The EUS-AI-R study is an observational, single-center, two-phase (retrospective-prospective) study designed to develop and validate artificial intelligence (AI) models for predicting chemotherapy response and oncological outcomes in patients with pancreatic ductal adenocarcinoma (PDAC).
Patients who underwent endoscopic ultrasound (EUS) with tissue acquisition (EUS-FNA/FNB) for suspected pancreatic lesions at IRCCS San Raffaele Hospital between January 1st, 2019 and January 2026 will be retrospectively included. All patients have a histologically confirmed diagnosis of PDAC and a minimum follow-up of six months. These data derive from an IRB-approved institutional study (BIOPANCREAS; NCT06552078).
Retrospective multimodal data, including EUS imaging (B-mode, elastography, contrast-enhanced EUS), clinical and laboratory variables, CT/MRI imaging, digital pathology, and molecular data when available, will be used to develop and internally validate multiple AI models.
In the prospective phase, the best-performing AI model will be applied to an independent cohort of patients undergoing EUS at the same institution to evaluate feasibility, calibration, and real-world performance.
No additional procedures beyond standard clinical practice will be performed.
Pathologically confirmed diagnosis (final pathology report) of pancreatic cancer obtained through endoscopic ultrasound-guided tissue sampling (EUS-FNA or EUS-FNB)
Age ≥ 18 years at the time of diagnosis
Minimum follow-up duration of 6 months after diagnosis
Absence of other concomitant neoplastic diseases
All patients who underwent endoscopic ultrasound with tissue sampling at the Pancreato-Biliary Endoscopy and Endoscopic Ultrasound Unit of IRCCS San Raffaele Hospital but do not meet the inclusion criteria will be excluded from the final analysis cohorts.
Age<18 years
Inability to understand and make informed decisions
Refusal to participate in the study
All patients who underwent EUS at the Pancreato-Biliary Endoscopy and Endoscopic Ultrasound Unit of IRCCS San Raffaele Hospital with an histological diagnosis of PDAC.
Cohort
Other
Endoscopic ultrasound (EUS), with or without tissue acquisition (EUS-FNA/FNB), performed according to standard clinical practice. No study-specific intervention is introduced.
Other interventionEndoscopic ultrasound (EUS), with or without tissue acquisition (EUS-FNA/FNB), performed according to standard clinical practice. No study-specific intervention is introduced.
Development of an AI algorithm predicting chemotherapy response in patients with pancreatic cancer
Development of AI models to predict chemotherapy response in patients with PDAC by evaluating the predictive performance of: 1. An EUS-based AI model (pre-treatment EUS images/videos) 2. A clinical/exposome-based AI model (pre-treatment clinical and laboratory variables) 3. A radiology-based AI model (pre-treatment CT/MRI radiomics) 4. A digital pathology-based AI model (histopathology slides) 5. A multimodal AI model combining all available data sources (EUS + clinical/exposome + CT/MRI radiomics + digital pathology ± molecular data when available) Chemotherapy response will be defined according to radiological response criteria (RECIST) and biochemical response assessed by CA19-9 levels. Model performance will be assessed using AUC-ROC, sensitivity, and specificity.
Recurrence-Free Survival (RFS) Rate based on AI Models
To evaluate the predictive performance of the AI models (single-modality and multimodal) using pre-treatment imaging features to determine the rate and time to recurrence-free survival (RFS) / time to recurrence.
Progression-Free Survival (PFS) Rate based on AI Models
To evaluate the predictive performance of the AI models (single-modality and multimodal) using pre-treatment imaging features to determine the progression-free survival (PFS) rate.
Overall Survival (OS) Rate based on AI Models
To evaluate the predictive performance of the AI models (single-modality and multimodal) using pre-treatment imaging features to determine the overall survival (OS) rate.
Diagnostic Accuracy and Discrimination (AUC-ROC)
Evaluation of the Area Under the Receiver Operating Characteristic Curve (AUC-ROC) for the artificial intelligence (machine learning and deep learning) models developed on retrospective multimodal and multi-omic data (EUS, clinical, exposome, radiomics, pathology, and molecular data) to predict chemotherapy response and oncological outcomes in pancreatic cancer patients.
Diagnostic Accuracy (Sensitivity and Specificity) of AI Models
Assessment of sensitivity and specificity rates across validation folds of the AI models developed and internally validated on retrospective data for predicting chemotherapy response and oncological outcomes.
Model Calibration, Stability, and Prospective Feasibility
Evaluation of model calibration and stability across validation folds on retrospective data, alongside the assessment of feasibility and preliminary performance when the selected AI approach is applied prospectively in an independent patient population.
Click on the lead sponsor to view all of their trials.
This trial is not recruiting at the moment. You can still explore other options:
