Clinical trials

This prospective, single-center, randomized controlled trial aims to evaluate the clinical effectiveness of an Image-Guided Platform assisted by a deep learning model for sentinel lymph node (SLN) retrieval in patients with early gastric cancer undergoing laparoscopic-endoscopic cooperative surgery combined with sentinel lymph node navigation surgery (LECS-SNNS). A total of 36 eligible participants will be randomly assigned in a 1:1 ratio to either the Image-Guided Platform group or the Traditional Palpation group. Both groups will undergo standardized indocyanine green fluorescence-guided sentinel lymphatic basin dissection and initial retrieval of fluorescent sentinel lymph nodes. In the experimental group, the remaining sentinel lymphatic basin (SLB) tissue will be examined using the Image-Guided Platform, which integrates radiographic and optical imaging with a deep learning model to identify and localize suspected lymph nodes. In the control group, LN retrieval will be performed using traditional visual inspection and palpation. The primary objective is to determine whether Image-Guided Platform-assisted LN retrieval increases the total number of SLNs retrieved intraoperatively compared with Traditional Palpation. Secondary objectives include assessment of LN retrieval efficiency, pathological findings, additional LN identification during permanent pathological examination, concordance between intraoperative frozen-section and permanent pathological examination, and other procedural, pathological, technical, and clinical outcomes relevant to the feasibility and performance of the Image-Guided Platform and deep learning model.

This prospective randomized controlled trial will evaluate whether DeepMedFake improves the identification of medical images that require further verification. DeepMedFake is an artificial intelligence-based medical image analysis system that provides an image-authenticity risk assessment, a patient-image consistency risk assessment and a recommendation regarding further verification. Hospital physicians and healthcare audit professionals will participate in a randomized two-period crossover design. Each participant will assess one case set with DeepMedFake assistance and the other without AI assistance. The primary outcome in each cohort is the sensitivity of the final verification decision, evaluated separately in the hospital clinical and healthcare audit cohorts.

It is an observational study of non alcoholic fatty liver disease (NAFLD) patients with a calculated sample size of 500. Liver biopsy proved NAFLD patients will be recruited in this study for 10 years follow-up. Patients will be assessed at baseline, at every six months for blood count, liver function test, fasting blood-glucose, fasting insulin, ferritin, liver ultrasonography, and liver stiffness.

The goal of this observational study is to leverage the abundant patient resources and standardized medical records from Beijing Friendship Hospital, Xuanwu Hospital, and Beijing Anzhen Hospital, combined with the existing data and knowledge platform of guidelines, consensus, medical literature, and dialogue data from Beijing Haitian Ruisheng Science Technology Co.,Ltd, with Beijing Zhilan Medical Technology Co., Ltd. conducting the fine-tuning, optimization, and validation of the medical large language model. The model is fine-tuned according to the consultation and diagnostic needs of different departments to improve the quality and efficiency of hospital medical services, enhance intelligence, and elevate the level of medical care. Through deployment to hospitals at all levels, it aims to achieve standardized services and support graded diagnosis and treatment. The overall research includes medical big data construction, medical knowledge graph construction, medical large model training and fine-tuning, and large model application platform development and deployment.

The investigators propose to construct and validate an early HCC risk prediction model in a multicenter retrospective cohort of hepatitis B-related fibrosis/cirrhosis patients, using multimodal data encompassing longitudinal clinical data, serum glycomics profiles, and liver biopsy histopathological images.

The main treatment for early gastric cancer (EGC) include endoscopic submucosal dissection (ESD) and radical gastrectomy. However, appropriate treatment for patients who exceed the absolute indications and noncurative resection of ESD remains unestablished. Sentinel node navigation surgery (SNNS) enables limited lymph node resection, thereby facilitating function-preserving gastrectomy (FPG) and improving quality of life (QoL). SNNS seems to be the promising solution according to previous study, however evidence-based medicine was lacking. It is imperative to establish its safety and efficacy in patients with EGC. However, the optimal implementation of FPG remain unclear. Moreover, objective assessment of postoperative functional outcomes,remains limited.

