Machine Learning to Predict Anti–Tumor Necrosis Factor Drug Responses of Rheumatoid Arthritis Patients by Integrating Clinical and Genetic Markers

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.

[1]  Ivo D. Dinov,et al.  Complete hazard ranking to analyze right-censored data: An ALS survival study , 2017, PLoS Comput. Biol..

[2]  C. Wijbrandts,et al.  Prediction of Response to Targeted Treatment in Rheumatoid Arthritis , 2017, Mayo Clinic proceedings.

[3]  Monica Z. Weiland,et al.  Gaussian Process Regression for Predictive But Interpretable Machine Learning Models: An Example of Predicting Mental Workload across Tasks , 2017, Front. Hum. Neurosci..

[4]  R. Landewé,et al.  Adalimumab long-term safety: infections, vaccination response and pregnancy outcomes in patients with rheumatoid arthritis , 2016, Annals of the rheumatic diseases.

[5]  F. Raciborski,et al.  Personalized medicine in rheumatology , 2016, Reumatologia.

[6]  Qi Zhu,et al.  TNF-α Promoter Polymorphisms Predict the Response to Etanercept More Powerfully than that to Infliximab/Adalimumab in Spondyloarthritis , 2016, Scientific Reports.

[7]  Matti Pirinen,et al.  Crowdsourced assessment of common genetic contribution to predicting anti-TNF treatment response in rheumatoid arthritis , 2016, Nature Communications.

[8]  Chunxiao Wu,et al.  Effect of Anti-TNF Antibodies on Clinical Response in Rheumatoid Arthritis Patients: A Meta-Analysis , 2016, BioMed research international.

[9]  N. Jewell,et al.  A longitudinal genome-wide association study of anti-tumor necrosis factor response among Japanese patients with rheumatoid arthritis , 2016, Arthritis Research & Therapy.

[10]  J. Colombel,et al.  Loss of Response to Anti-TNFs: Definition, Epidemiology, and Management , 2016, Clinical and Translational Gastroenterology.

[11]  Yan Liu,et al.  Interpretable Deep Models for ICU Outcome Prediction , 2016, AMIA.

[12]  Y. Okada,et al.  Genetic studies of rheumatoid arthritis , 2015, Proceedings of the Japan Academy. Series B, Physical and biological sciences.

[13]  Johannes Gehrke,et al.  Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission , 2015, KDD.

[14]  A. Barton,et al.  Genetic and genomic markers of anti-TNF treatment response in rheumatoid arthritis. , 2015, Biomarkers in medicine.

[15]  David A. Drubin,et al.  Blood-based identification of non-responders to anti-TNF therapy in rheumatoid arthritis , 2015, BMC Medical Genomics.

[16]  A. Barton,et al.  Impact of inadequate adherence on response to subcutaneously administered anti-tumour necrosis factor drugs: results from the Biologics in Rheumatoid Arthritis Genetics and Genomics Study Syndicate cohort , 2014, Rheumatology.

[17]  J. Aguillón,et al.  Clinical parameters and biomarkers for anti-TNF treatment prognosis in rheumatoid arthritis patients , 2014, Clinical Rheumatology.

[18]  U. Vogel,et al.  Anti-TNF Treatment Response in Rheumatoid Arthritis Patients Is Associated with Genetic Variation in the NLRP3-Inflammasome , 2014, PloS one.

[19]  Jeffrey R Curtis,et al.  “Design characteristics of the CORRONA CERTAIN study: a comparative effectiveness study of biologic agents for rheumatoid arthritis patients” , 2014, BMC Musculoskeletal Disorders.

[20]  Jing Liu,et al.  A Multiobjective Evolutionary Algorithm Based on Similarity for Community Detection From Signed Social Networks , 2014, IEEE Transactions on Cybernetics.

[21]  E. Karlson,et al.  Parity and the risk of developing rheumatoid arthritis: results from the Swedish Epidemiological Investigation of Rheumatoid Arthritis study , 2013, Annals of the rheumatic diseases.

[22]  I. de la Torre,et al.  Anti-TNF treatments in rheumatoid arthritis: economic impact of dosage modification , 2013, Expert review of pharmacoeconomics & outcomes research.

[23]  Gustavo Stolovitzky,et al.  Crowdsourcing genetic prediction of clinical utility in the Rheumatoid Arthritis Responder Challenge , 2013, Nature Genetics.

[24]  Masa Umicevic Mirkov,et al.  Genome-wide association analysis of anti-TNF drug response in patients with rheumatoid arthritis , 2012, Annals of the rheumatic diseases.

[25]  A. Barton,et al.  Genetic and genomic predictors of anti-TNF response. , 2011, Pharmacogenomics.

[26]  Ying Liu,et al.  FaST linear mixed models for genome-wide association studies , 2011, Nature Methods.

[27]  M. McDermott,et al.  Anti-TNF treatment in rheumatoid arthritis. , 2011, Current pharmaceutical design.

[28]  A. Barton,et al.  Genome-Wide Association Study of Genetic Predictors of Anti–Tumor Necrosis Factor Treatment Efficacy in Rheumatoid Arthritis Identifies Associations with Polymorphisms at Seven Loci , 2011, Arthritis and rheumatism.

