1.Dental plaque microecological characteristics and salivary inflammatory factors levels in school aged children
TIAN Jincong, AO Yang, ZHAO Xiaoxue
Chinese Journal of School Health 2026;47(1):121-124
Objective:
To analyze the dental plaque microecological characteristics and the levels of salivary interleukin (IL)-5, IL-12, and IL-16 in school aged children with mixed dentition, providing a theoretical basis for the prevention and control of childhood dental caries.
Methods:
A total of 199 school aged children admitted aged 6-12 years to Tianjin Stomatological Hospital from January 2023 to January 2025 were selected. According to the decayed missing and filled teeth(DMFT) index, they were divided into high caries group ( n =68, DMFT index≥4), low caries group ( n =65, 1≤DMFT index≤3) and caries free group ( n =66, DMFT index=0). The microbial composition of dental plaque was analyzed by 16S rDNA high throughput sequencing. Salivary levels of IL-5, IL-12 and IL-16 were detected by enzymelinked immunosorbent assay kit. Pearson correlation test was used to analyze the correlation between levels of salivary IL-5, IL-12 and IL-16 and the DMFT index in children with caries.
Results:
Species richness and evenness (Shannon index) and uniformity (Shannonevenness index) in the high caries group were (3.28±0.64) and (0.61±0.13), respectively, which were lower than (3.66±0.52) and (0.74±0.15) in low caries group, and ( 3.60± 0.49) and (0.72±0.16) in caries free group ( F =9.08, 15.20, both P <0.05). The relative abundances of Firmicutes and Actinobacteria in the high caries group were higher than those in the low caries and caries free groups, while the relative abundances of Bacteroidetes, Fusobacteria, and Candidate phylum TM7 were lower than those in the low caries and caries free groups. The relative abundances of Streptococcus, Leptotrichia, Veillonella, Prevotella, and Actinomycesin in the high caries group were higher than those in the low caries and caries free groups, while the relative abundances of Capnocytophagaand Porphyromonas were lower ( F = 47.55- 1 969.24 , all P <0.05). The levels of salivary IL-5, IL-12, and IL-16 in the high caries group [(12.57±3.21, 28.73±6.79, 45.31 ±11.14)pg/mL] were higher than those in the low caries [(8.63±2.39, 18.16±4.62, 32.60±9.46)pg/mL] and caries free groups [(7.84±2.17, 14.94±3.83, 29.55±8.21)pg/mL] ( F =62.08, 141.23, 49.35, all P <0.05). Pearson correlation test results showed that salivary IL-5, IL-12, and IL-16 levels were positively correlated with the DMFT index in children with caries ( r = 0.73 , 0.68, 0.65, all P <0.05).
Conclusions
The microecological structure of dental plaque in school aged children with mixed dentition caries is significantly altered, the levels of pro inflammatory factors are significantly elevated, and these levels are positively correlated with the severity of caries.Oral microbial dysbiosis and local inflammatory responses may play a key role in the development and progression of dental caries.
