Recommended TopicsMore+- Application of artificial intelligence in mental health management: toward early screening, assessment, and intervention
- Interpretation of the Diagnosis and treatment norms for colorectal cancer in China (2025 edition)
- Artificial intelligence empowers precision rehabilitation for stroke: assessment, intervention, and remote management
- “Preventive treatment of disease” and whole-course management: an interpretation of the Implementation Plan for the “Weight Management Years” Campaign
- Expert consensus on the principles of severe injury treatment by emergency medical rescue teams in major nuclear accidents (2025 edition)
- Consensus on artificial intelligence-assisted ultrasound management for breast nodules
- Reshaping modern medicine: applications, challenges, and future prospects of artificial intelligence
- Artificial intelligence-assisted endoscopy for early screening, diagnosis, and therapy of gastrointestinal tumors
- Artificial intelligence-assisted CT diagnosis of lymph node metastasis: integrated models,multi-cancer applications,and interpretability challenges
- Artificial intelligence in gynecological surgery: current situation,challenges and prospects
- Current Discuss
- First Published
- Album Paper
-
Artificial intelligence-driven innovations in reproductive medicine: practices, advances, and prospects
2026,47(5):583-592 ,DOI: 10.16781/j.CN31-2187/R.20250667
Abstract:
Artificial intelligence (AI) has been increasingly applied in reproductive medicine, with achievements made in embryo/oocyte/sperm quality assessment, optimization of ovarian stimulation protocols, and laboratory workflow management. Multimodal data integration, deep learning algorithms, interpretable models, and automated systems have been shown to enhance diagnostic accuracy, improve individualized treatment strategies, and promote procedural standardization. The adoption of AI in reproductive medicine is expected to improve healthcare accessibility, promote equity, and advance precision fertility care, thereby providing a robust technological foundation for addressing population and health challenges.
-
Effect of alveolar macrophage-derived exosome microRNA-380 on airway mucus hypersecretion in chronic obstructive pulmonary disease and its mechanism
YUE Xueting, ZOU Xiangyang, CHEN Donghai, CHEN Qianqian, ZHANG Rong, DONG Yuchao, ZHANG Jingxi
2026,47(5):593-605 ,DOI: 10.16781/j.CN31-2187/R.20240840
Abstract:
Objective To investigate the effect of alveolar macrophage-derived exosome microRNA-380 (miR-380) on the biological function of airway epithelial cells in chronic obstructive pulmonary disease (COPD) and its related mechanism. Methods A rat model of COPD was established by intranasal instillation of lipopolysaccharide combined with cigarette smoke exposure. Alveolar macrophages from COPD rats were assigned to blank control group, miR-380 overexpression (miR-380 mimic) group, miR-380 underexpression (miR-380 inhibitor) group, or corresponding vector control groups. Exosomes from each group were extracted and identified, then co-cultured with airway epithelial cells from COPD rats. The expression levels of mucin 5AC (MUC5AC), mucin 5B (MUC5B), cystic fibrosis transmembrane conductance regulator (CFTR), caveolin-1 (CAV-1), phosphorylated p38 (p-p38), phosphorylated p65 (p-p65), phosphorylated JNK (p-JNK), phosphorylated JAK (p-JAK), and phosphorylated sterol regulatory element-binding protein (p-SREBP) were detected by Western blotting and/or immunofluorescence. The levels of interleukin (IL)-1β, IL-6 and tumor necrosis factor (TNF)-α were detected by enzyme-linked immunosorbent assay. Normal rats were injected with miR-380-overexpressing exosomes (miR-380-OE-EXO) via the tail vein, and COPD rats were injected with miR-380 antagonist (antagomiR-380) via the tail vein, with corresponding control groups set up simultaneously. Lung tissues were collected to detect the expression of MUC5AC, MUC5B, p-MAPK, p-NF-κB, p-JNK, p-JAK, and p-SREBP; and bronchoalveolar lavage fluid (BALF) was collected to detect the levels of IL-1β, IL-6, and TNF-α. Results Compared with the control group, the expression levels of MUC5AC and MUC5B in airway epithelial cells were significantly increased in the miR-380 mimic group, while the expression level of CFTR was significantly decreased. Additionally, the phosphorylation levels of p65, p38 and JNK and the expression levels of inflammatory cytokines IL-1β, IL-6 and TNF-α were significantly increased (all P<0.05). The levels of the above proteins and inflammatory factors in the miR-380 inhibitor group showed opposite trends to those in the miR-380 mimic group. In normal rats after miR-380-OE-EXO injection, the expression levels of MUC5AC and MUC5B in lung tissues were significantly increased, and the phosphorylation levels of p65, p38 and JNK in lung tissues and the levels of IL-1β, IL-6 and TNF-α in BALF were significantly increased (all P<0.05). In COPD rats after antagomiR-380 injection, the expression of MUC5AC and MUC5B in lung tissues was significantly decreased, and the phosphorylation levels of p65, p38 and JNK in lung tissues and the levels of IL-1β, IL-6 and TNF-α in BALF were also significantly decreased (all P<0.05). Conclusion Alveolar macrophages in COPD promote the hypersecretion of mucus in airway epithelial cells through paracrine exosomal miR-380. The underlying mechanism may be that miR-380 inhibits the CFTR function of epithelial cells, increases the phosphorylation levels of p65, p38 and JNK, and promotes the secretion of inflammatory mediators such as IL-1β, TNF-α, and IL-6.
