An observational study in Autoimmune Pancreatitis and Pancreatic Ductal Adenocarcinoma (PDAC), sponsored by Ruijin Hospital. Not yet recruiting. Open to participants aged 18 Years and older. Per ClinicalTrials.gov, last updated 2026-11-09.
Sponsored by Ruijin Hospital · Observational
Focal autoimmune pancreatitis (f-AIP) and pancreatic ductal adenocarcinoma (PDAC) exhibit substantial overlap in clinical manifestations and imaging features, posing a major diagnostic challenge in pancreatic diseases. Given the marked differences in treatment strategies and prognosis, accurate differentiation is essential to avoid unnecessary surgery and ensure timely initiation of anticancer treatment.
This study aims to collect endoscopic ultrasound (EUS) images from patients with confirmed f-AIP or PDAC across multiple centers, using a previously established multicenter database. Data collected before January 2026 will be used to develop an artificial intelligence (AI) model based on EUS radiomics for differential diagnosis. Subsequently, prospectively collected data from participating centers from 2026 onward will be used for model testing and validation. The diagnostic performance of the model will be evaluated and compared with that of endoscopists with different levels of experience.
Furthermore, this study will investigate the clinical value of interpretable radiomic features, with particular emphasis on challenging diagnostic scenarios, including IgG4-negative AIP, AIP with elevated carbohydrate antigen 19-9 (CA19-9) levels, and PDAC with imaging features resembling those of AIP. The ultimate goal is to provide a reliable tool for accurate, noninvasive preoperative differential diagnosis while promoting the standardization of multicenter AIP databases and the sharing and utilization of imaging data resources.
28 studies on the registry are indexed under Autoimmune Pancreatitis; 7 are open to participants now.
This study's planned enrollment of 690 is above the median of 130 across 17 observational studies indexed under Autoimmune Pancreatitis.
Browse Autoimmune Pancreatitis studies →Ruijin Hospital is the lead sponsor of 679 studies on the registry; 387 are open to participants now.
Counted across the registry records on this site, refreshed daily.
This multicenter ambispective observational study will include patients with confirmed focal autoimmune pancreatitis (f-AIP) or pancreatic ductal adenocarcinoma (PDAC) who undergo endoscopic ultrasound (EUS) examination at participating hospitals in China. The retrospective cohort will include at least 450 patients (150 with f-AIP and 300 with PDAC) for AI model development and internal validation. An independent prospective cohort will include at least 240 patients (80 with f-AIP and 160 with PDAC) for external validation. EUS images, clinical characteristics, laboratory findings, and pathological data will be collected. All examinations and treatments will follow routine clinical practice, without study-specific interventions.
Inclusion C**Inclusion Criteria:**
**1. Focal Pancreatitis (f-AIP) Group**
**2. Pancreatic Ductal Adenocarcinoma (PDAC) Group**
**Exclusion Criteria:**
The following criteria apply to both groups:
Exclusion Criteria:
-
Underlined terms in the criteria open these too. Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
A condition in which the immune system attacks the body’s own tissues, such as rheumatoid arthritis, lupus, psoriasis, type 1 diabetes or inflammatory bowel disease.
Immunotherapy studies often leave out active autoimmune disease, and some name exceptions, such as thyroid disease on replacement hormone. Check the exceptions this study lists.
A biopsy takes a small piece of tissue to examine. “Archival tissue” is a sample already taken, for example at diagnosis, and kept by the hospital.
Whether a stored sample will do depends on when it was taken, how much there is and what the study needs. Ask whether the study accepts your stored sample or needs a new biopsy.
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Anti-inflammatory medicines such as prednisone, prednisolone and dexamethasone — not the anabolic steroids used for muscle.
Studies differ in what they allow: check which steroid medicines, routes (tablets, injections, creams, inhalers, eye drops) and doses this study accepts.
Autoimmune disease
A condition in which the immune system attacks the body’s own tissues, such as rheumatoid arthritis, lupus, psoriasis, type 1 diabetes or inflammatory bowel disease.
Immunotherapy studies often leave out active autoimmune disease, and some name exceptions, such as thyroid disease on replacement hormone. Check the exceptions this study lists.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Biopsy and archival tissue
A biopsy takes a small piece of tissue to examine. “Archival tissue” is a sample already taken, for example at diagnosis, and kept by the hospital.
Whether a stored sample will do depends on when it was taken, how much there is and what the study needs. Ask whether the study accepts your stored sample or needs a new biopsy.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Informed consent
Before you join, the study team explains what taking part involves — its purpose, what happens, the risks and possible benefits — and answers your questions, so you can decide freely. Consent is usually recorded on a form (the informed consent form, ICF) signed by you or, where the law allows, by someone legally authorised to decide for you.
You can keep asking questions during the study, you are told of new information that matters, and you can choose to leave at any time.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Corticosteroids (steroids)
Anti-inflammatory medicines such as prednisone, prednisolone and dexamethasone — not the anabolic steroids used for muscle.
Studies differ in what they allow: check which steroid medicines, routes (tablets, injections, creams, inhalers, eye drops) and doses this study accepts.
