1.Revisiting Intelligent Syndrome Differentiation in Traditional Chinese Medicine under the Disease-Syndrome Combination Model:Perspectives from Disease "Ambiguity and Precision"
Xinlong LI ; Sulin WANG ; Dongning YAN ; Xinran ZHAO ; Genming ZHANG
Journal of Traditional Chinese Medicine 2026;67(7):705-709
The ambiguity of symptom information in traditional Chinese medicine (TCM) syndrome differentiation can be amplified in the direct reasoning process from symptoms to syndromes in the absence of constraints, which affects the accuracy and stability of intelligent syndrome differentiation. TCM disease concepts, while historically rational, are structurally ambiguous in both their connotation and extension, making it difficult to serve as stable prior knowledge in intelligent modeling. In contrast, modern medical diseases, based on objective testing and quantifiable indicators, have relatively clear boundaries and reproducible standards. This study proposes a disease-syndrome combination model, adopting modern medical diseases as structural prior variables to reconstruct the hierarchical relationships among disease, symptoms, and syndromes. By applying disease constraints, effective screening of information from the four examinations and compressing the reasoning space are achieved. Furthermore, by integrating artificial intelligence technologies, such as multimodal fusion and knowledge graphs, an intelligent syndrome differentiation model driven by both prior knowledge and clinical data is constructed, providing a feasible path to enhance the accuracy of syndrome differentiation and realize the intelligentization of TCM diagnosis and treatment.
2.Prediction of Mismatch Repair Deficiency Status in Endometrial Cancer Using Multiparametric MRI Radiomics and Deep Learning: A Multimodal Model with Preliminary Validation
Liru WANG ; Shangying YANG ; Boyu CHEN ; Fuze CONG ; Xinran LI ; Xinyu LIU ; Huadan XUE ; Zhengyu JIN ; Yang XIANG ; Yonglan HE ; Yuan LI
Medical Journal of Peking Union Medical College Hospital 2026;17(4):976-984
To explore the clinical value of a multimodal predictive model based on multiparametric magnetic resonance imaging(MRI) radiomics combined with deep learning(DL) features for the preoperative noninvasive assessment of mismatch repair-deficient(MMRd) status in endometrial cancer(EC). Patients diagnosed with EC at Peking Union Medical College Hospital from January 2015 to December 2021 were retrospectively enrolled and randomly divided into a training set and a validation set at a ratio of 8∶2. Relevant clinical data were collected, and radiomics features and DL features were extracted from preoperative contrast-enhanced T1-weighted imaging(CE-T1WI), fat-suppressed T2-weighted imaging(fs-T2WI), and diffusion-weighted imaging(DWI) sequences. High-dimensional feature selection and dimensionality reduction were performed sequentially using the recursive feature elimination(RFE) algorithm to generate a radiomics score(Rad-score) and a deep learning score(DL-score), respectively. Multivariate logistic regression was utilized to construct a clinical model, a pure radiomics model, a clinical-radiomics model, and an integrated multimodal model incorporating clinical indicators, Rad-score, and DL-score. Model performance was assessed and compared using area under receiver operating characteristic curve(AUC) and DeLong test. A total of 509 patients were enrolled in this study, comprising 413 in the training cohort and 96 in the validation cohort. Independent predictors: Multivariate analysis indicated that preoperative fasting blood glucose level, histological grade, lymph node metastasis status, Rad-score, and DL-score were all independent significant predictors of MMRd status in EC patients. The integrated multimodal model demonstrated optimal predictive performance with an AUC of 0.699(95% CI: 0.635-0.763) in the training set, which was superior to the clinical model(AUC=0.629, 95% CI: 0.561-0.697) and the pure radiomics model(AUC=0.641, 95% CI: 0.575-0.706). In the validation set, the integrated model maintained good generalizability, achieving an AUC of 0.655(95% CI: 0.535-0.775), and its diagnostic efficacy was higher than that of the clinical model(AUC=0.578, 95% CI: 0.450-0.705) and the pure radiomics model(AUC=0.611, 95% CI: 0.488-0.734). According to the DeLong test, the incorporation of DL features resulted in the clinicalradiomicsdeep learning model performing better than both the clinicalonly model( The initially developed clinical-radiomics-deep learning model exhibits a certain predictive potential for the MMRd status in patients with EC. The inclusion of DL features may help complement the limitations of traditional evaluations, offering a preliminary radiological reference for preoperative non-invasive screening. However, given the current diagnostic performance, its overall accuracy and clinical generalizability warrant further validation in multi-center, large-sample external cohort studies.
