ObjectiveTo explore the effect of the medical-community linkage model on activities of daily living, psychological status and motor function of stroke patients in the community. MethodsA total of 60 stroke patients admitted to two community health service centers and their affiliated stations in Fengtai District, Beijing, from January, 2024 to August, 2025 were enrolled and randomly divided into control group (n = 30) and intervention group (n = 30). The control group received routine medicine, dietary care and rehabilitation management, while the intervention group underwent rehabilitation with the medical-community linkage model, for twelve weeks. They were assessed with modified Barthel Index (MBI), Hamilton Anxiety Scale (HAMA), Hamilton Depression Scale (HAMD) and Fugl-Meyer Assessment (FMA) before and after intervention. ResultsAfter intervention, the MBI, HAMA, HAMD and FMA scores of patients improved in both groups (|t| > 5.599, P < 0.001), and improved more in the intervention group than in the control group (P < 0.05), except MBI. The HAMA and HAMD scores of family members decreased in both groups (|t| > 10.333, P < 0.001), and decreased more in the intervention group than in the control group (t > 5.681, P < 0.001). ConclusionThe medical-community linkage model can further improve the motor function of stroke patients in community, as well as the psychological status of both patients and their family members.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

ObjectiveDiscriminating atypical hepatocellular carcinoma (HCC) from other malignancies in liver nodules classified as Liver Imaging Reporting and Data System category M (LR-M) remains a significant diagnostic challenge on conventional ultrasound examination. The LR-M category, originally intended to capture non-HCC malignancies, paradoxically contains up to 63% of atypical HCCs that deviate from classic enhancement patterns, leading to potential misdiagnosis and suboptimal treatment planning. While deep learning has shown promise in HCC diagnosis, most existing models rely exclusively on single-modality ultrasound, overlooking the diagnostic benefits of integrating complementary information from multiple imaging sources. To address this gap, we propose a novel attention-weighted tri-modal ultrasound network (TUS-Net) that integrates contrast-enhanced ultrasound (CEUS), B-mode ultrasound (BUS), and time-intensity curves (TICs) to improve diagnostic accuracy for these clinically challenging lesions. MethodsOur framework incorporates a three-dimensional convolutional neural network (C3D) backbone to extract spatiotemporal features from CEUS videos, capturing dynamic vascular patterns critical for lesion characterization. To effectively fuse complementary modalities, we introduce a dual-channel feature fusion module (DCFFM) that adaptively combines features from CEUS and BUS through channel-wise attention mechanisms, allowing the model to dynamically weigh the contribution of each modality based on diagnostic relevance. Additionally, we propose a temporal intensity feature fusion module (TIFFM) that leverages quantitative hemodynamic information from TICs to guide the model’s attention toward diagnostically critical temporal phases, such as arterial wash-in and portal venous washout. The model is further enhanced by automated lesion localization using YOLOX and class activation mapping for interpretability, ensuring that predictions align with clinically meaningful imaging features. ResultsEvaluated on a tri-modal ultrasound dataset comprising 161 patients with pathologically confirmed LR-M nodules (131 atypical HCC and 30 non-HCC malignancies), our model achieved an accuracy of 86.83%, a sensitivity of 92.50%, a specificity of 75.50%, and an AUC of 89.32% in screening atypical HCC. Compared to single-modality baselines, TUS-Net demonstrated superior specificity, a clinically critical metric given the higher risk associated with misclassifying non-HCC malignancies. Ablation studies confirmed the contribution of each module, with the full model outperforming both standard C3D and 3D ResNet backbones integrated with attention mechanisms. A reader study involving junior and senior radiologists further validated the clinical utility of AI assistance, showing consistent improvements in specificity and inter-reader consistency, particularly for less experienced clinicians. ConclusionThese results surpass existing benchmark models and demonstrate the potential of our approach to enhance diagnostic precision in clinically specific cases. By intelligently fusing multi-modal ultrasound data with attention-guided mechanisms, TUS-Net offers a reliable and interpretable tool that holds promise for improving the non-invasive diagnosis of atypical HCC in challenging LR-M liver nodules.

Non-functioning pituitary adenomas(NFPAs)are relatively common.Apart from hyperprolactinemia caused by pituitary compression,they typically lack overt hormonal hypersecretion and usually present with clinical symptoms due to mass effects.Previously considered a uniform entity,NFPAs are actually a highly heterogeneous group of tumors,including aggressive subtypes like silent corticotroph adenomas(SCA)and null cell adenomas.The 2022 WHO new classification of pituitary tumors employs transcription factors[e.g.,pituitary-specific transcription factor 1(PIT-1),T-box transcription factor 19(TBX19,also known as TPIT),steroidogenic factor 1(SF-1)]for detailed categorization,allowing precise subclassification of NFPAs into multiple subtypes derived from distinct cell lineages,including silent gonadotroph adenomas,SCA,and plurihormonal PIT-1-positive adenomas.This helps identify highly invasive subtypes with high recurrence risk,guiding clinical diagnosis and treatment,prognostic assessment,and individualized management.The new classification also provides a theoretical basis for targeted therapies of NFPAs(e.g.,somatostatin analogs and temozolomide).This review comprehensively discusses the latest pathological classification of NFPAs and its clinical implications,aiming to enhance understanding of this disease and offer valuable insights for precise diagnosis,treatment,and prognostic assessment.