This is an observational study (multicenter retrospective real-world cohort study). The purpose of this study is to assess the predictive performance of liver stiffness measurement (LSM, including baseline LSM1, current LSMC and their dynamic changes) acquired by domestic iLivTouch device for liver-related events (LREs) and all-cause mortality among MAFLD patients with compensated advanced chronic liver disease (cACLD), and to explore the prognostic value of dynamic LSM changes. The study population consists of adult patients aged ≥18 years of either sex, clinically diagnosed with MAFLD-related cACLD (defined as baseline LSM1 ≥10 kPa per Baveno-VII consensus), with at least two LSM measurements separated by ≥12-month follow-up interval, and without other confounding chronic liver diseases, excessive alcohol intake or predefined exclusion comorbidities. This study aims to answer several major questions: whether dynamic LSM parameters measured by iLivTouch can predict LREs and all-cause mortality in MAFLD-cACLD patients; whether risk of LREs differs between patients with significant LSMC decline and those without such decline in the resolved cACLD subgroup; whether liver-related mortality differs between resolved and persistent cACLD patients; and whether pharmacological interventions influence LRE risk and cACLD resolution.

This retrospective, observational cohort study aimed to establish a comprehensive research cohort utilizing a large-scale prospective clinical registry. The primary objectives were to characterize the real-world demographic profiles, clinical features, psychological characteristics, and treatment patterns of Chinese patients with gastroesophageal reflux disease (GERD), as well as to evaluate post-treatment improvements in both GERD symptoms and psychological well-being. The study retrospectively enrolled approximately 5,000 patients with a confirmed diagnosis of GERD, with data derived from the prospective registry of the National Clinical Research Center for Digestive Diseases. Investigators systematically extracted data on baseline demographics, clinical presentations, objective diagnostic findings, preoperative psychological status, surgical complications, and longitudinal follow-up outcomes for all eligible patients. Ultimately, this study sought to provide high-quality, China-specific evidence to inform the precise phenotyping of GERD and to guide standardized, individualized clinical decision-making.

Esophageal variceal bleeding is one of the serious and life-threatening complications of chronic liver disease (CLD). Studies have shown that the prevalence of esophageal varices (EV) in patients with liver cirrhosis is about 50%-60%. The annual incidence of variceal bleeding in these patients is about 5%-15%, and the rebleeding rate can reach 30%-40% within 6 weeks after the first bleeding. The 6-week mortality related to variceal bleeding is as high as 10%-20%, which seriously threatens the life safety of patients with liver disease. Clinically, esophagogastroduodenoscopy (EGD) is the gold standard for the diagnosis and grading of esophageal varices. However, EGD is an invasive examination, which has certain application limitations such as related complications and high cost, which limits the promotion and application of this technology. Therefore, there is an urgent need for an accurate, convenient and non-invasive method for esophageal varices. To address this clinical pain point, Baveno VII guidelines state that spleen stiffness measurement (SSM) based on vibration-controlled transient elastography (TE) can be used as a noninvasive marker to predict esophageal varices (EV). Several studies have shown that SSM measured by TE has good diagnostic performance in relation to the occurrence and severity of esophageal varices. A study involving 191 patients with liver disease showed that spleen stiffness was significantly higher in patients with varices than in those without varices (63.69 vs 47.78 kPa, P\<0.0001), and the AUC of SSM for the diagnosis of EV was 0.74. In another study involving 260 patients with chronic liver disease, the AUC of SSM was 0.728 (95% CI: 0.665-0.791) for EV and 0.780 (95% CI: 0.714-0.846) for high-risk varix (HRV). The above results indicate that SSM has good clinical value in the prediction of EV. Pro9000X, a liver function shear wave quantization detector based on vibration control TE, has been developed by Wuxi Hisiel Medical Technology Co., LTD. The device integrates ultrasound image positioning and TE function, aiming to achieve rapid, quantitative and non-invasive detection of liver stiffness measurement (LSM) and SSM. The results of EGD examination were used as the gold standard to evaluate the diagnostic performance of the spleen stiffness value detected by Pro9000X in patients with chronic liver disease, and the main evaluation indicators were the sensitivity and specificity of EV diagnosis. Secondary evaluation included AUROC, optimal cut-off value and diagnostic value of high-risk EV.

To analyze and compare the effect of OFA scheme and traditional balanced anesthesia scheme on QoR15 after thyroidectomy, and further clarify the safety and rationality of OFA scheme in perioperative application of thyroid surgery.