3.Research progresses in deep learning reconstruction of low-dose CT image
Jiayuan LI ; Zhenxia LI ; Yiyu CHEN ; Xinran CHEN ; Hongyang GAN ; Qingming HUANG
Chinese Journal of Medical Imaging Technology 2025;41(7):1167-1170
Reconstruction of low-dose CT image faced problems such as low resolution,blurred artifacts and strong noise.Deep learning reconstruction met the needs of reducing radiation dose and improving imaging quality,promoted reconstruction of CT image towards high efficiency,intelligence and integration of clinical diagnosis and treatment.The research progresses in deep learning low-dose CT imaging reconstruction were reviewed in this article.
4.Risk factors of recurrence in patients with systemic juvenile idiopathic arthritis
Xinran WEN ; Lingling GENG ; Yue PENG ; Li WANG ; Xiaoqing LI
Chinese Journal of Rheumatology 2025;29(7):568-574
Objective:To explore the potential risk factors of recurrence in patients with systemic juvenile idiopathic arthritis (sJIA).Methods:We enrolled patients with sJIA admitted to the Department of Rheumatology and Immunology, Xi′an Children′s Hospital affiliated to Xi′an Jiaotong University from January 2018 to June 2024. Cox proportional hazard models were used to identify clinical features associated with risk of recurrence.Results:This study included a total of 108 children with sJIA, with a median onset age of 79.5 (53.0, 121.5) months. Among them, 52 were male (48.1%) and 56 were female (51.9%). The median time from disease onset to diagnosis was 29.5 (19.0, 57.0) days, and 105 children achieved clinical remission during follow-up. Out of 108 patients with sJIA, 105 patients who achieved clinical remission were enrolled with a median follow-up of 38.0 months. Among them, 28 (26.7%) patients had at least once recurrence. According to the multivariate analysis, macrophage activation syndrome [HR(95% CI)=2.375(1.096, 5.149), P=0.028] and alkaline phosphatase [HR(95% CI)=1.006(1.001, 1.010), P=0.017] were associated with increased risk of recurrence. Conclusion:Our study indicated that recurrence could appear in at least 26.7% patients with sJIA. The high alkaline phosphatase and MAS at initial attack may be independent risk factors of recurrence in patients with systemic Juvenile Idiopathic Arthritis.
5.Structural and epitope characterization of HIV-1 V1V2 highly effective neutralizing antibodies based on AlphaFold 3
Junjie ZHANG ; Qianying WANG ; Ying LIU ; Shuhui WANG ; Li REN ; Shuo WANG ; Yutao SHI ; Yuhua RUAN ; Xiaojing LIU ; Xinran DU ; Yanling HAO ; Dan LI
Chinese Journal of Experimental and Clinical Virology 2025;39(5):548-555
Objective:To screen broadly neutralizing antibodies in human immunodeficiency virus-1(HIV-1)chronically infected individuals and characterize their molecular features and to provide new strategies for rational vaccine development and antibody-based therapeutics.Methods:A total of 34 treatment-na?ve individuals with chronic HIV-1 infection were enrolled. Plasma antibody binding levels were measured against two HIV-1 envelope proteins. Single antigen-specific memory B cells were sorted from high-binding samples,and antibody variable region genes were amplified by PCR for paired expression. The monoclonal antibodies were evaluated for neutralizing activity using pseudovirus assays,and their structural features were analyzed by integrating AlphaFold 3 prediction with Discovery Studio molecular docking.Results:Plasma samples showed strong binding to DU422-GP140 and BG505-GP140. Eight monoclonal antibodies were isolated from two donors. Among them,antibodies 0919-A4,0919-A9 and 0808-A2 could cross-react with GP140 from HIV-1 subtypes AE,BC and B. The monoclonal antibody 0919-A9 demonstrated potent neutralizing activity against SF162(Tier 1)and CH181(Tier 2)pseudoviruses,with somatic hypermutation rates of 13.27%(heavy chain)and 15.58%(light chain). Structural modeling revealed its specific targeting of the V1V2 region on GP120.Conclusion:The isolated antibody 0919-A9 effectively neutralizes Tier 2 pseudoviruses. Its high somatic mutation frequency and V1V2-targeting property underlie its neutralizing activity,providing both a promising candidate and mechanistic insights for HIV vaccine development and antibody-based therapeutic strategies.
