Using Interpretable Machine Learning to Identify Baseline Predictive Factors of Remission and Drug Durability in Crohn’s Disease Patients on Ustekinumab
María Chaparro, Iria Bastón‐Rey, Estela Fernández Salgado, Javier González García, Laura Ramos, María Teresa Diz-Lois Palomares, Federico Argüelles‐Arias, Eva Iglesias Flores, Mercedes Cabello, Saioa Rubio Iturria, Andrea Núñez Ortiz, Mara Charro, Daniel Ginard, Carmen Dueñas Sadornil, Olga Merino Ochoa, David Busquets, Eduardo Iyo, Ana Gutiérrez, Patricia Ramírez de la Piscina, Marta Maia Boscá-Watts, M Arroyo, María José García, Esther Hinojosa, Jordi Gordillo, P Martínez Montiel, Benito Velayos Jiménez, Cristina Quílez Ivorra, Juan María Vázquez Morón, José María Huguet, Yago González‐Lama, Ana Isabel Muñagorri Santos, V Amo, María Dolores Martín‐Arranz, Fernando Bermejo, J Martínez Cadilla, Cristina Rubín de Célix, Paola Fradejas Salazar, Antonio Román, Nuria Jiménez, Santiago García‐López, Anna Figuerola, I Jiménez, F. Cerezo, Carlos Taxonera, Pilar Varela, Ruth de Francisco, David Monfort, G Molina Arriero, Alejandro Hernández-Camba, Francisco J. Garcı́a Alonso, Manuel Van Domselaar, R. Pajares-Villarroya, Alejandro Mena Nunez, Francisco Rodríguez‐Moranta, Ignacio Marín‐Jiménez, Virginia Robles Alonso, María del Mar Martín Rodríguez, Patricia Camo-Monterde, Iván García Tercero, Mercè Navarro‐Llavat, Lara Arias, Daniel Hervías Cruz, Sebastian Kloss, Alun Passey, Cynthia Novella, Eugenia Vispo, Manuel Barreiro‐de Acosta, Javier P. Gisbert
Abstract
Ustekinumab has shown efficacy in Crohn's Disease (CD) patients. To identify patient profiles of those who benefit the most from this treatment would help to position this drug in the therapeutic paradigm of CD and generate hypotheses for future trials. The objective of this analysis was to determine whether baseline patient characteristics are predictive of remission and the drug durability of ustekinumab, and whether its positioning with respect to prior use of biologics has a significant effect after correcting for disease severity and phenotype at baseline using interpretable machine learning. Patients' data from SUSTAIN, a retrospective multicenter single-arm cohort study, were used. Disease phenotype, baseline laboratory data, and prior treatment characteristics were documented. Clinical remission was defined as the Harvey Bradshaw Index ≤ 4 and was tracked longitudinally. Drug durability was defined as the time until a patient discontinued treatment. A total of 439 participants from 60 centers were included and a total of 20 baseline covariates considered. Less exposure to previous biologics had a positive effect on remission, even after controlling for baseline disease severity using a non-linear, additive, multivariable model. Additionally, age, body mass index, and fecal calprotectin at baseline were found to be statistically significant as independent negative risk factors for both remission and drug survival, with further risk factors identified for remission.