Explained by clinicaltrials.gg, not part of the registry record. The study team decides who can take part.
Patients diagnosed with focal autoimmune pancreatitis (f-AIP) according to established diagnostic criteria. Eligible patients will undergo endoscopic ultrasound (EUS) as part of routine clinical care. EUS images, clinical characteristics, laboratory findings, and relevant pathological data will be collected for the development and validation of an artificial intelligence-based differential diagnostic model. Both retrospective and prospective cases will be included. No study-specific interventions will be performed.
Patients with histologically or cytologically confirmed pancreatic ductal adenocarcinoma (PDAC) who have undergone endoscopic ultrasound (EUS) as part of routine clinical care. EUS images, clinical characteristics, laboratory findings, and relevant pathological data will be collected for comparison with patients with f-AIP and for the development and validation of an artificial intelligence-based differential diagnostic model. Both retrospective and prospective cases will be included. No study-specific interventions will be performed.
Area Under the Receiver Operating Characteristic Curve (AUC) of the AI Model for Differentiating f-AIP From PDAC
The diagnostic performance of the multimodal artificial intelligence (AI) model in differentiating focal autoimmune pancreatitis (f-AIP) from pancreatic ductal adenocarcinoma (PDAC) will be evaluated using the area under the receiver operating characteristic curve (AUC) in an independent prospective multicenter validation cohort. The AUC ranges from 0.5 (no discrimination) to 1.0 (perfect discrimination), with higher values indicating better diagnostic performance. The AUC and its 95% confidence interval will be calculated.
Time frame: At completion of data collection and diagnostic assessment in the prospective validation cohort, through December 2028.
Sensitivity of the AI Model for Differentiating f-AIP From PDAC
Sensitivity will be calculated as the proportion of patients with focal autoimmune pancreatitis (f-AIP) correctly identified by the AI model among all patients with confirmed f-AIP in the prospective validation cohort. Results will be reported as percentages with 95% confidence intervals.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Specificity of the AI Model for Differentiating f-AIP From PDAC
Specificity will be calculated as the proportion of patients with pancreatic ductal adenocarcinoma (PDAC) correctly identified as not having f-AIP among all patients with confirmed PDAC in the prospective validation cohort. Results will be reported as percentages with 95% confidence intervals.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Diagnostic Accuracy of the AI Model
Diagnostic accuracy will be defined as the proportion of correctly classified f-AIP and PDAC cases among all evaluated patients in the prospective validation cohort. Results will be reported as percentages with 95% confidence intervals.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Positive Predictive Value of the AI Model
Positive predictive value (PPV) will be calculated as the proportion of patients with confirmed f-AIP among all patients classified as f-AIP by the AI model in the prospective validation cohort. Results will be reported as percentages with 95% confidence intervals.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Negative Predictive Value of the AI Model
Negative predictive value (NPV) will be calculated as the proportion of patients with confirmed PDAC among all patients classified as PDAC by the AI model in the prospective validation cohort. Results will be reported as percentages with 95% confidence intervals.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Comparison of Diagnostic Performance Between the AI Model and Endoscopists
The diagnostic performance of the AI model will be compared with that of endoscopists at different experience levels (junior: less than 5 years; intermediate: 5-10 years; senior: 10 years or more). Diagnostic performance will be assessed using AUC, sensitivity, specificity, and accuracy in the prospective validation cohort. Differences in AUC will be evaluated using the DeLong test where applicable.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Comparison of Diagnostic Sensitivity Between the AI Model and Endoscopists
The sensitivity of the AI model for differentiating mass-forming autoimmune pancreatitis from pancreatic ductal adenocarcinoma will be compared with that of endoscopists at different experience levels in the prospective validation cohort. Sensitivity will be calculated as the proportion of patients with pancreatic ductal adenocarcinoma correctly identified as having pancreatic ductal adenocarcinoma.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Comparison of Diagnostic Specificity Between the AI Model and Endoscopists
The specificity of the AI model for differentiating mass-forming autoimmune pancreatitis from pancreatic ductal adenocarcinoma will be compared with that of endoscopists at different experience levels in the prospective validation cohort. Specificity will be calculated as the proportion of patients with mass-forming autoimmune pancreatitis correctly identified as having mass-forming autoimmune pancreatitis.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
Comparison of Diagnostic Accuracy Between the AI Model and Endoscopists
The diagnostic accuracy of the AI model will be compared with that of endoscopists at different experience levels in the prospective validation cohort. Accuracy will be calculated as the proportion of correctly classified patients among all evaluated patients.
Time frame: At completion of diagnostic assessment in the prospective validation cohort, through December 2028.
No study locations are listed for this record.
Plan to share: No — Individual participant data will not be made publicly available due to patient privacy considerations, institutional data protection requirements, and restrictions on sharing multicenter clinical imaging and health records. De-identified data will be accessed only by authorized researchers within the participating institutions in accordance with applicable ethical approvals and data management agreements.
No publications or documents are linked to this record.
Start is estimated for Nov 2026; primary completion for Jun 2028, 19 months later.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is not yet recruiting, as verified in Oct 2026. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.