6.Comparative analysis of the efficacy of dienogest and LNG-IUS in the treatment of intrinsic and extrinsic subtypes of adenomyosis
Lu LIU ; Jing WANG ; Xinran GAO ; Molin WANG ; Meng LI ; Chunliang SHANG ; Hongyan GUO
Chinese Journal of Obstetrics and Gynecology 2025;60(4):281-288
Objective:To compare the efficacy of dienogest (DNG) and levonorgestrel-releasing intrauterine system (LNG-IUS) in the treatment of intrinsic and extrinsic subtypes of adenomyosis.Methods:Totally 232 patients were enrolled in the study who were diagnosed as adenomyosis by ultrasound or pelvic magnetic resonance imaging (MRI), and were classified into intrinsic and extrinsic subtypes according to different locations of lesions in MRI, treated with DNG (DNG group) or LNG-IUS (LNG-IUS group) in Peking University Third Hospital from July 2019 to December 2023. Clinical data of patients were retrospectively collected to analyze the clinical and imaging characteristics of different MRI subtypes of adenomyosis and whether there were differences in the therapeutic effects of DNG and LNG-IUS.Results:(1) Among the 232 patients enrolled, 129 were intrinsic subtype and 103 were extrinsic subtype. Among the 129 patients treated with DNG, the numbers of intrinsic and extrinsic subtype were 69 and 60, respectively. And among the 103 patients treated with LNG-IUS, the numbers of intrinsic and extrinsic subtype were 60 and 43, respectively. The mean age in DNG group [(37.5±5.6) years] was lower than that in LNG-IUS group [(40.3±4.3) years, P<0.001]. There were no significant differences in other clinical features (all P>0.05). (2) The visual analog scale (VAS) scores of dysmenorrhea and cancer antigen 125 (CA 125) levels in DNG group and LNG-IUS group were significantly decreased after treatment (all P<0.001), and hemoglobin levels were increased (both P<0.01). Compared between the two groups, the VAS score after treatment was lower in DNG group ( P<0.001), and the hemoglobin level was increased more significantly in DNG group ( P=0.016). The complete remission rates of dysmenorrhea in DNG group and LNG-IUS group were 73.0% (89/122) and 29.5% (28/95), respectively ( P=0.039). The incidence of irregular bleeding in DNG group was higher than LNG-IUS group, but there was no statistical significance [62.8% (81/129) vs 52.4% (54/103), P=0.112]. (3) Among patients with intrinsic adenomyosis, the incidence of menorrhagia was significantly higher than in those with extrinsic adenomyosis ( P<0.001), while the incidence and severity of dysmenorrhea were lower compared to extrinsic adenomyosis ( P=0.004, P=0.007, respectively). After treatment with DNG and LNG-IUS, there were no statistically significant differences in VAS scores between patients with intrinsic and extrinsic adenomyosis (all P>0.05). The incidence of irregular bleeding after DNG treatment was 78.3% (54/69) in intrinsic adenomyosis, which was higher than the 45.0% (27/60) observed in extrinsic adenomyosis ( P<0.01). Similarly, the incidence of irregular bleeding after LNG-IUS treatment was 63.3% (38/60) in intrinsic adenomyosis, higher than the 37.2% (16/43) in extrinsic adenomyosis ( P=0.009). (4) DNG treatment ( OR=19.163, 95% CI: 7.564-48.544; P<0.01) and duration of treatment ( OR=1.043, 95% CI: 1.012-1.075; P=0.007) were independent positive factors for complete remission of dysmenorrhea, while VAS score before treatment ( OR=0.654, 95% CI: 0.454-0.942; P=0.023) was negative factor. Intrinsic subtype was an independent risk factor for irregular bleeding ( OR=0.436, 95% CI: 0.235-0.811; P=0.009). Conclusions:DNG demonstrates greater advantages over LNG-IUS in terms of complete relief of dysmenorrhea and the degree of symptom alleviation. The incidence of irregular vaginal bleeding in patients with intrinsic adenomyosis is higher than in those with extrinsic adenomyosis. For patients with extrinsic adenomyosis, particularly those with prominent dysmenorrhea symptoms, DNG treatment offers greater benefits. However, for patients with intrinsic adenomyosis and those with significant menstrual disorders, a more cautious approach is required when selecting progestin therapy, along with enhanced monitoring and management.
