With the deepening application of artificial intelligence (AI) technology in the field of medical devices, pre-trained models have increasingly become a crucial engine driving innovation in intelligent healthcare due to their efficiency, generalization capability, and transfer learning performance. However, potential risks associated with pre-trained models—such as issues related to source diversity and quality controllability —pose new challenges to the safety and effectiveness of AI-based medical devices. Against this background, the National Medical Products Administration (NMPA) released the sectoral standard YY/T 1833.5-2024 Artificial Intelligence Medical Devices—Quality Requirements and Evaluation-Part 5: Pre-trained Models in September 2024. This standard provides essential technical guidance and a regulatory framework for standardizing the application of pre-trained models in medical devices, marking a milestone in ensuring the safety and efficacy of AI-powered medical products. This article offers an in-depth interpretation and analysis of the standard's background, orientation, and key technical consideration. It elucidates specific requirements regarding documentation for pre-trained models, definitions of critical quality attributes, and conformity assessment pathways. Furthermore, the practical and far-reaching implications of the standard are discussed, including its role in enhancing quality assurance throughout the entire lifecycle of AI-based medical devices and guiding technological innovation and healthy development within the industry. Additionally, by dissecting the standard, this article aims to support the industry in conducting prudent evaluations during model selection phases, thereby reducing the application of low-quality and high-risk models.

To investigate the clinical role of T-cell transcription factor (TBX21) and adenylate cyclase 9 antibody (ADCY9) gene polymorphisms in the development of childhood asthma. METHODS: Two hundred Han Chinese wheezing children aged 5 years and younger in Henan region from July 2016 to January 2017 were selected as the study group, and another 100 Han Chinese healthy children aged 5 years and younger in the same period were selected as the control group. Oral mucosal exfoliated cells were collected from both groups, and the genotypes of TBX21 gene rs2240017 polymorphic locus and ADCY9 gene rs2230739 polymorphic locus were detected by real-time fluorescence quantitative polymerase chain reaction (PCR) technique, and the risk level of asthma was assessed based on the test results. The children in the low-risk and high-risk groups were compared in terms of serum immunoglobulin E (IgE) levels, API positivity rate and allergic disease incidence, and the correlation between the risk level of asthma-related genetic polymorphisms and serum IgE levels, API and allergic disease incidence was analyzed. All children were followed up until 6 years of age to confirm the diagnosis of asthma, and the incidence of asthma was compared between the low-risk and high-risk groups. Children with asthma were treated with inhaled glucocorticoids and leukotriene receptor antagonists for 3 months, and the control of asthma and the impairment of lung function were compared between the low-risk and high-risk groups. RESULTS: The genotype detection results of rs2240017 polymorphic locus of TBX21 gene and rs2230739 polymorphic locus of ADCY9 gene in the study group compared with those in the control group were statistically significant (P<0.001). The percentages of CC, CT, and TT genotypes of rs2240017 polymorphic locus of TBX21 gene were 19.50%, 56.00%, and 24.50%, respectively, and the percentages of CC, CG, and GG genotypes of rs2230739 polymorphic locus of ADCY9 gene were 86.00%, 10.00%, and 4.00%, respectively, in 200 children with wheezing; serum IgE level, API positivity rate and allergic disease incidence were higher in the high-risk group than in the low-risk group (P< 0.001, <0.001, 0.021, respectively). The degree of risk of asthma-related gene polymorphisms in children with wheezing was positively correlated with serum IgE levels, API positivity, and the incidence of allergic diseases (P<0.001); the incidence of asthma (81.48%) and impaired lung function (74.07%) were higher in the high-risk group than in the low-risk group (4.90%, 3.50%) (P<0.001). There was no statistically significant difference between the asthma control rate of children with asthma in the high-risk group (79.55%) compared with the asthma control rate of children with asthma in the low-risk group (100.00%) (P=0.433). CONCLUSION: Gene polymorphisms at rs2240017 locus of TBX21 gene and rs2230739 locus of ADCY9 gene are closely associated with asthma development and impaired lung function in children with wheezing.

Objective:To evaluate the effectiveness of the artificial intelligence-assisted diagnosis and treatment system in distinguishing benign and malignant lung nodules.Methods:Clinical data of 1 650 patients with pulmonary nodules admitted to the Tianjin Chest Hospital Affiliated to Tianjin University from January 2015 to October 2022 were retrospectively analyzed, which included a total of 1 650 nodules. The malignant probability was compared to and analyzedpredict the benign and malignant nodules.Results:A total of 1 650 nodules were included, which were divided into a malignant tumor group(n=1 391, 84.3%) and a benign lesion group(n=259, 15.7%). Between the malignant tumor group and the benign lesion group, the malignant probability was significantly different, and the malignant probability could better distinguish malignant nodules and benign lesions[(78.85±22.91)% vs.(54.91±28.68)%, P<0.001]. The area under the curve( AUC) was 0.768. The critical value of malignant probability for diagnosis of lung cancer was 81.3% with a sensitivity of 0.620 and specificity of 0.815. Stratified analysis results showed that the accuracy of the AI intelligent system for diagnosing pulmonary nodules with the sizes of 0-1 cm, 1-2 cm and 2-3 cm was also increased, and the areas under ROC curve were 0.717, 0.769 and 0.804, respectively. Conclusion:The malignant probability of lung nodules calculated by the artificial intelligence-assisted diagnosis and treatment system can be used in the assessment of the preoperative benign and malignant lung nodules.

