Yuanfang Guan1, Hongjiu Zhang1, Daniel Quang1, Ziyan Wang1, Stephen C J Parker1, Dimitrios A Pappas2, Joel M Kremer3, Fan Zhu4. 1. University of Michigan, Ann Arbor. 2. Columbia University College of Physicians and Surgeons, New York, New York, and Corrona LLC, Waltham, Massachusetts. 3. Corrona LLC, Waltham, Massachusetts, and Albany Medical College and The Center for Rheumatology, Albany, New York. 4. Chinese Academy of Sciences, Chongqing, China.
Abstract
OBJECTIVE: Accurate prediction of treatment responses in rheumatoid arthritis (RA) patients can provide valuable information on effective drug selection. Anti-tumor necrosis factor (anti-TNF) drugs are an important second-line treatment after methotrexate, the classic first-line treatment for RA. However, patient heterogeneity hinders identification of predictive biomarkers and accurate modeling of anti-TNF drug responses. This study was undertaken to investigate the usefulness of machine learning to assist in developing predictive models for treatment response. METHODS: Using data on patient demographics, baseline disease assessment, treatment, and single-nucleotide polymorphism (SNP) array from the Dialogue on Reverse Engineering Assessment and Methods (DREAM): Rheumatoid Arthritis Responder Challenge, we created a Gaussian process regression model to predict changes in the Disease Activity Score in 28 joints (DAS28) for the patients and to classify them into either the responder or the nonresponder group. This model was developed and cross-validated using data from 1,892 RA patients. It was evaluated using an independent data set from 680 patients. We examined the effectiveness of the similarity modeling and the contribution of individual features. RESULTS: In the cross-validation tests, our method predicted changes in DAS28 (ΔDAS28), with a correlation coefficient of 0.405. It correctly classified responses from 78% of patients. In the independent test, this method achieved a Pearson's correlation coefficient of 0.393 in predicting ΔDAS28. Gaussian process regression effectively remapped the feature space and identified subpopulations that do not respond well to anti-TNF treatments. Genetic SNP biomarkers showed small contributions in the prediction when added to the clinical models. This was the best-performing model in the DREAM Challenge. CONCLUSION: The model described here shows promise in guiding treatment decisions in clinical practice, based primarily on clinical profiles with additional genetic information.
OBJECTIVE: Accurate prediction of treatment responses in rheumatoid arthritis (RA) patients can provide valuable information on effective drug selection. Anti-tumor necrosis factor (anti-TNF) drugs are an important second-line treatment after methotrexate, the classic first-line treatment for RA. However, patient heterogeneity hinders identification of predictive biomarkers and accurate modeling of anti-TNF drug responses. This study was undertaken to investigate the usefulness of machine learning to assist in developing predictive models for treatment response. METHODS: Using data on patient demographics, baseline disease assessment, treatment, and single-nucleotide polymorphism (SNP) array from the Dialogue on Reverse Engineering Assessment and Methods (DREAM): Rheumatoid Arthritis Responder Challenge, we created a Gaussian process regression model to predict changes in the Disease Activity Score in 28 joints (DAS28) for the patients and to classify them into either the responder or the nonresponder group. This model was developed and cross-validated using data from 1,892 RA patients. It was evaluated using an independent data set from 680 patients. We examined the effectiveness of the similarity modeling and the contribution of individual features. RESULTS: In the cross-validation tests, our method predicted changes in DAS28 (ΔDAS28), with a correlation coefficient of 0.405. It correctly classified responses from 78% of patients. In the independent test, this method achieved a Pearson's correlation coefficient of 0.393 in predicting ΔDAS28. Gaussian process regression effectively remapped the feature space and identified subpopulations that do not respond well to anti-TNF treatments. Genetic SNP biomarkers showed small contributions in the prediction when added to the clinical models. This was the best-performing model in the DREAM Challenge. CONCLUSION: The model described here shows promise in guiding treatment decisions in clinical practice, based primarily on clinical profiles with additional genetic information.
Authors: My Kieu Ha; Esther Bartholomeus; Luc Van Os; Julie Dandelooy; Julie Leysen; Olivier Aerts; Vasiliki Siozopoulou; Eline De Smet; Jan Gielen; Khadija Guerti; Michel De Maeseneer; Nele Herregods; Bouchra Lechkar; Ruth Wittoek; Elke Geens; Laura Claes; Mahmoud Zaqout; Wendy Dewals; Annelies Lemay; David Tuerlinckx; David Weynants; Koen Vanlede; Gerlant van Berlaer; Marc Raes; Helene Verhelst; Tine Boiy; Pierre Van Damme; Anna C Jansen; Marije Meuwissen; Vito Sabato; Guy Van Camp; Arvid Suls; Jutte Van der Werff Ten Bosch; Joke Dehoorne; Rik Joos; Kris Laukens; Pieter Meysman; Benson Ogunjimi Journal: Pediatr Rheumatol Online J Date: 2022-10-17 Impact factor: 3.413