The goal of this retrospective observational cohort study is to describe the real-world clinicopathological characteristics, evolving treatment patterns, and long-term oncological outcomes of early gastric cancer (EGC) patients in China, utilizing a large prospective clinical database. The main questions it aims to answer are: How do different treatment modalities, including endoscopic resection, laparoscopic surgery, open surgery, and combined laparoscopic-endoscopic approaches, influence the long-term survival (Overall Survival and Disease-Free Survival) and recurrence patterns in Chinese EGC patients? What are the key clinicopathological factors affecting prognosis in this population? This study will retrospectively enroll approximately 5000 patients with histopathologically confirmed gastric adenocarcinoma staged as early gastric cancer (per AJCC 8th edition) from the information database of the National Clinical Research Center for Digestive Diseases. Researchers will systematically collect baseline demographics, treatment details, surgical complications, pathological staging, and longitudinal follow-up data (up to 10 years post-surgery) for all eligible patients. By comparing the short-term safety profiles and long-term survival benefits across different treatment groups and identifying risk factors for recurrence, this study aims to provide high-quality, China-specific evidence to guide standardized and individualized clinical decision-making for early gastric cancer.

Invasive mold diseases (IMD) carry extremely high mortality rates in liver transplant recipients (aspergillosis prevalence \~1.8%, mortality 60%-90%; mucormycosis prevalence \~2%, mortality 38%-95%). Guidelines emphasize early antifungal therapy: liposomal amphotericin B (L-AmB) is the first-line choice in liver insufficiency; voriconazole remains the gold standard for aspergillosis (but ineffective against mucormycosis), yet its use is limited by significant drug-drug interactions-requiring a 50%-60% dose reduction of calcineurin inhibitors and contraindicated with sirolimus-thereby increasing the risk of graft rejection. Currently, no head-to-head clinical trials compare voriconazole and L-AmB in liver transplant recipients with IMD. Therefore, a prospective real-world study is planned to generate robust data to support updates to international or Chinese guidelines.

This is a multi-center, prospective, non-interventional real-world study. In a real-world environment, in line with the current status of the domestic diagnosis and treatment process, and on the premise of not increasing the burden of patients and medical resources, we explore the best indicators for predicting the outcome of patients with Clinical Research Coordinator (CRC) after surgery. The inclusion criteria for patients are perioperative patients with CRC. Real-world data analysis were conducted to determine whether immunization interventions versus non-interventions were able to improve patients' clinical outcomes (OS, PFS).

The goal of this clinical trial is to investigate the effects of a perioperative multimodal rehabilitation program on the incidence of postoperative complications and perioperative clinical indexes including functional capacity, nutritional and psychological status in patients with gastric cancer undergoing neoadjuvant therapy. Besides the investigators also develop a smart phone based digital platform aiming to evaluate its effectiveness in improving patient adherence, compared with the conventional telephone supervision approach. The main questions it aims to answer are: * Can the perioperative multimodal rehabilitation program reduce postoperative complications in patients with gastric cancer undergoing neoadjuvant therapy? * Can the smart phone based digital platform improve patients' adherence compared to traditional telephone supervision? * Can the perioperative multimodal rehabilitation program improve the perioperative clinical indicators of patients with gastric cancer undergoing neoadjuvant therapy, including functional capacity, nutritional status and psychological condition? The investigators will compare the perioperative multimodal rehabilitation program with the standard treatment alone to determine whether this program has the effects mentioned above. Participants will follow the perioperative multimodal rehabilitation program from neoadjuvant therapy through to four weeks after discharge.

This is a prospective, multicenter, randomized controlled trial aimed at comparing different radiotherapy fractionation regimens combined with sequential dual immunotherapy versus traditional chemoradiotherapy in neoadjuvant treatment for locally advanced rectal cancer (LARC). A total of 342 pMMR/MSS LARC patients will be enrolled and randomly assigned in a 1:1:1 ratio to short-course radiotherapy (5×5Gy) followed by sequential dual immunotherapy (paromlimab + tuvonralimab + CAPEOX), long-course radiotherapy followed by sequential dual immunotherapy, or conventional long-course chemoradiotherapy. The primary endpoint is the complete response rate (pCR + cCR). Secondary endpoints include the proportion of patients adopting the "watch-and-wait" strategy, disease-free survival, overall survival, and safety. This study innovatively explores the synergistic mechanism of different radiotherapy fractionations with dual immunotherapy, optimizes the timing of immunotherapy initiation, and constructs a clinical-imaging-pathology multimodal efficacy prediction model, aiming to advance LARC treatment from empirical to precision therapy while achieving organ and function preservation.

