1.Multimodal imaging combined with artificial intelligence in the study of ocular biometric parameters in high myopia
Minghui LIU ; Chusheng CAI ; Shaolin DU
International Eye Science 2026;26(3):477-482
High myopia(HM)is one of the leading causes of irreversible visual impairment, characterized by pathological changes such as axial elongation and multidimensional abnormalities in fundus biometric parameters. This review systematically summarizes the dynamic characteristics of fundus biometric parameters(including those of the retina, optic disc, macula, and choroid)in HM patients, as visualized via multimodal imaging techniques [e.g., optical coherence tomography(OCT)and optical coherence tomography angiography(OCTA)], and their association with HM progression and related complications. The article further highlights the strategies and advantages of multimodal imaging integration and discusses recent advances and challenges in combining artificial intelligence(AI)with these imaging modalities to automate fundus parameter analysis, lesion detection, risk stratification, and clinical decision-making for HM. This review aims to provide an evidence-based foundation for the early warning, precise intervention, and personalized management of HM, thereby facilitating a clinical paradigm shift from “reactive treatment” to “active health management”.
2.A machine learning-based depression recognition model integrating spirit-expression features from traditional Chinese medicine
Minghui YAO ; Rongrong ZHU ; Peng QIAN ; Huilin LIU ; Xirong SUN ; Limin GAO ; Fufeng LI
Digital Chinese Medicine 2026;9(1):68-79
Objective:
To develop a depression recognition model by integrating the spirit-expression diagnostic framework of traditional Chinese medicine (TCM) with machine learning algorithms. The proposed model seeks to establish a TCM-informed tool for early depression screening, thereby bridging traditional diagnostic principles with modern computational approaches.
Methods:
The study included patients with depression who visited the Shanghai Pudong New Area Mental Health Center from October 1, 2022 to October 1, 2023, as well as students and teachers from Shanghai University of Traditional Chinese Medicine during the same period as the healthy control group. Videos of 3 – 10 s were captured using a Xiaomi Pad 5, and the TCM spirit and expressions were determined by TCM experts (at least 3 out of 5 experts agreed to determine the category of TCM spirit and expressions). Basic information, facial images, and interview information were collected through a portable TCM intelligent analysis and diagnosis device, and facial diagnosis features were extracted using the Open CV computer vision library technology. Statistical analysis methods such as parametric and non-parametric tests were used to analyze the baseline data, TCM spirit and expression features, and facial diagnosis feature parameters of the two groups, to compare the differences in TCM spirit and expression and facial features. Five machine learning algorithms, including extreme gradient boosting (XGBoost), decision tree (DT), Bernoulli naive Bayes (BernoulliNB), support vector machine (SVM), and k-nearest neighbor (KNN) classification, were used to construct a depression recognition model based on the fusion of TCM spirit and expression features. The performance of the model was evaluated using metrics such as accuracy, precision, and the area under the receiver operating characteristic (ROC) curve (AUC). The model results were explained using the Shapley Additive exPlanations (SHAP).
Results:
A total of 93 depression patients and 87 healthy individuals were ultimately included in this study. There was no statistically significant difference in the baseline characteristics between the two groups (P > 0.05). The differences in the characteristics of the spirit and expressions in TCM and facial features between the two groups were shown as follows. (i) Quantispirit facial analysis revealed that depression patients exhibited significantly reduced facial spirit and luminance compared with healthy controls (P < 0.05), with characteristic features such as sad expressions, facial erythema, and changes in the lip color ranging from erythematous to cyanotic. (ii) Depressed patients exhibited significantly lower values in facial complexion L, lip L, and a values, and gloss index, but higher values in facial complexion a and b, lip b, low gloss index, and matte index (all P < 0.05). (iii) The results of multiple models show that the XGBoost-based depression recognition model, integrating the TCM “spirit-expression” diagnostic framework, achieved an accuracy of 98.61% and significantly outperformed four benchmark algorithms—DT, BernoulliNB, SVM, and KNN (P < 0.01). (iv) The SHAP visualization results show that in the recognition model constructed by the XGBoost algorithm, the complexion b value, categories of facial spirit, high gloss index, low gloss index, categories of facial expression and texture features have significant contribution to the model.
Conclusion
This study demonstrates that integrating TCM spirit-expression diagnostic features with machine learning enables the construction of a high-precision depression detection model, offering a novel paradigm for objective depression diagnosis.
