PURPOSE: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accuracy of ITF classification. METHODS: We trained a network called YOLOX-SwinT, which is based on the You Only Look Once X (YOLOX) object detection network with Swin Transformer (SwinT) as the backbone architecture, using 762 radiographic ITF examinations as the training set. Subsequently, we recruited 5 senior orthopedic trauma surgeons (SOTS) and 5 junior orthopedic trauma surgeons (JOTS) to classify the 85 original images in the test set, as well as the images with the prediction results of the network model in sequence. Statistical analysis was performed using the SPSS 20.0 (IBM Corp., Armonk, NY, USA) to compare the differences among the SOTS, JOTS, SOTS + AI, JOTS + AI, SOTS + JOTS, and SOTS + JOTS + AI groups. All images were classified according to the AO/OTA 2018 classification system by 2 experienced trauma surgeons and verified by another expert in this field. Based on the actual clinical needs, after discussion, we integrated 8 subgroups into 5 new subgroups, and the dataset was divided into training, validation, and test sets by the ratio of 8:1:1. RESULTS: The mean average precision at the intersection over union (IoU) of 0.5 (mAP50) for subgroup detection reached 90.29%. The classification accuracy values of SOTS, JOTS, SOTS + AI, and JOTS + AI groups were 56.24% ± 4.02%, 35.29% ± 18.07%, 79.53% ± 7.14%, and 71.53% ± 5.22%, respectively. The paired t-test results showed that the difference between the SOTS and SOTS + AI groups was statistically significant, as well as the difference between the JOTS and JOTS + AI groups, and the SOTS + JOTS and SOTS + JOTS + AI groups. Moreover, the difference between the SOTS + JOTS and SOTS + JOTS + AI groups in each subgroup was statistically significant, with all p < 0.05. The independent samples t-test results showed that the difference between the SOTS and JOTS groups was statistically significant, while the difference between the SOTS + AI and JOTS + AI groups was not statistically significant. With the assistance of AI, the subgroup classification accuracy of both SOTS and JOTS was significantly improved, and JOTS achieved the same level as SOTS. CONCLUSION In conclusion, the YOLOX-SwinT network algorithm enhances the accuracy of AO/OTA subgroups classification of ITF by orthopedic trauma surgeons.
Humans ; Hip Fractures/diagnostic imaging* ; Orthopedic Surgeons ; Algorithms ; Artificial Intelligence

Objective:An in vivo mammalian hepatocyte Unscheduled DNA Synthesis(UDS)test was used to evaluate the genotoxicity of Cross-linked Sodium Hyaluronate Gel and Bone Repair Materials,providing experimental evidence for establishing a UDS testing method for medical devices and materials.Methods:0.9％sodium chloride injection and cottonseed oil were used as the solvent for test materials and negative control,respectively.N-dimethylnitrosamine(NDMA)was used as the positive control for the early sampling times,and 2-acetylaminofluorene(2-AAF)was used as the positive control for the late sampling times.SD rats were administered a single dose for toxic exposure,and liver tissues were collected at 4 h and 16 h,respectively.Hepatocytes were isolated using collagenase perfusion.After labeling with 5-ethynyl-2'-deoxyuridine(EdU),and the net average fluorescence intensity(NAFI)of cell nuclei and nucleoplasm was measured by fluorescence microscope.Data from 50 cells were used to analyze the DNA repair level.Results:Compared with the negative control groups,the positive control groups(NDMA and 2-AAF)showed highly statistically significant differences in NAFI(P＜0.01),indicating successful induction of DNA damage.There was no statistically significant differences between the cross-linked sodium hyaluronate gel groups,bone repair material groups and the negative control group(P＞0.05),suggesting that these materials did not significantly induce DNA damage under the experimental conditions.Conclusion:This study first applied EdU labeling technology to the in vivo hepatic UDS assay,achieving non-radioactive labeling through click chemistry reactions.Under the conditions of this study,cross-linked sodium hyaluronate gel and bone repair materials did not exhibit genotoxicity.In the follow-up,the sample range can be expanded and the observation period can be prolonged to further improve the genotoxicity evaluation system of medical devices.