-
Exogenous glucose reduces hypoxic injury of C8-D1A astrocytes by regulating metabolism
ZHANG Jiayi, JIANG Xiufang, FEI Xuechao, XIE Liyun, ZHAO Tong, ZHU Lingling
2026,47(5):606-615 ,DOI: 10.16781/j.CN31-2187/R.20250770
Abstract:
Objective To investigate the effects of hypoxia on energy metabolism and cell viability in astrocytes and to verify the potential protective effect of glucose supplementation. Methods Mouse cerebellar astrocytes, C8-D1A, were assigned to control group, hypoxia group, hypoxia plus glucose (10 mmol/L) group, or hypoxia plus high-dose glucose (15 mmol/L) group. Cell viability was detected by cell counting kit 8 (CCK-8) assay and adenosine triphosphate (ATP) measurement. Mitochondrial respiratory function and glycolysis level were determined using a Seahorse XF Cell Energy Analyzer. Quantitative polymerase chain reaction and Western blotting were performed to detect the expression levels of genes and proteins related to glucose metabolism, A1/A2 phenotype, and apoptosis. In addition, the levels of glucose, lactate, and brain-derived neurotrophic factor (BDNF) in the culture supernatant were measured, and reactive oxygen species (ROS) fluorescent probes were used to assess oxidative stress levels. Results The proliferation of C8-D1A cells was inhibited after 6 h of hypoxia, the mitochondrial apoptotic pathway was activated after 12 h, and the p-Akt/Akt signaling pathway was suppressed after 24 h. Under hypoxia, the cellular energy metabolism shifted from oxidative phosphorylation to glycolysis, accompanied by increased glucose uptake, elevated lactate production, and upregulation of key glycolytic enzyme genes. Supplementation with 10 and 15 mmol/L glucose enhanced glycolytic flux of the C8-D1A astrocytes, as evidenced by elevated expression of the glucose uptake gene (glucose transporter 1) and enhanced transcription of glycolysis-related enzyme genes (hexokinase, pyruvate kinase, pyruvate dehydrogenase kinase). Among them, 10 mmol/L glucose regulated apoptosis-related signaling pathways, inhibited the mitochondrial pathway of cell apoptosis, and alleviated oxidative stress. Meanwhile, glucose supplementation promoted the polarization of C8-D1A astrocytes toward the neuroprotective A2 phenotype, activated the cAMP-response element-binding protein-BDNF signaling pathway, and increased the secretion of BDNF. Conclusion Hypoxia induces functional disorders such as inhibited proliferation, increased apoptosis and metabolic reprogramming in C8-D1A astrocytes. Exogenous glucose supplementation can ameliorate these abnormalities. The neuroprotective effects of glucose are likely achieved through the concerted actions of metabolic support, apoptosis attenuation, and phenotypic remodeling.
-
Role of cardiomyocyte ferroptosis in pathogenesis of dilated cardiomyopathy
WANG Chuyi, ZHOU Jingwen, XU Xiangyang, ZHAO Quangong, GONG Dejun, WANG Guokun, HAN Lin*
2026,47(5):616-623 ,DOI: 10.16781/j.CN31-2187/R.20250070
Abstract:
Objective To investigate the expression changes and potential mechanisms of ferroptosis-related molecules in cardiomyocytes during the pathogenesis of dilated cardiomyopathy (DCM). Methods Left ventricular tissue samples from DCM patients (n=10) and non-DCM patients (control group, n=5) were obtained from the specimen bank of Department of Cardiovascular Surgery of The First Affiliated Hospital of Naval Medical University. DCM mouse models (n=15) were induced by intraperitoneal injection of doxorubicin (DOX) (8 mg/kg, once a week for 4 consecutive weeks), while the control mice (n=15) were injected with an equivalent volume of normal saline. The human cardiomyocyte cell line AC16 was stimulated with 2 μmol/L DOX and treated with 10 μmol/L ferrostatin-1 (Fer-1) to inhibit ferroptosis. Hematoxylin-eosin staining and Masson staining were used to observe the pathological morphological changes in myocardial tissue. The expression changes of ferroptosis-related markers including ferritin heavy chain 1 (FTH1), solute carrier family 7 member 11 (SLC7A11), and glutathione peroxidase 4 (GPX4) were detected by immunohistochemical staining and Western blotting. Echocardiography was used to evaluate left ventricular function in mice. Cardiomyocyte viability was assessed by cell counting kit-8 assay, and the levels of glutathione (GSH) and malondialdehyde (MDA) were measured using assay kits. Results Compared with the control group, the DCM patients showed disordered cell arrangement and significant collagen deposition in the left ventricular tissue, with significantly decreased expression levels of ferroptosis markers FTH1, SLC7A11, and GPX4. In addition, the DCM model mice exhibited a marked decrease in left ventricular ejection fraction and left ventricular fractional shortening (both P<0.05), a significant increase in left ventricular myocardial fibrosis, and significant downregulation of FTH1, SLC7A11, and GPX4 in myocardial tissue. In AC16 cells stimulated with DOX, the expression levels of FTH1, SLC7A11, and GPX4, as well as GSH level, were significantly reduced; MDA level was significantly increased; and cell viability was significantly decreased (all P<0.01). These changes were significantly reversed after treatment with Fer-1 (all P<0.05). Conclusion Ferroptosis in cardiomyocytes may play a regulatory role in the pathogenesis of DCM, and inhibiting ferroptosis could be a potential therapeutic strategy for DCM.
