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 To investigate the mechanism of sanguinarine(SA)for alleviating ulcerative colitis(UC)induced by dextran sodium sulfate(DSS)in mice.Methods Male C57BL/6 mouse models of 3.5%DSS-induced UC were randomized for treatment with 1,5 and 10 mg/kg SA by gavage,400 mg/kg sulfasalazine by gavage,or 10 mg/kg SA combined with intraperitoneal injection of 30 mg/kg ML385(a Nrf2 inhibitor).The changes in intestinal inflammation was assessed by monitoring weight changes,disease activity index(DAI)score,colon length measurement,and HE staining.After the treatments,the colon tissues were collected for detection of malondialdehyde(MDA)content using colorimetry,mRNA expressions of inflammatory factors using RT-qPCR,and the expressions of Nrf2,HO-1,Keap-1,p-p65,p65,occludin,and ZO-1 proteins were detected using Western blotting.Results SA treatment obviously alleviated weight loss,colon length shortening and DAI score increase and ameliorated structural destruction of the colon glands and colonic crypts in mice with DSS-induced UC.SA intervention significantly decreased the levels of TNF-α,IL-1β and IL-6 mRNA and lowered ROS and MDA levels in the colon tissue of UC mice.The mouse models receiving SA treatment showed significantly increased expressions of Nrf2,HO-1,occludin and ZO-1 and lowered expressions of Keap-1 and P-P65 in the colon tissue without significant changes of p65 expression,and these changes were SA dose-dependent.Treatment with ML385 obviously attenuated the effect of high-dose SA for improving UC in the mouse models.Conclusion SA can improve UC-like enteritis in mice possibly by activating the Nrf2 pathway and inhibiting the NF-κB pathway in the colon tissue.

Objective To investigate the effect of sanguinarine(SAN)on proliferation and ferroptosis of colorectal cancer cells.Methods SW620 and HCT-116 cells treated with different concentrations of SAN were examined for cell viability changes using CCK8 assay to determine the IC50 of SAN in the two cells.The inhibitory effects of SAN on proliferation,invasion and migration of the cells were evaluated using colony-forming assay and Transwell assays.ROS production in the treated cells was analyzed with flow cytometry,and lipid peroxide production was assessed by detecting malondialdehyde(MDA)level.Glutathione(GSH)levels in the cells were detected,and Western blotting was used to detect the expressions of ferroptosis-related proteins STUB1 and GPX4.Results SAN significantly inhibited the proliferation,invasion and migration of SW620 and HCT-116 cells.SAN treatment significantly promoted ROS production,increased intracellular MDA level,and lowered GSH level in the two cells(P<0.05).Western blotting showed that SAN significantly upregulated the expression of STUB1 and down-regulated the expression of its downstream protein GPX4(P<0.05).Conclusion SAN induces ferroptosis in colorectal cancer cells by regulating STUB1/GPX4,which may serve as a new therapeutic target for colorectal cancer.

Objective To investigate the mechanism of sanguinarine(SA)for alleviating ulcerative colitis(UC)induced by dextran sodium sulfate(DSS)in mice.Methods Male C57BL/6 mouse models of 3.5%DSS-induced UC were randomized for treatment with 1,5 and 10 mg/kg SA by gavage,400 mg/kg sulfasalazine by gavage,or 10 mg/kg SA combined with intraperitoneal injection of 30 mg/kg ML385(a Nrf2 inhibitor).The changes in intestinal inflammation was assessed by monitoring weight changes,disease activity index(DAI)score,colon length measurement,and HE staining.After the treatments,the colon tissues were collected for detection of malondialdehyde(MDA)content using colorimetry,mRNA expressions of inflammatory factors using RT-qPCR,and the expressions of Nrf2,HO-1,Keap-1,p-p65,p65,occludin,and ZO-1 proteins were detected using Western blotting.Results SA treatment obviously alleviated weight loss,colon length shortening and DAI score increase and ameliorated structural destruction of the colon glands and colonic crypts in mice with DSS-induced UC.SA intervention significantly decreased the levels of TNF-α,IL-1β and IL-6 mRNA and lowered ROS and MDA levels in the colon tissue of UC mice.The mouse models receiving SA treatment showed significantly increased expressions of Nrf2,HO-1,occludin and ZO-1 and lowered expressions of Keap-1 and P-P65 in the colon tissue without significant changes of p65 expression,and these changes were SA dose-dependent.Treatment with ML385 obviously attenuated the effect of high-dose SA for improving UC in the mouse models.Conclusion SA can improve UC-like enteritis in mice possibly by activating the Nrf2 pathway and inhibiting the NF-κB pathway in the colon tissue.