Objective:An in vivo mammalian hepatocyte Unscheduled DNA Synthesis(UDS)test was used to evaluate the genotoxicity of Cross-linked Sodium Hyaluronate Gel and Bone Repair Materials,providing experimental evidence for establishing a UDS testing method for medical devices and materials.Methods:0.9％sodium chloride injection and cottonseed oil were used as the solvent for test materials and negative control,respectively.N-dimethylnitrosamine(NDMA)was used as the positive control for the early sampling times,and 2-acetylaminofluorene(2-AAF)was used as the positive control for the late sampling times.SD rats were administered a single dose for toxic exposure,and liver tissues were collected at 4 h and 16 h,respectively.Hepatocytes were isolated using collagenase perfusion.After labeling with 5-ethynyl-2'-deoxyuridine(EdU),and the net average fluorescence intensity(NAFI)of cell nuclei and nucleoplasm was measured by fluorescence microscope.Data from 50 cells were used to analyze the DNA repair level.Results:Compared with the negative control groups,the positive control groups(NDMA and 2-AAF)showed highly statistically significant differences in NAFI(P＜0.01),indicating successful induction of DNA damage.There was no statistically significant differences between the cross-linked sodium hyaluronate gel groups,bone repair material groups and the negative control group(P＞0.05),suggesting that these materials did not significantly induce DNA damage under the experimental conditions.Conclusion:This study first applied EdU labeling technology to the in vivo hepatic UDS assay,achieving non-radioactive labeling through click chemistry reactions.Under the conditions of this study,cross-linked sodium hyaluronate gel and bone repair materials did not exhibit genotoxicity.In the follow-up,the sample range can be expanded and the observation period can be prolonged to further improve the genotoxicity evaluation system of medical devices.

Objective To study the need for blood compatibility evaluation of medical devices that come into indirect contact with blood in order to accurately evaluate the risk of their interaction with blood.Methods Seven medical devices with indirect contact with blood were selected as samples including extension tubes of central venous catheters,port bodies of implantable drug delivery devices,infusion sets,receiving lines of dialysis equipment,auxiliary lines of left ventricular assist devices,blood monitors and catheter holders,with high-density polyethylene as the negative control,glass beads as the positive control and blank whole blood or plasma for the blank control.Partial thromboplastin time(PTT)test,platelet count test and hematology test(white blood cell and red blood cell count)were performed by direct contact method and indirect contact method,respectively.In the direct contact method,whole blood or plasma was in direct contact with the sample;while in the indirect contact method,whole blood or plasma was not in direct contact with the extraction solution,with no direct contact with the sample.Results With the indirect contact method the ratios(expressed as a percentage)of the PTT,platelate,WBC and RBC counts of the samples,positive and negative controls to those of the blank control were all higher than those with the direct contact method,and the indirect contact method had the sensitivity lower than that of the direct contact method.Conclusion Medical devices indirectly contacting blood have low risks for causing coagulation and platelet and hematologic adverse reactions,which are suggested to be evaluated for hemolysis testing only in case of the history of safe clinical use.[Chinese Medical Equipment Journal,2025,46(8):44-49]

Experimental teaching is an important component of the course Medical Immunology,which requires the use of experimental animals and the execution of experimental animals by medical students.By applying the carbon dioxide euthanasia system,it can effectively reduce the pain of experimental animals,ensure their welfare,and meet ethical requirements.It can also improve the efficiency of experimental teaching in Medical Immunology,reduce environmental pollution,and promote medical students to estab-lish scientific values and worldviews that pay attention to experimental animals and respect life,which is conducive to becoming future medical service talents.In the experimental teaching of Medical Immunology,the appropriate application of carbon dioxide euthanasia system combined with effective ideological and political construction of the curriculum can further implement the Party's educational policy of cultivating morality and talents,and lay a good foundation for cultivating medical talents with comprehensive knowledge,high skills and excellent quality.

Experimental teaching is an important component of the course Medical Immunology,which requires the use of experimental animals and the execution of experimental animals by medical students.By applying the carbon dioxide euthanasia system,it can effectively reduce the pain of experimental animals,ensure their welfare,and meet ethical requirements.It can also improve the efficiency of experimental teaching in Medical Immunology,reduce environmental pollution,and promote medical students to estab-lish scientific values and worldviews that pay attention to experimental animals and respect life,which is conducive to becoming future medical service talents.In the experimental teaching of Medical Immunology,the appropriate application of carbon dioxide euthanasia system combined with effective ideological and political construction of the curriculum can further implement the Party's educational policy of cultivating morality and talents,and lay a good foundation for cultivating medical talents with comprehensive knowledge,high skills and excellent quality.