-
Creatine kinase M regulates the JNK/c-Jun-HK2 axis in the progression of cisplatin resistance in laryngeal carcinoma
WANG Jingjie, YAO Hui, ZHU Guanghao, LI Haopu, ZHU Minhui
2026,47(5):624-632 ,DOI: 10.16781/j.CN31-2187/R.20260016
Abstract:
Objective To explore the role and mechanism of creatine kinase M (CKM) in the cisplatin resistance of laryngeal cancer cells. Methods The Cancer Genome Atlas (TCGA) database was used to analyze the expression of CKM in head and neck squamous cell carcinoma and its relationship with patients’ prognosis. A total of 64 cases of laryngeal cancer tissue samples and paired adjacent normal mucosal tissues were collected, and the expression characteristics of CKM were verified by immunohistochemistry. A cisplatin-resistant laryngeal cancer cell line, TU686-R, was constructed, and CKM overexpression or knockdown was achieved by plasmid transfection. Cell counting kit 8 assay, colony formation assay, and Transwell assay were used to detect cell viability, proliferation, and migration ability, respectively. The Seahorse XFe24 metabolic analyzer and related kits were used to detect the levels of glycolysis-related parameters. Western blotting, chromatin immunoprecipitation (ChIP), and dual-luciferase reporter assay were used to verify the regulatory effect of CKM on the JNK/c-Jun-HK2 pathway. Results TCGA database analysis showed that the expression of CKM in head and neck squamous cell carcinoma tissues was significantly lower than that in normal mucosal tissues (P<0.05). Verification using clinical tissue samples showed that the 5-year overall survival rate of patients with low CKM expression (28.5%) was significantly lower than that of the high expression group (50.2%, P<0.001). The low expression rate of CKM in laryngeal cancer tissues (57.2%) was significantly higher than that in adjacent normal mucosal tissues (12.5%, P<0.01), and low CKM expression was correlated with advanced T stage and lymph node metastasis (all P<0.05). The expression of CKM in drug-resistant cells was significantly lower than that in parental cells; overexpression of CKM decreased the IC50 of cisplatin in drug-resistant cells and inhibited colony formation and migration of drug-resistant cells. Low CKM expression could mediate the activation of the JNK/c-Jun pathway, promote the binding of c-Jun to the HK2 promoter and upregulate HK2, thereby enhancing cellular glycolytic activity, and these changes could be reversed by inhibiting JNK or knocking down HK2. Conclusion Low expression of CKM can promote glycolytic compensation by activating the JNK/c-Jun-HK2 axis, and then accelerate cisplatin resistance in laryngeal cancer; CKM can be used as a potential marker for the prognosis evaluation of laryngeal cancer, and JNK and HK2 are expected to become drug-resistance intervention targets.
