Clinical Research Directory

Development of a Multimodal AI System for GIST Management

Background: Gastrointestinal Stromal Tumors (GISTs) are the most common mesenchymal tumors of the gastrointestinal tract. Accurate pre-operative diagnosis, risk stratification, and genotyping are critical for determining the appropriate surgical approach and targeted therapy (such as Imatinib). However, current methods often rely on invasive postoperative pathology and expensive genetic testing. Study Objective: The purpose of this study is to develop and validate a multimodal Artificial Intelligence (AI) model that integrates clinical data, CT radiomics (imaging features), and pathomics (digital pathology features) to improve the precision of GIST management. Study Design: This is a prospective, observational study. The researchers will recruit patients with suspected gastric submucosal tumors who are scheduled for surgery or biopsy at The Fourth Hospital of Hebei Medical University. Core Tasks: The AI model will be trained to perform three specific tasks: Diagnosis: Distinguish GISTs from other non-GIST mesenchymal tumors (e.g., leiomyomas, schwannomas). Risk Assessment: Stratify GISTs into risk categories (e.g., Low vs. High risk) to predict malignant potential. Genotyping: Predict specific gene mutations (e.g., KIT or PDGFRA mutations) to guide immunotherapy or targeted therapy. Methodology: Patient data (CT scans, pathology slides, and clinical history) will be collected and analyzed by the AI system. The AI's predictions will be compared against the "Gold Standard" results derived from postoperative pathological examination and Next-Generation Sequencing (NGS). This study is non-interventional; the AI results will not affect the standard of care received by the patients.

Motor Cortex Stimulation for Post-Stroke Thalamic Pain

The goal of this clinical trial is to investigate the mechanisms and predictive factors of motor cortex stimulation (MCS) for treating post-stroke thalamic pain, a challenging central neuropathic pain condition. Approximately 25% of patients show no short-term response to MCS, and about 20% experience long-term efficacy decay, yet the underlying analgesic mechanisms remain unclear and objective predictive biomarkers are lacking. This study aims to answer the following main questions: How does MCS modulate thalamic pain through the coordinated interaction of structural connectivity, functional network dynamics, and metabolic balance in the brain? What are the distinct neuroimaging characteristics that differentiate short-term non-responders, long-term responders, and those with long-term efficacy decay? Which multimodal imaging biomarkers can reliably predict short-term and long-term MCS efficacy? Participants will undergo a two-stage MCS surgical procedure. In stage I, epidural electrodes are implanted over the motor cortex, followed by a 2-week external trial stimulation. Participants who achieve a ≥50% reduction in Visual Analog Scale (VAS) pain score will proceed to stage II, receiving an implanted pulse generator for long-term stimulation. Those who do not respond in the short term will have the electrodes removed without undergoing stage II implantation. All participants will complete baseline clinical assessments and multimodal MRI scans (including T1, DTI, resting-state fMRI, and MRS) before surgery. Participants who receive the permanent implant will undergo follow-up clinical evaluations and repeat MRI scans at 3 and 6 months post-surgery. Researchers will compare imaging features across three outcome groups-short-term non-responders, long-term responders, and long-term decay group-to identify predictive biomarkers. Multimodal imaging data will be integrated using LASSO regression to build prediction models for both short-term screening and long-term efficacy warning. This research is expected to establish a "mechanism exploration - efficacy prediction - clinical decision" paradigm, providing objective imaging-based evidence to guide patient selection and postoperative management for MCS treatment.