BackgroundLow medication compliance among patients with severe mental disorders increases the disease burden on both the patients' families and the society. Medication adherence is influenced by numerous factors. Traditional methods such as Logistic regression struggle to quantify the importance of these factors. By introducing Extreme Gradient Boosting （XGBoost） combined with Shapley Additive Explanations （SHAP）， enables the quantification of the relative contribution weights of each factor， providing support for identifying the core influencing factors. ObjectiveTo explore the influencing factors of medication adherence among patients with severe mental disorders in Zhuhai， aiming to provide references for optimizing patient management strategies. MethodsExtract the data of patients with severe mental disorders who were registered on the mental health system platform in Zhuhai City from January 1， 2023 to March 31， 2025. A total of 9 329 patients were finally included for analysis. Influencing factors were screened using univariate analysis and multivariate logistic regression analysis， and an XGBoost model combined with the SHAP algorithm was constructed to quantify the importance of each influencing factor. ResultsAmong 9 329 patients， 8 446 demonstrated medication adherence， yielding an adherence rate of 90.53%. Multivariable analysis identified several risk factors significantly associated with medication non-adherence， being unmarried （OR=1.237， 95% CI： 1.019–1.502） or divorced （OR=1.389， 95% CI： 1.038–1.832）， a diagnosis of mental retardation with psychiatric disorders （OR=3.025， 95% CI： 2.402–3.796） or paranoid psychosis （OR=5.117， 95% CI： 3.086–8.299）， a disease duration of 2–4 years （OR=1.355， 95% CI： 1.085–1.696）， 4–6 years （OR=2.143， 95% CI： 1.671–2.747）， or >6 years （OR=1.681， 95% CI： 1.365–2.079）， lack of guardian subsidies （OR=1.412， 95% CI： 1.099–1.801）， absence of a disability certificate （OR=1.900， 95% CI： 1.588–2.282）， not being enrolled in care and support groups （OR=1.384， 95% CI： 1.183–1.617） or community services （OR=1.313， 95% CI： 1.042–1.645）， and not cohabiting with a guardian （OR=1.257， 95% CI： 1.048–1.501）. Conversely， the enrollment in special outpatient disease programs （OR=0.716， 95% CI： 0.609–0.842） and a family history of mental illness （OR=0.713， 95% CI： 0.503–0.982） were identified as protective factors. The XGBoost model exhibited robust predictive performance， with a sensitivity of 0.433， specificity of 0.944， accuracy of 0.891， Area Under the Curve （AUC） of 0.837， and F1 value of 0.449. Feature importance ranking indicated that the top three factors were disease duration， diagnosis， and the acquisition of disability certificates. ConclusionPolicy-based support （acquisition of disability certificates， special outpatient disease enrollment） and clinical disease characteristics （disease duration， diagnosis type） are key factors affecting medication adherence among patients with severe mental disorders in Zhuhai City. ［Funded by Zhuhai Medical Research Project （number， 2220009000281）］

OBJECTIVE: To explore the clinical and genetic features of a child with Pontocerebellar hypoplasia type 2B (PCH2B) due to compound heterozygous variants of the TSEN2 gene. METHODS: A PCH2B patient presented at Department of Pediatric Neurology, Xiangya Hospital of Central South University in June 2023 was selected as the study subject. Clinical data of the patient were retrospectively analyzed. The patient and her parents were subjected to whole exome sequencing and bioinformatic analysis. Pathogenicity of the candidate variants were classified based on the guidelines from the American College of Medical Genetics and Genomics (ACMG). A literature review was also conducted by searching the China National Knowledge Infrastructure (CNKI), Wanfang Data, and PubMed databases from their establishment to May 2025 using keywords "TSEN2 gene" "PCH2B" and "Pontocerebellar Hypoplasia 2B" to summarize the clinical and genotypic features of patients with PCH2B due to variants of the TSEN2 gene. This study was approved by the Medical Ethics Committee of the Hospital (No.: #202310892). RESULTS: The patient, a 6-year-5-month-old girl, had exhibited severe global developmental delay, developmental regression, autism spectrum disorder, myoclonus of eyelids, feeding difficulty, irritability, progressive microcephaly, esotropia, and hypotonia. MRI showed reduced volume of bilateral cerebellar hemispheres and vermis. Genetic testing revealed that she has harbored compound heterozygous variants of the TSEN2 gene (NM_025265.4), namely c.1054A>T (p.Lys352*) and c.899G>T (p.Ser300Ile), which were inherited from her father and mother, respectively. Both variants were classified as likely pathogenic based on the ACMG guidelines and were previously unreported. Literature review has identified six PCH2B patients with missense, nonsense, frameshift, and splice site variants of the TSEN2 gene. Their main clinical manifestations included global developmental delay, progressive microcephaly, feeding difficulties, irritability, and vermis hypoplasia. Cranial MRI and genetic testing are crucial for definite diagnosis. CONCLUSION The c.1054A>T (p.Lys352*) and c.899G>T (p.Ser300Ile) compound heterozygous variants of the TSEN2 gene probably underlay the pathogenesis in this patient. Above findings has expanded the genotypic and phenotypic spectra of TSEN2-related PCH2B, and offered guidance for genetic counseling for this family.