-
Association between visuospatial working memory and brain functional connectivity in university students with depressive symptoms
WANG Zixian, DING Feng, WEN Haiyan, LI Shufan, REN Yuxi, XU Bin
2026,47(5):633-643 ,DOI: 10.16781/j.CN31-2187/R.20250818
Abstract:
Objective To examine the relationship between depressive symptoms and visuospatial working memory (VSWM) in university students from the perspectives of behavioral performance and brain functional connectivity, to analyze the coordinated patterns of spontaneous brain neural activity, and to identify potential electroencephalogram (EEG)-based connectivity markers for early screening of depressive symptoms. Methods A case-control design was adopted. Sixty university students with depressive symptoms and 60 healthy controls from 7 universities in Songjiang University Town, Shanghai, were enrolled. Depressive symptoms were assessed using the Beck depression inventory-Ⅱ (BDI-Ⅱ). Five minutes of eyes-closed resting-state EEG were recorded, and VSWM was evaluated using a 2-back task. Brain functional connectivity was analyzed using graph-theoretical methods with BrainNet Viewer. Results Compared with healthy controls, students with depressive symptoms showed significantly prolonged reaction time in the 2-back task (P<0.001), with EEG differences mainly observed in the α2 and β1 bands across right parietal, occipital, right central, right temporal, and posterior temporal regions. Depressive symptom scores were positively correlated with VSWM reaction time (r=0.633, P<0.01). EEG and brain functional connectivity analyses revealed the following findings: in the α2 band, the depressive symptom group exhibited higher mean functional connectivity density (0.75) and strength (0.68) in parietal, occipital, and lateral temporal regions than healthy controls (mean density=0.43, mean strength=0.55); in the β1 band, students with better VSWM performance showed higher mean functional connectivity density (0.68) and strength (0.72) in the parietal, right central, and lateral temporal regions than those with poorer performance (mean density=0.61, mean strength=0.70). At a connectivity threshold of 0.9, connectivity differences were primarily localized in the O1-O2 (occipital) pathway in the α2 band and the P4-T6 (right parietal-right posterior temporal) pathway in the β1 band. Conclusion VSWM alterations associated with depressive symptoms in university students are mainly reflected in slowed information processing rather than reduced accuracy, accompanied by distinct resting-state EEG functional connectivity patterns. Specifically, the α2 band O1-O2 (occipital) pathway may represent a key marker of depressive symptom risk, while the β1 band P4-T6 (right parietal-right posterior temporal) pathway may indicate individual differences in VSWM capacity.
-
Treatment of insomnia associated with myasthenia gravis: recent progress
Lü Shiyi, ZHAO Xiangxiang, BI Xiaoying*
2026,47(5):644-650 ,DOI: 10.16781/j.CN31-2187/R.20250823
Abstract:
Insomnia is a common comorbidity in patients with myasthenia gravis (MG), which not only significantly impacts their quality of life but may also exacerbate the neuromuscular symptoms of MG. Notably, certain commonly prescribed medications for insomnia may trigger or worsen MG symptoms, posing a therapeutic dilemma. Thus, selecting safe and effective interventions for insomnia is crucial for MG management. This review synthesizes current strategies and research progress in treating MG-related insomnia, encompassing pharmacological therapy, psychotherapy, physical therapy, and traditional Chinese medicine therapy, to support clinical decision-making. Currently, clinical studies specifically addressing insomnia in MG remain scarce, highlighting the need for increased awareness among clinicians regarding neuropsychological symptoms throughout the course of MG.
-
Imaging of retroperitoneal sarcoma: research progress
ZHENG Anqi, WANG Qi, WANG Shi, ZHU Hai, SHAO Chengwei, HAO Qiang, ZHANG Qianwen
2026,47(5):651-657 ,DOI: 10.16781/j.CN31-2187/R.20250785
Abstract:
Retroperitoneal sarcoma (RPS) is a rare malignant tumor of mesenchymal origin arising from the retroperitoneal space, including the presacral and pelvic floor spaces. RPS is characterized by complex tissue origins, diverse pathological types, and highly variable biological behaviors, which pose significant challenges in clinical diagnosis and treatment and result in a generally poor prognosis. Imaging plays a crucial role in the management of RPS; however, the overlapping imaging features across different pathological subtypes make accurate differential diagnosis challenging. As a result, many patients still require image-guided core needle biopsy or surgical pathology for definitive diagnosis. In recent years, with rapid advancements in imaging technology and the growing application of artificial intelligence, researchers worldwide have made considerable progress in the non-invasive prediction of pathological subtypes and grading, as well as in assessing recurrence risk and predicting survival based on imaging characteristics. This review aims to provide a systematic overview of recent advances in imaging studies of RPS, focusing on diagnosis, differential diagnosis, treatment response evaluation, and prognosis assessment.
-
Treatment of intrahepatic cholangiocarcinoma: progress and challenges
WANG Huan, WANG Mengmeng, ZHANG Haijing, CHENG Yuqiang, CHENG Shuqun
2026,47(5):658-666 ,DOI: 10.16781/j.CN31-2187/R.20240131
Abstract:
Intrahepatic cholangiocarcinoma (ICC) is the second most common primary malignant liver tumor. It is asymptomatic and highly invasive, with non-specific early symptoms. Consequently, most patients are diagnosed at an advanced stage, thus missing the optimal window for surgical resection. For patients with unresectable advanced ICC, systemic chemotherapy remains the standard treatment, with various combination regimens available. Neoadjuvant chemotherapy may enable surgical resection in patients with advanced ICC. Additionally, local therapy, targeted therapy, immunotherapy, and nanotechnology applications offer diverse treatment options. The multidisciplinary diagnosis and treatment model enables accurate and effective personalized therapies for patients with advanced ICC.