7.Visualization analysis on research status and hotspots of TCM syndrome differentiation and treatment for headache based on VOSviewer
Xinran ZHAO ; Xinlong LI ; Yu ZHANG ; Wenna LIU ; Xing LYU
International Journal of Traditional Chinese Medicine 2025;47(7):999-1004
Objective:To explore the research status and hotspots of TCM syndrome differentiation and treatment for headache using bibliometrics.Methods:Literature about TCM syndrome differentiation and treatment for headache was retrieved from CNKI, VIP, Wanfang Data, and CBM from the establishment of the databases to July 18, 2024. Excel 2023 was used to extract information such as publication time, author, unit and keywords of the literature. The authors' affiliation and keywords were preprocessed. VOSviewer software was used for keyword co-occurrence analysis and clustering analysis, and a keyword temporal overlay network was constructed.Results:Totally 1 513 articles were finally included. The journal with the largest number of publications was Henan Traditional Chinese Medicine. 346 authors were involved, initially forming research teams represented with Cao Kegang, Zhou Jianwei, Ni Jinjun, etc., mainly from Beijing University of Chinese Medicine, Henan University of Chinese Medicine, Shandong University of Traditional Chinese Medicine, etc.; the included literature included a total of 2 153 keywords, which the frequency of 5 931 times in total. The top three keywords in frequency were acupuncture and moxibustion therapy, clinical efficacy, and experience of famous doctors. Current research hotspots included data mining, network pharmacology, literature research, syndrome elements, medication law, venturing and bloodletting therapy, calcitonin gene-related peptide, classic prescriptions, nitric oxide, etc. Conclusions:At present, research on TCM syndrome differentiation and treatment for headache mainly focuses on three major sections: acupuncture, moxibustion and massage, clinical efficacy of TCM syndrome differentiation and treatment, and experience of famous doctors. Future research mainly focuses on data mining, medication law, network pharmacology, syndrome elements, and pathogenesis.
8.Research progresses of artificial intelligence in imaging diagnosis of children developmental dysplasia of hip
Haoyue LUO ; Xin CHEN ; Jiajun SI ; Jun LI ; Yiran WANG ; Xinran LI ; Ling HE
Chinese Journal of Medical Imaging Technology 2025;41(1):160-163
Developmental dysplasia of hip(DDH)usually occurs in children,and delayed diagnosis of DDH might lead to serious complications and influence long-term prognosis.The application of artificial intelligence(AI)in medical images helps to quantitatively individualize image data,reduce bias generated by manual analysis and achieve early and accurate diagnosis of children DDH.The research progresses of AI in imaging diagnosis of children DDH were reviewed in this article.
