Nghia H Nguyen1, Dominic Picetti1, Parambir S Dulai1, Vipul Jairath2,3, William J Sandborn1, Lucila Ohno-Machado4, Peter L Chen5, Siddharth Singh1,4. 1. Division of Gastroenterology, Department of Medicine, University of California San Diego, La Jolla, CA, USA. 2. Department of Epidemiology and Biostatistics, Western University, London, ON, Canada. 3. Division of Gastroenterology, Western University, London, ON, Canada. 4. Division of Biomedical Informatics, University of California San Diego, La Jolla, CA, USA. 5. HyperPlanar, San Diego, CA, USA.
Abstract
BACKGROUND AND AIMS: There is increasing interest in machine learning-based prediction models in inflammatory bowel diseases [IBD]. We synthesised and critically appraised studies comparing machine learning vs traditional statistical models, using routinely available clinical data for risk prediction in IBD. METHODS: Through a systematic review till January 1, 2021, we identified cohort studies that derived and/or validated machine learning models, based on routinely collected clinical data in patients with IBD, to predict the risk of harbouring or developing adverse clinical outcomes, and reported its predictive performance against a traditional statistical model for the same outcome. We appraised the risk of bias in these studies using the Prediction model Risk of Bias ASsessment [PROBAST] tool. RESULTS: We included 13 studies on machine learning-based prediction models in IBD, encompassing themes of predicting treatment response to biologics and thiopurines and predicting longitudinal disease activity and complications and outcomes in patients with acute severe ulcerative colitis. The most common machine learning models used were tree-based algorithms, which are classification approaches achieved through supervised learning. Machine learning models outperformed traditional statistical models in risk prediction. However, most models were at high risk of bias, and only one was externally validated. CONCLUSIONS: Machine learning-based prediction models based on routinely collected data generally perform better than traditional statistical models in risk prediction in IBD, though frequently have high risk of bias. Future studies examining these approaches are warranted, with special focus on external validation and clinical applicability.
BACKGROUND AND AIMS: There is increasing interest in machine learning-based prediction models in inflammatory bowel diseases [IBD]. We synthesised and critically appraised studies comparing machine learning vs traditional statistical models, using routinely available clinical data for risk prediction in IBD. METHODS: Through a systematic review till January 1, 2021, we identified cohort studies that derived and/or validated machine learning models, based on routinely collected clinical data in patients with IBD, to predict the risk of harbouring or developing adverse clinical outcomes, and reported its predictive performance against a traditional statistical model for the same outcome. We appraised the risk of bias in these studies using the Prediction model Risk of Bias ASsessment [PROBAST] tool. RESULTS: We included 13 studies on machine learning-based prediction models in IBD, encompassing themes of predicting treatment response to biologics and thiopurines and predicting longitudinal disease activity and complications and outcomes in patients with acute severe ulcerative colitis. The most common machine learning models used were tree-based algorithms, which are classification approaches achieved through supervised learning. Machine learning models outperformed traditional statistical models in risk prediction. However, most models were at high risk of bias, and only one was externally validated. CONCLUSIONS: Machine learning-based prediction models based on routinely collected data generally perform better than traditional statistical models in risk prediction in IBD, though frequently have high risk of bias. Future studies examining these approaches are warranted, with special focus on external validation and clinical applicability.
Authors: Klaus Gottlieb; Simon Travis; Brian Feagan; Fez Hussain; William J Sandborn; Paul Rutgeerts Journal: Inflamm Bowel Dis Date: 2015-10 Impact factor: 5.325
Authors: Akbar K Waljee; Joel C Joyce; Sijian Wang; Aditi Saxena; Margaret Hart; Ji Zhu; Peter D R Higgins Journal: Clin Gastroenterol Hepatol Date: 2009-10-14 Impact factor: 11.382
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; Beth I Wallace; Shirley Cohen-Mekelburg; Yumu Liu; Boang Liu; Kay Sauder; Ryan W Stidham; Ji Zhu; Peter D R Higgins Journal: JAMA Netw Open Date: 2019-05-03
Authors: Cláudia Camila Dias; Pedro Pereira Rodrigues; Rosa Coelho; Paula Moura Santos; Samuel Fernandes; Paula Lago; Cidalina Caetano; Ângela Rodrigues; Francisco Portela; Ana Oliveira; Paula Ministro; Eugénia Cancela; Ana Isabel Vieira; Rita Barosa; José Cotter; Pedro Carvalho; Isabelle Cremers; Daniel Trabulo; Paulo Caldeira; Artur Antunes; Isadora Rosa; Joana Moleiro; Paula Peixe; Rita Herculano; Raquel Gonçalves; Bruno Gonçalves; Helena Tavares Sousa; Luís Contente; Henrique Morna; Susana Lopes; Fernando Magro Journal: J Crohns Colitis Date: 2017-04-01 Impact factor: 9.071