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

Objective: To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE). Materials and Methods: We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson’s partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation. Results: In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%). Conclusion Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.

Objective: To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE). Materials and Methods: We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson’s partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation. Results: In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%). Conclusion Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.

Objective: To explore glymphatic impairment in pediatric refractory epilepsy (RE) using multi-parameter magnetic resonance imaging (MRI), assess its relationship with white-matter (WM) abnormalities and clinical indicators, and preliminarily evaluate the performance of multi-parameter MRI in discriminating RE from drug-sensitive epilepsy (DSE). Materials and Methods: We retrospectively included 70 patients with DSE (mean age, 9.7 ± 3.5 years; male:female, 37:33) and 26 patients with RE (9.0 ± 2.9 years; male:female, 12:14). The diffusion tensor imaging analysis along the perivascular space (DTI-ALPS) index as well as fractional anisotropy (FA), mean diffusivity (MD), and nodal efficiency values were measured and compared between patients with RE and DSE. With sex and age as covariables, differences in the FA and MD values were analyzed using tract-based spatial statistics, and nodal efficiency was analyzed using a linear model. Pearson’s partial correlation was analyzed. Receiver operating characteristic (ROC) curves were used to evaluate the discrimination performance of the MRI-based machine-learning models through five-fold cross-validation. Results: In the RE group, FA decreased and MD increased in comparison with the corresponding values in the DSE group, and these differences mainly involved the callosum, right and left corona radiata, inferior and superior longitudinal fasciculus, and posterior thalamic radiation (threshold-free cluster enhancement, P < 0.05). The RE group also showed reduced nodal efficiency, which mainly involved the limbic system, default mode network, and visual network (false discovery rate, P < 0.05), and significantly lower DTI-ALPS index (F = 2.0, P = 0.049). The DTI-ALPS index was positively correlated with FA (0.25 ≤ r ≤ 0.32) and nodal efficiency (0.22 ≤ r ≤ 0.37), and was negatively correlated with the MD (-0.24 ≤ r≤ -0.34) and seizure frequency (r = -0.47). A machine-learning model combining DTI-ALPS, FA, MD, and nodal efficiency achieved a cross-validated ROC curve area of 0.83 (sensitivity, 78.2%; specificity, 84.8%). Conclusion Pediatric patients with RE showed impaired glymphatic function in comparison with patients with DSE, which was correlated with WM abnormalities and seizure frequency. Multi-parameter MRI may be feasible for distinguishing RE from DSE.

Objective:To synthesize 18F labeled PET imaging probe based on giredestrant (GDC-9545), an estrogen receptor α (ERα) degrader and antagonist, and evaluate its ERα-targeting properties. Methods:The precursor-GDC (PGDC), GDC and 18F-GDC were synthesized. The radiochemical yields, radiochemical purity, specific activity, lipid water partition coefficient log P, and stability of 18F-GDC were determined. Cellular uptake and blocking assays of 18F-GDC were performed using ERα high-expressing MCF-7 cells and ERα low-expressing MDA-MB-231 cells. MCF-7 and MDA-MB-231 tumor-bearing mice were constructed and microPET imaging was performed. The biodistribution of 18F-GDC in MCF-7 tumor-bearing mice was studied. Data were analyzed by using two-way repeated measures analysis of variance and Bonferroni correction method. Results:PGDC and GDC were successfully prepared with the purity more than 95%. 18F-GDC was successfully synthesized with the labeling yield of (11.25±3.18)%, radiochemical purity more than 98%, specific activity of (140.66±17.20)GBq/μmol and lipid water partition coefficient log P of 2.12±0.13. 18F-GDC was stable in PBS or mouse serum, with the radiochemical purity still more than 98% after 2 h of incubation. After incubation for 60 and 120min, the uptakes of 18F-GDC in MCF-7 cells were significantly higher than those in MDA-MB-231 cells ( F values: 113.78, 369.70, P values: 0.002, 0.001 (Bonferroni correction method)), and could be blocked by GDC. 18F-GDC had a high uptake in MCF-7 tumors and could be blocked by GDC. Tumor uptake at 60 min post-injection was (7.23±0.74) percentage activity of injection dose per gram of tissue (%ID/g) and the tumor/muscle uptake ratio was 2.83±0.29 in MCF-7 tumors, while 18F-GDC had a lower uptake in MDA-MB-231 tumors, with (2.01±0.46)%ID/g at 60min post-injection, and a tumor/muscle uptake ratio of 0.96±0.22 ( F values: 77.28, 55.44, P values: 0.002, 0.006 (Bonferroni correction method)). 18F-GDC was mainly distributed in MCF-7 tumors and organs including heart, liver, spleen, kidney, stomach and intestines. Conclusions:18F-GDC is successfully synthesized, with high radiochemical purity and stability, and can concentrate in the ERα-overexpressing cancer cells and lesion area of xenograft tumor mouse. It presents good image contrast in PET imaging, indicating excellent diagnostic performance.