2.Mechanism of Acanthopanacis Senticosi Radix et Rhizoma seu Caulis Extract in Treating Parkinson's Disease Based on Lipidomics
Ningxia LU ; Ao GAO ; Yehao WANG ; Jinjin YANG ; Yi LU ; Fang LU ; Shumin LIU
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(6):91-99
ObjectiveAbnormal lipids in neurons can cause the accumulation of α-synuclein(α-syn). This study aimed to explore the mechanism of Acanthopanacis Senticosi Radix et Rhizoma seu Caulis extract (ASH) in treating Parkinson's disease (PD) mice using lipidomics combined with network pharmacology. MethodsMice were divided into the blank group, model group and ASH (45.5 mg·kg-1) group. Motor ability was evaluated by pole climbing time and autonomous activity count; The oxidative stress indicators were detected by enzyme-linked immunosorbent assay (ELISA). Lipid biomarkers in brain tissues were screened and identified by ultra-performance liquid chromatography-tandem mass spectrometry (UPLC-MS/MS), and metabolic pathway analysis was conducted. The key targets of ASH for PD treatment were explored using network pharmacology. The Kyoto Encyclopedia of Genes and Genomes (KEGG) database was used for pathway enrichment analysis, and the "compound-reaction-enzyme-gene" network was constructed using the MetScape plugin. The protein expression levels of glutathione S-transferase P1 (GSTP1), glutathione S-transferase Mu 2 (GSTM2), prostaglandin peroxide synthase 1 (PTGS1), prostaglandin peroxide synthase 2 (PTGS2), and prostaglandin E synthase (PTGES) were validated by Western blot. ResultsCompared with the blank group, the model group showed significantly prolonged pole climbing time and reduced autonomous activity count (P<0.01). Compared with the model group, the ASH group demonstrated significantly faster pole climbing and increased autonomous activity count (P<0.01). The model group exhibited significantly decreased superoxide dismutase (SOD) and glutathione peroxidase (GSH-Px) levels, and increased malondialdehyde (MDA) level in brain tissues compared with the blank group (P<0.01). The ASH group showed increased SOD and GSH-Px levels and decreased MDA level compared with the model group (P<0.05, P<0.01). Lipidomics analysis identified 10 differential metabolites and 8 differential metabolic pathways. Network pharmacological analysis revealed 213 intersection targets between ASH components and PD, with KEGG enrichment involving the sphingolipid signaling pathway, lipid arteriosclerosis, phosphoinositide 3-kinase/protein kinase B(PI3K/Akt) signaling pathway, mitogen-activated protein kinase(MAPK) signaling pathway, and hypoxia inducible factor-1(HIF-1) signaling pathway. Integrated lipidomics and network pharmacology analysis highlighted the central role of the arachidonic acid metabolic pathway. The Western blot results showed that ASH effectively up-regulated GSTP1, GSTM2, and PTGS1 protein expression, and down-regulated PTGS2 and PTGES protein expression. ConclusionASH can ameliorate behavioral deficits, exert antioxidant effects, regulate lipid differential metabolites and the arachidonic acid metabolic pathway, thereby exerting therapeutic effects in PD model mice.
3.Development and application of a three-dimensional digital visualization system for children's neck acupoints
Xiaojing AO ; Kun LI ; Yuhang LIU ; Xiaoxuan YANG ; Xing WANG ; Zhijun LI ; Xiaoyan REN ; Shaojie ZHANG
Chinese Journal of Tissue Engineering Research 2025;29(9):1834-1840
BACKGROUND:Currently,there have been studies on three-dimensional digitalization and visualization systems for adult acupoints,but there are not many reports on the visualization of pediatric acupoints based on real pediatric digital sectional anatomical datasets. OBJECTIVE:To design and develop a digital three-dimensional visualization system for children's neck acupoints,to provide a basis for acupuncture and moxibustion,meridian and acupoint science teaching,clinical practice,acupuncture manipulation practice,and acupuncture safety research,and to provide a basis for the development of children's acupoint simulation system. METHODS:Based on a real cross-sectional anatomical dataset of pre-school boys,a three-dimensional digital virtual anatomical model of the neck region of children and internal multi-organ three-dimensional reconstruction were completed using PhotoShop 2021 and Digihuman Reconstruction System software.A database of 11 acupoints was compiled,including Fengfu and Fengchi,using the Unity database language.A three-dimensional model of children's neck anatomy,acupoint database,and writing acupuncture operation codes were integrated in Unity3D software.A three-dimensional digital visualization system for children's neck acupoints was successfully created,which integrated simulation acupoint positioning,three-dimensional acupoint anatomy,acupuncture training,clinical teaching,and acupuncture safety research. RESULTS AND CONCLUSION:(1)This study was based on real child specimens.Manual layer by layer segmentation of cross-sectional images was used to ensure the accuracy of the three-dimensional model to the greatest extent possible.The 3D software Digihuman Reconstruction System was utilized to extract and save independent segmentation data.PhotoShop 2021 software was collaborated with to complete dozens of three-dimensional reconstruction anatomical models of the outer skin of the neck and its internal bone structure,cervical spinal cord,blood vessels and nerves,muscles,and ligaments in children.The basic morphology and overall contour integrity verification of each independent structure were completed in MeshLab software.The 3-material research 13.0 software was applied for final fine tuning and anatomical position confirmation,successfully simulating and restoring the true anatomical morphology of the neck of preschool children.(2)Based on and referring to the national standards of the People's Republic of China,a database of commonly used acupoints in children's neck region was collected and organized,including their names,meridians,positioning,local anatomy,needle insertion levels,acupuncture methods,acupuncture accidents and prevention,acupoint indications,and two-dimensional anatomical sectional images.(3)Unity3D software was employed to integrate the three-dimensional model of children's neck,acupuncture simulation operation,and acupoint database,and a three-dimensional digital children's neck acupoint acupuncture visualization system was successfully constructed.The system displayed information on children's neck acupoints,two-dimensional and three-dimensional anatomical structures,and achieved two-dimensional and three-dimensional acupuncture simulation functions and acupuncture safety research functions for children's neck acupoints.Based on the ultra-thin sectional anatomical dataset of real child specimens,the first three-dimensional digital and visualization system for acupoints in the neck region of children had been constructed.Compared with previous acupoint acupuncture systems,it is more in line with the anatomical and morphological development characteristics of Asian children and has high application value in the fields of acupuncture safety research,clinical teaching,and acupuncture simulation training.