This study aims to address the lack of intelligent governance tools in clinical data management to promote efficient governance and secure sharing of real-world health data. To achieve this, a self-adaptive, automated governance intelligent agent will be developed based on a High-Order Programming (HOP) architecture, integrating Large Language Models (LLMs) and deep learning techniques. The agent will continuously monitor and correct data quality issues in real time, improving data accuracy and usability. In parallel, the project will establish a trusted data-sharing framework by integrating AI Confidential Computing (AICC) with Trusted Data Matrix (TDM) technologies. This framework will enable secure, real-time cross-institutional data exchange and collaborative computation while protecting sensitive information. Overall, the study aims to transform fragmented clinical data into high-quality, standardized, and securely accessible resources, thereby facilitating the circulation of data value and advancing collaborative medical research.

The goal of this clinical trial is to verify the safety and efficacy of the pedicle "Nine-grid Zoning Method" in assisting percutaneous vertebroplasty (PVP) for the treatment of lumbar osteoporotic vertebral compression fractures (OVCF) in adults. It also aims to standardize the puncture path of PVP and optimize the intraoperative operation process. The main questions it aims to answer are: * Does the "Nine-grid Zoning Method" significantly increase the rate of achieving ideal intraoperative puncture endpoints and reduce operative time compared with the traditional pedicle puncture method? * Does the novel puncture method reduce intraoperative fluoroscopy times, radiation exposure, and the incidence of postoperative bone cement leakage without increasing surgical risks? Researchers will compare the modified PVP assisted by the "Nine-grid Zoning Method" (experimental group) with conventional PVP adopting the traditional "10 o'clock/2 o'clock" pedicle puncture point (control group) to confirm the clinical superiority and safety of the new standardized puncture path. Participants will: * Receive unilateral transpedicular PVP surgery via either the nine-grid zoning puncture path or the traditional puncture path for single-segment acute lumbar OVCF * Complete preoperative baseline examinations including bone density detection, VAS pain score, ODI functional score and SF-36 quality of life score assessment * Receive standardized intraoperative data recording covering operative time, fluoroscopy frequency, radiation dose, bone cement filling and leakage conditions * Undergo postoperative follow-up at 1 day after surgery, discharge, 3 months, 6 months and 1 year after operation, with regular imaging re-examination and scale evaluation to monitor fracture recovery and postoperative complications

This project focuses on developing a risk prediction model for the recurrence and malignant transformation of colorectal adenomas by integrating multimodal features from both Traditional Chinese Medicine (TCM) and Western medicine. Led by Dr. Wei Hongtao from Beijing Friendship Hospital, Capital Medical University, the primary objective is to mine clinical characteristics from both medical systems to construct a robust predictive model. The research encompasses several key aspects: a multicenter, large-sample cohort study design with a clearly defined sample size and calculation basis; patient recruitment from multiple institutions nationwide to form training and validation sets; and strict adherence to standardized TCM and Western diagnostic criteria. Through comprehensive observation of demographic, TCM clinical (e.g., syndromes, tongue and pulse diagnosis), and Western clinical features, the study ensures data accuracy via rigorous monitoring and follow-up. Various algorithms are employed to extract and analyze these multi-source features-including endoscopic data-to build and evaluate the prediction model. Furthermore, the study aims to identify dominant subgroups to optimize TCM intervention strategies. Key performance indicators include establishing the risk model, identifying target populations, publishing high-quality papers, and training graduate students. By innovatively constructing this multimodal fusion model, the project provides a novel perspective and evidence-based foundation for the prevention and treatment of colorectal adenomas using TCM.

This study aims to utilise a real-world data platform to integrate multi-omics data-including radiomics, gut microbiota, pathological quality control and liquid biopsy-to construct a multidimensional predictive model for the efficacy of rectal cancer treatment following neoadjuvant therapy. By integrating multimodal data, the study aims to accurately assess the efficacy of neoadjuvant therapy and identify patients suitable for a 'watch-and-wait' strategy, thereby achieving tumour control and preserving organ function without the need for surgery. Furthermore, it seeks to provide scientific evidence for the efficacy of the 'watch-and-wait' strategy and the selection of optimal timing for surgery, whilst validating the model's effectiveness and assessing its clinical feasibility through prospective clinical trials.

This is a prospective, single-center, single-arm, open phase II clinical study. Forty-nine participants with pathologically or cytologically confirmed gastric cancer or gastroesophageal junction cancer are scheduled to be enrolled in this study. All participants will be treated with 2 to 8 cycles of adebrelimab, apatinib, oxaliplatin, and tigio before surgery. Participants will evaluate the treatment effect after every 2 cycles of medication. By the investigator assessment as an operable subject, apatinib was discontinued for one cycle. The adjuvant treatment will be determined by the investigators based on the participants' postoperative pathology results. Participants requiring adjuvant therapy, with a postoperative interval of at least 4 weeks, but not more than 10 weeks. When the resection standard isn't met for 8 cycles of treatment, the treatment is switched to a maintenance phase, which the subject treatment regimen is determined by the investigator. During the treatment period, participants will receive the study drugs on Day 1 of each 21-day cycle until evidence of disease progression or unacceptable toxicity.