-
Brief mindfulness-based interventions: current status and advances
ZHOU Xiaona, LIU Junlan, GUO Jiahui, JIANG Chunlei*
2026,47(5):667-674 ,DOI: 10.16781/j.CN31-2187/R.20230063
Abstract:
In recent years, mindfulness-based interventions (MBIs) have gradually entered the public sphere and drawn widespread attention. MBIs have been applied in various fields, such as alleviating mental disorders, assisting in the treatment of physical illnesses, improving emotional states, and regulating stress. Traditional mindfulness-based interventions have been proven to have broad effects and remarkable therapeutic efficacy. Brief mindfulness-based interventions (bMBIs) maintain the core mindfulness principles, while modifying therapeutic duration, innovating techniques, shortening training time, and simplifying implementation procedures. These modifications make bMBIs more feasible and adaptable for non-professionals, thereby greatly expanding their application scope and potential value. Consequently, exploring the effects of bMBIs is particularly important. This paper reviews the research findings and advances of bMBIs in recent years in areas such as stress and emotion regulation, cognitive function, and pain management, aiming to provide theoretical guidance for the implementation of bMBIs.
-
Current status of military health convalescence and countermeasures for quality and efficiency improvement
LI Wenyao, WANG Yonglin, CHU Xueyan, LI Junqiang*
2026,47(5):675-679 ,DOI: 10.16781/j.CN31-2187/R.20250235
Abstract:
With the transformation and function shift of military convalescent institutions, health convalescence is crucial for maintaining health and enhancing combat capability in officers and soldiers, and it urgently needs to adapt to new situations and challenges. This paper analyzes the current development of health convalescence in the military and identifies problems in differentiated services, health management, resource utilization, modernization upgrading, and quality evaluation systems; and proposes improvements in strengthening system establishment, improving the health care model, enhancing the connotation of convalescence, and promoting talent development, so as to provide a theoretical reference for improving military convalescent institutions, to better meet the health needs of officers and soldiers, and to serve the goal of enhancing combat capability.
-
Efficacy analysis of a small incision suture anchor assisted Krackow “double-parachute” suture technique for inferior pole fractures of the patella
YU Huiqi, CHEN Mengchen, ZHANG Hao, DING Chen
2026,47(5):680-684 ,DOI: 10.16781/j.CN31-2187/R.20260101
Abstract:
Objective To investigate the feasibility and clinical efficacy of the Krackow “double-parachute” suture technique using suture anchors via a small incision for the treatment of inferior pole fractures of the patella. Methods A retrospective analysis was conducted on 22 patients with fractures of the inferior pole of the patella treated with the Krackow “double-parachute” suture technique using suture anchors via a small incision in The First Affiliated Hospital of Naval Medical University between Jul. 2021 and Jul. 2024. A longitudinal midline incision approximately 4 cm in length was made centered on the fracture site. After exposing the fracture ends and evacuating the hematoma, two 3.5-mm-diameter suture anchors were inserted into the proximal fracture fragment. Fixation was achieved by applying the Krackow suture technique in conjunction with the anchor sutures, resulting in a construct resembling a “double-parachute” configuration. Perioperative data and follow-up outcomes were recorded, and functional outcomes were evaluated using the Böstman patellar fracture functional scoring system. Results All 22 patients underwent the procedure successfully. The mean operative time was (61.8±2.1) min, mean incision length was (3.8±0.5) cm, mean intraoperative blood loss was (50.2±5.2) mL, and mean hospital stay was (5.2±1.1) d. No adverse events such as incision infection, dehiscence, skin necrosis, or deep infection were observed during the postoperative monitoring period. All 22 patients were followed up for a mean duration of (14.5±2.5) months (range 12-17 months). During follow-up, no postoperative complications such as fracture redisplacement, nonunion, neurovascular injury, or implant-related adverse reactions occurred, except for 1 patient who developed deep vein thrombosis of the lower extremity. The mean time to fracture union was (11.3±0.7) weeks. At the final follow-up, the mean Böstman patellar fracture functional score was 28.4±2.3. According to the Böstman grading criteria, outcomes were excellent in 18 patients, good in 2, and fair in 2, yielding an excellent-to-good rate of 90.9% (20/22). Conclusion The Krackow “double-parachute” suture technique using suture anchors via a small incision is a minimally invasive, reliable fixation method for fractures of the inferior pole of the patella, characterized by reduced surgical trauma, low postoperative complication rates, and secure suture fixation. This technique warrants further clinical application and promotion.