[29]  Christopher M. Danforth,et al.  Temporal Patterns of Happiness and Information in a Global Social Network: Hedonometrics and Twitter , 2011, PloS one.

[30]  Jing Cui,et al.  Using genetic and clinical data to understand response to disease-modifying anti-rheumatic drug therapy: data from the Brigham and Women's Hospital Rheumatoid Arthritis Sequential Study. , 2011, Rheumatology.

[31]  B. Franke,et al.  Genetic Variants in Toll-Like Receptors Are Not Associated with Rheumatoid Arthritis Susceptibility or Anti-Tumour Necrosis Factor Treatment Outcome , 2010, PloS one.

[32]  P. Gregersen,et al.  Rheumatoid arthritis risk allele PTPRC is also associated with response to anti-tumor necrosis factor alpha therapy. , 2010, Arthritis and rheumatism.

[33]  Ji-Hyun Kim,et al.  Estimating classification error rate: Repeated cross-validation, repeated hold-out and bootstrap , 2009, Comput. Stat. Data Anal..

[34]  R. Tibshirani,et al.  Blood autoantibody and cytokine profiles predict response to anti-tumor necrosis factor therapy in rheumatoid arthritis , 2009, Arthritis research & therapy.

[35]  P. Sarzi-Puttini,et al.  Predicting response to anti-TNF treatment in rheumatoid arthritis patients. , 2009, Autoimmunity reviews.

[36]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[37]  Issa J Dahabreh,et al.  Infliximab and methotrexate in the treatment of rheumatoid arthritis: a systematic review and meta-analysis of dosage regimens. , 2008, Clinical therapeutics.

[38]  Wentian Li,et al.  Genome-Wide Association Scan Identifies Candidate Polymorphisms Associated with Differential Response to Anti-TNF Treatment in Rheumatoid Arthritis , 2008, Molecular medicine.

[39]  B. Franke,et al.  The tumour necrosis factor receptor superfamily member 1b 676T>G polymorphism in relation to response to infliximab and adalimumab treatment and disease severity in rheumatoid arthritis , 2008, Annals of the rheumatic diseases.

[40]  P. Ravaud,et al.  A single tumour necrosis factor haplotype influences the response to adalimumab in rheumatoid arthritis , 2007, Annals of the rheumatic diseases.

[41]  David S. Wishart,et al.  Applications of Machine Learning in Cancer Prediction and Prognosis , 2006, Cancer informatics.

[42]  A. Silman,et al.  Predictors of Response to Anti-tnf-therapy among Patients with Rheumatoid Arthritis: Results from the British Society for Rheumatology Biologics Register , 2022 .

[43]  B. Dijkmans,et al.  Aiming at low disease activity in rheumatoid arthritis with initial combination therapy or initial monotherapy strategies: the BeSt study. , 2006, Clinical and experimental rheumatology.

[44]  J. Kremer,et al.  The CORRONA database. , 2006, Autoimmunity reviews.

[45]  M. Uffmann,et al.  Acute phase reactants add little to composite disease activity indices for rheumatoid arthritis: validation of a clinical activity score , 2005, Arthritis research & therapy.

[46]  P. Klimiuk,et al.  Heterogeneity of rheumatoid arthritis: from phenotypes to genotypes , 2004, Springer Seminars in Immunopathology.

[47]  P. Helliwell,et al.  Ethnic differences in responses to disease modifying drugs. , 2003, Rheumatology.

[48]  M. Genovese,et al.  The Early Rheumatoid Arthritis (ERA) trial comparing the efficacy and safety of etanercept and methotrexate. , 2003, Clinical and experimental rheumatology.

[49]  J. Smolen,et al.  Toxicity profiles of traditional disease modifying antirheumatic drugs for rheumatoid arthritis , 2003, Annals of the rheumatic diseases.

[50]  J. Braun,et al.  Side effects of anti-TNF therapy: current knowledge. , 2002, Clinical and experimental rheumatology.

[51]  R N Maini,et al.  Infliximab and methotrexate in the treatment of rheumatoid arthritis. Anti-Tumor Necrosis Factor Trial in Rheumatoid Arthritis with Concomitant Therapy Study Group. , 2000, The New England journal of medicine.

[52]  B. Diamond,et al.  Autoimmune diseases , 2000, Bone Marrow Transplantation.

[53]  M. Prevoo,et al.  Development and validation of the European League Against Rheumatism response criteria for rheumatoid arthritis. Comparison with the preliminary American College of Rheumatology and the World Health Organization/International League Against Rheumatism Criteria. , 1996, Arthritis and rheumatism.

[54]  M. Prevoo,et al.  Modified disease activity scores that include twenty-eight-joint counts. Development and validation in a prospective longitudinal study of patients with rheumatoid arthritis. , 1995, Arthritis and rheumatism.

[55]  M. Liang,et al.  The American Rheumatism Association 1987 revised criteria for the classification of rheumatoid arthritis. , 1988, Arthritis and rheumatism.