Child ; Female ; Humans ; Cerebellar Diseases/genetics* ; Exome Sequencing ; Heterozygote ; Mutation

Objective: To evaluate the feasibility of dynamic contrast-enhanced MRI (DCE-MRI) in differentiating tumor deposits (TDs) from metastatic lymph nodes (MLNs) in rectal cancer. Materials and Methods: A retrospective analysis was conducted on 70 patients with rectal cancer, including 168 lesions (70 TDs and 98 MLNs confirmed by histopathology), who underwent pretreatment MRI and subsequent surgery between March 2019 and December 2022. The morphological characteristics of TDs and MLNs, along with quantitative parameters derived from DCE-MRI (K trans , kep, and v e) and DWI (ADCmin, ADCmax, and ADCmean), were analyzed and compared between the two groups.Multivariable binary logistic regression and receiver operating characteristic (ROC) curve analyses were performed to assess the diagnostic performance of significant individual quantitative parameters and combined parameters in distinguishing TDs from MLNs. Results: All morphological features, including size, shape, border, and signal intensity, as well as all DCE-MRI parameters showed significant differences between TDs and MLNs (all P < 0.05). However, ADC values did not demonstrate significant differences (all P > 0.05). Among the single quantitative parameters, v e had the highest diagnostic accuracy, with an area under the ROC curve (AUC) of 0.772 for distinguishing TDs from MLNs. A multivariable logistic regression model incorporating short axis, border, v e, and ADC mean improved diagnostic performance, achieving an AUC of 0.833 (P = 0.027). Conclusion The combination of morphological features, DCE-MRI parameters, and ADC values can effectively aid in the preoperative differentiation of TDs from MLNs in rectal cancer.

ObjectiveTo investigate the mechanism of kidney-tonifying and liver-regulating cyclical therapy and its formula in regulating endometrial receptivity during the "implantation window" in rats with polycystic ovary syndrome （PCOS）. MethodsSix rats were randomly selected from 36 SPF SD female rats as the normal group， and the remaining rats were administered letrozole to induce a PCOS model. By using a random number method， the rats were divided into the following groups： normal group， model group， Xiaoyaosan group （11.97 g·kg^-1）， Sanzi Yangmo decoction group （28.35 g·kg^-1）， cyclical therapy group （11.97/28.35 g·kg^-1）， and aspirin group （8 × 10^-3 mg·kg^-1）. After 12 days of continuous administration by gavage （equivalent to three estrous cycles）， female and male rats were co-housed. On the fifth day of pregnancy， the number of blastocyst implantation in each group was counted. Hematoxylin-eosin （HE） staining was used to observe the pathological morphology of rat endometrial tissue. Enzyme-linked immunosorbent assay （ELISA） was used to measure the levels of estradiol （E₂） and progesterone （P） in rat serum. Western blot was used to detect the protein expression of vascular endothelial growth factor （VEGF）， progesterone receptor （PR）， estrogen receptor （ER）， androgen receptor （AR）， and integrin（ITG） αvβ3 in rat endometrial blood vessels. Real-time fluorescence quantitative polymerase chain reaction （Real-time PCR） was used to detect the mRNA expression of miR-140-5 P， VEGF， vascular endothelial growth factor receptor 2 （VEGFR2）， PR， ER， AR， and ITGαvβ3 in rat endometrium. ResultsCompared with normal group， the estrous cycle of the rats in model group continued to be in the estrus interval and the estrous cycle lost regular changes. The endometrium was significantly thinner， the number of uterine glands and blood vessels were significantly reduced （P<0.01）， and the pregnancy rate was significantly reduced. Compared with the model group， each drug group restored the regular estrous cycle to varying degrees， and the endometrial thickness and the number of blood vessels were significantly improved （P<0.01）. The pregnancy rate of each drug group increased， and the effect of the cycle therapy group could reach the normal level. The results of molecular biology experiments showed that compared with the normal group， the levels of serum E₂ and P in the model group were significantly decreased （P<0.01）， the expression of VEGF， ER， PR and ITGαvβ3 protein was significantly decreased （P<0.05，P<0.01）， the expression of AR protein was significantly increased （P<0.01）， the expression of miR-140-5P and AR mRNA was significantly increased （P<0.01）， and the expression of VEGF， VEGFR2， ER， PR and ITGαvβ3 mRNA was significantly decreased （P<0.01）. Compared with model group， the serum E₂ level in the Xiaoyaosan group was significantly increased （P<0.01）.The levels of E₂ and P in serum of rats in Sanzi Yangmo decoction group， cycle therapy group and aspirin group were significantly increased （P<0.01）. The expression of AR protein in each drug group was significantly decreased （P<0.01）. The expression of VEGF and ITGαvβ3 protein in Xiaoyaosan group was significantly increased （P<0.01）. The expression of VEGF， ER and PR protein in Sanzi Yangmo decoction group was increased to varying degrees （P<0.05，P<0.01）. The expression of VEGF， PR， ER and ITGαvβ3 protein in the cycle therapy group and the aspirin group increased to varying degrees （P<0.05，P<0.01）. The expression of miR-140-5P and AR mRNA in each drug group was significantly decreased （P<0.01）. The expression of VEGF， VEGFR2， ER， PR and ITGαvβ3 mRNA in each drug group increased to varying degrees （P<0.05，P<0.01）. Compared with Xiaoyaosan group and Sanzi Yangmo decoction group， the expression of miR-140-5P， VEGFR2， ER， PR， AR and ITGαvβ3 mRNA in the cycle therapy group were significantly different （P<0.05，P<0.01）. ConclusionThe kidney-tonifying and liver-regulating cyclical therapy may reduce the activity of miR-140-5P， target the upregulation of VEGF expression， mediate angiogenesis， and promote endometrial angiogenesis， thereby playing a synergistic role in improving endometrial receptivity in PCOS-induced infertility. Its efficacy in increasing pregnancy rates surpasses that of Xiaoyaosan or Sanzi Yangmo decoction used alone.

