1.Network Meta analysis on the effects of different exercise modalities on executive function in school aged children
XU Hongru, LIU Mingyi, WANG Haolin, CHU Pengyi, LU Donglei, KONG Nianxin, CAI Jingjie, PENG Li ao
Chinese Journal of School Health 2026;47(2):256-262
Objective:
To explore the intervention effects of different exercise modalities on executive function in school aged children, providing references for formulating exercise prescriptions to promote school aged children executive function.
Methods:
A systematic literature search was conducted using PubMed, Embase, Cochrane Library, Web of Science, CNKI, Wanfang, VIP and CBM to identify studies on the effects of exercises on executive function in school aged children. The search period spanned from the database inception to August 2025. Two researchers independently screened the literature, extracted data, and evaluated the risk of bias of the included studies. Network Meta analysis was performed using Stata 16.0.
Results:
A total of 51 studies involving 5 710 school aged children and seven modalities of exercises(control group,small ball sports,large ball sports,aerobic exercise,combined exercise,sport game,gymnastic and dance sports) were finally included. Network Meta analysis showed that, in terms of inhibitory control development of school aged children, small ball sports ( SMD =-0.98,95% CI =-1.32 to -0.64 ), large ball sports ( SMD =-0.64,95% CI =-0.91 to -0.36), and mixed sports ( SMD =-0.26,95% CI =-0.50 to -0.02]) were more effective than the control group; in terms of working memory, largeball sports ( SMD =-1.26,95% CI =-1.88 to -0.65) and small ball sports ( SMD =-0.91,95% CI =-1.64 to -0.19) were superior to the control group; in terms of improving cognitive flexibility, large ball sports ( SMD =-1.02,95% CI =-1.28 to -0.76), gymnastics and dance sports ( SMD =-0.80,95% CI =-1.21 to -0.40), and small ball sports ( SMD =-0.75,95% CI =-1.15 to -0.36) were more effective than the control group (all P <0.05). Surface under cumulative ranking curve(SUCRA) showed that small ball sports had the highest value (SUCRA=98.9%) in improving inhibitory control, while large ball sports achieved the highest score(SUCRA=92.6%) in enhancing working memory, and large ball sports also had the highest value(SUCRA=94.7%) in promoting cognitive flexibility.
Conclusions
For developing inhibitory control in school aged children, small ball sports are recommended as a priority. For enhancing working memory and cognitive flexibility, large ball sports are recommended.
2.Targeted Regulation of Inflammation-related Signaling Pathways by Traditional Chinese Medicine for Prevention and Treatment of Atherosclerosis: A Review
Shuang ZHAO ; Mingxue ZHANG ; Ning LIU ; Jianan SU ; Yuhan AO ; Jing LI
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(3):273-283
Atherosclerosis (AS) is the main pathological basis of cardiovascular diseases and seriously threatens human quality of life. Its prevention and treatment urgently need breakthroughs. The inflammatory response, which runs through the physiological and pathological evolution process of AS, is one of the important mechanisms for AS occurrence. Currently, the treatment methods for AS in Western medicine are relatively mature. However, they have adverse reactions such as abnormal liver and kidney function, drug tolerance, target vessel restenosis, and stent thrombosis, which remain the key bottleneck restricting clinical efficacy. Traditional Chinese medicine (TCM), characterized by multiple components, multiple targets, and multi-pathway synergy, shows unique clinical application potential and efficacy advantages in the intervention of AS. This article reviewed the research progress of TCM in intervening in AS by regulating inflammatory-related signaling pathways, such as nuclear factor-κB (NF-κB), Toll-like receptors (TLRs), mitogen-activated protein kinase (MAPK), and Janus kinase/signal transducer and activator of transcription (JAK/STAT), in the past five years. It summarized the combined mechanism of action of TCM monomers, TCM pairs, and compound preparations in inhibiting the inflammatory cascade reaction through multiple targets, regulating lipid metabolism disorders, and improving vascular endothelial dysfunction and the imbalance of the microenvironment. It deepened the research on the molecular mechanism of TCM in anti-AS, so as to provide a scientific basis for the clinical transformation application and related theoretical research of TCM in anti-AS.