4.Plasma miRNA testing in the differential diagnosis of very early-stage hepatocellular carcinoma: a multicenter real-world study
Jie HU ; Ying XU ; Ao HUANG ; Lei YU ; Zheng WANG ; Xiaoying WANG ; Xinrong YANG ; Zhenbin DING ; Qinghai YE ; Yinghong SHI ; Shuangjian QIU ; Huichuan SUN ; Qiang GAO ; Jia FAN ; Jian ZHOU
Chinese Journal of Clinical Medicine 2025;32(3):350-354
Objective To explore the application of plasma 7 microRNA (miR7) testing in the differential diagnosis of very early-stage hepatocellular carcinoma (HCC). Methods This study is a multicenter real-world study. Patients with single hepatic lesion (maximum diameter≤2 cm) who underwent plasma miR7 testing at Zhongshan Hospital, Fudan University, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Anhui Provincial Hospital, and Peking University People’s Hospital between January 2019 and December 2024 were retrospectively enrolled. Patients were divided into very early-stage HCC group and non-HCC group, and the clinical pathological characteristics of the two groups were compared. The value of plasma miR7 levels, alpha-fetoprotein (AFP), and des-gamma-carboxy prothrombin (DCP) in the differential diagnosis of very early-stage HCC was evaluated using receiver operating characteristic (ROC) curves and area under the curve (AUC). In patients with both negative AFP and DCP (AFP<20 ng/mL, DCP<40 mAU/mL), the diagnostic value of plasma miR7 for very early-stage HCC was analyzed. Results A total of 64 528 patients from 4 hospitals underwent miR7 testing, and 1 682 were finally included, of which 1 073 were diagnosed with very early-stage HCC and 609 were diagnosed with non-HCC. The positive rate of miR7 in HCC patients was significantly higher than that in non-HCC patients (67.9% vs 24.3%, P<0.001). ROC curves showed that the AUCs for miR7, AFP, and DCP in distinguishing HCC patients from the non-HCC individuals were 0.718, 0.682, and 0.642, respectively. The sensitivities were 67.85%, 43.71%, and 44.45%, and the specificities were 75.70%, 92.78%, and 83.91%, respectively. The pairwise comparison of AUCs showed that the diagnostic efficacy of plasma miR7 detection was significantly better than that of AFP or DCP (P<0.05). Although its specificity was slightly lower than AFP and DCP, the sensitivity was significantly higher. Among patients negative for both AFP and DCP, miR7 maintained an AUC of 0.728 for diagnosing very early-stage HCC, with 67.82% sensitivity and 77.73% specificity. Conclusions Plasma miR7 testing is a potential molecular marker with high sensitivity and specificity for the differential diagnosis of small hepatic nodules. In patients with very early-stage HCC lacking effective molecular markers (negative for both AFP and DCP), miR7 can serve as a novel and effective molecular marker to assist diagnosis.