9.Effect of Processed Polygonatum cyrtonema in Preventing Depression Induced by Chronic Unpredictable Mild Stress in Female Rats
Xinyu DENG ; Chunhua MA ; Zimeng WANG ; Man TANG ; Xinran LI ; Lurong YU ; Xianyuan HE
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(7):117-124
ObjectiveTo observe the prevention and control effect of processed Polygonatum cyrtonema on depression induced by chronic unpredictable mild stress (CUMS) in female rats. MethodsForty rats were assigned into control, model, and low-, medium-, and high-dose processed P. cyrtonema groups according to the random number table method, with 8 rats in each group. The rat model of depression was established with the CUMS method. The body mass, open field test, forced swimming test, Morris water maze test, levels of neurotransmitters [dopamine (DA), 5-hydroxytryptamine (5-TH), and acetylcholine (ACh)], serum levels of sex hormones [gonadotropin-releasing hormone(GnRH), testosterone (T), and estradiol (E2)] and inflammatory factors [tumor necrosis factor-α (TNF-α), interleukin (IL)-6, and IL-10], and mRNA and protein levels of factors in the brain-derived neurotrophic factor (BDNF)/tyrosine kinase receptor B (TRKB)/cAMP-response element binding protein (CREB) pathway were employed to evaluate the effect of processed P. cyrtonema on the CUMS-induced depression in female rats. ResultsThe body mass, open field test results, and forced swimming test results showed that the rat model of depression was successfully established. The comparison of behaviors, neurotransmitters, sex hormones, inflammatory factors, and neural pathways among groups showed that processed P. cyrtonema had different effects of preventing the development of depression in female rats. SPSS 25 was used for statistical analysis of error and significance. T test was conducted between groups. Each treatment group showed significant therapeutic effect compared with the model group (P<0.05). Processed P. cyrtonema elevated the level of 5-TH (P<0.01) and lowered the levels of DA and ACh (P<0.01) in the brain tissue of female rats. In addition, it reduced the serum levels of GnRH, T, E2, TNF-α, and IL-6 (P<0.05) and up-regulated the mRNA levels of BDNF and TRKB in the rat brain. ConclusionProcessed P. cyrtonema has a non-hyperactive preventive effect on CUMS-induced depression in rats, which provides a theoretical basis for the development of processed P. cyrtonema as a functional food product.
10.Effect of Processed Polygonatum cyrtonema in Preventing Depression Induced by Chronic Unpredictable Mild Stress in Female Rats
Xinyu DENG ; Chunhua MA ; Zimeng WANG ; Man TANG ; Xinran LI ; Lurong YU ; Xianyuan HE
Chinese Journal of Experimental Traditional Medical Formulae 2025;31(7):117-124
ObjectiveTo observe the prevention and control effect of processed Polygonatum cyrtonema on depression induced by chronic unpredictable mild stress (CUMS) in female rats. MethodsForty rats were assigned into control, model, and low-, medium-, and high-dose processed P. cyrtonema groups according to the random number table method, with 8 rats in each group. The rat model of depression was established with the CUMS method. The body mass, open field test, forced swimming test, Morris water maze test, levels of neurotransmitters [dopamine (DA), 5-hydroxytryptamine (5-TH), and acetylcholine (ACh)], serum levels of sex hormones [gonadotropin-releasing hormone(GnRH), testosterone (T), and estradiol (E2)] and inflammatory factors [tumor necrosis factor-α (TNF-α), interleukin (IL)-6, and IL-10], and mRNA and protein levels of factors in the brain-derived neurotrophic factor (BDNF)/tyrosine kinase receptor B (TRKB)/cAMP-response element binding protein (CREB) pathway were employed to evaluate the effect of processed P. cyrtonema on the CUMS-induced depression in female rats. ResultsThe body mass, open field test results, and forced swimming test results showed that the rat model of depression was successfully established. The comparison of behaviors, neurotransmitters, sex hormones, inflammatory factors, and neural pathways among groups showed that processed P. cyrtonema had different effects of preventing the development of depression in female rats. SPSS 25 was used for statistical analysis of error and significance. T test was conducted between groups. Each treatment group showed significant therapeutic effect compared with the model group (P<0.05). Processed P. cyrtonema elevated the level of 5-TH (P<0.01) and lowered the levels of DA and ACh (P<0.01) in the brain tissue of female rats. In addition, it reduced the serum levels of GnRH, T, E2, TNF-α, and IL-6 (P<0.05) and up-regulated the mRNA levels of BDNF and TRKB in the rat brain. ConclusionProcessed P. cyrtonema has a non-hyperactive preventive effect on CUMS-induced depression in rats, which provides a theoretical basis for the development of processed P. cyrtonema as a functional food product.

Result Analysis
Print
Save
E-mail