Pancreatic ductal adenocarcinoma (PDAC) has a poor prognosis, with early diagnosis crucial for improving survival. Due to the absence of effective screening methods, most patients are diagnosed at advanced stages. The population undergoing low-dose computed tomography (LDCT) screening significantly overlaps with those at high risk for PDAC; however, traditional imaging methods have limited sensitivity for detecting pancreatic lesions. This study utilizes the Pancreatic Cancer Detection with Artificial Intelligence (PANDA) system to enhance LDCT for pancreatic cancer screening in a prospective, multicenter, observational cohort. PANDA will analyze LDCT images, followed by a multidisciplinary team (MDT) reassessment of abnormal interpretations. Based on MDT evaluation, individuals will be recalled for further examination, placed under a personalized follow-up plan, or monitored for at least one year. The primary outcomes include pancreatic cancer detection rate, positive predictive value, consensus rate, and recall rate, while secondary outcomes focus on early-stage cancers, resectable tumors, and safety indicators such as false positive rates and unnecessary procedures. This study aims to assess the effectiveness and safety of AI-assisted LDCT for PDAC detection, providing a practical solution for improving public health and enhancing early diagnostic capabilities.
Age 50 years and above.
Voluntary signing of informed consent.
Completion of LDCT examination.
Previous history of pancreatic cancer.
Abdominal inflammation or diagnosis of acute pancreatitis within 6 months.
Poor image quality due to ascites, pancreatic trauma, thoracic/abdominal surgery, radiotherapy or chemotherapy.
Research subjects unable to complete follow-up due to physical or other reasons.
The study population includes asymptomatic individuals aged 50 years and above who have undergone routine low-dose chest CT (LDCT) scans at health check-up centers. Eligible participants must provide written informed consent and be willing to attend all scheduled follow-up visits. Exclusion criteria include a previous history of pancreatic cancer, abdominal inflammation or diagnosis of acute pancreatitis within 6 months, poor image quality due to ascites, pancreatic trauma, thoracic/abdominal surgery, radiotherapy or chemotherapy, and research subjects unable to complete follow-up due to physical or other reasons.
Cohort
Prospective
Diagnostic Evaluation for Positive AI Findings
Diagnostic testMDT will review positive AI findings (including PDAC, pancreatic precursor lesions and benign lesion) cases to determine next steps: (1) Suspected PDAC and pancreatic precursor lesions are referred for hospital examination with diagnostic results collected; (2) Benign lesion cases receive personalized monitoring until endpoint events or study end; (3) Cases with positive AI findings but MDT-confirmed normal pancreatic issues receive at least one year of follow-up. If any abnormal results arise, management will transition to either plan (1) or (2).
Pancreatic cancer detection rate
The proportion of individuals with abnormal AI assessment confirmed as pancreatic cancer or precancerous lesions among the total screened population
Positive predictive value
The proportion of individuals with abnormal AI assessment confirmed as pancreatic cancer or precancerous lesions among all individuals with abnormal AI assessment
Consensus rate
The proportion of individuals with abnormal AI assessment deemed suspicious for pancreatic cancer or precancerous lesions by MDT requiring recall among the total screened population.
Recall rate
The proportion of individuals actually recalled among the total screened population.
Early-stage pancreatic cancer proportion
The proportion of individuals with abnormal AI assessment confirmed as early-stage pancreatic cancer among the total number of confirmed pancreatic cancer cases.
Resectable pancreatic cancer proportion
The proportion of individuals with surgically resectable pancreatic cancer among the total number of confirmed pancreatic cancer cases.
False positive rate
The proportion of individuals with abnormal AI assessment who actually have benign conditions or no lesions, among the total number of individuals with abnormal AI assessment.
Unnecessary invasive examination proportion
The proportion of individuals with abnormal AI assessment who underwent invasive examinations but were found to have benign conditions or no lesions, among the total number of individuals with abnormal AI assessment.
Unnecessary surgery proportion
The proportion of individuals with abnormal AI assessment who underwent surgery but were confirmed to have benign lesions by postoperative pathology, among the total number of individuals with abnormal AI assessment.
Pancreatic cancer 5-year survival rate
The proportion of pancreatic cancer patients detected by AI who are still alive after 5 years of follow-up, among the total number of pancreatic cancer patients detected by AI.
Click on the lead sponsor to view all of their trials.
Changhai Hospital
Lead sponsor
The Affiliated People's Hospital of Ningbo University
Collaborator
Jiaxing University Affiliated Second Hospital
Collaborator
Meinian Onehealth Healthcare Holdings Co., Ltd
Collaborator
Ruici Medical Examination Institution
Collaborator
