Skip to content

Colon Cancer

Background

This documentation summarizes the Medial EarlySign research regarding the Colon Cancer algorithm. All data points, performance metrics, and deployment history listed below are sourced exclusively from publicly available literature and peer-reviewed manuscripts. This serves as a technical overview of the original MES methodology.

Overview

The Colon cancer model was developed to detect colon and rectal cancer using data from Maccabi Healthcare Services (MHS), the second largest HMO in Israel. First version published in 2015, with the final version completed in 2018.

The model has undergone external validation at numerous sites across various regions. A partial list of related publications is provided below.

Deployments

Publicly available deployments were in:

  • Maccabi Healthcare Services - Israel (since 2015)
  • Geisinger Health System - US (since 2018)

List of Publications

  • Partial list of publications.
Manuscript Population Year Model Study Type Research Organization
Development and validation of a predictive model for detection of colorectal cancer in primary care by analysis of complete blood counts: a binational retrospective study MHS Israel, THIN - UK 2016 Retrospective, Outcomes were retrieved after scoring + External validation MES
Performance analysis of a machine learning flagging system used to identify a group of individuals at a high risk for colorectal cancer MHS Israel 2017 Prospective Observational MES
Evaluation of a prediction model for colorectal cancer: retrospective analysis of 2.5 million patient records UK - CPRD 2017 Retrospective, External Validation Oxford
Early Colorectal Cancer Detected by Machine Learning Model Using Gender, Age, and Complete Blood Count Data US - Kaiser Permanente North West 2017 Retrospective, External Validation MES
Computer-Assisted Flagging of Individuals at High Risk of Colorectal Cancer in a Large Health Maintenance Organization Using the ColonFlag Test MHS Israel 2018 Prospective Interventional MHS
Prediction of findings at screening colonoscopy using a machine learning algorithm based on complete blood counts (ColonFlag) Canada 2018 Retrospective, External Validation MES
Potential roles of artificial intelligence learning and faecal immunochemical testing for prioritisation of colonoscopy in anaemia UK - gastroenterology clinic in Plymouth, Royal London Hospital 2019 Prospective Observational Barts
Validation of an Algorithm to Identify Patients at Risk for Colorectal Cancer Based on Laboratory Test and Demographic Data in Diverse, Community-Based Population US - Kaiser Permanente North West 2020 Retrospective, External Validation University of Washington + KP
Collaboration to Improve Colorectal Cancer Screening Using Machine Learning US - Geisinger Health System 2022 Prospective Interventional Geisinger
Diagnostic application of the ColonFlag AI tool in combination with faecal immunochemical test in patients on an urgent lower gastrointestinal cancer pathway UK - Barts Health - Urgency pathway 2024 Prospective Interventional Barts
Machine Learning-Guided Cancer Screening: The Benefits of Proactive Care Geisinger 2024 Prospective Interventional Geisinger

Less important publication:

Manuscript Population Year Model Study Type Research Organization Comment
Use of ColonFlag score for prioritisation of endoscopy in colorectal cancer UK - Barts Health - Urgency pathway 2021 Prospective Interventional Barts There is a new publication from 2024 with more data
Predicting the presence of colon cancer in members of a health maintenance organisation by evaluating analytes from standard laboratory records MHS Israel 2017 Retrospective MES Different model
Development and Validation of a Colorectal Cancer Prediction Model: A Nationwide Cohort-Based Study Clalit - Israel 2024 Clalit Model Retrospective, Developent and internal validation Clalit