3.Targeted Regulation of Inflammation-related Signaling Pathways by Traditional Chinese Medicine for Prevention and Treatment of Atherosclerosis: A Review
Shuang ZHAO ; Mingxue ZHANG ; Ning LIU ; Jianan SU ; Yuhan AO ; Jing LI
Chinese Journal of Experimental Traditional Medical Formulae 2026;32(3):273-283
Atherosclerosis (AS) is the main pathological basis of cardiovascular diseases and seriously threatens human quality of life. Its prevention and treatment urgently need breakthroughs. The inflammatory response, which runs through the physiological and pathological evolution process of AS, is one of the important mechanisms for AS occurrence. Currently, the treatment methods for AS in Western medicine are relatively mature. However, they have adverse reactions such as abnormal liver and kidney function, drug tolerance, target vessel restenosis, and stent thrombosis, which remain the key bottleneck restricting clinical efficacy. Traditional Chinese medicine (TCM), characterized by multiple components, multiple targets, and multi-pathway synergy, shows unique clinical application potential and efficacy advantages in the intervention of AS. This article reviewed the research progress of TCM in intervening in AS by regulating inflammatory-related signaling pathways, such as nuclear factor-κB (NF-κB), Toll-like receptors (TLRs), mitogen-activated protein kinase (MAPK), and Janus kinase/signal transducer and activator of transcription (JAK/STAT), in the past five years. It summarized the combined mechanism of action of TCM monomers, TCM pairs, and compound preparations in inhibiting the inflammatory cascade reaction through multiple targets, regulating lipid metabolism disorders, and improving vascular endothelial dysfunction and the imbalance of the microenvironment. It deepened the research on the molecular mechanism of TCM in anti-AS, so as to provide a scientific basis for the clinical transformation application and related theoretical research of TCM in anti-AS.
4.The Structure and Function of The YopJ Family Effectors in The Bacterial Type III Secretion System
Ao-Ning LI ; Wen-Bo LI ; Yu-Ying LU ; Min-Hui ZHU ; Yu-Long QIN ; Yong ZHAO ; Zhao-Huan ZHANG
Progress in Biochemistry and Biophysics 2026;53(3):516-533
The Type III Secretion System (T3SS) serves as a pivotal virulence apparatus for numerous Gram-negative bacterial pathogens, enabling them to infect both animal and plant hosts. Functioning as a molecular syringe, the T3SS directly translocates bacterial effector proteins from the bacterial cytoplasm into the interior of eukaryotic host cells. These effectors are central weapons that precisely manipulate a wide spectrum of host cellular physiological processes, ranging from cytoskeletal dynamics to immune signaling, to establish a favorable niche for bacterial survival and proliferation. Among the diverse arsenal of T3SS effectors, the YopJ family constitutes a critical group of virulence factors. Members of this family are characterized by a conserved catalytic triad structure—a hallmark of the CE clan of cysteine proteases that has been evolutionarily repurposed to confer acetyltransferase activity. A defining and intriguing feature of these enzymes is their stringent dependence on a host-derived eukaryotic cofactor, inositol hexakisphosphate (IP6), for allosteric activation. This requirement acts as a sophisticated molecular safeguard, ensuring enzymatic activity only within the appropriate host environment, thereby preventing detrimental effects on the bacterium itself. While seminal studies on individual members such as Yersinia’s YopJ and Salmonella’s AvrA have provided deep mechanistic insights, a systematic and integrative understanding of the structure-function relationships across the entire family remains fragmented. Key questions persist regarding how a conserved catalytic core has diverged to recognize distinct host substrates in different kingdoms of life. To address this gap, this article provides a systematic review of the YopJ family, focusing on three interconnected aspects: their structural features, their catalytic mechanism, and their divergent immunosuppressive strategies in animal versus plant hosts. By conducting a comparative analysis of the sequences and resolved