This study is a single-center, prospective, observational clinical trial enrolling patients with locally advanced rectal cancer (cT3-4aN0M0 and cT1-4aN1-2M0). By collecting tissue and blood samples at multiple timepoints, and integrating multi-omics data including ctDNA mutations, copy number variations, and mtDNA profiles, a multi-omics model will be constructed to predict the efficacy of neoadjuvant therapy for rectal cancer.

The goal of this clinical trial is to evaluate the safety and tolerability of a novel bioartificial liver (CiPS-BAL) in patients with liver failure or small-for-size syndrome. The study will also collect preliminary data on clinical outcomes and laboratory parameters during treatment. The main questions it aims to answer are: Is the novel bioartificial liver system safe and well tolerated in patients with liver failure or small-for-size syndrome? What effects does the treatment have on liver function and other clinical and laboratory indicators? Researchers will treat participants with the CiPS-BAL system, which uses hepatocytes derived from chemically induced pluripotent stem cells (CiPS) within a bioartificial liver device.

This project integrates multimodal eye data (CFP, OCT, OCTA) from 50,000 cases, brain MR data from 150,000 cases, and ICD diagnoses, medical orders, and test results from an eye-brain paired cohort of 8,000 cases to construct an eye-brain cross-modal mapping model and an eye-brain-systemic disease association model. It aims to clarify the quantitative associations between multimodal ocular features and brain structural and vascular characteristics as well as systemic disease ICD diagnoses, thereby uncovering the cross-organ and cross-modal linkage mechanisms between the eye and brain. Ultimately, it seeks to achieve mapping and prediction of brain imaging features based on ocular data, enable ocular-based diagnosis and prediction of various diseases, and contribute significantly to early disease screening, risk stratification, and optimization of clinical diagnosis and treatment.

The goal of this \[study type: clinical trial\] is to \[primary purpose: evaluate the efficacy and safety of a novel calcium channel modulator in treating Restless Legs Syndrome (RLS) and its variant subtypes\] in \[describe participant population/primary condition: adult patients aged 18-75 years with confirmed RLS or its variant subtypes, who meet the study's eligibility criteria\]. The main question\[s\] it aims to answer \[is/are\]: * Does the novel calcium channel modulator improve RLS-related symptoms (assessed by the International Restless Legs Syndrome Study Group Rating Scale, IRLS) after the treatment period? * What is the safety profile (incidence of adverse events) of this calcium channel modulator in RLS patients? Participants will \[describe the main tasks participants will be asked to do, interventions they'll be given\]: * Receive oral administration of the novel calcium channel modulator (40mg twice daily) for 12 consecutive weeks * Complete scheduled follow-up visits for symptom assessments, safety monitoring, and questionnaire completion

Background: Chronic hepatitis B (CHB)-related cirrhosis is a common cause of portal hypertension, which leads to the development of gastroesophageal varices (EGVs). High-risk varices (HRV) are associated with a higher risk of bleeding and require timely interventions. Endoscopy is the gold standard for diagnosing HRV but is invasive and not suitable for routine screening in large populations. Objective: This study aims to develop a noninvasive model based on hepatic and splenic microcirculatory perfusion parameters derived from intravoxel incoherent motion (IVIM) magnetic resonance imaging (MRI) to predict and rule out HRV in patients with compensated CHB-related cirrhosis receiving antiviral therapy. Methods: This observational, retrospective study will include patients with compensated CHB-related cirrhosis who have undergone both esophagogastroduodenoscopy (EGD) and IVIM MRI. Microcirculatory perfusion parameters will be extracted from IVIM images using a biexponential model, and their ability to predict HRV will be assessed. Outcomes: The study will validate the performance of the Hepato-Splenic Microcirculatory Perfusion Model (HSMP) in ruling out HRV compared to conventional noninvasive tests like APRI, FIB-4, and LSM. The model's diagnostic accuracy will be evaluated with a focus on reducing unnecessary endoscopic procedures. Significance: If successful, this model could reduce the need for invasive endoscopy and improve the management of cirrhosis patients by providing a safer and more accessible screening tool for HRV.