Objective    To investigate the clinical value of artificial intelligence (AI)-assisted chest computed tomography (CT) in the diagnosis of peripheral lung shadow. Methods    The CT image data of 810 patients with peripheral pulmonary shadow treated by thoracic surgery in Tianjin Chest Hospital Affiliated to Tianjin University from January 2018 to July 2019 were retrospectively analyzed using AI-assisted chest CT imaging diagnosis system. There were 339 males and 471 females with a median age of 63 years. The malignant probability of preoperative AI-assisted diagnosis of peripheral pulmonary shadow was compared with the results of postoperative pathology. Results    The pathological diagnosis of 810 patients with peripheral pulmonary shadow was lung cancer in 627 (77.4%) patients, precancerous lesion in 30 (3.7%) patients and benign lesion in 153 (18.9%) patients. The median probability of malignant AI diagnosis before operation was 86.0% (lung cancer), 90.0% (precancerous lesion) and 37.0% (benign lesion), respectively. According to the analysis of receiver operating characteristic (ROC) curve of AI malignant probability distribution in this group of patients, the area under the ROC curve was 0.882. The critical value of malignant probability for diagnosis of lung cancer was 75.0%with a sensitivity of 0.856 and specificity of 0.814. A total of 571 patients were diagnosed with AI malignancy probability≥ 75.0%, among whom 537 patients were pathologically diagnosed as lung cancer with a positive predictive value of 94.0%(537/571). Conclusion    The AI-assisted chest CT diagnosis system has a high accuracy in the diagnosis of peripheral lung cancer with malignant probability≥75.0% as the diagnostic threshold.

Cre/LoxP system has been widely used as new type of gene targeting, which can transform genes in specific tissues and organs, remove specific gene fragments, and help to study the effects of specific genes on growth and development.Cre/LoxP system is the core technology of conditional gene targeting, which induces gene targeting, and spatiotemporal specific gene targeting.The resource about the mechanism of the Cre/LoxP system is helpful to obtain the Cre transgenic mouse model on different cell types of the retina.The Cre transgenic mice with specific expression in retinal bipolar cells and ganglion cells can provide the experimental basis for the absence of specific tissue single genes during growth and development.This review focused on the Cre/LoxP system and specific Cre recombinase mouse model in eyes.

OBJECTIVEThis research estimated shear bond durability of zirconia and different substrates cemented by two self-adhesive resin cements (Clearfil SA Luting and RelyX U100) before and after aging conditioning.

METHODSMachined zirconia ceramic discs were cemented with four kinds of core material (cobalt-chromium alloy, flowable composite resin core material, packable composite resin, and dentin) with two self-adhesive resin cements (Clearfil SA Luting and RelyX U100). All specimens were divided into eight test groups, and each test group was divided into two subgroups. Each subgroup was subjected to shear test before and after 10 000 thermal cycles.

RESULTSAll factors (core materials, cements, and thermal cycle) significantly influenced bond durability of zirconia ceramic (P<0.00 1). After 10 000 thermal cycles, significant decrease was not observed in shear bond strength of cobalt-chromium alloy luted with Clearfil SA Luting (P>0.05); observed shear bond strength was significantly higher than those of other substrates (P<0.05). Significantly higher shear bond strength was noted in Clearfil SA Luting luted with cobalt-chromium alloy, flowable composite resin core material, and packable composite resin than that of RelyX U100 (P<0.05). However, significant difference was not observed in shear bond strength of dentin luted with Clearfil SA Luting and RelyX U100 (P>0.05).

CONCLUSIONSDifferent core materials and self-adhesive resin cements can significantly affect bond durability of zirconia ceramic. 
.

Adhesives ; Ceramics ; Chromium Alloys ; Composite Resins ; Dental Bonding ; Dental Cementum ; Dentin ; Humans ; Materials Testing ; Resin Cements ; Zirconium

This paper introduced the key points in fabricating anterior esthetic restorations with all ceramic materials, including pre-operative smile design, standard tooth preparation, provisional restoration fabrication, all ceramic materials selection, all ceramic restoration bonding, ceramic crack and fracture prevention. And then, the authors summarized and reviewed the clinical common problems in anterior esthetic restorations.
Ceramics ; Dental Porcelain ; Esthetics ; Humans

OBJECTIVETo evaluate the coronal microleakage of teeth restored with fiber posts and composite cores with four different resin bonding systems.

METHODSSixty extracted human maxillary single-rooted teeth were endodontically treated and randomly divided into four groups. Post spaces were prepared in the root canals. Four different resin bonding systems (RelyX Unicem, Dulink, DC core Automix, Luxacore) were used respectively to bond fiber posts and reconstruct cores. The specimens were immersed in India ink for one week. Subsequently all teeth were demineralized, dehydrated and rendered transparent. Then microleakage was observed with stereomicroscope.

RESULTSThe microleakage degrees among four resin bonding systems were significantly different (P = 0.007), and group C showed the least microleakage compared with the other three.

CONCLUSIONSelf-etching resin bonding systems have a super margin sealing ability.

Composite Resins ; Dental Bonding ; Dental Leakage ; Dentin-Bonding Agents ; Humans ; Post and Core Technique ; Resin Cements