The University of Southampton
University of Southampton Institutional Repository

Machine learning to predict early recurrence after oesophageal cancer surgery

Machine learning to predict early recurrence after oesophageal cancer surgery
Machine learning to predict early recurrence after oesophageal cancer surgery

Background: Early cancer recurrence after oesophagectomy is a common problem, with an incidence of 20–30 per cent despite the widespread use of neoadjuvant treatment. Quantification of this risk is difficult and existing models perform poorly. This study aimed to develop a predictive model for early recurrence after surgery for oesophageal adenocarcinoma using a large multinational cohort and machine learning approaches. Methods: Consecutive patients who underwent oesophagectomy for adenocarcinoma and had neoadjuvant treatment in one Dutch and six UK oesophagogastric units were analysed. Using clinical characteristics and postoperative histopathology, models were generated using elastic net regression (ELR) and the machine learning methods random forest (RF) and extreme gradient boosting (XGB). Finally, a combined (ensemble) model of these was generated. The relative importance of factors to outcome was calculated as a percentage contribution to the model. Results: A total of 812 patients were included. The recurrence rate at less than 1 year was 29·1 per cent. All of the models demonstrated good discrimination. Internally validated areas under the receiver operating characteristic (ROC) curve (AUCs) were similar, with the ensemble model performing best (AUC 0·791 for ELR, 0·801 for RF, 0·804 for XGB, 0·805 for ensemble). Performance was similar when internal–external validation was used (validation across sites, AUC 0·804 for ensemble). In the final model, the most important variables were number of positive lymph nodes (25·7 per cent) and lymphovascular invasion (16·9 per cent). Conclusion: The model derived using machine learning approaches and an international data set provided excellent performance in quantifying the risk of early recurrence after surgery, and will be useful in prognostication for clinicians and patients.

0007-1323
1042-1052
Rahman, Saqib, Andrew
80f270ce-6283-4af9-83c0-6f3242e22791
Walker, Robert
c8fbfe1c-349d-497f-b24e-0295c84c4634
Lloyd, Megan
5325a2c4-a0dc-4c99-88ad-a5adfab5c258
Grace, Ben L
1d477b43-87f8-461f-ba91-782c37cd1837
van Boxel, Gijs
805263ef-b4e1-4f29-9b95-108c0c3d1b1b
Kingma, B.Feike
72cf93be-0bfd-460c-82f9-f7f0425212d3
Ruurda, Jelle P
c6ba7807-16d1-4ee3-a1cd-1f081005069c
van Hillegersberg, Richard
6194c82d-0673-47ce-bbd6-6c37bbb445ff
Harris, Scott
5a50d54f-f7b9-47ff-8fa6-112b2077bc59
Parsons, Simon
641a27ab-f6f3-4325-bfd0-5bb4dcd45a7b
Mercer, Stuart
af593340-9bff-4e5d-89c7-7a77d369b9e9
Griffiths, Ewen A
4488f717-0b5f-4203-b0fd-15f084110442
o'neill, J.Robert
04dc738e-602a-4427-8ee5-0018c30fc4ff
Turkington, Richard
21b3c462-6852-4b3c-af20-5dff17862779
Fitzgerald, Rebecca
51acda24-0da7-4ab1-b94b-f84cebbd202c
Underwood, Timothy
8e81bf60-edd2-4b0e-8324-3068c95ea1c6
Rahman, Saqib, Andrew
80f270ce-6283-4af9-83c0-6f3242e22791
Walker, Robert
c8fbfe1c-349d-497f-b24e-0295c84c4634
Lloyd, Megan
5325a2c4-a0dc-4c99-88ad-a5adfab5c258
Grace, Ben L
1d477b43-87f8-461f-ba91-782c37cd1837
van Boxel, Gijs
805263ef-b4e1-4f29-9b95-108c0c3d1b1b
Kingma, B.Feike
72cf93be-0bfd-460c-82f9-f7f0425212d3
Ruurda, Jelle P
c6ba7807-16d1-4ee3-a1cd-1f081005069c
van Hillegersberg, Richard
6194c82d-0673-47ce-bbd6-6c37bbb445ff
Harris, Scott
5a50d54f-f7b9-47ff-8fa6-112b2077bc59
Parsons, Simon
641a27ab-f6f3-4325-bfd0-5bb4dcd45a7b
Mercer, Stuart
af593340-9bff-4e5d-89c7-7a77d369b9e9
Griffiths, Ewen A
4488f717-0b5f-4203-b0fd-15f084110442
o'neill, J.Robert
04dc738e-602a-4427-8ee5-0018c30fc4ff
Turkington, Richard
21b3c462-6852-4b3c-af20-5dff17862779
Fitzgerald, Rebecca
51acda24-0da7-4ab1-b94b-f84cebbd202c
Underwood, Timothy
8e81bf60-edd2-4b0e-8324-3068c95ea1c6

