An Artificial Intelligence System for ROSE of EUS-FNA Sample: a Prospective, Multicenter, Diagnostic Study.

NCT06718725 | Recruiting

• 1 other identifier: 2024SDU-QILU-1
• Study Type: observational
• Target: 236
• Locations: 1 country
• Sites: 1

Brief Summary

This is an observational study with a prospective, multicenter, disgnostic design. An artificial intelligence system named ROSE-AI system was developed using cytopathological slide images taken by microscope camera or smartphone of pancreas, bile duct, liver and lymph node, collected retrospectively from patients who underwent EUS-FNA and ROSE, and the performance of ROSE-AI system was validated in the datasets collected prospectively.This study aims to assist endoscopists in conducting rapid on-site cytopathology evaluations during EUS-FNA without the presence of cytopathologists. In addition, the diagnostic field was compared between the cytopathologists and ROSE-AI system, endoscopists with or without ROSE-AI system.

Conditions

The Malignant Lesions and Non-malignant Lesions of Pancreas, Bile Duct, Liver and Lymph Node

Outcome Measures

Primary Outcomes (1)

• the accuracy, sensitivity and specificity of the ROSE-AI system in identifying malignant/non-malignant ROSE samples

  The primary outcome of the study is to evaluate the performance of the ROSE-AI system in identifying the malignant/non-malignant ROSE samples of pancreatic, bile duct, hepatic and lymph node based on both images taken by microscope camera and smartphone, and comparing the performance between the ROSE-AI system and endoscopists, cytopathologists.

  During procedure

Secondary Outcomes (1)

• comparing the diagnostic performance between endoscopists with ROSE-AI system and without ROSE-AI system

  During procedure

Study Arms (1)

Patients undergoing EUS-FNA and ROSE

Patients ≥18 years with pancreatic, bile duct, hepatic, or lymph node lesions accepted EUS-FNA and ROSE.

Diagnostic Test: ROSE-AI system

Interventions

ROSE-AI system DIAGNOSTIC_TEST

The cytopathological slide images of the patients' ROSE samples will be identified by the ROSE-AI system.

Patients undergoing EUS-FNA and ROSE

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adult patients with pancreatic, bile duct, hepatic, or lymph node lesions undergoing EUS-FNA and ROSE from the participating hospitals.

You may qualify if:

• the patient age ≥18 years accepted EUS-FNA+ROSE.
• agree to participate in the research and be able to sign written informed consent.

You may not qualify if:

• uncorrectable coagulopathy (PTT \>50 seconds or INR \>1.5) and/or uncorrectable thrombocytopenia (platelet count \<50 × 109 /L).
• patients who were too clinically ill to undergo an EUS examination.
• lesions that were deemed inaccessible for EUS-guided sampling.
• unsuccessful EUS-FNA (e.g., failure to obtain an adequate specimen, patient intolerance, intraoperative accidents, etc.).
• Patients with unqualified ROSE smear.
• Patients who underwent biopsy during EUS-FNA but did not receive a definitive pathological diagnosis or pathological report.
• pregnancy.

Sponsors & Collaborators

• Qilu Hospital of Shandong University: lead
• Taian City Central Hospital: collaborator
• Qilu Hospital of Shandong University (Qingdao): collaborator
• Shandong Provincial Hospital: collaborator
• Liaocheng People's Hospital: collaborator
• The Affiliated Hospital of Qingdao University: collaborator
• Binzhou People's Hospital: collaborator
• Binzhou Medical University: collaborator
• 960th Hospital of PLA: collaborator
• Yidu Central Hospital of Weifang: collaborator

Study Sites (1)

Qilu Hospital of Shandong University

Jinan, Shandong, 250012, China

RECRUITING

Biospecimen

Retention: SAMPLES WITHOUT DNA

cytopathological slide images from patients who underwent EUS-FNA and ROSE

Central Study Contacts

Zhen Li

CONTACT

18560086106; qilulizhen@sdu.edu.cn

Study Design

• Study Type: observational
• Observational Model: CASE ONLY
• Time Perspective: PROSPECTIVE
• Target Duration: 6 Months
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: December 2, 2024
• First Posted: December 5, 2024
• Study Start: September 1, 2024
• Primary Completion: April 1, 2026
• Study Completion: April 1, 2026
• Last Updated: December 5, 2024

Record last verified: 2024-09

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)