Objective:To design and synthesize a 18F-labeled small molecule PET imaging probe targeting carbonic anhydrase Ⅸ (CAⅨ), named as 18F-single-acetazolamide (SAZ), and to evaluate its biological properties preliminarily. Methods:Acetazolamide was used as raw material to synthesize the precursor SAZ, and the target probe 18F-SAZ was obtained through nucleophilic substitution and other reactions. The radiochemical yield, radiochemical purity, specific activity, lipid water partition coefficient log P, and stability of 18F-SAZ were determined. Cancer cell lines OS-RC-2 (CAⅨ-positive) and HCT116 (CAⅨ-negative) were used for cell uptake experiments, and corresponding tumor-bearing mice were constructed for microPET imaging. Biodistribution of the probe in OS-RC-2 tumor-bearing mice was analyzed. The difference among groups was analyzed by repeated measures analysis of variance and Bonferroni method. Results:The probe 18F-SAZ was successfully prepared with the labelling yield of (5.60±0.51)%, specific activity of (7.90±0.62)MBq/nmol, radiochemical purity more than 99%, and the lipid water partition coefficient log P of -0.38±0.01. After incubation with PBS or mouse serum for 4 h, the radiochemical purity was still more than 99%. The uptake of 18F-SAZ in OS-RC-2 cells reached (1.47±0.24) percentage of the added radioactivity dose (%AD) at 30min, which was significantly higher than the uptake in the blocked group and that in HCT116 cells ((0.60±0.07)%AD, (0.50±0.05)%AD; F=24.31, P values: 0.012, 0.013 (Bonferroni correction method)). The results of microPET imaging showed that the uptake of 18F-SAZ in OS-RC-2 tumors reached the maximum at 30min ((2.92±0.07) percentage activity of injection dose per gram of tissue (%ID/g)), while the maximum uptakes in the blocked group and HCT116 tumors were only (1.36±0.02) and (1.12±0.07)%ID/g, respectively. 18F-SAZ was mainly distributed in tumors and organs including kidney, intestine, liver, stomach in OS-RC-2 tumor-bearing mice. Conclusions:The probe 18F-SAZ is successfully synthesized. It has high radiochemical purity and good stability in vitro, and can specifically target tumor cells with high expression of CAⅨ. It is expected to be a new CAⅨ-targeting PET imaging probe.

Under the background of the Healthy China Strategy, public hospitals urgently need to break through the limitations of the traditional medical mode, build a precise and continuous medical service system to meet the growing personalized health needs of the people. In 2022, a tertiary public hospital launched a multidisciplinary whole course management service practice. By integrating multidisciplinary medical and health resources, clarifying service targets and contents, forming a whole course management service team, constructing a supporting information platform, linking full process services, creating standardized service processes, and providing patients with comprehensive, full process, professional, and accurate full cycle intervention management and care. The hospital covered diseases in stages, ensuring continuous medical for patients after leaving the hospital, improving their medical experience, and supporting the high-quality development of the hospital. As of June 2024, the hospital′s multidisciplinary whole course management services had covered 25 departments and 41 disease, and 43 management teams have been established. A total of 7 453 patients signed up for the whole course service. This practice achieved good results, could provide references for the implementation of whole course management services led by public hospitals.

Objective To investigate the feasibility and safety of transoral transgastric natural orifice transluminal endoscopic surgery(TG-NOTES)cholecystectomy in miniature pigs.Methods A total of 11 miniature pigs were selected as the experimental subjects and underwent TG-NOTES cholecystectomy.These pigs were divided into the Group A and Group B according to the surgical procedures.Among them,7 miniature pigs in the Group A underwent endoscopic cholecystectomy without dissecting the gallbladder triangle,while 4 miniature pigs in the Group B underwent endoscopic cholecystectomy after dissecting the gallbladder triangle.The success rate of surgery,the time of each stage of surgery,the incidence of complications,the success rate of cholecystectomy and the survival rate of miniature pigs in the two groups were counted.One miniature pig in the Group A and 4 miniature pigs in the Group B were selected for survival experiments.After surviving for 1 week,they were killed and dissected to observe the healing of incision and incidence of complications.Results The surgical survival rate of experimental animals was 100%,and the success rate of cholecystectomy was 100%.There was no significant difference in the surgical time,time of cut the stomach into the abdomen,time of gallbladder exploration or time of gallbladder removal of miniature pigs between the two groups(P>0.05).The time of ligating gallbladder artery of miniature pigs in the Group B was longer than that in the Group A,and the time of isdating gallbladder was shorter than that in the Group A,with statistically significant differences(P<0.05).There was no significant difference in the average number of complications of miniature pigs between the two groups(P>0.05).The dissection of animals after survival experiments revealed that the incisions healed well without serious complications.Conclusion This study successfully establishes the surgical model of TG-NOTES cholecystectomy,and confirms the safety and feasibility of TG-NOTES cholecystectomy.

Wastewater-based epidemiology has emerged as a transformative surveillance tool for estimating substance consumption and monitoring disease prevalence, particularly during the COVID-19 pandemic. It enables the population-level monitoring of illicit drug use, pathogen prevalence, and environmental pollutant exposure. In this perspective, we summarize the key challenges specific to the Chinese context: (1) Sampling inconsistencies, necessitating standardized 24-hour composite protocols with high-frequency autosamplers (≤ 15 min/event) to improve the representativeness of samples; (2) Biomarker validation, requiring rigorous assessment of excretion profiles and in-sewer stability; (3) Analytical method disparities, demanding inter-laboratory proficiency testing and the development of automated pretreatment instruments; (4) Catchment population dynamics, reducing estimation uncertainties through mobile phone data, flow-based models, or hydrochemical parameters; and (5) Ethical and data management concerns, including privacy risks for small communities, mitigated through data de-identification and tiered reporting platforms. To address these challenges, we propose an integrated framework that features adaptive sampling networks, multi-scale wastewater sample banks, biomarker databases with multidimensional metadata, and intelligent data dashboards. In summary, wastewater-based epidemiology offers unparalleled scalability for equitable health surveillance and can improve the health of the entire population by providing timely and objective information to guide the development of targeted policies.
China/epidemiology* ; Humans ; Wastewater/analysis* ; COVID-19/epidemiology* ; Public Health ; Wastewater-Based Epidemiological Monitoring ; SARS-CoV-2