OBJECTIVES: This study aimed to explore the impact of chronic kidney disease (CKD) on prognosis of patients older than 80 years after hip fracture. METHODS: This retrospective, observational, single-center study included patients older than 80 years who underwent hip fracture operations between Feburary 2013 to June 2021 at our hospital. Patients were divided into CKD and non-GKD groups based on the estimated glomerular filtration rate (eGFR) < 60 mL/(min·1.73m²)] or not. Outcomes were the incidence of in-hospital postoperative infectious and non-infectious complications, 30-day readmission, and in-hospital death. Logistic regression analysis was used to calculate the odds ratio (OR) of CKD on these outcomes. RESULTS: A total of 498 patients were included, 165 in the CKD group and 333 in the non-CKD group. Eighty-seven (52.7%) CKD patients experienced 140 episodes of postoperative complications. In comparison, 114 (34.2%) non-CKD patients had 158 episodes of postoperative complications. CKD patients were more likely to have postoperative complications than non-CKD patients (OR = 2.143, 95% CI: 1.465-3.134, P < 0.001). CKD increased the risk of cardiovascular complications (OR = 2.044, 95% CI: 1.245-3.356, P = 0.004), acute kidney injury (OR = 3.401, 95% CI: 1.905-6.072, P < 0.001), delirium (OR = 2.276, 95% CI: 1.140-4.543, P = 0.024), and gastrointestinal bleeding (OR = 4.151, 95% CI: 1.025-16.812, P = 0.031). The transfusion rate (OR = 2.457, 95% CI: 1.668-3.618, P < 0.001) and incidence of 30-day readmission (OR = 2.426, 95% CI:1.203-4.892, P = 0.011) in CKD patients were significantly higher than those in patients without CKD. CONCLUSIONS CKD is associated with poor postoperative outcomes in geriatric hip fracture patients. Special attention should be paid to patients with CKD.
Humans ; Renal Insufficiency, Chronic/physiopathology* ; Aged, 80 and over ; Postoperative Complications/epidemiology* ; Hip Fractures/complications* ; Male ; Female ; Patient Readmission/statistics & numerical data* ; Retrospective Studies ; Glomerular Filtration Rate

OBJECTIVE: To explore prevalence, incidence and possible factors of immediate herniated discs after posterior cervical expansive open-door laminoplasty (EODL). METHODS: Totally 29 patients with cervical spinal stenosis and intervertebral disc herniation who underwent EODL from October 2020 to December 2021 were collected, including 24 males and 5 females, aged from 43 to 81 years old with an average of (61.3±9.0) years old;the courses of disease ranged from 1 to 120 months with an average of (36.4±37.0) months. Three or more intervertebral discs on C₃-C₇ were observed. The clinical efficacy was evaluated according to Japanese Orthopaedic Association (JOA) score before operation, 3 days and 1, 3, 6 and 12 months after operation, respectively. The changes of herniated disc before and after operation were measured by multipoint area method and two-dimensional distance method, and incidence and percentage of herniated disc regression were further calculated. Cervical imaging parameters such as Cobb angle (C₃-C₇), intervertebral angle, T₁ slope (T₁S), spinal canal sagittal diameter, K-line angle, dural sac sagittal diameter were measured and compared before and after operation. Pearson correlation was used to analyze correlation between cervical sagittal imaging parameters and disc herniation changes before and after operation. RESULTS: All patients obtained grade A wound healing, and 14 of them were followed up for 3(1.00, 5.25) months. There were no immediate or long-term postoperative complications. Totally 101 herniated intervertebral discs were measured, of which 79 regression numbers were obtained by area measurement. The number of intervertebral disc regressions by distance measurement was 77. There was no statistically significant difference in Cobb angle, intervertebral angle, T₁S and K-line angle of C₃-C₇ (P>0.05), however, there were statistically significant differences in sagittal diameter of spinal canal, sagittal diameter of dural sac, and JOA score before and after operation(P<0.05). The regression ratio of disc herniation ranged from 5% to 50%, and regression ratio of disc herniation was greater than 25% in 45.57%(36/79). Disc herniation in C_4,5 was positively correlated with sagittal plane diameter in C₅(r=0.423, P=0.028). There was a negative correlation between changes of C_3,4 and C_3,4 intervertebral angle (r=-0.450, P=0.041). The improvement rate of cervical JOA score immediately after operation was (59.54±15.07) %, and postoperative follow-up improved to (76.57±14.66) %. CONCLUSION Herniated disc regression immediately after EODL is a common occurrence, and EODL should be selected as far as possible under the premise of satisfying surgical indications. The regression of disc herniation is positively correlated with spinal canal sagittal diameter, and spinal canal should be enlarged as far as possible in the appropriate scope during EODL, so as to create more opportunities and conditions for disc regression and achieve better clinical results.
Humans ; Female ; Male ; Intervertebral Disc Displacement/diagnostic imaging* ; Spinal Stenosis/diagnostic imaging* ; Laminoplasty/methods* ; Middle Aged ; Aged ; Cervical Vertebrae/diagnostic imaging* ; Adult ; Aged, 80 and over ; Intervertebral Disc/surgery*