5.Analyzing the quality control evaluation results of occupational health examination institutions in Guizhou Province in 2022
Mei YANG ; Dongxia LI ; Yunxia AO ; Jun LI ; Hourui MA
China Occupational Medicine 2025;52(1):71-75
Objective To understand the status of quality control in occupational medical examination (OME) institutions in Guizhou Province. Methods A total of 124 registered OME institutions actively conducting OME in Guizhou Province were selected as the study subjects using the judgment sampling method. The evaluation was conducted by on-site document reviews, practical skill assessments, and investigation of OME practices for quality evaluation and analyzing their quality control performance. Results The public institutions accounted for 71.0% with a 41.5% of OME workload, while private institutions accounted for 29.0% with a 58.5% of OME workload among these 124 OME institutions. The overall pass rate for quality evaluation of OME institutions was 16.9% (21/124), with a total of 1 296 items failed to pass the quality evaluation. Among the unqualified items, organizational structure, quality control management systems, OME quality control, and information reporting accounted for 15.2%, 21.7%, 52.8%, and 10.3%, respectively. The unqualified rate of quality assessment items of OME institutions was 24.5% (1 296/5 288), and the unqualified rate was lower in public institutions compared with private institutions (22.4% vs 29.3%, P<0.01). The rates of the three key unqualified items, including chest radiography conclusion evaluation, audiogram calculation and conclusion evaluation, and blood lead comparison were 9.8%, 74.8% and 71.4%, respectively. The rates of unqualified audiometry operation test and chief physician theory test were 74.8% and 9.7%, respectively. Conclusion The quality of OME institutions in Guizhou Province requires continuous improvement, particularly in enhancing the abilities of audiometry operation, calculating audiogram results and conducing right conclusion, and blood lead inter-laboratory comparision.
6.Correlation of MET Status with Clinicopathological Features and Prognosis of Advanced Prostatic Acinar Adenocarcinoma
Weiying HE ; Wenjia SUN ; Huiyu LI ; Yanggeling ZHANG ; De WU ; Chunxia AO ; Jincheng WANG ; Yanan YANG ; Xuexue XIAO ; Luyao ZHANG ; Xiyuan WANG ; Junqiu YUE
Cancer Research on Prevention and Treatment 2025;52(8):698-704
Objective To explore the correlation of MET status in patients with advanced prostatic acinar adenocarcinoma with the clinical pathological parameters and prognosis. Methods The specimen from 135 patients with advanced prostatic acinar adenocarcinoma was included. The expression of c-MET protein was detected via immunohistochemistry, and MET gene amplification was assessed by fluorescence in situ hybridization. The relationships of c-MET expression and gene amplification with clinicopathological features and prognosis were analyzed. Results The positive expression rate of c-MET was 52.60% (71/135). Compared with the c-MET expression in adjacent tissues, that in tumor tissues showed lower heterogeneous expression. Among the cases, 1.71% (2/117) exhibited MET gene polyploidy, but no gene amplification was detected. Positive c-MET expression was significantly correlated with high Gleason scores and grade groups (P=
7.Study on the effect and mechanism of Xinyang Tablet on myocardial ferroptosis in mice with chronic heart failure
Jinhua KANG ; Pengpeng LIANG ; Xiaoxiong ZHOU ; Ao LIU ; Zhongqi YANG ; Hongyan WU
Journal of Beijing University of Traditional Chinese Medicine 2025;48(4):516-528
Objective:
Exploring the effect and mechanism of Xinyang Tablet on reduction of ferroptosis in myocardial cells from mice with chronic heart failure.
