AI-enhanced low-dose CT to screen for pancreatic cancer

Artificial Intelligence-powered Low-Dose Computed Tomography for Screening of Pancreatic Cancer

Observational Changhai Hospital · NCT07117045

This project will test whether an AI tool called PANDA can read low-dose CT scans to find early pancreatic cancer in people aged 50 and older.

Quick facts

Study typeObservational
Enrollment400000 (estimated)
Ages50 Years and up
SexAll
SponsorChanghai Hospital Academic / other
Drugs / interventionschemotherapy, radiation
Locations5 sites (Shanghai, Shanghai Municipality and 4 other locations)
Trial IDNCT07117045 on ClinicalTrials.gov

What this trial studies

This prospective, multicenter observational cohort uses the PANDA artificial intelligence system to analyze low-dose CT (LDCT) images collected at participating centers. When PANDA flags an abnormality, a multidisciplinary team (MDT) reviews the finding and decides whether to recall the person for further testing, create a personalized follow-up plan, or monitor for at least one year. Primary outcomes include pancreatic cancer detection rate and positive predictive value, with secondary tracking of follow-up pathways and diagnostic yield. The protocol enrolls people aged 50 and older who complete LDCT, excluding those with prior pancreatic cancer, recent acute pancreatitis, or poor-quality scans.

Who should consider this trial

Good fit: Ideal candidates are adults aged 50 or older who undergo LDCT, can give informed consent, and have no prior pancreatic cancer or recent severe abdominal inflammation.

Not a fit: People with a history of pancreatic cancer, recent acute pancreatitis, or LDCT scans of poor quality are unlikely to benefit.

Why it matters

Potential benefit: If successful, this could enable earlier, less invasive detection of pancreatic cancer from routine low-dose CT scans, improving chances for curative treatment.

How similar studies have performed: Previous multi-center and real-world testing of PANDA and similar AI tools has reported high sensitivity and specificity for pancreatic lesion detection across tens of thousands of cases.

Eligibility criteria

Show full inclusion / exclusion criteria
Inclusion Criteria:

1. Age 50 years and above.
2. Voluntary signing of informed consent.
3. Completion of LDCT examination.

Exclusion Criteria:

1. Previous history of pancreatic cancer.
2. Abdominal inflammation or diagnosis of acute pancreatitis within 6 months.
3. Poor image quality due to ascites, pancreatic trauma, thoracic/abdominal surgery, radiotherapy or chemotherapy.
4. Research subjects unable to complete follow-up due to physical or other reasons.

Where this trial is running

Shanghai, Shanghai Municipality and 4 other locations

Study contacts

How to participate

  1. Review the eligibility criteria above with your treating physician.
  2. Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
  3. Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.
Conditions Pancreatic CancerIntraductal Papillary Mucinous NeoplasmHigh-grade Pancreatic Intraepithelial NeoplasiaPDAC - Pancreatic Ductal AdenocarcinomaMucinous Cystic NeoplasmScreeningEarly DiagnosisArtificial Intelligence
Last reviewed 2026-06-13 by the Find a Trial editorial team. Information on this page is for educational purposes and is not medical advice. Always consult qualified healthcare professionals about clinical trial participation.