Objective To investigate the effect of sanguinarine(SAN)on proliferation and ferroptosis of colorectal cancer cells.Methods SW620 and HCT-116 cells treated with different concentrations of SAN were examined for cell viability changes using CCK8 assay to determine the IC50 of SAN in the two cells.The inhibitory effects of SAN on proliferation,invasion and migration of the cells were evaluated using colony-forming assay and Transwell assays.ROS production in the treated cells was analyzed with flow cytometry,and lipid peroxide production was assessed by detecting malondialdehyde(MDA)level.Glutathione(GSH)levels in the cells were detected,and Western blotting was used to detect the expressions of ferroptosis-related proteins STUB1 and GPX4.Results SAN significantly inhibited the proliferation,invasion and migration of SW620 and HCT-116 cells.SAN treatment significantly promoted ROS production,increased intracellular MDA level,and lowered GSH level in the two cells(P<0.05).Western blotting showed that SAN significantly upregulated the expression of STUB1 and down-regulated the expression of its downstream protein GPX4(P<0.05).Conclusion SAN induces ferroptosis in colorectal cancer cells by regulating STUB1/GPX4,which may serve as a new therapeutic target for colorectal cancer.

Aim To explore the effect of CXCL7/CX-CR2 axis on obesity-related cognitive dysfunction at both animal and cellular levels.Methods The novel object recognition test was performed to assess the cog-nition.After the preparation of the frozen sections,the activation of microglia and astrocytes in hippocampi and the level of PSD95 were determined by immunoflu-orescence staining.The content of CXCL7 in hipp-ocampi was determined by enzymelinked immunosor-bent assay.The dendritic spine density of hippocampal neurons was observed by Golgi staining.Furthermore,HT22 cells were treated with the recombinant mouse CXCL7 and/or si-RNA targeting CXCR2.After the treatment,the levels of CXCL7 and PSD95 were ob-served by immunocytochemistry staining.Results Compared with animals in the control group,there was significantly decreased discrimination index,increased activation of microglia and astrocytes,decreased con-tent of PSD95,decreased density of dendritic spine,and increased content of CXCL7 in hippocampi in the DIO group.Compared with animals in the DIO group,there were significantly increased discrimination index in the AWL group.In HT22 cells,the level of PSD95 significantly decreased in the Ctrl+CXCL7 group com-pared with the control group.This decrease was attenu-ated in the si-CXCR2+CXCL7 group compared with the Ctrl+CXCL7 group.Conclusion Chronic high-fat diet induces neuroinflammation and subsequently induces cognitive dysfunction,which may be related to the synaptic plasticity mediated by the CXCL7/CXCR2 axis.

Objective To propose a method for classifying small bowel capsule endoscopy images by combining the Swin Transformer network with an improved Adapt-RandAugment data augmentation approach,aiming to enhance the accuracy and efficiency of small bowel lesion classification and recognition.Methods An Adapt-RandAugment data augmentation approach was formulated based on the RandAugment data enhancement sub-strategy and the principles of no feature loss and no distortion when enhancing small bowel capsule endoscopy images.In the publicly available Kvasir-Capsule dataset of small bowel capsule endoscopic images,the Adapt-RandAugment data augmentation approach was trained based on the Swin Transformer network,and the convolutional neural networks ResNet152 and DenseNet161 were used as the benchmarks to validate the combined Swin Transformer network and Adapt-RandAugment data augmentation approach for small bowel capsule endoscopy image classification.Results The proposed algorithm gained advantages over ResNet152 and DenseNet161 networks in the indicators,which had the macro average precision(MAC-PRE),macro average recall(MAC-REC),macro average F1 score(MAC-Fi-S)being 0.383 2,0.314 8 and 0.290 5 respectively,the micro average precision(MIC-PRE),micro average recall(MIC-REC)and micro average F1 score(MIC-Fi-S)all being 0.755 3,and the Matthews correlation coe-fficient(MCC)being 0.452 3.Conclusion The proposed small bowel capsule endoscopy image classification method based on Swin Transformer network and Adapt-RandAugment data augmentation approach behaves well in classified recognition efficiency and accuracy.[Chinese Medical Equipment Journal,2024,45(6):9-16]

