AI Prediction Model and Risk Stratification for Lung Metastasis in Colorectal Cancer

Development and Validation of an Artificial Intelligence Prediction Model and a Survival Risk Stratification for Lung Metastasis in Colorectal Cancer From Highly Imbalanced Data

Background:

To assist clinicians with diagnosis and optimal treatment decision-making, we attempted to develop and validate an artificial intelligence prediction model for lung metastasis (LM) in colorectal cancer (CRC) patients.

Method:

The clinicopathological characteristics of 46037 CRC patients from the Surveillance, Epidemiology, and End Results (SEER) database and 2779 CRC patients from a multi-center external validation set were collected retrospectively. After feature selection by univariate and multivariate analyses, six machine learning (ML) models, including logistic regression, K-nearest neighbor, support vector machine, decision tree, random forest, and balanced random forest (BRF), were developed and validated for the LM prediction. The optimization model with best performance was compared to the clinical predictor. In addition, stratified LM patients by risk score were utilized for survival analysis.

Study Overview

• Status: Completed
• Conditions: Colorectal Cancer; Lung Metastases
• Intervention / Treatment: Other: The location of the patient's treatment

• Study Type: Observational
• Enrollment (Actual): 2779

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child; Adult; Older Adult
• Accepts Healthy Volunteers: N/A

• Sampling Method: Non-Probability Sample

Study Population

patients with pathologic confirmation of a primary CRC diagnosis

Description

Inclusion Criteria:

• patients with pathologic confirmation of a primary CRC diagnosis

Exclusion Criteria:

• (1) patients with multiple primary cancers or other malignancies; (2) patients identified via autopsy or death certificate; and (3) patients with uncertain clinical data values

Study Plan

How is the study designed?

Number of groups / cohorts

2

Cohorts and Interventions

Group / Cohort	Intervention / Treatment
validation set 1; The validation set 1 was comprised of patients with CRC diagnosed and treated between January 1, 2016, and December 31, 2020, at the Cancer Hospital Chinese Academy of Medical Sciences and Peking Union Medical College.	Other: The location of the patient's treatment; The location of the patient's treatment
validation set 2; The validation set 2 was comprised of patients with CRC diagnosed and treated between January 1, 2016, and December 31, 2020, at the Second Affiliated Hospital of Harbin Medical University.	Other: The location of the patient's treatment; The location of the patient's treatment

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
lung metastasis	diagnosed with lung metastasis	through study completion, an average of 3 month

Collaborators and Investigators

• Sponsor: Peking Union Medical College
• Collaborators: The Second Affiliated Hospital of Harbin Medical University

Study record dates

Study Major Dates

• Study Start (Actual): January 1, 2016
• Primary Completion (Actual): December 31, 2020
• Study Completion (Actual): December 31, 2020

Study Registration Dates

• First Submitted: April 5, 2023
• First Submitted That Met QC Criteria: April 5, 2023
• First Posted (Actual): April 18, 2023

Study Record Updates

• Last Update Posted (Actual): April 18, 2023
• Last Update Submitted That Met QC Criteria: April 5, 2023
• Last Verified: April 1, 2023

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Digestive System Diseases; Pathologic Processes; Respiratory Tract Diseases; Neoplasms; Lung Diseases; Neoplasms by Site; Gastrointestinal Neoplasms; Digestive System Neoplasms; Gastrointestinal Diseases; Respiratory Tract Neoplasms; Thoracic Neoplasms; Colonic Diseases; Intestinal Diseases; Intestinal Neoplasms; Rectal Diseases; Neoplastic Processes; Lung Neoplasms; Colorectal Neoplasms; Neoplasm Metastasis
• Other Study ID Numbers: PekingUMC02

Drug and device information, study documents

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