ObjectiveTo investigate the mechanism of kidney-tonifying and liver-regulating cyclical therapy and its formula in regulating endometrial receptivity during the "implantation window" in rats with polycystic ovary syndrome （PCOS）. MethodsSix rats were randomly selected from 36 SPF SD female rats as the normal group， and the remaining rats were administered letrozole to induce a PCOS model. By using a random number method， the rats were divided into the following groups： normal group， model group， Xiaoyaosan group （11.97 g·kg^-1）， Sanzi Yangmo decoction group （28.35 g·kg^-1）， cyclical therapy group （11.97/28.35 g·kg^-1）， and aspirin group （8 × 10^-3 mg·kg^-1）. After 12 days of continuous administration by gavage （equivalent to three estrous cycles）， female and male rats were co-housed. On the fifth day of pregnancy， the number of blastocyst implantation in each group was counted. Hematoxylin-eosin （HE） staining was used to observe the pathological morphology of rat endometrial tissue. Enzyme-linked immunosorbent assay （ELISA） was used to measure the levels of estradiol （E₂） and progesterone （P） in rat serum. Western blot was used to detect the protein expression of vascular endothelial growth factor （VEGF）， progesterone receptor （PR）， estrogen receptor （ER）， androgen receptor （AR）， and integrin（ITG） αvβ3 in rat endometrial blood vessels. Real-time fluorescence quantitative polymerase chain reaction （Real-time PCR） was used to detect the mRNA expression of miR-140-5 P， VEGF， vascular endothelial growth factor receptor 2 （VEGFR2）， PR， ER， AR， and ITGαvβ3 in rat endometrium. ResultsCompared with normal group， the estrous cycle of the rats in model group continued to be in the estrus interval and the estrous cycle lost regular changes. The endometrium was significantly thinner， the number of uterine glands and blood vessels were significantly reduced （P<0.01）， and the pregnancy rate was significantly reduced. Compared with the model group， each drug group restored the regular estrous cycle to varying degrees， and the endometrial thickness and the number of blood vessels were significantly improved （P<0.01）. The pregnancy rate of each drug group increased， and the effect of the cycle therapy group could reach the normal level. The results of molecular biology experiments showed that compared with the normal group， the levels of serum E₂ and P in the model group were significantly decreased （P<0.01）， the expression of VEGF， ER， PR and ITGαvβ3 protein was significantly decreased （P<0.05，P<0.01）， the expression of AR protein was significantly increased （P<0.01）， the expression of miR-140-5P and AR mRNA was significantly increased （P<0.01）， and the expression of VEGF， VEGFR2， ER， PR and ITGαvβ3 mRNA was significantly decreased （P<0.01）. Compared with model group， the serum E₂ level in the Xiaoyaosan group was significantly increased （P<0.01）.The levels of E₂ and P in serum of rats in Sanzi Yangmo decoction group， cycle therapy group and aspirin group were significantly increased （P<0.01）. The expression of AR protein in each drug group was significantly decreased （P<0.01）. The expression of VEGF and ITGαvβ3 protein in Xiaoyaosan group was significantly increased （P<0.01）. The expression of VEGF， ER and PR protein in Sanzi Yangmo decoction group was increased to varying degrees （P<0.05，P<0.01）. The expression of VEGF， PR， ER and ITGαvβ3 protein in the cycle therapy group and the aspirin group increased to varying degrees （P<0.05，P<0.01）. The expression of miR-140-5P and AR mRNA in each drug group was significantly decreased （P<0.01）. The expression of VEGF， VEGFR2， ER， PR and ITGαvβ3 mRNA in each drug group increased to varying degrees （P<0.05，P<0.01）. Compared with Xiaoyaosan group and Sanzi Yangmo decoction group， the expression of miR-140-5P， VEGFR2， ER， PR， AR and ITGαvβ3 mRNA in the cycle therapy group were significantly different （P<0.05，P<0.01）. ConclusionThe kidney-tonifying and liver-regulating cyclical therapy may reduce the activity of miR-140-5P， target the upregulation of VEGF expression， mediate angiogenesis， and promote endometrial angiogenesis， thereby playing a synergistic role in improving endometrial receptivity in PCOS-induced infertility. Its efficacy in increasing pregnancy rates surpasses that of Xiaoyaosan or Sanzi Yangmo decoction used alone.

