Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data - A Review

Sep 17, 2026

Uploaded by Jiven

Incorporating machine-learning-derived models into systematic reviews of colorectal cancer risk prediction models remains uncommon. While prior reviews reported methodological limitations and constrained performance among included models, the reasons for the absence of machine-learning models and whether they share similar methodological problems were unclear. This scoping review identifies machine-learning models, evaluates their methodologies, and compares their performance with earlier review findings.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages22

Reading Time55 min

AccessFree to download

Introduction

Abstract

Keywords

School of Nursing and Midwifery Faculty of Health 2023-01-13 Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review Bruce Burnett Shang Ming Zhou School of Nursing and Midwifery Sinead Brophy Phil Davies Paul Ellis et al. See next page for additional authors Let us know how access to this document benefits you General rights All content in PEARL is protected by copyright law. Author manuscripts are made available in accordance with publisher policies. Please cite only the published version using the details provided on the item record or document. In the absence of an open licence (e.g. Creative Commons), permissions for further reuse of content should be sought from the publisher or author. Take down policy If you believe that this document breaches copyright please contact the library providing details, and we will remove access to the work immediately and investigate your claim. Follow this and additional works at: [https://pearl.plymouth.ac.uk/nm-research](https://pearl.plymouth.ac.uk/nm-research) Recommended Citation Burnett, B., Zhou, S., Brophy, S., Davies, P., Ellis, P., Kennedy, J., Bandyopadhyay, A., Parker, M., & Lyons, R.(2023) 'Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review', Diagnostics, 13(2) . Available at: [https://doi.org/10.3390/diagnostics13020301](https://doi.org/10.3390/diagnostics13020301) This Article is brought to you for free and open access by the Faculty of Health at PEARL. It has been accepted for inclusion in School of Nursing and Midwifery by an authorized administrator of PEARL. For more information, please [contact](contact openresearch@plymouth.ac.uk)[ openresearch@plymouth.ac.uk](contact openresearch@plymouth.ac.uk). Authors Bruce Burnett, Shang Ming Zhou, Sinead Brophy, Phil Davies, Paul Ellis, Jonathan Kennedy, Amrita Bandyopadhyay, Michael Parker, and Ronan A. Lyons This article is available at PEARL: [https://pearl.plymouth.ac.uk/nm-research/529](https://pearl.plymouth.ac.uk/nm-research/529) diagnostics Review Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review Bruce Burnett 1, Shang-Ming Zhou 2, *, Sinead Brophy 1, Phil Davies 3, Paul Ellis 3, Jonathan Kennedy 1, Amrita Bandyopadhyay 1, Michael Parker 1 and Ronan A. Lyons 1 Citation: Burnett, B.; Zhou, S.-M.; Brophy, S.; Davies, P.; Ellis, P.; Kennedy, J.; Bandyopadhyay, A.; Parker, M.; Lyons, R.A. Machine Learning in Colorectal Cancer Risk Prediction from Routinely Collected Data: A Review. Diagnostics 2023, 13, 301. [https://doi.org/10.3390/](https://doi.org/10.3390/)[ ](https://doi.org/10.3390/)diagnostics13020301 Academic Editor: Sameer Antani Received: 17 November 2022 Revised: 5 January 2023 Accepted: 7 January 2023 Published: 13 January 2023 Copyright: © 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license ([https://](https://)[ ](https://)[creativecommons.org/licenses/by/](creativecommons.org/licenses/by/)[ ](creativecommons.org/licenses/by/)[4.0/](4.0/)) . 1 Swansea University Medical School, Swansea SA2 8PP, UK 2 Faculty of Health, University of Plymouth, Plymouth PL4 8AA, UK 3 Clinithink Ltd., Bridgend CF31 1LH, UK * Correspondence: [shangming.zhou@plymouth.ac.uk or](shangming.zhou@plymouth.ac.uk or) [smzhou@ieee.org](smzhou@ieee.org) Abstract: The inclusion of machine-learning-derived models in systematic reviews of risk prediction models for colorectal cancer is rare. Whilst such reviews have highlighted methodological issues and limited performance of the models included, it is unclear why machine-learning-derived models are absent and whether such models suffer similar methodological problems. This scoping review aims to identify machine-learning models, assess their methodology, and compare t

FAQs

What gap does the review address about machine-learning models in colorectal cancer risk prediction?

The review addresses why machine-learning-derived models are rarely included in systematic reviews and whether they exhibit similar methodological problems to non-machine-learning models.

How was the scoping review conducted?

A literature search of four databases was performed for colorectal cancer prediction and prognosis publications that included at least one machine-learning model, and 14 publications were included.

What were the main findings regarding methodology and performance?

Machine-learning models showed similar methodological problems to those seen in reviews of non-machine-learning models, though overall model performance was better.

Sep 17, 2026

Uploaded by Jiven