Rahman, Saqib, Andrew, Walker, Robert, Lloyd, Megan, Grace, Ben L, van Boxel, Gijs, Kingma, B.Feike, Ruurda, Jelle P, van Hillegersberg, Richard, Harris, Scott, Parsons, Simon, Mercer, Stuart, Griffiths, Ewen A, o'neill, J.Robert, Turkington, Richard, Fitzgerald, Rebecca and Underwood, Timothy (2020) Machine learning to predict early recurrence after oesophageal cancer surgery. British Journal of Surgery, 107 (8), 1042-1052. (doi:10.1002/bjs.11461).

Record type: Article

Abstract

Background: Early cancer recurrence after oesophagectomy is a common problem, with an incidence of 20–30 per cent despite the widespread use of neoadjuvant treatment. Quantification of this risk is difficult and existing models perform poorly. This study aimed to develop a predictive model for early recurrence after surgery for oesophageal adenocarcinoma using a large multinational cohort and machine learning approaches. Methods: Consecutive patients who underwent oesophagectomy for adenocarcinoma and had neoadjuvant treatment in one Dutch and six UK oesophagogastric units were analysed. Using clinical characteristics and postoperative histopathology, models were generated using elastic net regression (ELR) and the machine learning methods random forest (RF) and extreme gradient boosting (XGB). Finally, a combined (ensemble) model of these was generated. The relative importance of factors to outcome was calculated as a percentage contribution to the model. Results: A total of 812 patients were included. The recurrence rate at less than 1 year was 29·1 per cent. All of the models demonstrated good discrimination. Internally validated areas under the receiver operating characteristic (ROC) curve (AUCs) were similar, with the ensemble model performing best (AUC 0·791 for ELR, 0·801 for RF, 0·804 for XGB, 0·805 for ensemble). Performance was similar when internal–external validation was used (validation across sites, AUC 0·804 for ensemble). In the final model, the most important variables were number of positive lymph nodes (25·7 per cent) and lymphovascular invasion (16·9 per cent). Conclusion: The model derived using machine learning approaches and an international data set provided excellent performance in quantifying the risk of early recurrence after surgery, and will be useful in prognostication for clinicians and patients.

Text
manuscript_rev.1 - Accepted Manuscript
Download (384kB)
Text
manuscripttables_rev1 - Accepted Manuscript
Download (153kB)
Image
Figure 1 - Consort - Accepted Manuscript
Download (613kB)
Image
Figure 2 - Internal Validation - Accepted Manuscript
Download (2MB)
Image
Figure3 - Calibration - Accepted Manuscript
Download (1MB)

Show all 5 downloads.

More information

Accepted/In Press date: 13 November 2019
e-pub ahead of print date: 30 January 2020
Published date: 1 July 2020
Additional Information: © 2020 The Authors. BJS published by John Wiley & Sons Ltd on behalf of BJS Society Ltd.

Identifiers

Local EPrints ID: 436107
URI: http://eprints.soton.ac.uk/id/eprint/436107
ISSN: 0007-1323
PURE UUID: 8c416976-83b6-44a9-95a7-6709d08beeb3
ORCID for Timothy Underwood: ORCID iD orcid.org/0000-0001-9455-2188

Catalogue record

Date deposited: 28 Nov 2019 17:30
Last modified: 17 Mar 2024 05:04

Export record

Altmetrics

Contributors

Author: Saqib, Andrew Rahman
Author: Robert Walker
Author: Megan Lloyd
Author: Ben L Grace
Author: Gijs van Boxel
Author: B.Feike Kingma
Author: Jelle P Ruurda
Author: Richard van Hillegersberg
Author: Scott Harris
Author: Simon Parsons
Author: Stuart Mercer
Author: Ewen A Griffiths
Author: J.Robert o'neill
Author: Richard Turkington
Author: Rebecca Fitzgerald

Download statistics

Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.

View more statistics

Atom RSS 1.0 RSS 2.0

Contact ePrints Soton: eprints@soton.ac.uk

ePrints Soton supports OAI 2.0 with a base URL of http://eprints.soton.ac.uk/cgi/oai2

This repository has been built using EPrints software, developed at the University of Southampton, but available to everyone to use.

We use cookies to ensure that we give you the best experience on our website. If you continue without changing your settings, we will assume that you are happy to receive cookies on the University of Southampton website.

×