Through a comprehensive analysis combining network pharmacology prediction and transcriptomics, this study systematically explained the multi-target mechanism of Cyanotis arachnoidea(CA) Gel in improving melasma. A melasma model was induced in female SD rats by progesterone injection combined with ultraviolet B(UVB) irradiation for 40 consecutive days, while the blank control group was only fed routinely. After successful model establishment, the rats were randomly divided into five groups and administered different doses of CA ethanol extract gel(high, medium, and low doses) or arbutin Gel(positive control), which were applied once daily for 28 consecutive days. Subsequently, the levels of superoxide dismutase(SOD), malondialdehyde(MDA), and tyrosinase(TYR) in the skin, serum, and liver tissues were measured. Hematoxylin-eosin(HE) staining and Masson-Fontana staining were used to observe the pathological changes in the tissues. Network pharmacology combined with transcriptomics was employed to identify core targets and pathways, and the differential gene expression was validated by quantitative real-time PCR(qPCR). Pharmacodynamic experiments showed that CA Gel significantly increased SOD activity and decreased MDA and TYR levels in the skin, serum, and liver of model rats. It also improved epidermal thickening, inflammatory infiltration, collagen loss, and melanin deposition. Network pharmacology analysis showed that CA mainly regulated core targets such as signal transducer and activator of transcription 3(STAT3), epidermal growth factor receptor(EGFR), and interleukin-6(IL-6), and modulated the phosphatidylinositol 3-kinase(PI3K)-protein kinase B(AKT) and interleukin-17(IL-17) signaling pathways. Transcriptomic analysis showed that CA Gel significantly downregulated the gene expression of heat shock protein 90β family member 1(Hsp90b1), heat shock protein 90α family member 1(Hsp90aa1), and the key steroid synthesis enzyme cytochrome P450 family 17 subfamily A member 1(Cyp17a1), while upregulating thioredoxin 1(Txn1). qPCR results confirmed that CA Gel regulated oxidative stress and inflammatory response by inhibiting the IL-17 signaling pathway and steroid hormone synthesis. This study, for the first time, reveals the molecular mechanism of CA Gel in improving melasma through multi-target synergistic regulation of oxidative stress, inflammatory response, and hormone metabolism pathways, providing a scientific basis for the treatment of pigmentation diseases with traditional Chinese medicine.
Animals ; Rats ; Female ; Rats, Sprague-Dawley ; Network Pharmacology ; Drugs, Chinese Herbal/administration & dosage* ; Melanosis/metabolism* ; Transcriptome/drug effects* ; Humans ; Superoxide Dismutase/genetics* ; Signal Transduction/drug effects* ; Malondialdehyde/metabolism*

Cardiotocography (CTG) is a non-invasive and important tool for diagnosing fetal distress during pregnancy. To meet the needs of intelligent fetal heart monitoring based on deep learning, this paper proposes a TWD-MOAL deep active learning algorithm based on the three-way decision (TWD) theory and multi-objective optimization Active Learning (MOAL). During the training process of a convolutional neural network (CNN) classification model, the algorithm incorporates the TWD theory to select high-confidence samples as pseudo-labeled samples in a fine-grained batch processing mode, meanwhile low-confidence samples annotated by obstetrics experts were also considered. The TWD-MOAL algorithm proposed in this paper was validated on a dataset of 16 355 prenatal CTG records collected by our group. Experimental results showed that the algorithm proposed in this paper achieved an accuracy of 80.63% using only 40% of the labeled samples, and in terms of various indicators, it performed better than the existing active learning algorithms under other frameworks. The study has shown that the intelligent fetal heart monitoring model based on TWD-MOAL proposed in this paper is reasonable and feasible. The algorithm significantly reduces the time and cost of labeling by obstetric experts and effectively solves the problem of data imbalance in CTG signal data in clinic, which is of great significance for assisting obstetrician in interpretations CTG signals and realizing intelligence fetal monitoring.
Humans ; Pregnancy ; Female ; Cardiotocography/methods* ; Deep Learning ; Neural Networks, Computer ; Algorithms ; Fetal Monitoring/methods* ; Heart Rate, Fetal ; Fetal Distress/diagnosis* ; Fetal Heart/physiology*

Retrieving keyframes most relevant to text from small intestine videos with given labels can efficiently and accurately locate pathological regions. However, training directly on raw video data is extremely slow, while learning visual representations from image-text datasets leads to computational inconsistency. To tackle this challenge, a small bowel video keyframe retrieval based on multi-modal contrastive learning (KRCL) is proposed. This framework fully utilizes textual information from video category labels to learn video features closely related to text, while modeling temporal information within a pretrained image-text model. It transfers knowledge learned from image-text multimodal models to the video domain, enabling interaction among medical videos, images, and text data. Experimental results on the hyper-spectral and Kvasir dataset for gastrointestinal disease detection (Hyper-Kvasir) and the Microsoft Research video-to-text (MSR-VTT) retrieval dataset demonstrate the effectiveness and robustness of KRCL, with the proposed method achieving state-of-the-art performance across nearly all evaluation metrics.
