Acute Pancreatitis (AP), Chronic Pancreatitis, Diagnose Disease, IPMN, Pancreatic, Pancreatic Cancer, Pancreatic Cystic Lesions, Pancreatic Neuroendocrine Tumor
Conditions
Keywords
Artificial Intelligence (AI), Deep Learning, Contrast-Enhanced CT, Multicenter Clinical Trial, Real-World Study
Brief summary
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.
Detailed description
MEHTOD： This multicenter clinical trial evaluates the reliability and effectiveness of an AI system for patients with pancreatic diseases in a real-world clinical environment. The study calculates the AI system's classification accuracy using pathological diagnosis (biopsy/surgery results) or long-term follow-up as the "gold standard" for comparison. Additionally, the safety and clinical utility of the management strategies recommended by the AI are assessed by measuring the risk of missing malignant lesions, the rate of unnecessary surgeries for pancreatic diseases, and the level of agreement with traditional clinical decisions. STUDY DESIGN All contrast-enhanced CT images from patients with pancreatic diseases are analyzed by the AI system to generate a classification result (Intervention, Intensive Surveillance, or Routine Surveillance). Simultaneously, clinical doctors review the same data and categorize patients into these three groups to determine their actual care plan: 1. INTERVENTION: Patients assessed by doctors as needing "Intervention" are recommended for further surgical evaluation or treatment. 2. INTENSIVE SURVEILLANCE: Patients assessed by doctors as needing "Intensive Surveillance" receive a personalized, high-frequency follow-up plan until the study endpoint. 3. ROUTINE SURVEILLANCE: Patients assessed by doctors as needing "Routine Surveillance" undergo follow-up for at least one year. If abnormalities arise during this period, the patient is transferred to the appropriate "Intervention" or "Intensive Surveillance" protocol. OUTCOMES： The study compares the performance of the AI system against clinical doctors regarding classification accuracy, the risk of missed diagnoses, unnecessary surgery rates, and decision consistency. These metrics are used to validate the AI system's value, safety, and utility in the clinical management of pancreatic diseases.
Interventions
DIAGNOSTIC_TESTDiagnosis by Artificial Intelligence model
To 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.
Sponsors
Changhai Hospital
The First Affiliated Hospital with Nanjing Medical University
The Affiliated People's Hospital of Ningbo University
The Second Affiliated Hospital of Jiaxing University
Shanghai Changzheng Hospital
Xinhua Hospital, Shanghai Jiao Tong University School of Medicine
Shengjing Hospital
Shanghai Fourth People's Hospital Tongji University
The First Affiliated Hospital of Medical School of Zhejiang University
Shanghai Fudan University Cancer Center
Study design
Observational model
COHORT
Time perspective
PROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to 80 Years
Healthy volunteers
No
Inclusion criteria
* Clinically suspected pancreatic disease. * Scheduled to undergo contrast-enhanced CT. * Signed informed consent form indicating agreement to participate.
Exclusion criteria
* 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. * Unsuitability for participation as determined by the investigator, including but not limited to: pregnancy or lactation, severe psychiatric disorders or cognitive impairment, significant comorbidities that may interfere with study results or patient safety.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Classification accuracy | From date of contrast-enhanced CT scan to 1 year | The percentage of cases correctly classified by AI out of the total number of cases. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Agreement rate with clinical decisions | From date of contrast-enhanced CT scan to 1 year | The proportion of total cases where AI and clinician classification results are in agreement. |
| Percentage decrease in unnecessary surgical procedures | From date of contrast-enhanced CT scan to 1 year | The percentage reduction in the unnecessary surgery rate achieved by AI decision-making compared to traditional decision-making. |
| Malignancy miss rate | From date of contrast-enhanced CT scan to 1 year | The proportion of cases classified by AI as non-surgical that actually required surgery. |
Countries
China
Contacts
CONTACTBeilei Wang, Doctor
Outcome results
None listed