Deep learning vs conventional learning algorithms for clinical prediction in Crohn's disease: A proof-of-concept study

作     者：Danny Con Daniel R van Langenberg Abhinav Vasudevan 

作者机构：Department of Gastroenterology and HepatologyEastern HealthBox Hill 3128VictoriaAustralia Faculty of MedicineNursing and Health SciencesMonash UniversityBox Hill 3128VictoriaAustralia 

出 版 物：《World Journal of Gastroenterology》 (世界胃肠病学杂志（英文版）)

年 卷 期：2021年第27卷第38期

页      面：6476-6488页

核心收录：

学科分类：1002[医学-临床医学] 100201[医学-内科学(含：心血管病、血液病、呼吸系病、消化系病、内分泌与代谢病、肾病、风湿病、传染病)] 10[医学] 

主　　题：Machine learning Artificial intelligence Precision medicine Personalized medicine Deep learning 

摘      要：BACKGROUND Traditional methods of developing predictive models in inflammatory bowel diseases(IBD)rely on using statistical regression approaches to deriving clinical scores such as the Crohn s disease(CD)activity ***,traditional approaches are unable to take advantage of more complex data structures such as repeated *** learning methods have the potential ability to automatically find and learn complex,hidden relationships between predictive markers and outcomes,but their application to clinical prediction in CD and IBD has not been explored *** To determine and compare the utility of deep learning with conventional algorithms in predicting response to anti-tumor necrosis factor(anti-TNF)therapy in *** This was a retrospective single-center cohort study of all CD patients who commenced anti-TNF therapy(either adalimumab or infliximab)from January 1,2010 to December 31,*** was defined as a C-reactive protein(CRP)5 mg/L at 12 mo after anti-TNF *** supervised learning algorithms were compared:(1)A conventional statistical learning algorithm using multivariable logistic regression on baseline data only;(2)A deep learning algorithm using a feed-forward artificial neural network on baseline data only;and(3)A deep learning algorithm using a recurrent neural network on repeated *** performance was assessed using area under the receiver operator characteristic curve(AUC)after 10×repeated 5-fold *** A total of 146 patients were included(median age 36 years,48%male).Concomitant therapy at anti-TNF commencement included thiopurines(68%),methotrexate(18%),corticosteroids(44%)and aminosalicylates(33%).After 12 mo,64%had CRP5 mg/*** conventional learning algorithm selected the following baseline variables for the predictive model:Complex disease behavior,albumin,monocytes,lymphocytes,mean corpuscular hemoglobin concentration and gamma-glutamyl transferase,and had a cross-valid