-
A nomogram model based on age, neutrophil count, and baseline NIHSS score for predicting 90-d adverse outcomes in acute ischemic stroke
ZHOU Yang, ZHONG Ping, DING Guojuan, ZHOU Yu, LIU Xinyan
2026,47(5):685-691 ,DOI: 10.16781/j.CN31-2187/R.20240297
Abstract:
Objective To develop a nomogram model based on clinical data and laboratory parameters, and to investigate its clinical value in predicting 90-d adverse outcomes in patients with acute ischemic stroke (AIS). Methods A retrospective study was conducted on AIS patients hospitalized in Shaoxing People’s Hospital between Jan. 2020 and Dec. 2022. Eligible participants were randomly assigned to training set or validation set. Age, sex, smoking history, alcohol history, past medical history (hypertension, diabetes mellitus, coronary heart disease, and atrial fibrillation), baseline blood pressure, baseline National Institutes of Health stroke scale (NIHSS) score, Trial of Org 10172 in Acute Stroke Treatment (TOAST) classification, and 90-d adverse outcomes (modified Rankin scale score≥3) were collected and recorded. Laboratory parameters obtained within 24 h of admission, including routine blood tests, liver and renal function tests, blood lipids, and albumin, were collected. Multivariate logistic regression analysis was used to screen predictors of 90-d adverse outcomes, and a nomogram model was constructed. The discrimination ability of the nomogram was assessed using the area under the receiver operating characteristic (ROC) curve. Results A total of 867 patients were enrolled. Among them, 519 cases were randomly assigned to the training set, while 348 cases were allocated to the validation set. Ninety-day adverse outcomes occurred in 100 patients (19.27%) in the training set and 51 patients (14.66%) in the validation set, respectively. Multivariate logistic regression analysis revealed that age (odds ratio [OR]=1.03, 95% confidence interval [CI] 1.00-1.06, P=0.021), baseline NIHSS score (OR=1.35, 95%CI 1.25-1.47, P<0.001), and neutrophil count (OR=1.83, 95%CI 1.07-3.14, P=0.027) were independent risk factors for 90-d adverse outcomes in AIS patients. These key variables were used to construct the nomogram. The ROC analysis demonstrated an area under the curve of 0.839 (95%CI 0.789-0.889) in the training set and 0.880 (95%CI 0.817-0.944) in the validation set for the nomogram model. Conclusion The nomogram model constructed based on age, baseline NIHSS score, and neutrophil count can be used to predict 90-d advese outcomes in AIS.
-
Borderline serous tumor of the testis: a case report
GU Xiaoyu, XU Jingjing, ZHANG Shunmin, ZHU Yan*
2026,47(5):692-694 ,DOI: 10.16781/j.CN31-2187/R.20220839
Abstract:
人工智能+医学科研
Original article
Review
学术园地
Short article
Case report
-
Application of artificial intelligence in mental health management: toward early screening, assessment, and intervention
HE Jiali, BAI Yonghai, WANG Yihao, ZHANG Yanfei, SONG Yang, LU Li*
2026,47(3):300-308, DOI: 10.16781/j.CN31-2187/R.20250707
Abstract:
Mental health problems have become a major global public health challenge, and traditional mental health service systems face persistent obstacles in early screening, assessment, and intervention, including limited resources, poor accessibility, and insufficient precision. Leveraging machine learning, deep learning, natural language processing, and multimodal data fusion, artificial intelligence (AI) is breaking service barriers, alleviating workforce shortages, and reducing stigma, thus enabling a continuous, dynamic, and personalized closed-loop paradigm for mental health management. This review synthesizes recent advances in AI-driven early screening through audio-video analysis, social media text mining, and wearable monitoring; early assessment through multimodal integration and biomarker modeling; and early intervention through personalized recommendation systems, digital therapeutics, and virtual agent-based interventions. Focusing on critical risks such as data privacy and security, algorithmic bias, algorithmic fairness, and ethical responsibility, the present paper further discusses future directions including constructing collaborative networks and data-sharing, developing brain-computer interfaces and neural regulation, and promoting global collaborative governance.
-
Interpretation of the Diagnosis and treatment norms for colorectal cancer in China (2025 edition)
2026,47(3):295-299, DOI: 10.16781/j.CN31-2187/R.20250848
Abstract:
The Diagnosis and treatment norms for colorectal cancer in China (2025 edition) has been revised based on the latest evidence-based medicine, domestic and international research, and clinical practice outcomes. In this article, we aim to make an interpretation of its core contents, primarily focusing on the following 3 major directions. (1) Better precise surgical treatment: refining the indications for local resection of early-stage cancer; emphasizing the principle of sphincter preservation in rectal cancer and introducing robotic surgery. (2) Better optimized comprehensive treatment: emphasizing the importance of magnetic resonance imaging examination for rectal cancer and determining the treatment pathway based on the position relative to the peritoneal reflection and tumor risk; clarifying immunotherapy as the core strategy for patients with mismatch repair-deficient (dMMR)/high microsatellite instability (MSI-H); promoting total neoadjuvant therapy and the “watch-and-wait (W&W)” strategy; expanding treatment for liver metastases, such as the “liver-first” approach. (3) Comprehensive empowerment by new technologies: highlighting 7 cutting-edge technologies, including liquid biopsy (e.g., circulating tumor DNA), fluorescence laparoscopy, and fibroblast activation protein inhibitor imaging, to improve diagnosis, surgery, radiotherapy, and precision drug therapy. By strengthening multidisciplinary collaboration, optimizing clinical pathways, and incorporating more new advancements, the 2025 edition aims to enhance clinicians’ understanding of both standardized treatment and cutting-edge trends, promoting standardization, precision, and humanization in colorectal cancer diagnosis and treatment, thereby continuously improving therapeutic outcomes.
