Machine Learning Prediction of Treatment Response to Biological Disease-Modifying Antirheumatic Drugs in Rheumatoid Arthritis

被引:8
作者
Salehi, Fatemeh [1 ]
Lopera Gonzalez, Luis I. [2 ]
Bayat, Sara [3 ,4 ]
Kleyer, Arnd [5 ]
Zanca, Dario [1 ]
Brost, Alexander [6 ]
Schett, Georg [3 ,4 ]
Eskofier, Bjoern M. [1 ,7 ]
机构
[1] Friedrich Alexander Univ Erlangen Nuremberg, Dept Artificial Intelligence Biomed Engn, Machine Learning & Data Analyt Lab, D-91052 Erlangen, Germany
[2] Friedrich Alexander Univ Erlangen Nuremberg, Inst Digital Hlth, D-91052 Erlangen, Germany
[3] Univ Hosp Erlangen, Dept Internal Med Rheumatol & Immunol 3, D-91054 Erlangen, Germany
[4] Deutsch Zentrum Immuntherapie DZI, D-91054 Erlangen, Germany
[5] Charite Univ Med Berlin, Dept Rheumatol & Clin Immunol, D-10117 Berlin, Germany
[6] Siemens Healthcare GmbH, D-91301 Forchheim, Germany
[7] Helmholtz Ctr Munich, Inst AI Hlth, German Res Ctr Environm Hlth, Translat Digital Hlth Grp, D-85764 Neuherberg, Germany
关键词
bDMARDs; machine learning predictive model; rheumatoid arthritis; treatment response; prediction; FACTOR-ALPHA AGENTS; IMPACT; COSTS;
D O I
10.3390/jcm13133890
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: Disease-modifying antirheumatic drugs (bDMARDs) have shown efficacy in treating Rheumatoid Arthritis (RA). Predicting treatment outcomes for RA is crucial as approximately 30% of patients do not respond to bDMARDs and only half achieve a sustained response. This study aims to leverage machine learning to predict both initial response at 6 months and sustained response at 12 months using baseline clinical data. Methods: Baseline clinical data were collected from 154 RA patients treated at the University Hospital in Erlangen, Germany. Five machine learning models were compared: Extreme Gradient Boosting (XGBoost), Adaptive Boosting (AdaBoost), K-nearest neighbors (KNN), Support Vector Machines (SVM), and Random Forest. Nested cross-validation was employed to ensure robustness and avoid overfitting, integrating hyperparameter tuning within its process. Results: XGBoost achieved the highest accuracy for predicting initial response (AUC-ROC of 0.91), while AdaBoost was the most effective for sustained response (AUC-ROC of 0.84). Key predictors included the Disease Activity Score-28 using erythrocyte sedimentation rate (DAS28-ESR), with higher scores at baseline associated with lower response chances at 6 and 12 months. Shapley additive explanations (SHAP) identified the most important baseline features and visualized their directional effects on treatment response and sustained response. Conclusions: These findings can enhance RA treatment plans and support clinical decision-making, ultimately improving patient outcomes by predicting response before starting medication.
引用
收藏
页数:16
相关论文
共 42 条
[1]   Epidemiology of adult rheumatoid arthritis [J].
Alamanos, Y ;
Drosos, AA .
AUTOIMMUNITY REVIEWS, 2005, 4 (03) :130-136
[2]   Toxicity profiles of traditional disease modifying antirheumatic drugs for rheumatoid arthritis [J].
Aletaha, D ;
Kapral, T ;
Smolen, JS .
ANNALS OF THE RHEUMATIC DISEASES, 2003, 62 (05) :482-486
[3]  
Antoni C, 2002, CLIN EXP RHEUMATOL, V20, pS152
[4]   Efficacy and Treatment Costs of Monotherapy with bDMARDs in the Treatment of Rheumatoid Arthritis in Patients Intolerant to or Inappropriate to Continue Treatment with Methotrexate [J].