Methods:
Sixty C57BL/6J mice were randomly assigned to the sham, model, Xinyang Tablet low-dose (0.34 g/kg), Xinyang Tablet medium-dose (0.68 g/kg), Xinyang Tablet high-dose (1.36 g/kg), and perindopril (0.607 mg/kg) groups using a random number table method (10 mice in each group). Except for the sham group, all other groups underwent aortic arch constriction surgery to construct a chronic heart failure model. On the third day after completion of the modeling, each treatment group was administered the corresponding medication by gavage, while the sham and model groups were administered equal volumes of water by gavage once a day for eight consecutive weeks. After treatment, cardiac ultrasound was used to detect the structure and function of the mouse heart. Hematoxylin and eosin staining was used to detect pathological changes in mouse heart tissue. Masson staining was used to detect the proportion of fibrotic area of mouse heart tissue. Realtime fluorescence PCR was used to detect the mRNA expression of atrial natriuretic peptide (ANP), brain natriuretic peptide (BNP), collagen 3α (Col3α), and myosin heavy chain 7 (MYH7) in mouse myocardial tissue. Transmission electron microscope was used to detect the ultrastructure of myocardial cell mitochondria. Reactive oxygen species (ROS) staining was used to detect the mean fluorescence intensity of ROS in myocardial tissue. Micro-determination was used to detect superoxide dismutase (SOD) activity in myocardial tissue. An immunofluorescence assay was used to detect the mean fluorescence intensity of phosphorylated histone deacetylase 2 (p-HDAC2) in myocardial cell. Western blotting was used to detect the protein expression of nuclear factor-erythroid 2-related factor 2 (Nrf2), p-HDAC2, nicotinamide adenine dinucleotide phosphate oxidase 1 (NOX1), glutathione peroxidase 4 (GPX4), and cystine glutamate reverse transporter (xCT) in mouse myocardial tissue.
Results:
Compared to the sham group, the model group showed a decrease in left ventricular ejection fraction (LVEF), left ventricular fraction shortening (LVFS), an increase in left ventricular end-systolic diameter(LVESD) and left ventricular end-diastolic diameter (LVEDD), an increase in the proportion of cardiac fibrosis area, an increase in relative expression levels of ANP, BNP, Col3α, and MYH7 mRNA, an increase in ROS mean fluorescence intensity, a decrease in SOD activity, an increase in mean fluorescence intensity of p-HDAC2, an increase in relative expression levels of p-HDAC2 and NOX1 proteins, and a decrease in relative expression levels of Nrf2, GPX4, and xCT proteins (P<0.05). Myocardial fibrosis lesions are obvious, with disordered mitochondrial arrangement, decreased volume and shrinkage, increased membrane density, and reduced mitochondrial cristae. Compared to the model group, the LVEF and LVFS of mice in each dose group of Xinyang Tablet and the perindopril group increased, LVESD and LVEDD decreased, the proportion of fibrotic area of heart tissue decreased, the relative expression levels of ANP, BNP, Col3α, MYH7 mRNA decreased, ROS mean fluorescence intensity decreased, SOD activity increased, mean fluorescence intensity of p-HDAC2 decreased, relative expression levels of p-HDAC2 and NOX1 proteins decreased, and relative expression levels of Nrf2 and xCT proteins increased (P<0.05). Myocardial fibrosis was reduced, the mitochondrial arrangement was more regular, the mitochondria enlarged, the membrane density was reduced, and mitochondrial cristae increased. Compared to the model group, the relative expression level of the GPX4 protein in myocardial tissue increased in the Xinyang Tablet medium-, high-dose, and the perindopril groups (P<0.05).
Conclusion
Xinyang Tablet can improve ferroptosis and ventricular remodeling in mice with chronic heart failure by regulating the HDAC2-mediated Nrf2 antioxidant pathway.
8.Integration and innovation of wet granulation and continuous manufacturing technology: a review of on-line detection, modeling, and process scale-up.
Guang-di YANG ; Ge AO ; Yang CHEN ; Yu-Fang HUANG ; Shu CHEN ; Dong-Xun LI ; Wen-Liu ZHANG ; Tian-Tian WANG ; Guo-Song ZHANG
China Journal of Chinese Materia Medica 2025;50(6):1484-1495
Continuous manufacturing, as an innovative pharmaceutical production model, offers advantages such as high production efficiency and ease of control compared to traditional batch production, aligning with the future trend of drug production moving toward greater efficiency and intelligence. However, the development of continuous manufacturing technology in wet granulation has been slow. On one hand, this is closely related to its high technical complexity, substantial equipment investment costs, and stringent process control requirements. On the other hand, the long-term use of the traditional batch production model has created strong path dependence, and the lack of mature standardized processes further increases the difficulty of technological transformation. To promote the deep integration of wet granulation technology with continuous manufacturing, this review systematically outlines the current application of wet granulation in continuous manufacturing. It focuses on the development of key technologies such as online detection, process modeling, and process scale-up, with the aim of providing a reference for process innovation and application in wet granulation.