-
Artificial intelligence empowers precision rehabilitation for stroke: assessment, intervention, and remote management
HUANG Xiaonan, WANG Han, SHI Lei, SONG Jialiang, Lü Can, FANG Fanfu*
2026,47(2):160-175, DOI: 10.16781/j.CN31-2187/R.20250673
Abstract:
This paper reviews the key advances in the application of artificial intelligence (AI) for stroke rehabilitation, including quantitative assessment, personalized treatment prescription, and closed-loop training, and proposes pathways for clinical translation. Based on recent high-quality engineering and clinical evidence, we centered on assessment/diagnosis, therapeutic intervention, and remote management, integrating computer vision, brain-computer interfaces, exoskeletons, virtual/augmented reality, and edge-to-cloud platforms. We emphasized the alignment of "algorithm-engineering-clinical" evidence. On the assessment side, AI leverages multimodal sensing and imaging analytics to automate functional scale scoring and enhance prognostic precision. On the treatment side, AI empowers brain-computer interfaces and exoskeletons through intent decoding and adaptive control to deliver highly individualized closed-loop training that maximizes neuroplasticity. On the remote management side, AI-driven wearables combined with remote platforms enable continuous home-based monitoring and quality control. Despite challenges-including variable evidence quality, limited algorithmic generalization, and potential safety risks-AI shows substantial promise for deeper integration of rehabilitation care and management and for achieving individualized precision therapy.
-
“Preventive treatment of disease” and whole-course management: an interpretation of the Implementation Plan for the “Weight Management Years” Campaign
2026,47(2):155-159, DOI: 10.16781/j.CN31-2187/R.20250738
Abstract:
In response to the chronic disease prevention and control objectives of the Healthy China Initiative (2019-2030), China's National Health Commission and 15 other government bodies jointly launched the Implementation Plan for the "Weight Management Years" Campaign (hereinafter referred to as the Plan). This national initiative aims to establish a comprehensive system for preventing and managing abnormal body weight, thereby shifting the focus of chronic disease intervention towards earlier prevention. This article examines the context of the Plan's introduction, highlights its key policy innovations, and provides an in-depth discussion of critical challenges, including individual adherence and monitoring system development. The article proposes concrete implementation strategies for healthcare providers within clinical settings, focusing on preventive care, targeted public education, and integrated obesity management throughout the care continuum, which support the clinical translation of the Plan and weight management practices.
-
Expert consensus on the principles of severe injury treatment by emergency medical rescue teams in major nuclear accidents (2025 edition)
2026,47(2):147-154, DOI: 10.16781/j.CN31-2187/R.20250408
Abstract:
The treatment of severe injuries resulting from major nuclear accidents faces significant challenges due to the complex causes and severity of these injuries, the unique rescue environments, and a current lack of unified national standards. To make emergency medical rescue more scientific, standardized, and timely, this consensus focuses on the specific injury factors at nuclear accident sites and provides a standardized approach for managing life-threatening multiple and combined injuries. It introduces the guiding principles of "balancing radiation and injury" and "timely treatment", which guide clinical practice based on a damage-control concept. The former requires simultaneous decontamination and the dual achievement of treating trauma and controlling radiation hazards. The latter prioritizes rapidly stabilizing vital signs through emergency measures like hemostasis and respiratory/circulatory support, followed by staged damage control surgery for wounded personnel who require it. This expert consensus, developed through evidence-based medicine and extensive multidisciplinary expert discussion, systematically incorporates protective measures for special populations such as children and pregnant women, and for the first time identifies psychosocial trauma as a core pathological feature influencing physiological outcomes, mandating its assessment and intervention. The consensus aims to guide medical response during both the early and subsequent phases of a major nuclear accident and is applicable to hospitals, emergency teams, and institutions involved in formulating national standards.
-
Consensus on artificial intelligence-assisted ultrasound management for breast nodules
2026,47(1):19-27, DOI: 10.16781/j.CN31-2187/R.20250610
Abstract:
Cancer prevention and treatment have become a strategic priority for national development and public health. As breast cancer is one of the most common cancers in women, early diagnosis, timely treatment, and evidence-based management are essential. High-frequency ultrasonography is a critical tool for the screening and diagnosis of breast cancer. Artificial intelligence (AI)-assisted ultrasound has shown significant potential in differentiating benign and malignant breast nodules, predicting axillary lymph node metastasis, and evaluating response to neoadjuvant chemotherapy. The experts from the Artificial Intelligence and Remote Ultrasound Group of Ultrasound Medicine Branch of Shanghai Medical Association, the Special Committee on Artificial Intelligence and Remote Ultrasound of Ultrasound Medical Branch of Shanghai Association of Social Medical Institutions, and the Vasculature and Superficial Organ Group of Medical Ultrasound Branch of Chinese Medical Association formed a consensus group. After reviewing the latest domestic and internation literatures and clinical research data, the group reached some consensus on the clinical applications of AI in breast nodule management. This document provides evidence-based recommendations to standardize AI-assisted diagnosis and treatment and serves as a practical reference for clinicians nationwide.