Batticciotto, Alberto ;
Ravasio, Roberto ;
Riva, Marta ;
Sarzi-Puttini, Piercarlo .
ADVANCES IN THERAPY, 2016, 33 (08) :1360-1373
[5]  
Cawley GC, 2010, J MACH LEARN RES, V11, P2079
[6]   Selecting critical features for data classification based on machine learning methods [J].
Chen, Rung-Ching ;
Dewi, Christine ;
Huang, Su-Wen ;
Caraka, Rezzy Eko .
JOURNAL OF BIG DATA, 2020, 7 (01)
[7]   Five-year Favorable Outcome of Patients with Early Rheumatoid Arthritis in the 2000s: Data from the ESPOIR Cohort [J].
Combe, Bernard ;
Rincheval, Nathalie ;
Benessiano, Joelle ;
Berenbaum, Francis ;
Cantagrel, Alain ;
Daures, Jean-Pierre ;
Dougados, Maxime ;
Fardellone, Patrice ;
Fautrel, Bruno ;
Flipo, Rene M. ;
Goupille, Philippe ;
Guillemin, Francis ;
Le Loet, Xavier ;
Logeart, Isabelle ;
Mariette, Xavier ;
Meyer, Olivier ;
Ravaud, Philippe ;
Saraux, Alain ;
Schaeverbeke, Thierry ;
Sibilia, Jean .
JOURNAL OF RHEUMATOLOGY, 2013, 40 (10) :1650-1657
[8]  
de la Torre I, 2013, EXPERT REV PHARM OUT, V13, P407, DOI [10.1586/ERP.13.24, 10.1586/erp.13.24]
[9]   Associations of Circulating Cytokines and Chemokines With Cancer Mortality in Men With Rheumatoid Arthritis [J].
England, Bryant R. ;
Sokolove, Jeremy ;
Robinson, William H. ;
Thiele, Geoffrey M. ;
Ganti, Apar K. ;
Sayles, Harlan ;
Michaud, Kaleb ;
Caplan, Liron ;
Davis, Lisa A. ;
Cannon, Grant W. ;
Sauer, Brian ;
Singh, Namrata ;
Solow, E. Blair ;
Reimold, Andreas M. ;
Kerr, Gail S. ;
Schwab, Pascale ;
Baker, Josh F. ;
Mikuls, Ted R. .
ARTHRITIS & RHEUMATOLOGY, 2016, 68 (10) :2394-2402
[10]   American College of Rheumatology/European League Against Rheumatism Provisional Definition of Remission in Rheumatoid Arthritis for Clinical Trials [J].
Felson, David T. ;
Smolen, Josef S. ;
Wells, George ;
Zhang, Bin ;
van Tuyl, Lilian H. D. ;
Funovits, Julia ;
Aletaha, Daniel ;
Allaart, Cornelia F. ;
Bathon, Joan ;
Bombardieri, Stefano ;
Brooks, Peter ;
Brown, Andrew ;
Matucci-Cerinic, Marco ;
Choi, Hyon ;
Combe, Bernard ;
de Wit, Maarten ;
Dougados, Maxime ;
Emery, Paul ;
Furst, Daniel ;
Gomez-Reino, Juan ;
Hawker, Gillian ;
Keystone, Edward ;
Khanna, Dinesh ;
Kirwan, John ;
Kvien, Tore K. ;
Landewe, Robert ;
Listing, Joachim ;
Michaud, Kaleb ;
Martin-Mola, Emilio ;
Montie, Pamela ;
Pincus, Theodore ;
Richards, Pamela ;
Siegel, Jeffrey N. ;
Simon, Lee S. ;
Sokka, Tuulikki ;
Strand, Vibeke ;
Tugwell, Peter ;
Tyndall, Alan ;
van der Heijde, Desiree ;
Verstappen, Suzan ;
White, Barbara ;
Wolfe, Frederick ;
Zink, Angela ;
Boers, Maarten .
ARTHRITIS AND RHEUMATISM, 2011, 63 (03) :573-586