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

The genome tagging project (GTP) plays a pivotal role in addressing a critical gap in the understanding of protein functions. Within this framework, we successfully generated a human influenza hemagglutinin-tagged sperm-specific protein 411 (HA-tagged Ssp411) mouse model. This model is instrumental in probing the expression and function of Ssp411. Our research revealed that Ssp411 is expressed in the round spermatids, elongating spermatids, elongated spermatids, and epididymal spermatozoa. The comprehensive examination of the distribution of Ssp411 in these germ cells offers new perspectives on its involvement in spermiogenesis. Nevertheless, rigorous further inquiry is imperative to elucidate the precise mechanistic underpinnings of these functions. Ssp411 is not detectable in metaphase II (MII) oocytes, zygotes, or 2-cell stage embryos, highlighting its intricate role in early embryonic development. These findings not only advance our understanding of the role of Ssp411 in reproductive physiology but also significantly contribute to the overarching goals of the GTP, fostering groundbreaking advancements in the fields of spermiogenesis and reproductive biology.
Animals ; Female ; Humans ; Male ; Mice ; Spermatids/metabolism* ; Spermatogenesis/physiology* ; Spermatozoa/metabolism* ; Thioredoxins/genetics*

OBJECTIVE: To examine the effectiveness of Chinese medicine (CM) Lianhua Qingwen Granule (LHQW) and Jingyin Gubiao Prescription (JYGB) in asymptomatic or mild patients with Omicron infection in the shelter hospital. METHODS: This single-center retrospective cohort study was conducted in the largest shelter hospital in Shanghai, China, from April 10, 2022 to May 30, 2022. A total of 56,244 asymptomatic and mild Omicron cases were included and divided into 4 groups, i.e., non-administration group (23,702 cases), LHQW group (11,576 cases), JYGB group (12,112 cases), and dual combination of LHQW and JYGB group (8,854 cases). The length of stay (LOS) in the hospital was used to assess the effectiveness of LHQW and JYGB treatment on Omicron infection. RESULTS: Patients aged 41-60 years, with nadir threshold cycle (C_T) value of N gene <25, or those fully vaccinated preferred to receive CM therapy. Before or after propensity score matching (PSM), the multiple linear regression showed that LHQW and JYGB treatment were independent influence factors of LOS (both P<0.001). After PSM, there were significant differences in LOS between the LHQW/JYGB combination and the other groups (P<0.01). The results of factorial design ANOVA proved that the LHQW/JYGB combination therapy synergistically shortened LOS (P=0.032). CONCLUSIONS Patients with a nadir C_T value <25 were more likely to accept CM. The LHQW/JYGB combination therapy could shorten the LOS of Omicron-infected individuals in an isolated environment.
Humans ; Drugs, Chinese Herbal/therapeutic use* ; Male ; Female ; Middle Aged ; Adult ; China/epidemiology* ; Hospitalization ; COVID-19 Drug Treatment ; COVID-19/epidemiology* ; SARS-CoV-2 ; Retrospective Studies ; Treatment Outcome ; Length of Stay ; Young Adult ; Aged

Traditional Chinese medicine (TCM) represents a paradigmatic approach to personalized medicine, developed through the systematic accumulation and refinement of clinical empirical data over more than 2000 years, and now encompasses large-scale electronic medical records (EMR) and experimental molecular data. Artificial intelligence (AI) has demonstrated its utility in medicine through the development of various expert systems (e.g., MYCIN) since the 1970s. With the emergence of deep learning and large language models (LLMs), AI's potential in medicine shows considerable promise. Consequently, the integration of AI and TCM from both clinical and scientific perspectives presents a fundamental and promising research direction. This survey provides an insightful overview of TCM AI research, summarizing related research tasks from three perspectives: systems-level biological mechanism elucidation, real-world clinical evidence inference, and personalized clinical decision support. The review highlights representative AI methodologies alongside their applications in both TCM scientific inquiry and clinical practice. To critically assess the current state of the field, this work identifies major challenges and opportunities that constrain the development of robust research capabilities-particularly in the mechanistic understanding of TCM syndromes and herbal formulations, novel drug discovery, and the delivery of high-quality, patient-centered clinical care. The findings underscore that future advancements in AI-driven TCM research will rely on the development of high-quality, large-scale data repositories; the construction of comprehensive and domain-specific knowledge graphs (KGs); deeper insights into the biological mechanisms underpinning clinical efficacy; rigorous causal inference frameworks; and intelligent, personalized decision support systems.
Medicine, Chinese Traditional/methods* ; Artificial Intelligence ; Humans ; Precision Medicine ; Decision Support Systems, Clinical