three-dimensional structures of three representative members (e.g., HopZ1a, PopP2, AvrA), we elucidate regions of significant variation embedded within the conserved core catalytic architecture. These variable regions, often involving surface loops and substrate-binding interfaces, are crucial determinants of target specificity and functional specialization. The functional divergence of this effector family is most apparent when comparing their modes of action in different hosts. In animal hosts, YopJ-family effectors primarily sabotage innate immune signaling pathways. They achieve this by acetylating key serine and threonine residues within the activation loops of critical kinases in the MAPK and NF‑κB pathways. This post-translational modification blocks the phosphorylation and subsequent activation of these kinases, leading to potent suppression of inflammatory cytokine production. Conversely, in plant hosts, the strategy broadens to dismantle the two-tiered plant immune system. YopJ homologs target a more diverse set of substrates, including immune-associated receptor-like cytoplasmic kinases (RLCKs), microtubule networks via tubulin acetylation (which disrupts cellular trafficking and signaling), and transcription factors central to defense gene regulation. This multi-target approach effectively suppresses both Pattern-Triggered Immunity (PTI) and Effector-Triggered Immunity (ETI). In conclusion, this synthesis aims to deepen the mechanistic understanding of YopJ family-mediated pathogenesis by integrating structural biology with cellular function across host kingdoms. Elucidating the precise molecular basis for substrate selection—how conserved platforms achieve target diversity—is a major frontier. Furthermore, this knowledge provides a vital theoretical foundation for developing novel anti-virulence strategies. Targeting the conserved IP6-binding pocket or the catalytic acetyltransferase activity itself represents a promising avenue for designing broad-spectrum inhibitors that could disarm this critical family of bacterial effectors, potentially offering new therapeutic approaches against a range of pathogenic bacteria.
5.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
6.Tracing origin of "Qinggong Maidong" production area based on analysis of literature and historical materials and identification of characteristics of Qinggong medicinal materials and cultural relics.
Ao-Yu REN ; Ting YAO ; Feng-Yuan LI ; Hua-Sheng PENG
China Journal of Chinese Materia Medica 2025;50(11):2931-2937
Maidong products are categorized into "Hang Maidong" and "Chuan Maidong". Since the Ming and Qing Dynasties, "Hang Maidong" has been regarded as having superior quality, but currently, it remains in name only in the market. This article reviewed historical materia medica and local chronicles from the Ming and Qing Dynasties and analyzed the historical evolution of Maidong production areas. The history of Maidong production in Zhejiang can be traced back to the Song Dynasty, and cultivation had already developed by at least the Ming Dynasty. During the Ming and Qing Dynasties, it was consistently used as a tribute. Ming Dynasty chronicles record "Chuan Maidong", which had already been cultivated on a large scale by the Qing Dynasty. "Hang Maidong" and "Chuan Maidong" share the same origin, with the former identifiable by the "gourd waist" shape of its tuberous root. Based on this, it can be inferred that the "Maimendong" herb illustrated in the Origins of Materia Medica(Ben Cao Yuan Shi) and the Maidong stored in the Qing Palace Imperial Pharmacy were both "Hang Maidong". The protection and development of the authentic "Hang Maidong" medicinal herb are urgently needed.
China
;
Drugs, Chinese Herbal/history*
;
History, 17th Century
;
History, Ancient
;
Medicine, Chinese Traditional/history*
;
History, Medieval
;
History, 16th Century
;
History, 18th Century
;
History, 15th Century
;
Plants, Medicinal/chemistry*
;
History, 19th Century
;
History, 20th Century
;
Humans
;
Materia Medica/history*
;
History, 21st Century
7.Effects and mechanisms of Yuxuebi Tablets combined with ibuprofen in treating chronic musculoskeletal pain through "integrated regulation of inflammation and pain-related oxylipins".
