Multimodal Deep Learning Model Predicts Pancreatic Cancer Prognosis

NCT06760234 | Completed DMC

• 1 other identifier: PCPAI
• Study Type: observational
• Target: 247
• Locations: 1 country
• Sites: 1

Brief Summary

This study describes the development and validation of a deep learning prediction model, which extracts deep learning features from preoperative enhanced CT scans and analyzes postoperative pathological specimens of pancreatic cancer patients. The aim is to predict patient prognosis and response to chemotherapy treatment.

Conditions

Pancreatic Adenocarcinoma

Keywords

Deep Learning Model; Pancreatic adenocarcinoma; prognosis

Outcome Measures

Primary Outcomes (1)

• Performance of deep learning model

  The model's performance was evaluated using metrics including area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

  Baseline treatment

Study Arms (2)

Training Cohort

Patients diagnosed with pancreatic cancer who underwent surgery and other treatments at the Second Affiliated Hospital, Zhejiang University School of Medicine

Diagnostic Test: No Interventions

Test Cohort

Patients diagnosed with pancreatic cancer who underwent surgery and other treatments at the Fourth Affiliated Hospital, Zhejiang University School of Medicine and Hangzhou Hosptial of Traditional Chinese Medicine

Diagnostic Test: No Interventions

Interventions

No Interventions DIAGNOSTIC_TEST

The high-throughput extraction of quantitative image features from medical images

Test Cohort; Training Cohort

Eligibility Criteria

• Age: 18 Years - 90 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Pancreatic cancer patients who were undergo surgery and received adjuvant chemotherapy after surgery.

You may qualify if:

• Patients with pancreatic cancer, diagnosed through pathology;
• Patients underwent surgery and received adjuvant chemotherapy after surgery.

You may not qualify if:

• Missing or inadequate quality of CT,
• Incomplete clinical or pathological data.
• Multiple primary malignancies;
• History of malignancy.

Sponsors & Collaborators

• Second Affiliated Hospital, School of Medicine, Zhejiang University: lead
• Hangzhou Hospital of Traditional Chinese Medicine: collaborator
• The Fourth Affiliated Hospital of Zhejiang University School of Medicine: collaborator

Study Sites (1)

the Second Affiliated Hospital Zhejiang University School of Medicine

Hangzhou, Zhejiang, 310009, China

Location

Related Publications (1)

• Fan Y, Du B, Pu K, Sun Y, Lv C, Hu S, Song T, Wu R, Chen Y, Tang J, Zhong Y, Bian W, Wu J, Zhang H, Ding Y, Xu H, Wu Y, Li X. Noninvasive evaluation and clinical value prediction of tumor-infiltrating neutrophil-to-T-cell ratio in pancreatic ductal adenocarcinoma. NPJ Digit Med. 2026 Jan 3;9(1):123. doi: 10.1038/s41746-025-02303-9.

  PMID: 41484243 DERIVED

Study Officials

• Yulian Wu, PhD.

  Second Affiliated Hospital of Zhejiang University School of Medicine

  PRINCIPAL INVESTIGATOR

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: December 29, 2024
• First Posted: January 6, 2025
• Study Start: July 5, 2024
• Primary Completion: December 15, 2024
• Study Completion: January 3, 2026
• Last Updated: January 7, 2026

Record last verified: 2024-07

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)