3.Association between physical activity level and dyslipidemia among freshmen of a medical college
Yushuang LUO ; Yan WANG ; Yanli LIU ; Jin ZHANG ; Minghui HE ; Wanhong HE ; Juan WU ; Yihan GU ; Chenyang ZHENG ; WANG WANG
Journal of Public Health and Preventive Medicine 2026;37(2):170-174
Objective To investigate the association between physical activity levels and blood lipids among college freshmen, and to provide scientific evidence for the health management of college freshmen. Methods An electronic questionnaire survey on physical activity was conducted on freshmen of a university, and fasting blood biochemical indicators were detected. The International Physical Activity Questionnaire (IPAQ) short form was used to evaluate the physical activity levels of the participants. Dyslipidemia was defined as an abnormality in any one of the following serum lipid parameters: total cholesterol, triglycerides, low-density lipoprotein cholesterol (LDL-C), high-density lipoprotein cholesterol (HDL-C), or non-high-density lipoprotein cholesterol. Binary logistic regression and stratified analyses were employed to explore the relationship between physical activity and blood lipids. Results A total of 3 401 participants were included, with an average age of 18.45 ± 0.92 years, and 60.5% were female. The prevalence of dyslipidemia was 17.7%, with a higher rate among males (22.1%) than females (14.8%). After adjusting for confounding factors related to blood lipids, high-intensity physical activity was negatively associated with the risk of elevated LDL-C among males (OR = 0.36, 95% CI: 0.13–0.99, P = 0.049). Conclusion Among freshmen at a medical college in Hubei Province, high-intensity physical activity is negatively associated with the risk of elevated LDL-C in males, but this association needs to be further confirmed by larger prospective cohort studies.
4.Epidemiological characteristics analysis of tuberculosis among college students in Yangzhou during 2020-2024
Chinese Journal of School Health 2026;47(1):109-112
Objective:
To analyze the epidemiological characteristics of pulmonary tuberculosis (PTB) among college students in Yangzhou from 2020 to 2024, so as to provide a scientific basis for developing prevention and control strategies.
Methods:
An epidemiological investigation was conducted among 162 college students with PTB, and 7 134 of their contacts were screened. Data were obtained from the tuberculosis information management system and on campus screening records. Using descriptive epidemiological methods, trends in incidence, seasonal distribution, and bacteriological characteristics were analyzed.
Results:
From 2020 to 2024, the annual average incidence of pulmonary tuberculosis among college students in Yangzhou was 29.42 per 100 000, showing an overall fluctuating downward trend ( χ 2=12.36, P <0.01). Cases were mainly concentrated in summer and autumn, with the highest proportion in autumn (41.36%, 67/162), followed by summer (23.46%, 38/162). The proportion of etiologically positive cases increased from 37.21% in 2020 to 71.43% in 2024; among positive cases, the proportion of latent tuberculosis infection (LTBI) decreased from 66.67% (10/15) to 26.67% (4/15). The etiological positive rate was higher in females than in males ( χ 2= 11.76 , P <0.01). Comparison of screening methods showed that among index cases, the LTBI detection rate of the recombinant Mycobacterium tuberculosis fusion protein skin test (C-TST) was higher than that of the tuberculin skin test (TST), but the difference was not statistically significant ( χ 2=0.65, P =0.42); among close contacts, the detection rate of TST was higher than that of C-TST (15.1%,10.1%; χ 2=5.23, P <0.05).
Conclusion
From 2020 to 2024, the annual average incidence of pulmonary tuberculosis among college students in Yangzhou showed an overall fluctuating downward trend, with differences in TB infection screening methods and gender.