-
Reshaping modern medicine: applications, challenges, and future prospects of artificial intelligence
PENG Ying, WU Yuhui, YU Guangjun
2026,47(1):9-18, DOI: 10.16781/j.CN31-2187/R.20250678
Abstract:
Artificial intelligence (AI) is systematically reshaping the modern medical landscape with unprecedented depth and breadth, transforming research and development paradigms, diagnostic and therapeutic workflows, and public health systems. This paper comprehensively summarizes the groundbreaking applications of AI in key areas, including genomics, drug development, medical imaging, clinical decision support, surgery, and public health. It elucidates how AI is propelling medicine towards greater precision, efficiency, and personalization by decoding complex biological data, accelerating target identification, enhancing diagnostic accuracy, and optimizing the allocation of medical resources. However, this advancement is confronted with multiple challenges, including data quality, model interpretability, algorithmic bias, clinical integration, and ethical regulation. Based on an analysis of these core issues, this article envisions a new blueprint for the future of medicine: supported by robust governance frameworks and profound interdisciplinary collaboration, AI will comprehensively empower the healthcare sector, ultimately fostering a health ecosystem that is more precise, efficient, equitable, and humane. Only through a balanced focus on technological innovation and ethical governance can the sustainable development of AI in medicine be ensured, thereby truly benefiting all of humanity.
-
Artificial intelligence-assisted endoscopy for early screening, diagnosis, and therapy of gastrointestinal tumors
2026,47(1):1-8, DOI: 10.16781/j.CN31-2187/R.20250887
Abstract:
In response to the severe challenge of high incidence but low early detection rate of gastrointestinal cancers in China and the limitations of traditional endoscopic screening, artificial intelligence (AI)-assisted endoscopy is emerging as a key solution for early screening, diagnosis, and treatment. Deep learning-based computer-aided detection and diagnosis systems have demonstrated significant potential to enhance clinical sensitivity, specificity, and operational efficiency in the early identification, pathological characterization, and guidance of precision endoscopic therapy for esophageal, gastric, and colorectal cancers. Although challenges remain in data standardization, algorithm interpretability, and regulatory compliance and ethical governance, the deep integration of AI and digestive endoscopy is transforming the diagnostic and therapeutic paradigm from “experience-dependent” to “data-driven”, and offers a core driving force for achieving comprehensive and precise prevention and control of gastrointestinal tumors.
-
Artificial intelligence-assisted CT diagnosis of lymph node metastasis: integrated models,multi-cancer applications,and interpretability challenges
XING Wanting, BIAN Yun, SHAO Chengwei*
2025,46(12):1525-1531, DOI: 10.16781/j.CN31-2187/R.20250456
Abstract:
Accurate diagnosis of lymph node metastasis is critical for cancer staging, treatment selection, and prognostic evaluation. Computed tomography(CT), as a conventional imaging modality, plays a significant role in diagnosing lymph node metastasis. However, it remains limited in the identification of nodes with short-axis diameter <1 cm and micrometastases. In recent years, artificial intelligence(AI) technology has advanced rapidly in the field of medical image analysis, offering novel technical pathways to improve the accuracy of CT-based diagnosis of lymph node metastasis. This article reviews the research progress in AI-assisted CT diagnosis of lymph node metastasis, with a focus on the technical characteristics, diagnostic performance, and clinical applications of radiomics, deep learning, and their integrated models across various cancer types. Future directions and existing challenges are also discussed.
-
Artificial intelligence in gynecological surgery: current situation,challenges and prospects
2025,46(12):1519-1524, DOI: 10.16781/j.CN31-2187/R.20250346
Abstract:
The rapid development of artificial intelligence(AI) provides new technical support for the precision and personalized of gynecological surgery. This paper systematically reviews the application of AI in the whole process of gynecological surgery, including preoperative planning and simulation based on image and clinical data, real-time intraoperative navigation and robot-assisted decision making, postoperative complication prediction and prognosis assessment, and virtual surgical training. Studies have shown that AI significantly improves surgical accuracy and patient safety, but still faces challenges such as data privacy, algorithm generalization, and insufficient clinical validation. In the future, it is necessary to promote the deep integration of AI, robotics and biosensing through multidisciplinary collaboration to further improve the intelligent development of gynecological surgery.
人工智能+医学科研
Guideline interpretation
人工智能+医学科研
Guideline interpretation
Norms and consensus
人工智能+医学科研
院士论坛
人工智能+医学科研
Youth forum
About
Supervised by:Naval Medical University (Second Military Medical University)
Sponsored by:Teaching and Research Support Center, Naval Medical University (Second Military Medical University)
Address:800 Xiangyin Road, Shanghai 200433, China
Zip Code:200433
Phone:021-25074344
Email:bxue@smmu.edu.cn
CN:31-2187/R
ISSN:2097-1338