Under the background of rapid development of artificial intelligence(AI),this paper systematically proposes AI-based education(AIBE).It empowers the teaching process,learning process,research process,and teaching management with AI,and constructs an AI-based educational paradigm,including AI-based teaching(AIBT),AI-based learning(AIBL),AI-based re-search(AIBR),and AI-based management(AIBM).Taking the AI course of immunology teaching as an example,this paper deeply analyzes the practices and explorations of implementing AIBT,AIBL,AIBR and AIBM based on the AI course,so as to accelerate the promotion of the transformation of the fourth generation of medical education.

Under the background of rapid development of artificial intelligence(AI),this paper systematically proposes AI-based education(AIBE).It empowers the teaching process,learning process,research process,and teaching management with AI,and constructs an AI-based educational paradigm,including AI-based teaching(AIBT),AI-based learning(AIBL),AI-based re-search(AIBR),and AI-based management(AIBM).Taking the AI course of immunology teaching as an example,this paper deeply analyzes the practices and explorations of implementing AIBT,AIBL,AIBR and AIBM based on the AI course,so as to accelerate the promotion of the transformation of the fourth generation of medical education.

Medical record homepage is a core basis for healthcare quality management, medical insurance payment, and public hospital performance evaluation.The completeness and accuracy of its data directly affect the medical quality and economic benefits of hospitals. Since July 2022, a tertiary hospital had built an auxiliary decision-making system for diagnosis omissions based on artificial intelligence technology, which was officially launched in January 2023. The system aimed to improve the quality of data on the first page of medical records and ensure reasonable payment by medical insurance. This system was built on the hospital′s electronic medical records, and integrated natural language processing, medical knowledge graphs and deep learning technologies to create three engines: diagnosis omission recognition, ICD coding and DRG grouping. The diagnosis omission recognition engine identified both explicit and implicit omitted diagnoses by using a context semantic analysis model and a contrastive learning framework for dual judgment. It also interacted with the ICD coding and DRG grouping engines to enhance the accuracy of DRG grouping. Since its launched, the system has achieved remarkable results. A comparative analysis revealed that the rate of missing diagnoses on hospital medical record homepages has decreased from 31.31% during January to September 2022 to 12.34% during the same period in 2023, and the quality control time for a single medical record had been reduced from 20 minutes to 5 minutes. Additionally, a simulation calculation showed that the system-assisted DRG grouping can increase the hospital′s medical insurance surplus. The system could provide reference and guidance for public hospitals in China to improve the quality of the homepage of medical records and better adapt to medical insurance payment reform.

Objective To study the need for blood compatibility evaluation of medical devices that come into indirect contact with blood in order to accurately evaluate the risk of their interaction with blood.Methods Seven medical devices with indirect contact with blood were selected as samples including extension tubes of central venous catheters,port bodies of implantable drug delivery devices,infusion sets,receiving lines of dialysis equipment,auxiliary lines of left ventricular assist devices,blood monitors and catheter holders,with high-density polyethylene as the negative control,glass beads as the positive control and blank whole blood or plasma for the blank control.Partial thromboplastin time(PTT)test,platelet count test and hematology test(white blood cell and red blood cell count)were performed by direct contact method and indirect contact method,respectively.In the direct contact method,whole blood or plasma was in direct contact with the sample;while in the indirect contact method,whole blood or plasma was not in direct contact with the extraction solution,with no direct contact with the sample.Results With the indirect contact method the ratios(expressed as a percentage)of the PTT,platelate,WBC and RBC counts of the samples,positive and negative controls to those of the blank control were all higher than those with the direct contact method,and the indirect contact method had the sensitivity lower than that of the direct contact method.Conclusion Medical devices indirectly contacting blood have low risks for causing coagulation and platelet and hematologic adverse reactions,which are suggested to be evaluated for hemolysis testing only in case of the history of safe clinical use.[Chinese Medical Equipment Journal,2025,46(8):44-49]