Akbar K Waljee1,2,3, Rachel Lipson1, Wyndy L Wiitala1, Yiwei Zhang4, Boang Liu4, Ji Zhu4, Beth Wallace5,3, Shail M Govani2,3, Ryan W Stidham2, Rodney Hayward1,6,3, Peter D R Higgins2. 1. VA Center for Clinical Management Research, VA Ann Arbor Health Care System, Ann Arbor, Michigan. 2. Division of Gastroenterology and Hepatology, Department of Internal Medicine, University of Michigan Health System, Ann Arbor, Michigan. 3. University of Michigan Medical School, Institute for Healthcare Policy and Innovation, Ann Arbor, Michigan. 4. Department of Statistics, University of Michigan, Ann Arbor, Michigan. 5. Division of Rheumatology, Department of Internal Medicine, University of Michigan Health System, Ann Arbor, Michigan. 6. Division of General Medicine, Department of Internal Medicine, University of Michigan Health System, Ann Arbor, Michigan.
Abstract
Background: Inflammatory bowel disease (IBD) is a chronic disease characterized by unpredictable episodes of flares and periods of remission. Tools that accurately predict disease course would substantially aid therapeutic decision-making. This study aims to construct a model that accurately predicts the combined end point of outpatient corticosteroid use and hospitalizations as a surrogate for IBD flare. Methods: Predictors evaluated included age, sex, race, use of corticosteroid-sparing immunosuppressive medications (immunomodulators and/or anti-TNF), longitudinal laboratory data, and number of previous IBD-related hospitalizations and outpatient corticosteroid prescriptions. We constructed models using logistic regression and machine learning methods (random forest [RF]) to predict the combined end point of hospitalization and/or corticosteroid use for IBD within 6 months. Results: We identified 20,368 Veterans Health Administration patients with the first (index) IBD diagnosis between 2002 and 2009. Area under the receiver operating characteristic curve (AuROC) for the baseline logistic regression model was 0.68 (95% confidence interval [CI], 0.67-0.68). AuROC for the RF longitudinal model was 0.85 (95% CI, 0.84-0.85). AuROC for the RF longitudinal model using previous hospitalization or steroid use was 0.87 (95% CI, 0.87-0.88). The 5 leading independent risk factors for future hospitalization or steroid use were age, mean serum albumin, immunosuppressive medication use, and mean and highest platelet counts. Previous hospitalization and corticosteroid use were highly predictive when included in specified models. Conclusions: A novel machine learning model substantially improved our ability to predict IBD-related hospitalization and outpatient steroid use. This model could be used at point of care to distinguish patients at high and low risk for disease flare, allowing individualized therapeutic management. Published by Oxford University Press on behalf of Crohn’s & Colitis Foundation of America 2017.
Background: Inflammatory bowel disease (IBD) is a chronic disease characterized by unpredictable episodes of flares and periods of remission. Tools that accurately predict disease course would substantially aid therapeutic decision-making. This study aims to construct a model that accurately predicts the combined end point of outpatient corticosteroid use and hospitalizations as a surrogate for IBD flare. Methods: Predictors evaluated included age, sex, race, use of corticosteroid-sparing immunosuppressive medications (immunomodulators and/or anti-TNF), longitudinal laboratory data, and number of previous IBD-related hospitalizations and outpatient corticosteroid prescriptions. We constructed models using logistic regression and machine learning methods (random forest [RF]) to predict the combined end point of hospitalization and/or corticosteroid use for IBD within 6 months. Results: We identified 20,368 Veterans Health Administration patients with the first (index) IBD diagnosis between 2002 and 2009. Area under the receiver operating characteristic curve (AuROC) for the baseline logistic regression model was 0.68 (95% confidence interval [CI], 0.67-0.68). AuROC for the RF longitudinal model was 0.85 (95% CI, 0.84-0.85). AuROC for the RF longitudinal model using previous hospitalization or steroid use was 0.87 (95% CI, 0.87-0.88). The 5 leading independent risk factors for future hospitalization or steroid use were age, mean serum albumin, immunosuppressive medication use, and mean and highest platelet counts. Previous hospitalization and corticosteroid use were highly predictive when included in specified models. Conclusions: A novel machine learning model substantially improved our ability to predict IBD-related hospitalization and outpatientsteroid use. This model could be used at point of care to distinguish patients at high and low risk for disease flare, allowing individualized therapeutic management. Published by Oxford University Press on behalf of Crohn’s & Colitis Foundation of America 2017.
Authors: Javier P Gisbert; Fernando Bermejo; Jose-Lázaro Pérez-Calle; Carlos Taxonera; Isabel Vera; Adrian G McNicholl; Alicia Algaba; Pilar López; Natalia López-Palacios; Marta Calvo; Yago González-Lama; Jose-Antonio Carneros; Marta Velasco; José Maté Journal: Inflamm Bowel Dis Date: 2009-08 Impact factor: 5.325
Authors: A W Forrey; C J McDonald; G DeMoor; S M Huff; D Leavelle; D Leland; T Fiers; L Charles; B Griffin; F Stalling; A Tullis; K Hutchins; J Baenziger Journal: Clin Chem Date: 1996-01 Impact factor: 8.327
Authors: Ashwin N Ananthakrishnan; Lydia R Weber; Josh F Knox; Susan Skaros; Jeanne Emmons; Sarah Lundeen; Mazen Issa; Mary F Otterson; David G Binion Journal: Am J Gastroenterol Date: 2007-12-11 Impact factor: 10.864
Authors: Akbar K Waljee; Kay Sauder; Anand Patel; Sandeep Segar; Boang Liu; Yiwei Zhang; Ji Zhu; Ryan W Stidham; Ulysses Balis; Peter D R Higgins Journal: J Crohns Colitis Date: 2017-07-01 Impact factor: 9.071
Authors: Akbar K Waljee; Wyndy L Wiitala; Shail Govani; Ryan Stidham; Sameer Saini; Jason Hou; Linda A Feagins; Nabeel Khan; Chester B Good; Sandeep Vijan; Peter D R Higgins Journal: PLoS One Date: 2016-06-23 Impact factor: 3.240
Authors: Julia J Liu; Thomas Brent Rosson; Jesse J Xie; Zachary P Harris; Regina G McBride; Eric Siegel; Curt Hagedorn Journal: Dig Dis Sci Date: 2019-02-12 Impact factor: 3.487
Authors: David Chen; Clifton Fulmer; Ilyssa O Gordon; Sana Syed; Ryan W Stidham; Niels Vande Casteele; Yi Qin; Katherine Falloon; Benjamin L Cohen; Robert Wyllie; Florian Rieder Journal: J Crohns Colitis Date: 2022-03-14 Impact factor: 10.020
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
Authors: John Gubatan; Steven Levitte; Akshar Patel; Tatiana Balabanis; Mike T Wei; Sidhartha R Sinha Journal: World J Gastroenterol Date: 2021-05-07 Impact factor: 5.742