Interpretable Machine Learning Models for Prognosis in Gastric Cancer Patients

NCT06548464 | Completed DMC

• 1 other identifier: 2024KY154
• Study Type: observational
• Target: 18,000
• Locations: 1 country
• Sites: 1

Brief Summary

This multicenter, retrospective cohort study aimed to develop and validate an explainable prediction model for prognosis after gastrectomy in patients with gastric cancer.

Conditions

Stomach Neoplasms; Gastrectomy; Machine Learning

Keywords

Machine Learning; Prognosis; Stomach Neoplasms; Gastrectomy

Outcome Measures

Primary Outcomes (1)

• Survival

  Assessment of overall survival outcomes in gastric cancer patients after gastrectomy.

  Up to 5 years after surgery

Secondary Outcomes (5)

• Early Recurrence

  Within 2 years after surgery

• Late Recurrence

  From 2 years up to 5 years after surgery

• Postoperative Complications

  Within 30 days after surgery

• Neoadjuvant Treatment Efficacy

  From initiation of neoadjuvant therapy to surgery (typically 2-3 months)

• 5-Year Survival Rate

  5 years after surgery

Eligibility Criteria

• Sex: all
• Healthy Volunteers: No
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

This study includes adult patients of all genders who were diagnosed with primary gastric or gastroesophageal junction adenocarcinoma and underwent radical gastrectomy at participating institutions in China. The study population represents a diverse group of gastric cancer patients, varying in age, tumor stage, and treatment approaches, including those who received neoadjuvant therapy. This cohort aims to provide a comprehensive representation of gastric cancer patients treated with curative intent, allowing for the development and validation of prognostic models applicable to a wide range of clinical scenarios.

You may qualify if:

• Patients diagnosed with primary gastric or gastroesophageal junction cancer
• Underwent radical gastrectomy
• Complete clinical and pathological data available

You may not qualify if:

• Presence of distant metastases before surgery
• Non-adenocarcinoma histology
• Incomplete follow-up data

Sponsors & Collaborators

• Chang-Ming Huang, Prof.: lead

Study Sites (1)

Chang-ming Huang

Fuzhou, Fujian, 350001, China

Location

MeSH Terms

Conditions

Stomach Neoplasms

Condition Hierarchy (Ancestors)

Gastrointestinal Neoplasms; Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Gastrointestinal Diseases; Stomach Diseases

Study Officials

• Chang-Ming Huang, MD

  Fujian Medical University Union Hospital

  PRINCIPAL INVESTIGATOR

Study Design

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

Study Record Dates

• First Submitted: August 6, 2024
• First Posted: August 12, 2024
• Study Start: June 1, 2024
• Primary Completion: August 1, 2024
• Study Completion: August 6, 2024
• Last Updated: August 12, 2024

Record last verified: 2024-08

Locations

CN (1)