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.Nanomaterials evoke pyroptosis boosting cancer immunotherapy.
Zhenhua LI ; Ziyue XI ; Chuanyong FAN ; Xinran XI ; Yao ZHOU ; Ming ZHAO ; Lu XU
Acta Pharmaceutica Sinica B 2025;15(2):852-875
Cancer immunotherapy is currently a very promising therapeutic strategy for treating tumors. However, its effectiveness is restricted by insufficient antigenicity and an immunosuppressive tumor microenvironment (ITME). Pyroptosis, a unique form of programmed cell death (PCD), causes cells to swell and rupture, releasing pro-inflammatory factors that can enhance immunogenicity and remodel the ITME. Nanomaterials, with their distinct advantages and different techniques, are increasingly popular, and nanomaterial-based delivery systems demonstrate significant potential to potentiate, enable, and augment pyroptosis. This review summarizes and discusses the emerging field of nanomaterials-induced pyroptosis, focusing on the mechanisms of nanomaterials-induced pyroptosis pathways and strategies to activate or enhance specific pyroptosis. Additionally, we provide perspectives on the development of this field, aiming to accelerate its further clinical transition.
4.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.
5.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.
6.Establishing a risk prediction model for the onset of female stress urinary incontinence based on machine learning
Xinran SHI ; Zhen PANG ; Ting QIAO ; Jingjing LI ; Qinzhang WANG
Journal of Modern Urology 2025;30(3):196-206
Objective: To construct prediction models of female stress urinary incontinence (SUI), and evaluate the efficacy of each model, so as to provide reference for the early diagnosis of SUI. Methods: Female SUI patients treated in our hospital during Oct. 2019 and Oct. 2023 and healthy women undergoing physical examination during the same period were involved. Women 42 days after delivery were included in the postpartum group (n=611), and perimenopausal and postmenopausal women were included in the non-postpartum group (n=409). The number of random seeds was set and the participants were divided into the training and verification sets in a ratio of 7∶3. Relevant clinical data were collected, and meaningful variables were screened using single factor and Lasso regression, which were then incorporated into the K-nearest neighbor method (KNN), support vector machine (SVM),decision tree (DT) and random forest (RF) algorithms. The sensitivity, specificity, accuracy and area under the receiver operating characteristic curve (AUC) of the models were calculated to screen out the optimal model. Results: There were 352 SUI patients (57.6%) in the postpartum group. According to single factor and Lasso regression, significant variables included age, body mass index (BMI), maximum rapid muscle stage, parity, bladder neck mobility (BND), urethral rotation angle (URA), lateral perineal incision, past incontinence, and constipation. In the verification set, the AUC of KNN,SVM,DT and RF models were 0.881,0.878,0.750 and 0.905,respectively; the AUC, accuracy, F1 index and Kappa value of RF model were the largest. In the non-postpartum group, there were 260 SUI patients, accounting for 63.6%. The significant variables were age,BMI, maximum value and recovery time of fast muscle stage, mean value of slow muscle stage, post-resting stage variability, vaginal delivery, past incontinence, and constipation. In the verification set, the AUC of KNN,SVM,DT and RF models were 0.819,0.805,0.603 and 0.830, respectively; the AUC, accuracy, Kappa value of the RF model were the largest. Conclusion: This study successfully established 4 prediction models for the incidence of SUI in women at 42 days postpartum, perimenopausal and postmenopausal women based on machine learning. Among them, the model adopting the RF algorithm had the best prediction efficiency.
7.Effect of electroacupuncture on learning and memory abilities in vascular dementia rats via the NCOA4/FTH1 signaling pathway-mediated ferritinophagy.
Wei SUN ; Yinghua CHEN ; Tong WU ; Hongxu ZHAO ; Haoyu WANG ; Ruiqi QIN ; Xiaoqing SU ; Junfeng LI ; Yuanyu SONG ; Yue MIAO ; Xinran LI ; Yusheng HAN
Chinese Acupuncture & Moxibustion 2025;45(9):1271-1280
OBJECTIVE:
To observe the effect of electroacupuncture at "Sishencong" (EX-HN1) and "Fengchi" (GB20) on hippocampal neuronal ferritinophagy mediated by the nuclear receptor coactivator 4 (NCOA4)/ferritin heavy chain 1 (FTH1) signaling pathway in vascular dementia (VD) rats, and to explore the potential mechanisms of electroacupuncture for VD.
METHODS:
A total of 60 male rats of SPF grade were randomly divided into a blank group (12 rats), a sham surgery group (12 rats) and a modeling group (36 rats). In the modeling group, the modified 4-vessel occlusion method was used to establish the VD model. The 24 successfully modeled rats were randomly divided into a model group and an electroacupuncture group, with 12 rats in each group. In the electroacupuncture group, electroacupuncture was applied at left and right "Sishencong" (EX-HN1), and bilateral "Fengchi" (GB20), with continuous wave, in frequency of 2 Hz and current intensity of 1 mA, 30 min a time, once daily for 21 consecutive days. The learning and memory abilities were assessed using the Morris water maze test before modeling, after modeling and after intervention, as well as the novel object recognition test after intervention. After intervention, the neuronal morphology in the hippocampus was observed by Nissl staining; the iron deposition was observed by Prussian blue staining; the reactive oxygen species (ROS) level was detected by dihydroethidium (DHE) fluorescence staining; the levels of iron, malondialdehyde (MDA) and superoxide dismutase (SOD) in the hippocampal tissue were measured by the colorimetric assay, TBA method, and WST-1 method, respectively; the positive expression of NCOA4, FTH1 and glutathione peroxidase 4 (GPX4) was detected by immunohistochemistry; the protein expression of NCOA4, FTH1, GPX4, and the ratio of microtubule-associated protein 1 light chain 3B (LC3B) Ⅱ/Ⅰ in the hippocampus were detected by Western blot.