5.Effect of different doses of Botulinum toxin type A injected under ultrasound guidance combined with modified catheter-balloon localization for post-stroke cricopharyngeal dysfunction: a randomized controlled trial
Liubo FAN ; Tingting SHAN ; Baohua LIU ; Mimi LUO ; Luding ZHANG ; Minghui WANG
Chinese Journal of Rehabilitation Theory and Practice 2026;32(7):776-787
ObjectiveTo investigate the short-term efficacy and safety of different doses of Botulinum toxin type A (BTX-A) injected under ultrasound guidance combined with modified catheter-balloon localization for post-stroke cricopharyngeal dysfunction (CPD), and to explore a relatively appropriate dose. MethodsA total of 136 patients with post-stroke CPD admitted to Taizhou Hospital of Zhejiang Province from December, 2023 to February, 2026 were randomly assigned into control group, 50 U group, 70 U group and 100 U group, with 34 patients in each group. The control group received conventional rehabilitation, whereas the three BTX-A groups received conventional rehabilitation plus the corresponding dose of BTX-A injected under ultrasound guidance combined with modified catheter-balloon localization. Videofluoroscopic Swallowing Study (VFSS) scores, Functional Oral Intake Scale (FOIS) scores, Yale Pharyngeal Residue Severity Rating Scale (YPR-SRS) grades, Murray Secretion Severity Scale (MSS) grades and ultrasonographic parameters were compared before and two weeks after intervention. ResultsAfter intervention, FOIS scores improved significantly in all groups (|Z| > 2.843, P < 0.01), and YPR-SRS and MSS grades also showed significant improvements in all BTX-A groups (|Z| > 4.147, P < 0.001). Pairwise comparisons revealed that the order of improvement from best to worst for FOIS, YPR-SRS and MSS grades was the 100 U group, followed by 70 U group, and then 50 U group (P < 0.05). For VFSS scores, the effect of time, group and interaction were all significant (F > 9.68, P < 0.001); pairwise comparisons showed that 100 U group achieved the best outcomes (P < 0.001). Regarding the activity and velocity of the geniohyoid muscle, the effects of time, group and interaction were also significant (F > 7.34, P < 0.001); pairwise comparisons indicated that 100 U group outperformed the other groups in both activity and velocity (P < 0.001). For hyoid bone displacement distance and shortening rate, the effects of time and interaction were significant (F > 3.07, P < 0.05), and the main effects of time on duration and velocity were significant (P < 0.01); pairwise comparisons showed that the 100 U group had superior displacement distance and shortening rate compared to the other groups (P < 0.05). During the treatment and follow-up periods, no serious adverse event occurred in any group. ConclusionUltrasound-guided BTX-A injection assisted by modified catheter-balloon localization may further improve short-term swallowing function in patients with post-stroke CPD, with a dosage of 100 U.
6.The characteristics and mechanism of dynamic changes of different components in microenvironment in regulating the progression of liver fibrosis
Huilan ZHAO ; Zongxu LIU ; Shumin LI ; Zhifeng WANG ; Minghui LIU ; Qian SHENG ; Kunbin KE ; Xinan SHI
Journal of Clinical Hepatology 2025;41(4):755-760
The liver has diverse functions such as metabolism, detoxification, and immune defense, and the maintenance of hepatic microenvironment homeostasis is crucial for overall bodily health. The hepatic microenvironment consists of the components such as parenchymal cells, non-parenchymal cells, and non-cellular components. Chronic inflammatory responses induced by various etiological factors may promote the formation and progression of liver fibrosis. During the dynamic progression of liver fibrosis, from the early to advanced stages, various components within the hepatic microenvironment undergo a series of changes, which can promote the malignant progression of liver fibrosis. An in-depth exploration of the mechanisms underlying such changes in each component of the liver fibrosis microenvironment is of great significance for understanding the pathogenesis of liver fibrosis and discovering potential treatment strategies.
7.Intelligent depression detection based on multi-physiological signals acquired by wearable devices
Keming CAO ; Lulu ZHAO ; Minghui ZHAO ; Zining WANG ; Jianqing LI ; Chengyu LIU
Chinese Journal of Medical Physics 2025;42(9):1191-1196
Depression,as a severe psychological and psychiatric disorder,significantly impairs the long-term physical and mental health of patients.Current depression detection methods are plagued by strong subjectivity,limited techniques,and inadequate intelligence.Previous studies have mostly relied on single-modal signal analysis,making it difficult to comprehensively reflect the multidimensional characteristics of depression.Based on the independently developed intelligent depression detection system,wearable devices are used to collect prefrontal dual-lead EEG signals,PPG signals,and single-lead ECG signals.Data from 30 patients with depression and 40 healthy controls are collected and analyzed.A multimodal depression recognition model named RBLF-Net is proposed,which integrates spatiotemporal features,weighted attention,and random forests to utilize the multi-signal features for depression recognition.The model exhibits superior performance in the five-fold cross-validation,achieving a classification accuracy of 81.43%,a precision of 81.02%,and a recall rate of 81.25%,outperforming other comparative models,and thus providing an intelligent analysis approach for depression recognition from the perspective of multi-modal fusion.