Humans ; Video Recording ; Intestine, Small/diagnostic imaging* ; Machine Learning ; Image Processing, Computer-Assisted/methods* ; Algorithms

ObjectiveTo explore the correlation between the occurrence of cardiovascular events in rheumatoid arthritis（RA） and traditional Chinese medicine（TCM） syndrome. MethodsThe cross-sectional study selected 6713 RA patients from 122 centres nationwide， in which general information such as name， gender， age， height， body weight， and course of disease were collected by completing a questionnaire； patients were classified into eight types of syndrome according to the information of their four examinations，i.e. wind-dampness obstruction syndrome， cold-dampness obstruction syndrome， dampness-heat obstruction syndrome， phlegm-stasis obstruction syndrome， stasis-blood obstructing collateral syndrome， qi-blood deficiency syndrome， liver-kidney insufficiency syndrome， and qi-yin deficiency syndrome. According to the occurrence of cardiovascular events， they were divided into the occurrence group and the non-occurrence group， and the condition assessment data and laboratory examination indexes were recorded. The test of difference between groups was used to analyse the possible risk factors for the occurrence of RA cardiovascular events， and binary logistic regression was used to analyse the correlation between TCM syndromes and RA cardiovascular events. ResultsA total of 6713 RA patients were included， including 256 cases in occurrence group and 6457 in non-occurrence group. There was no statistically significant difference between groups in terms of height， gender， insomnia， appetite， white blood cell（WBC）， hemoglobin（HGB）， platelets（PLT）， rheumatoid factor（RF）， anti-cyclic peptide containing citrulline（CCP）， alanine aminotransferase（ALT）， aspartate aminotransferase（AST）， γ-glutamyl transpeptidase（GGT）， urea creatinine（CREA）， and glucose（GLU）（P＞0.05）. The TCM syndromes between groups showed significant statistic differences（P＜0.05）. Patients in occurrence group had longer disease duration， heavier body weight， and older age； more severe conditions such as disease activity（DAS-28）， number of painful joints（TJC）， number of swollen joints（SJC）， health questionnaire scores（HAQ）， visual analog scores（VAS）， restlessness， and fatigue； higher blood sedimentation rate（ESR）， low-density lipoprotein（LDL-C）， triglyceride（TG）， total cholesterol（TC）， D-Dimer， and lower high-density lipoprotein（HDL-C）（P＜0.05）. The distribution of syndrome types showed that dampness-heat obstruction syndrome accounted for the largest proportion of patients in both groups and was higher in RA cardiovascular events. Logistic regression analysis showed that the occurrence of RA cardiovascular events was strongly associated with dampness-heat obstruction syndrome［OR=5.937， 95%CI （4.434， 7.949）， P＜0.001］. ConclusionThe occurrence of RA cardiovascular events were associated with TCM syndromes， and the probability of cardiovascular events in the RA patients with dampness-heat obstruction syndrome was 5.937 times higher than patients with other TCM syndromes.

Objective: To analyze the HLA typing and STR loci chimerism in a patient with recurrent acute lymphoblastic leukemia after HLA-haploidentical hematopoietic stem cell transplantation. Methods: HLA typing was performed on peripheral blood, buccal swabs and saliva samples after transplantation using PCR-sequence-specific oligonucleotide probes (PCR-SSOP) and next-generation sequencing (NGS). Additionally, STR analysis was conducted on these samples using a 21-locus STR assay kit to detect STR loci. Results: The HLA typing and STR locus outcomes of the patient's peripheral blood and the second saliva sample post-transplantation were in full concordance with the test results of the donor (father), whereas the HLA typing and STR locus results derived from the buccal swabs and the first saliva sample indicated chimerism between the donor and the recipient. Conclusion: In the follow-up and monitoring after transplantation, apart from focusing on peripheral blood samples, it is recommended to regularly monitor HLA typing and STR loci chimerism in patients' buccal swabs and saliva samples to comprehensively evaluate the transplantation effect and recurrence risk.