A K Waljee1,2, B Liu3, K Sauder2, J Zhu3, S M Govani2, R W Stidham2, P D R Higgins2. 1. VA Center for Clinical Management Research, VA Ann Arbor Health Care System, Ann Arbor, MI, USA. 2. Division of Gastroenterology and Hepatology, Department of Internal Medicine, University of Michigan Health System, Ann Arbor, MI, USA. 3. Department of Statistics, University of Michigan, Ann Arbor, MI, USA.
Abstract
BACKGROUND: Vedolizumab is an effective therapy for ulcerative colitis (UC), but costly and slow to work. New clinical responses occur after 30 weeks of therapy. AIMS: To enable physicians, patients, and insurers to predict whether a patient with UC will respond to vedolizumab at an early time point after starting therapy. METHODS: The clinical study data request website provided the phase 3 clinical trial data for vedolizumab. Random forest models were trained on 70% and tested on 30% of the data to predict corticosteroid-free endoscopic remission at week 52. Models were constructed using baseline data, or data through week 6 of vedolizumab therapy from 491 subjects. RESULTS: The AuROC for prediction of corticosteroid-free endoscopic remission at week 52 using baseline data was only 0.62 (95% CI: 0.53-0.72), but was 0.73 (95% CI: 0.65-0.82) when using data through week 6. A total of 47% of subjects were predicted to be remitters, and 59% of these subjects achieved corticosteroid-free endoscopic remission, in contrast to 21% of the predicted non-remitters. A week 6 prediction using FCP ≤234 μg/g was nearly as accurate. CONCLUSIONS: A machine learning algorithm using laboratory data through week 6 of vedolizumab therapy was able to accurately identify which UC patients would achieve corticosteroid-free endoscopic remission on vedolizumab at week 52. Application of this algorithm could have significant implications for clinical decisions on whom to continue on this costly medication when the benefits of the vedolizumab are not clinically apparent in the first 6 weeks of therapy.
BACKGROUND:Vedolizumab is an effective therapy for ulcerative colitis (UC), but costly and slow to work. New clinical responses occur after 30 weeks of therapy. AIMS: To enable physicians, patients, and insurers to predict whether a patient with UC will respond to vedolizumab at an early time point after starting therapy. METHODS: The clinical study data request website provided the phase 3 clinical trial data for vedolizumab. Random forest models were trained on 70% and tested on 30% of the data to predict corticosteroid-free endoscopic remission at week 52. Models were constructed using baseline data, or data through week 6 of vedolizumab therapy from 491 subjects. RESULTS: The AuROC for prediction of corticosteroid-free endoscopic remission at week 52 using baseline data was only 0.62 (95% CI: 0.53-0.72), but was 0.73 (95% CI: 0.65-0.82) when using data through week 6. A total of 47% of subjects were predicted to be remitters, and 59% of these subjects achieved corticosteroid-free endoscopic remission, in contrast to 21% of the predicted non-remitters. A week 6 prediction using FCP ≤234 μg/g was nearly as accurate. CONCLUSIONS: A machine learning algorithm using laboratory data through week 6 of vedolizumab therapy was able to accurately identify which UC patients would achieve corticosteroid-free endoscopic remission on vedolizumab at week 52. Application of this algorithm could have significant implications for clinical decisions on whom to continue on this costly medication when the benefits of the vedolizumab are not clinically apparent in the first 6 weeks of therapy.
Authors: R W Stidham; T C H Lee; P D R Higgins; A R Deshpande; D A Sussman; A G Singal; B J Elmunzer; S D Saini; S Vijan; A K Waljee Journal: Aliment Pharmacol Ther Date: 2014-02-09 Impact factor: 8.171
Authors: A Amiot; M Serrero; L Peyrin-Biroulet; J Filippi; B Pariente; X Roblin; A Buisson; C Stefanescu; C Trang-Poisson; R Altwegg; P Marteau; T Vaysse; A Bourrier; S Nancey; D Laharie; M Allez; G Savoye; J Moreau; L Vuitton; S Viennot; A Aubourg; A-L Pelletier; G Bouguen; V Abitbol; C Gagniere; Y Bouhnik Journal: Aliment Pharmacol Ther Date: 2017-06-08 Impact factor: 8.171
Authors: A Stallmach; C Langbein; R Atreya; T Bruns; A Dignass; K Ende; J Hampe; F Hartmann; M F Neurath; J Maul; J C Preiss; R Schmelz; B Siegmund; H Schulze; N Teich; U von Arnim; D C Baumgart; C Schmidt Journal: Aliment Pharmacol Ther Date: 2016-10-07 Impact factor: 8.171
Authors: Brian G Feagan; Paul Rutgeerts; Bruce E Sands; Stephen Hanauer; Jean-Frédéric Colombel; William J Sandborn; Gert Van Assche; Jeffrey Axler; Hyo-Jong Kim; Silvio Danese; Irving Fox; Catherine Milch; Serap Sankoh; Tim Wyant; Jing Xu; Asit Parikh Journal: N Engl J Med Date: 2013-08-22 Impact factor: 91.245
Authors: R W Stidham; T C H Lee; P D R Higgins; A R Deshpande; D A Sussman; A G Singal; B J Elmunzer; S D Saini; S Vijan; A K Waljee Journal: Aliment Pharmacol Ther Date: 2014-04-20 Impact factor: 8.171
Authors: Parambir S Dulai; Siddharth Singh; Xiaoqian Jiang; Farhad Peerani; Neeraj Narula; Khadija Chaudrey; Diana Whitehead; David Hudesman; Dana Lukin; Arun Swaminath; Eugenia Shmidt; Shuang Wang; Brigid S Boland; John T Chang; Sunanda Kane; Corey A Siegel; Edward V Loftus; William J Sandborn; Bruce E Sands; Jean-Frederic Colombel Journal: Am J Gastroenterol Date: 2016-06-14 Impact factor: 12.045
Authors: S Kurnool; N H Nguyen; J Proudfoot; P S Dulai; B S Boland; N Vande Casteele; E Evans; E L Grunvald; A Zarrinpar; W J Sandborn; S Singh Journal: Aliment Pharmacol Ther Date: 2018-04-17 Impact factor: 8.171
Authors: Matthias Breidert; Pierre Eftekhari; François Louis; Claudia Rotoiu; Timo Rath; Markus F Neurath; Raja Atreya Journal: Crohns Colitis 360 Date: 2020-05-24
Authors: Nikolas Plevris; Philip W Jenkinson; Cher S Chuah; Mathew Lyons; Lynne M Merchant; Rebecca J Pattenden; Ian D Arnott; Gareth R Jones; Charlie W Lees Journal: Frontline Gastroenterol Date: 2019-07-03
Authors: Shirley Cohen-Mekelburg; Sameer Berry; Ryan W Stidham; Ji Zhu; Akbar K Waljee Journal: J Gastroenterol Hepatol Date: 2021-02 Impact factor: 4.029