Related Experiment Video
Updated: Feb 2, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
Published on: August 16, 2020
Prediction of findings at screening colonoscopy using a machine learning algorithm based on complete blood counts
Robert J Hilsden1, Steven J Heitman1, Barak Mizrahi2
1Departments of Medicine and Community Health Sciences, Cumming School of Medicine University of Calgary, Calgary, Alberta, Canada.
ColonFlag, a machine-learning tool using blood counts, can identify individuals with high-risk adenomatous polyps, aiding targeted colorectal cancer screening.
Area of Science:
- Oncology
- Medical Diagnostics
- Machine Learning
Background:
- Adenomatous polyps are precursors to colorectal cancer.
- Early detection of high-risk polyps is crucial for cancer prevention.
- Current screening methods have limitations in identifying at-risk individuals.
Purpose of the Study:
- To evaluate ColonFlag's ability to predict high-risk adenomatous polyps.
- To assess ColonFlag's utility in identifying individuals needing intensified colorectal cancer screening.
Main Methods:
- A retrospective study of 17,676 asymptomatic individuals aged 50-75 undergoing screening colonoscopy.
- ColonFlag algorithm utilized patient information and complete blood cell counts (CBC).
- ColonFlag scores were compared against colonoscopy findings of high-risk polyps.
Main Results:
- ColonFlag identified individuals with high-risk polyps with an odds ratio of 2.0 at 95% specificity.
- The algorithm demonstrated consistent predictive value across subgroups.
- A small percentage of participants had high-risk lesions (5.7%) or colorectal cancer (0.3%).
Conclusions:
- ColonFlag can predict the presence of high-risk adenomatous polyps using routine blood tests.
- The algorithm aids in identifying individuals for targeted colorectal cancer screening.
- ColonFlag offers a passive, non-invasive method to enhance screening compliance and efficacy.
More Related Videos
06:19Constructing and Visualizing Models using Mime-based Machine-learning Framework
Published on: July 22, 2025
04:09Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
Published on: October 10, 2018
Related Concept Videos
Endoscopic Procedures II: Colonoscopy
Predicting Molecular Geometry
Machines
A free-body diagram of the...
Trial and Error and Algorithm
Finding the Center of Gravity
Machines: Problem Solving II