AI Derived Biomarker to Select Neoadjuvant Treatment for Borderline Resectable Pancreatic Ductal Adenocarcinoma

A Retrospective/Prospective Study of an Artificial Intelligence Derived Histological Biomarker to Select Neoadjuvant Treatment for Patients With Borderline Resectable or Resectable Pancreatic Ductal Adenocarcinoma

To collect samples and information from patients who will be undergoing standard of care neoadjuvant treatment with either FOLFIRINOX or Gemcitabine + Nab-paclitaxel.

The information collected will be used to determine if there are any "biomarkers" in your blood or tumor tissue that, when compared to your response to the neoadjuvant treatment, could be used to choose the best treatment option for future patients with similar biomarkers.

Study Overview

• Status: Recruiting
• Conditions: Pancreatic Ductal Adenocarcinoma
• Intervention / Treatment: Other: Blood sample

• Study Type: Observational
• Enrollment (Estimated): 100

Contacts and Locations

• Study Contact: Name: Christos Fountzilas, MD; Phone Number: 716-845-2300; Email: Christos.fountzilas@roswellpark.org

Study Locations

• United States
  • New York
    • Buffalo, New York, United States, 14263
      • Recruiting
      • Roswell Park Comprehensive Cancer Center
    • West Islip, New York, United States, 11795
      • Recruiting
      • Good Samaritan University Hospital
      • Contact: John Loscalzo, MD; Phone Number: 631-417-8600
      • Principal Investigator: John Loscalzo, MD

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Adult; Older Adult
• Accepts Healthy Volunteers: No

• Sampling Method: Non-Probability Sample

Study Population

community practices and hospital clinics

Description

Inclusion Criteria:

• Have histologically or cytologically confirmed PDAC that is borderline resectable (BR) (Cohort A) OR have histologically or cytologically confirmed PDAC that is resectable (Cohort B) using the National Comprehensive Cancer Network criteria [35].
• Availability of archival tumor tissue (diagnostic for PDAC) required
• Have a documented ECOG Performance Status of ≤ 1
• Participant must understand the investigational nature of this study and sign an Independent Ethics Committee/Institutional Review Board approved written informed consent form (ICF) prior to receiving any study related procedure.

Exclusion Criteria:

• Has received prior systemic treatment (standard of care or experimental) for PDAC
• Participant has a concurrent malignancy requiring active treatment during the study.

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
Patients with Borderline Resectable (Cohort A); Pathological response of Patients with borderline resectable disease (per NCCD Criteria) treated with standard care chemotherapy	Other: Blood sample; To determine if there are any biomarkers in the blood that could be used to choose best treatment plan for future patients
Patients with Resectable (Cohort B); Pathological response of Patients with resectable disease (per NCCN criteria) treated with standard care chemotherapy	Other: Blood sample; To determine if there are any biomarkers in the blood that could be used to choose best treatment plan for future patients

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Retrospective prediction of pCR in resectable patients	Pathologic response is based on the American College of Pathology Criteria. The AI classified treatment is based on the best representative slide analyzed by the Valar Labs AI algorithm for V-FFX (is Folfirinox recommended) and V-GNP (is GEM/NAB-Paclitaxel recommended	Up to 2 years
Retrospective prediction of pCR in borderline resectable patients	Pathologic response is based on the American College of Pathology Criteria. The AI classified treatment is based on the best representative slide analyzed by the Valar Labs AI algorithm for V-FFX (is Folfirinox recommended) and V-GNP (is GEM/NAB-Paclitaxel recommended). Pathologic response is based on the American College of Pathology Criteria. The AI classified treatment is based on the best representative slide analyzed by the Valar Labs AI algorithm for V-FFX (is Folfirinox recommended) and V-GNP (is GEM/NAB-Paclitaxel recommended)	Up to 2 years

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Survival status	Medical chart will be reviewed for survival status	Up to 2 years
RECIST 1.1 response	Tumor response was determined by RECIST1.1	UP to 2 years

Collaborators and Investigators

• Sponsor: Roswell Park Cancer Institute
• Investigators: Principal Investigator: Christos Fountilas, MD, Roswell Park Comprehensive Cancer Center

Study record dates

Study Major Dates

• Study Start (Actual): January 2, 2024
• Primary Completion (Estimated): July 2, 2026
• Study Completion (Estimated): July 2, 2026

Study Registration Dates

• First Submitted: March 13, 2024
• First Submitted That Met QC Criteria: March 13, 2024
• First Posted (Actual): March 20, 2024

Study Record Updates

• Last Update Posted (Actual): April 30, 2026
• Last Update Submitted That Met QC Criteria: April 24, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Neoplasms; Neoplasms by Histologic Type; Neoplasms, Glandular and Epithelial; Carcinoma; Adenocarcinoma; Investigative Techniques; Specimen Handling; Clinical Laboratory Techniques; Diagnostic Techniques and Procedures; Diagnosis; Punctures; Surgical Procedures, Operative; Blood Specimen Collection
• Other Study ID Numbers: I-3574823

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No