Back to Search Start Over

Development and validation of a risk prediction model to diagnose Barrett's oesophagus (MARK-BE): a case-control machine learning approach

Authors :
Avi Rosenfeld, PhD
David G Graham, MBBS
Sarah Jevons, PhD
Jose Ariza, RGN
Daryl Hagan, MSc
Ash Wilson, BSc
Samuel J Lovat
Sarmed S Sami, MBBS
Omer F Ahmad, MBBS
Marco Novelli, ProfMBChB
Manuel Rodriguez Justo, MBBS
Alison Winstanley, MBBS
Eliyahu M Heifetz, PhD
Mordehy Ben-Zecharia, PhD
Uria Noiman, PhD
Rebecca C Fitzgerald, ProfMBChB
Peter Sasieni, ProfPhD
Laurence B Lovat, ProfMBBS
Karen Coker
Wanfeng Zhao
Kathryn Brown
Beverley Haynes
Tara Nuckcheddy Grant
Massimiliano di Pietro
Eleanor Dewhurst
Bincy Alias
Leanne Mills
Caroline Wilson
Elizabeth Bird-Lieberman
Jan Bornschein
Yean Lim
Kareem Shariff
Roberto Cayado Lopez
Myrna Udarbe
Claire Shaw
Glynis Rose
Ian Sargeant
M Al-Izzi
Roisin Schimmel
Elizabeth Green
Morgan Moorghen
Reshma Kanani
Mariann Baulf
Jayne Butcher
Adil Butt
Steve Bown
Gideon Lipman
Rami Sweis
Vinay Sehgal
Matthew Banks
Rehan Haidry
John Louis-Auguste
Darina Kohoutova
Sarah Kerr
Victor Eneh
Nigel Butter
Haroon Miah
Rommel Butawan
Grace Adesina
Sabrina Holohan
Joan Idris
Nick Hayes
Shajahan Wahed
Nelson Kath Houghton
Marc Hopton
Anne Eastick
Debasis Majumdar
Kassem Manuf
Lyndsey Fieldson
Helen Bailey
Jacobo Fernandez-Sordo Ortiz
Mina Patel
Suzanne Henry
Samantha Warburton
Jonathan White
Lisa Gadeke
Beverley Longhurst
Richmond Abeseabe
Peter Basford
Rupam Bhattacharyya
Scott Elliot
Roisin Bevan
Carly Brown
Philippa Laverick
Gayle Clifford
Anita Gibbons
Julie Ingmire
Abdullah Mawas
Jacquelyn Harvey
Sharon Cave
Source :
The Lancet: Digital Health, Vol 2, Iss 1, Pp e37-e48 (2020)
Publication Year :
2020
Publisher :
Elsevier, 2020.

Abstract

Summary: Background: Screening for Barrett's oesophagus relies on endoscopy, which is invasive and few who undergo the procedure are found to have the condition. We aimed to use machine learning techniques to develop and externally validate a simple risk prediction panel to screen individuals for Barrett's oesophagus. Methods: In this prospective study, machine learning risk prediction in Barrett's oesophagus (MARK-BE), we used data from two case-control studies, BEST2 and BOOST, to compile training and validation datasets. From the BEST2 study, we analysed questionnaires from 1299 patients, of whom 880 (67·7%) had Barrett's oesophagus, including 40 with invasive oesophageal adenocarcinoma, and 419 (32·3%) were controls. We randomly split (6:4) the cohort using a computer algorithm into a training dataset of 776 patients and a testing dataset of 523 patients. We compiled an external validation cohort from the BOOST study, which included 398 patients, comprising 198 patients with Barrett's oesophagus (23 with oesophageal adenocarcinoma) and 200 controls. We identified independently important diagnostic features of Barrett's oesophagus using the machine learning techniques information gain and correlation-based feature selection. We assessed multiple classification tools to create a multivariable risk prediction model. Internal validation of the model using the BEST2 testing dataset was followed by external validation using the BOOST external validation dataset. From these data we created a prediction panel to identify at-risk individuals. Findings: The BEST2 study included 40 diagnostic features. Of these, 19 added information gain but after correlation-based feature selection only eight showed independent diagnostic value including age, sex, cigarette smoking, waist circumference, frequency of stomach pain, duration of heartburn and acidic taste, and taking antireflux medication, of which all were associated with increased risk of Barrett's oesophagus, except frequency of stomach pain, with was inversely associated in a case-control population. Logistic regression offered the highest prediction quality with an area under the receiver-operator curve (AUC) of 0·87 (95% CI 0·84–0·90; sensitivity set at 90%; specificity of 68%). In the testing dataset, AUC was 0·86 (0·83–0·89; sensitivity set at 90%; specificity of 65%). In the external validation dataset, the AUC was 0·81 (0·74–0·84; sensitivity set at 90%; specificity of 58%). Interpretation: Our diagnostic model offers valid predictions of diagnosis of Barrett's oesophagus in patients with symptomatic gastro-oesophageal reflux disease, assisting in identifying who should go forward to invasive confirmatory testing. Our predictive panel suggests that overweight men who have been taking antireflux medication for a long time might merit particular consideration for further testing. Our risk prediction panel is quick and simple to administer but will need further calibration and validation in a prospective study in primary care. Funding: Charles Wolfson Charitable Trust and Guts UK.

Details

Language :
English
ISSN :
25897500
Volume :
2
Issue :
1
Database :
Directory of Open Access Journals
Journal :
The Lancet: Digital Health
Publication Type :
Academic Journal
Accession number :
edsdoj.1c2697d1f57456aa1b1b0078466e610
Document Type :
article
Full Text :
https://doi.org/10.1016/S2589-7500(19)30216-X