This multicenter clinical trial evaluates an artificial intelligence (AI) system designed to assist in the diagnosis and management of pancreatic diseases. Using contrast-enhanced CT scans, the study compares the AI's recommendations against the decisions of experienced clinicians to verify the system's accuracy and safety in a real-world setting. Patients are categorized into three management groups: Intervention (surgery/treatment), Intensive Surveillance (close monitoring), or Routine Surveillance (standard follow-up). The primary goal is to determine if the AI system can reliably classify patients, reduce the risk of missing malignant lesions, and prevent unnecessary surgeries, thereby improving clinical decision-making for pancreatic conditions.
Clinically suspected pancreatic disease.
Scheduled to undergo contrast-enhanced CT.
Signed informed consent form indicating agreement to participate.
History of pancreatic surgery.
Contraindications to contrast-enhanced CT, including known hypersensitivity to iodinated contrast media or severe renal/hepatic dysfunction.
Suboptimal image quality affecting diagnosis.
Concurrent participation in another interventional clinical trial.
The study enrolls patients with clinically suspected pancreatic disease who have available contrast-enhanced CT scans and provide informed consent. Patients are excluded if they have a history of pancreatic surgery, contraindications to contrast media, suboptimal image quality, or other conditions deemed unsuitable by the investigator (e.g., pregnancy, cognitive impairment, or concurrent trial participation).
Cohort
Prospective
Diagnosis by Artificial Intelligence model
Diagnostic testTo develop an artificial intelligence-based classification management system for pancreatic diseases, achieving automated and precise classification. Contrast-enhanced CT images from all study subjects will be analyzed by the AI system to generate classification results, categorizing patients into three groups: INTERVENTIOM, INTENSIVE SURVEILLANCE or ROUTINE SURVEILLANCE.
Classification accuracy
The percentage of cases correctly classified by AI out of the total number of cases.
Agreement rate with clinical decisions
The proportion of total cases where AI and clinician classification results are in agreement.
Percentage decrease in unnecessary surgical procedures
The percentage reduction in the unnecessary surgery rate achieved by AI decision-making compared to traditional decision-making.
Malignancy miss rate
The proportion of cases classified by AI as non-surgical that actually required surgery.
Click on the lead sponsor to view all of their trials.
Changhai Hospital
Lead sponsor
The First Affiliated Hospital with Nanjing Medical University
Collaborator
The Affiliated People's Hospital of Ningbo University
Collaborator
The Second Affiliated Hospital of Jiaxing University
Collaborator
Shanghai Changzheng Hospital
Collaborator
Xinhua Hospital, Shanghai Jiao Tong University School of Medicine
Collaborator
Shengjing Hospital
Collaborator
Shanghai Fourth People's Hospital Tongji University
Collaborator
The First Affiliated Hospital of Medical School of Zhejiang University
Collaborator
Shanghai Fudan University Cancer Center
Collaborator