8.Analysis of risk factors of bleeding caused by thrombus head shedding in patients with esophageal varices during endoscopic diagnosis and treatment and construction of nomogram prediction model
Minghui WANG ; Xiaofeng LIU ; Qun LI ; Jing WANG ; Wenbo LI
China Journal of Endoscopy 2025;31(7):25-30
Objective To investigate the risk factors of thrombus head shedding and bleeding during endoscopic treatment of patients with esophageal varices veins,and build a risk prediction model.Methods 209 cases of esophageal varices with thrombus head found by endoscopy from February 2009 to July 2024 were retrospectively analyzed,and divided into non-shedding group(n=186)and shedding group(n=23)according to whether thrombus head shedding bleeding occurred during endoscopic treatment.Clinical and endoscopic data of the two groups were compared.Statistically significant factors were included in multivariate Logistic regression analysis and their independent risk factors were explored.A nomogram risk prediction model was constructed by R software,and its prediction efficiency was evaluated.Results Multivariate Logistic regression analysis showed that red thrombus head((O^R)=6.231,95%CI:1.748~22.208),thrombus head diameter≥3 mm((O^R)=4.355,95%CI:1.341~14.144),conical thrombus head((O^R)=8.555,95%CI:2.427~30.154),and the presence of hematoma in the stomach((O^R)=7.079,95%CI:1.665~30.103)were risk factors for bleeding after thrombus head shedding during endoscopic diagnosis and treatment.A nomogram prediction model was constructed with a sensitivity of 0.870(95%CI:0.732~1.000)and a specificity of 0.887(95%CI:0.842~0.933).Conclusion The thrombus head being red,conical in shape,with a diameter of≥3 mm and the presence of hematoma in the stomach are independent risk factors for thrombus head shedding and bleeding during endoscopic diagnosis and treatment.Timely intervention should be made for the above factors to benefit patients.
9.Twelve cases of occupational acute 2- (2-thiophenyl) scopolamine glycolate poisoning
Yugui HAO ; Minghui WANG ; Jilai QU ; Xuechuang ZHU ; Jian LIU ; Xinxiao WANG
Chinese Journal of Industrial Hygiene and Occupational Diseases 2025;43(6):453-455
2- (2-thiophenyl) scopolamine glycolate is produced through an ester exchange reaction between scopine and methyl 2, 2-dithienylglycolate, and is used to synthesize tiotropium bromide. In this paper, the treatment process of 12 patients with acute 2- (2-thiophenyl) scopolamine glycolate poisoning was reviewed and their clinical data were analyzed. After a large amount of 2- (2-thiophenyl) scopolamine glycolate was absorbed through the respiratory tract, the poisoning patients presented with central nervous system injury as the main clinical manifestations, accompanied by symptoms such as blurred vision and irritability. After fluid replacement, ovulation induction and symptomatic supportive treatment, all patients improved and were discharged. The patients were followed up. After 6 months, only 3 patients had residual headache and dizziness. It is indicated that early intervention for acute 2- (2-thiophenyl) scopolamine glycolate poisoning has a good prognosis. Meanwhile, occupational protection should be strengthened to prevent the occurrence of poisoning.
10.Advances in research on mechanisms underlying damage of low-dose ionizing radiation to spermatogenesis and relevant protective measures
Shen ZHU ; Bo HU ; Minghui CUI ; Haobing YU ; Xiaoyu LIU ; Suiyi LIU ; Ying HE
Chinese Journal of Radiological Medicine and Protection 2025;45(8):818-826
Ionizing radiation occurs not only during nuclear and radiological terrorist attacks or nuclear accidents but also in medical applications and daily life. In recent years, the potential toxic effects of low-dose ionizing radiation on the male reproductive system have raised public health concerns. Most specifically, for the testis, a highly sensitive target organ to ionizing radiation, there is an urgent need to determine the mechanisms underlying the association between radiation-induced spermatogenic failure and male infertility. Focusing on the potential injurious effects of low-dose ionizing radiation on spermatogenesis, this review presents a summary and analysis of various underlying mechanisms including oxidative stress, apoptosis, and DNA damage repair and reviews recent domestic and international strategies for protecting against radiation-induced reproductive system damage in order to offer references for future research on the injurious effects of low-dose radiation on spermatogenesis and relevant protection.


Result Analysis
Print
Save
E-mail