Ao-Qing HUANG ; Wen-Li WANG ; Guo-Xin ZHANG ; Ying LIU ; Na LIN ; Chun-Yan ZHU
China Journal of Chinese Materia Medica 2025;50(13):3763-3777
This study adopted a three-dimensional "effect-dose-mechanism" evaluation system to screen the optimal regimen of Yuxuebi Tablets(YXB) combined with ibuprofen(IBU) for chronic musculoskeletal pain(CMP) intervention and elucidate its pharmacological mechanism, so as to provide a scientific basis for the clinical application of the regimen. The experiments were conducted using 8-week-old ICR mice, which were randomly divided into sham operation(sham) group, model(CFA) group, IBU group, YXB group, stasis paralysis tablets combined with ibuprofen low-dose group(IBU-L-YXB), stasis paralysis combined with ibuprofen high-dose group(IBU-H-YXB), stasis paralysis tablets combined with ibuprofen high-dose with ibuprofen discontinuation on the 10th day of administration(IBU-10-YXB), and stasis paralysis tablets combined with ibuprofen high-dose with ibuprofen halving on the 10th day of administration(IBU-1/2-YXB) group. An animal model was established using the CFA plantar injection method. On D0(the second day post-modeling), the success of model establishment was assessed, followed by continuous drug administration for 18 consecutive days from D1 to D18. During this period, mechanical pain threshold was measured by the Von Frey test; thermal hyperalgesia was detected by the hot plate test, and depression-like behavior was observed by the tail suspension test. After treatment, peripheral blood was collected from all groups for complete blood biochemical analysis, and the injected feet of the sham, CFA, IBU, YXB, IBU-YXB, and IBU-10-YXB groups were subjected to oxylipin metabolomics analysis. Immunofluorescence double staining was further performed to detect the co-expression of key oxylipin metabolic enzymes(COX2, LTA4H, and 5/12/15-LOX) and macrophage marker CD68 in the sham, CFA, IBU, and YXB-L/M/H groups. Subsequently, confirmatory analysis of positive indicators was conducted in the sham, CFA, IBU, YXB, IBU-YXB, and IBU-10-YXB groups. On D6(acute phase), mechanical pain sensitivity data showed that compared with the CFA group, only the three combination groups(IBU-YXB, IBU-10-YXB, and IBU-1/2-YXB) exhibited significantly increased paw withdrawal thresholds. On D17(chronic phase), only the IBU-10-YXB group showed a mechanical pain threshold significantly higher than all other monotherapy and combination groups. On D17, thermal pain data showed that compared with the CFA group, all groups except IBU-1/2-YXB had significantly prolonged paw withdrawal latency. On D18, tail suspension data showed that compared with the CFA group, the YXB, IBU-YXB, and IBU-10-YXB groups had significantly reduced immobility time. In summary, IBU-10-YXB stably improved the core symptoms of acute and chronic inflammatory pain. Complete blood count data showed that compared with the sham group, the CFA group had significantly increased mean platelet volume(MPV), while compared with the CFA group, the IBU-YXB and IBU-10-YXB groups had significantly reduced MPV. Moreover, the platelet distribution width(PDW) of the IBU-10-YXB group was further reduced compared with the CFA group. These data suggest that the IBU-10-YXB combination regimen has superior effects on inflammation and blood circulation improvement compared with other treatment groups. At the mechanistic level, each treatment group differentially regulated pro-inflammatory and pro-resolving oxylipin(SPM). Specifically, compared with the CFA group, the IBU and IBU-YXB groups significantly inhibited the synthesis of the prostaglandin family downstream of COX2, reducing pro-inflammatory oxylipins PGD2 and 6-keto-PGF1α but inhibiting PGE1 and PGE2, which played positive roles in peripheral circulation, vasodilation, and inflammation resolution. Compared with the CFA group, the YXB group tended to inhibit the pro-inflammatory oxylipin LTB4 downstream of LTA4H and increase SPMs such as LXA4. The IBU-10-YXB group