Professor ZHOU Peng has deeply discussed the pathological characteristics of psoriasis vulgaris,emphasizing that the disease is usually manifested deficiency interweaved with excess,leading to frequent recurrence and persistent refractory,which may lead to psychological and emotional problems of patients.This paper further expounds the effect of blood stasis on the pathogenesis,progression and prognosis of psoriasis,and puts forward a new method of combining Lingnan fire needling and filiform needling acupuncture technique to treat psoriasis vulgaris with blood stasis syndrome.Professor ZHOU Peng believes that the treatment principle of this disease is"regulating the mind first,rectifying blood as a base,syndrome differentiating and eliminating pathogenic factors",aiming at comprehensively considering the etiology and symptoms,in order to achieve more effective treatment results.Combined with the analysis of dermoscopic signs,it provides a possible improvement direction for the treatment of psoriasis vulgaris from a new perspective.

Objective To analyze the clinical manifestations and epidemiological characteristics of influenza in Hubei. Methods Pharyngeal swab specimens from 16,500 patients with suspected influenza infection admitted to our hospital from January 2020 to December 2022 were selected. Viral detection and serotyping were performed by fluorescence quantitative polymerase chain reaction. Furthermore, the epidemiological and clinical data of patients were collected to analyze the clinical features and epidemiological characteristics of influenza viruses. Results A total of 16 500 clinical specimens were tested in this study, with a positive detection rate of 16.27% (2 684/16 500). The positive detection rate was 5.10% (862/16 500) for influenza A virus, 10.13% (1 672/16 500) for influenza B virus and 0.91% (150/16 500) for mixed influenza. The positive detection rate of influenza viruses was on the rise from 2020 to 2022 , reaching 18.43% in 2022. Seasonal distribution analysis denoted that the highest positive detection rates were observed in spring (18.23%) and winter (19.72%), with statistical difference (P<0.05). In terms of age distribution, patients<12 years (19.14%) had the highest positive detection rate, followed by those >60 years (17.71%), with statistical difference (P<0.05). From 2020 to 2022, the positive detection rate of influenza virus was 16.89% in males, which was higher than 15.63% in females (P<0.05). The main clinical symptoms were fever (86.89%) and cough (80.27%) for influenza A virus infections, cough (92.52%) and fever (86.06%) for influenza B virus infections, and cough (94.00%), fever (88.00%) and runny nose (86.00%) for mixed infections. Conclusion The influenza B viruses are the leading cause of influenza in Hubei from 2020 to 2022, and the infection demonstrates an increasing annual trend, with a high prevalence in winter and spring. Furthermore, children and the elderly are high-risk populations, and clinical manifestions are mainly cough and fever.

Objective: To investigate the characteristics and trend of stroke incidence in Jining City, Shangdong Province from 2015 to 2022, so as to provide the reference for formulating prevention and control strategies of stroke. Methods: Data of stroke incidence in Jining City from 2015 to 2022 were collected from Shandong Provincial Chronic Disease Surveillance Information Management System. The crude incidence was estimated, standardized using the data of the sixth national population census in 2010, and analyzed by age, gender and subtype. The trend in incidence of stroke was analyzed using annual percent change (APC). Results: A total of 316 267 cases of stroke were reported in Jining City from 2015 to 2022, with a crude incidence of 474.17/105 and a standardized incidence of 371.43/105. The incidence of stroke peaked from March to May (90 409 cases, 28.59%). There were 278 901 cases of ischemic stroke (88.19%) and 37 366 cases of hemorrhagic stroke (11.81%). The crude incidence of stroke was higher in males than in females (525.45/105 vs. 420.16/105, P<0.05). The crude incidence of stroke increased with age (P<0.05), reaching a peak in the age group of 80 years and above (2 764.92/105). From 2015 to 2022, the crude incidence of stroke in the overall population, males, females, the age groups of 0-<30 years and 40-<50 years showed increasing trends (APC=6.142%, 6.992%, 5.054%, 3.693% and 6.587%, all P<0.05); the crude incidence of ischemic stroke in the overall population, males and females showed increasing trends (APC=7.489%, 6.593% and 5.456%, all P<0.05), while the crude incidence rates of hemorrhagic stroke did not show significant trends (APC=3.455%, 2.804% and 1.919%, all P>0.05). Conclusions The crude incidence of stroke increased in Jining City from 2015 to 2022, with ischemic stroke as the predominant subtype. March to May was the peak period for disease onset, and young and middle-aged men should be focused on.