lipid profile levels and dyslipidemia in Chinese adults aged 18 to 79 years.Methods:Based on the China National Human Biomonitoring (CNHBM) program, a cross-sectional survey was conducted from 2017 to 2018 using a multi-stage stratified random sampling method, including a total of 10 713 adults aged 18 to 79 years. Data was obtained through questionnaires, physical examinations, biological sample collection, and laboratory testing. Multiple linear mixed effect model (MLMM) and generalized linear mixed effect model (GLMM) were used to analyze the association of blood and creatinine-corrected urinary cadmium levels with lipid profile levels as well as dyslipidemia among adults.Results:The age of 10 713 participants was (47.23±0.24) years, with 5 372 males accounting for 61.3% of the national population. The weighted mean±standard error (SE) of total cholesterol (TC), triglycerides (TG), low-density lipoprotein cholesterol (LDL-C), and high-density lipoprotein cholesterol (HDL-C) was (5.21±0.03), (1.86±0.03), (2.96±0.03), and (1.43±0.01) mmol/L, respectively. The prevalence rate of hypercholesterolemia, hypertriglyceridemia, mixed hyperlipidemia, low HDL-C, and high LDL-C was 16.0%, 21.6%, 6.6%, 13.5%, and 10.0%, respectively. MLMM showed that, after adjusting for relevant confounders, log-transformed blood cadmium levels were positively associated with increased levels of TC, TG and LDL-C ( P<0.05). When blood cadmium levels were categorized into quartiles, compared to the lowest exposure group ( Q1), participants in the highest blood cadmium exposure group ( Q4) had increases of 0.19 (95% CI: 0.06, 0.32) mmol/L in TC and 0.25 (95% CI: 0.08, 0.43) mmol/L in TG. GLMM indicated that, after adjusting for confounders, higher blood cadmium exposure levels were associated with increased risks of hypercholesterolemia, hypertriglyceridemia, mixed hyperlipidemia, and high LDL-C ( P<0.05). Further analysis by quartiles showed that, compared to the blood cadmium Q1 exposure group, the OR value (95% CI) for the Q4 group was 1.53 (1.12, 2.08) for hypercholesterolemia, 1.54 (1.09, 2.17) for hypertriglyceridemia, 2.24 (1.47, 3.40) for mixed hyperlipidemia, and 1.49 (1.07, 2.09) for high LDL-C. Conclusion:The cadmium internal exposure levels are associated with blood lipid profile levels as well as the incidence of dyslipidemia in Chinese adults aged 18 to 79.