bidirectionally regulated pro-inflammatory oxylipins and SPMs. Compared with IBU, IBU-10-YXB significantly inhibited the pro-inflammatory mediator 5-HETE. Meanwhile, IBU-10-YXB broadly upregulated SPMs, as evidenced by significant upregulation of LXA4 compared with the CFA group, significant upregulation of LXA5 compared with the IBU and IBU-YXB groups, significant upregulation of RvD1 compared with the CFA group and all other treatment groups, and significant upregulation of RvD5 compared with the sham group. Immunofluorescence double staining results were as follows: compared with the CFA group, the IBU group specifically inhibited the oxylipin metabolic enzyme COX2. In the YXB group, COX2, LTA4H, and 5/12-LOX were significantly inhibited. Within the optimal analgesic dose range, YXB's inhibitory effects on COX2 and LTA4H were dose-dependent, while its inhibitory effects on 5/12-LOX were inversely dose-dependent. The two combination groups(IBU-YXB and IBU-10-YXB) inhibited COX2 and LTA4H without significantly affecting 5-LOX, while IBU-10-YXB further significantly inhibited 12-LOX. These results suggest that the IBU-10-YXB combination regimen effectively maintains stable inhibition of COX2, LTA4H, and 12-LOX while enhancing 5-LOX expression. This combinatorial strategy effectively suppresses pro-inflammatory oxylipins and promotes SPM biosynthesis, overcoming IBU's analgesic ceiling effect and its blockade of pain resolution pathways while compensating for YXB's inability to effectively intervene in acute pain and inflammation. Therefore, it achieves more stable anti-inflammatory, analgesic, and antidepressant effects.
Animals
;
Ibuprofen/administration & dosage*
;
Mice
;
Mice, Inbred ICR
;
Drugs, Chinese Herbal/administration & dosage*
;
Male
;
Musculoskeletal Pain/immunology*
;
Tablets
;
Humans
;
Chronic Pain/metabolism*
;
Drug Therapy, Combination
;
Disease Models, Animal
8.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
9.Brain midline segmentation method based on prior knowledge and path optimization.
Shuai GENG ; Yonghui LI ; Yu AO ; Weili SHI ; Yu MIAO ; Shuhan WANG ; Zhengang JIANG
Journal of Biomedical Engineering 2025;42(4):766-774
To address the challenges faced by current brain midline segmentation techniques, such as insufficient accuracy and poor segmentation continuity, this paper proposes a deep learning network model based on a two-stage framework. On the first stage of the model, prior knowledge of the feature consistency of adjacent brain midline slices under normal and pathological conditions is utilized. Associated midline slices are selected through slice similarity analysis, and a novel feature weighting strategy is adopted to collaboratively fuse the overall change characteristics and spatial information of these associated slices, thereby enhancing the feature representation of the brain midline in the intracranial region. On the second stage, the optimal path search strategy for the brain midline is employed based on the network output probability map, which effectively addresses the problem of discontinuous midline segmentation. The method proposed in this paper achieved satisfactory results on the CQ500 dataset provided by the Center for Advanced Research in Imaging, Neurosciences and Genomics, New Delhi, India. The Dice similarity coefficient (DSC), Hausdorff distance (HD), average symmetric surface distance (ASSD), and normalized surface Dice (NSD) were 67.38 ± 10.49, 24.22 ± 24.84, 1.33 ± 1.83, and 0.82 ± 0.09, respectively. The experimental results demonstrate that the proposed method can fully utilize the prior knowledge of medical images to effectively achieve accurate segmentation of the brain midline, providing valuable assistance for subsequent identification of the brain midline by clinicians.
Humans
;
Brain/diagnostic imaging*
;
Deep Learning
;
Image Processing, Computer-Assisted/methods*
;
Algorithms
;
Magnetic Resonance Imaging/methods*
;
Neural Networks, Computer
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