RESULTS:
Compared with the sham surgery group, in the model group, the escape latency was prolonged, and the number of platform crossings reduced (P<0.01), the recognition index (RI) was decreased (P<0.01); the hippocampal neurons displayed a blurred laminar structure, disorganized cellular arrangement, and the number of Nissl bodies was decreased (P<0.01); the percentage of iron deposition area in the hippocampus was increased (P<0.01); in the hippocampus, the levels of ROS, iron, MDA, and the protein expression of NCOA4, as well as the LC3B Ⅱ/Ⅰ ratio were increased (P<0.01), the SOD level, and the protein expression of FTH1 and GPX4 were decreased (P<0.01). Compared with the model group, in the electroacupuncture group, the escape latency was shortened and the number of platform crossings was increased (P<0.01), the RI was increased (P<0.01); the hippocampal neurons exhibited more regular morphology, better-organized cellular structure, and the number of Nissl bodies was increased (P<0.05); the percentage of iron deposition area in the hippocampus reduced (P<0.01); in the hippocampus, the levels of ROS, iron, MDA, and the protein expression of NCOA4, as well as the LC3B Ⅱ/Ⅰ ratio were decreased (P<0.01, P<0.05), the SOD level, and the protein expression of FTH1 and GPX4 were increased (P<0.01).
CONCLUSION
Electroacupuncture at "Sishencong" (EX-HN1) and "Fengchi" (GB20) can improve learning and memory abilities in VD rats, and its mechanism may be associated with the regulation of the hippocampal NCOA4/FTH1 signaling pathway, inhibition of ferritinophagy, and alleviation of oxidative stress damage.
Animals
;
Electroacupuncture
;
Dementia, Vascular/genetics*
;
Male
;
Rats
;
Signal Transduction
;
Humans
;
Memory
;
Rats, Sprague-Dawley
;
Nuclear Receptor Coactivators/genetics*
;
Ferritins/genetics*
;
Learning
;
Hippocampus/metabolism*
;
Acupuncture Points
8.Diagnostic value of MS score in macrophage activation syndrome associated with systemic juvenile idiopathic arthritis
Lingling GENG ; Yue PENG ; Duomei SHI ; Li WANG ; Xianyan TANG ; Xinran WEN ; Wenhua ZHANG ; Xiaoqing LI
International Journal of Pediatrics 2025;52(7):476-480
Objective:To explore the diagnostic value of the macrophage activation syndrome/systemic juvenile idiopathic arthritis(MS)score in macrophage activation syndrome(MAS)associated with systemic juvenile idiopathic arthritis(sJIA),and to provide a reference for clinical work.Methods:This study was a retrospective case-control analysis,conducted on the patients initially diagnosed as sJIA-associated with MAS and admitted into the Department of Rheumatology and Immunology of Children's Hospital Affiliated to Xi 'an Jiaotong University from July 1st,2016 to June 30th,2023. All of the patients met the diagnostic criteria for patients with MAS associated with sJIA according to the 2016 European Alliance of Associations for Rheumatology(EULAR)/American College of Rheumatology(ACR)/Pediatric Rheumatology International Trials Organization(PRINTO)standards. The basic information at baseline,clinical manifestations,and auxiliary examination results were collected. The MS score was applied to re-evaluate the children diagnosed as sJIA-associated with MAS. When the MS score ≥-2.1,the possibility of sJIA with MAS was high. Thirty cases of sJIA without MAS were randomly selected as the control group.Results:There were 28 cases in the MAS group,including 13 males(46.43%)and 15 females(53.57%),with an average age of(7.51±4.01)years. Compared with the control group,the MAS group were significantly more likely to have high fever( χ2=8.539, P=0.003),hepatomegaly( χ2=11.621, P<0.001),splenomegaly( χ2=11.710, P<0.001)and neurological involvement( χ2=27.619, P<0.001),with the differences being statistically significant. Meanwhile,there were statistically significant differences between the two groups in terms of white blood cell count( Z=-4.001, P<0.001),neutrophil count( Z=-3.659, P<0.001),platelet count( Z=-4.687, P<0.001),albumin level( Z=-4.018, P<0.001),alanine aminotransferase( Z=-3.846, P<0.001),aspartate aminotransferase( Z=-5.932, P<0.001),lactate dehydrogenase( Z=-6.150, P<0.001),triglycerides( Z=-5.874, P<0.001),fibrinogen( Z=-5.808, P<0.001),ferritin( Z=-5.280, P<0.001),erythrocyte sedimentation rate( Z=-3.971, P<0.001),ferritin/erythrocyte sedimentation rate( Z=-5.433, P<0.001),reduction of two-line cells in blood( χ2=11.408, P<0.001)and the presence of hemophagocytosis in bone marrow smears( χ2=28.260, P<0.001). Moreover,there was a statistically significant difference in MS scores between the two groups( Z=-6.148, P<0.001),with higher MS scores in the MAS group. Nevertheless,this study showed the median MS scores of both groups ≥-2.1. Conclusion:The MS score was significant to a certain degree as reference for the diagnosis of MAS,and this study showed that the MS score in the MAS group was significantly higher than the control group. However,the median MS scores in both groups were no less than -2.1. This might be related to the influence of factors during the assessment,which made it necessary to optimize the cutoff values of the MS score. Therefore,prospective studies should be carried out on the role of MS score in early identification of MAS.
9.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.
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