Multimodal Model Predicts Recurrence

NCT06690268 | Completed

• 1 other identifier: FUTURE12
• Study Type: observational
• Target: 93
• Locations: 1 country
• Sites: 1

Brief Summary

This study focuses on developing an advanced model that combines clinical information, imaging, and pathology data to predict the likelihood of cancer returning after surgery in patients with locally advanced gastric cancer. By using artificial intelligence (AI), this model analyzes various data sources to create a more accurate prediction of recurrence risk, which can help doctors, patients, and families better understand the chances of recurrence. This AI-driven approach allows healthcare providers to make more informed decisions about personalized follow-up care and potential additional treatments to improve patient outcomes.

Conditions

Gastric Adenocarcinoma

Outcome Measures

Primary Outcomes (1)

• Prediction accuracy of postoperative recurrence in locally advanced gastric cancer

  The primary outcome measure is the accuracy of the multimodal AI model in predicting the risk of postoperative recurrence in patients with locally advanced gastric cancer. This is assessed by comparing the model's predictions with actual recurrence events over a specified follow-up period, allowing evaluation of its effectiveness in identifying high-risk patients and guiding clinical decisions.

  24 months postoperative follow-up

Interventions

Multimodal AI-driven predictive model DIAGNOSTIC_TEST

This intervention involves a multimodal artificial intelligence (AI) model that integrates clinical data, imaging results, and pathology findings to predict the risk of postoperative recurrence in patients with locally advanced gastric cancer. Unlike traditional methods that may rely on single data sources, this AI-driven model synthesizes multiple types of patient information, offering a comprehensive and personalized prediction of recurrence risk. This approach aims to improve accuracy in identifying high-risk patients, allowing for more tailored follow-up and treatment planning to enhance patient outcomes.

Eligibility Criteria

• Age: 18 Years - 75 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

The study population includes adult patients (aged 18 and older) diagnosed with locally advanced gastric cancer (Stage II or III) who have undergone surgical resection. This population is selected based on the availability of complete clinical, imaging, and pathology data necessary for analysis by the multimodal AI-driven predictive model. The study focuses on assessing the postoperative recurrence risk in this specific group to improve personalized follow-up and treatment planning.

You may qualify if:

• Patients diagnosed with locally advanced gastric cancer (Stage II or III).
• Patients who have undergone surgical resection for gastric cancer.
• Patients with complete clinical, imaging, and pathology data available for analysis.
• Age 18 years or older.
• Patients who provide informed consent to participate in the study.

You may not qualify if:

• Patients with distant metastasis (Stage IV) at the time of diagnosis.
• Patients with incomplete or missing clinical, imaging, or pathology data.
• Patients who have received prior treatment for gastric cancer other than surgical resection.
• Patients with other concurrent malignancies.
• Patients who are unable or unwilling to comply with the study follow-up requirements.

Sponsors & Collaborators

• Qun Zhao: lead

Study Sites (1)

the Fourth Hospital of Hebei Medical University

Shijiazhuang, Hebei, 050011, China

Location

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Target Duration: 24 Months
• Sponsor Type: OTHER
• Responsible Party: SPONSOR INVESTIGATOR
• PI Title: Professor

Study Record Dates

• First Submitted: November 13, 2024
• First Posted: November 15, 2024
• Study Start: January 1, 2022
• Primary Completion: October 31, 2024
• Study Completion: October 31, 2024
• Last Updated: November 15, 2024

Record last verified: 2024-11

Locations

CN (1)