Drug Compounding/instrumentation*
;
Technology, Pharmaceutical/methods*
;
Drugs, Chinese Herbal/chemistry*
;
Models, Theoretical
9.Effect of medicinal parts and harvest seasons on nature-flavor correlation of plant-based Chinese materia medica.
Qi-Ao MA ; Guang YANG ; Hong-Chao WANG ; Ying LI ; Meng CHENG ; Tie-Lin WANG ; Kai SUN ; Xiu-Lian CHI
China Journal of Chinese Materia Medica 2025;50(15):4228-4237
This study selected 6 529 plant-based Chinese materia medica(PCMM) from Chinese Materia Medica as research subjects and applied a random permutation test to explore the overall correlation characteristics between nature and flavor, as well as the correlation characteristics after distinguishing different medicinal parts and harvest seasons. The results showed that the overall correlation characteristics between nature and flavor in PCMM were significantly associated in the following pairs: cold and bitter, cool and bitter, cool and astringent, cool and light, neutral and sweet, neutral and astringent, neutral and light, neutral and sour, hot and pungent, and warm and pungent. When analyzing the data by distinguishing medicinal parts and/or harvest seasons, new correlation patterns emerged, characterized by the disappearance of some significant correlations and the emergence of new ones. When analyzing by medicinal parts alone, significant correlations were found in the following cases: cold and light in leaves, cold and salty in barks, cool and sweet in fruits and seeds, neutral and pungent in whole herbs, neutral and salty in stems, and warm and salty in flowers. However, no significant correlations were found between cool and bitter in stems and other types of herbs, cool and astringent in fruits, seeds, flowers, and other types of herbs, cool and light in leaves, fruits, seeds, barks, flowers and other types of herbs, neutral and sweet in barks, neutral and astringent in whole herbs and stems, neutral and light in leaves, fruits, seeds, and flowers, neutral and sour in whole herbs, stems, barks, flowers, and other types of herbs, and hot and pungent in whole herbs, stems, flowers, and other types of herbs. When analyzing by harvest season alone, significant correlations were found in the following cases: cold and salty, and cool and sour in herbs harvested in winter, and neutral and salty in herbs harvested year-round. However, no significant correlation was found between cool and light in herbs harvested in winter. When considering both medicinal parts and harvest seasons, compared to the independent influence of medicinal parts, 14 new significant correlations emerged(e.g., the correlation between cool and bitter in stems harvested in spring), while 53 previously significant correlations disappeared(e.g., the correlation between cool and bitter in barks harvested in summer). Compared to the independent influence of harvest seasons, 11 new significant correlations appeared(e.g., the correlation between cold and light in barks harvested in autumn), while 50 previously significant correlations disappeared(e.g., the correlation between hot and pungent in leaves harvested in winter). This study is the first to reveal the influence of medicinal parts and harvest seasons on the correlation between nature and flavor in PCMM, which highlights that these two factors can interact and jointly affect nature-flavor correlations. Further research is needed to explore the underlying mechanisms. This study provides a deeper understanding of the inherent scientific connotations of herbal properties and offers a theoretical foundation for the cultivation and harvesting of PCMM.
Seasons
;
Plants, Medicinal/growth & development*
;
Drugs, Chinese Herbal/chemistry*
;
Taste
10.YOLOX-SwinT algorithm improves the accuracy of AO/OTA classification of intertrochanteric fractures by orthopedic trauma surgeons.
Xue-Si LIU ; Rui NIE ; Ao-Wen DUAN ; Li YANG ; Xiang LI ; Le-Tian ZHANG ; Guang-Kuo GUO ; Qing-Shan GUO ; Dong-Chu ZHAO ; Yang LI ; He-Hua ZHANG
Chinese Journal of Traumatology 2025;28(1):69-75
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


Result Analysis
Print
Save
E-mail