Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs
Abstract Background Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients ta...
Main Authors: | , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-02-01
|
Series: | Arthritis Research & Therapy |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13075-021-02439-5 |
id |
doaj-433cd7a561c442faa840fe6bb87c25c8 |
---|---|
record_format |
Article |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Asmir Vodencarevic Koray Tascilar Fabian Hartmann Michaela Reiser Axel J. Hueber Judith Haschka Sara Bayat Timo Meinderink Johannes Knitza Larissa Mendez Melanie Hagen Gerhard Krönke Jürgen Rech Bernhard Manger Arnd Kleyer Marcus Zimmermann-Rittereiser Georg Schett David Simon on behalf of the RETRO study group |
spellingShingle |
Asmir Vodencarevic Koray Tascilar Fabian Hartmann Michaela Reiser Axel J. Hueber Judith Haschka Sara Bayat Timo Meinderink Johannes Knitza Larissa Mendez Melanie Hagen Gerhard Krönke Jürgen Rech Bernhard Manger Arnd Kleyer Marcus Zimmermann-Rittereiser Georg Schett David Simon on behalf of the RETRO study group Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs Arthritis Research & Therapy Rheumatoid arthritis Machine learning Flare prediction |
author_facet |
Asmir Vodencarevic Koray Tascilar Fabian Hartmann Michaela Reiser Axel J. Hueber Judith Haschka Sara Bayat Timo Meinderink Johannes Knitza Larissa Mendez Melanie Hagen Gerhard Krönke Jürgen Rech Bernhard Manger Arnd Kleyer Marcus Zimmermann-Rittereiser Georg Schett David Simon on behalf of the RETRO study group |
author_sort |
Asmir Vodencarevic |
title |
Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs |
title_short |
Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs |
title_full |
Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs |
title_fullStr |
Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs |
title_full_unstemmed |
Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs |
title_sort |
advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugs |
publisher |
BMC |
series |
Arthritis Research & Therapy |
issn |
1478-6362 |
publishDate |
2021-02-01 |
description |
Abstract Background Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients tapering bDMARDs using machine learning methods. Methods Longitudinal clinical data of RA patients on bDMARDs from a randomized controlled trial of treatment withdrawal (RETRO) were used to build a predictive model to estimate the probability of a flare. Four basic machine learning models were trained, and their predictions were additionally combined to train an ensemble learning method, a stacking meta-classifier model to predict the individual flare probability within 14 weeks after each visit. Prediction performance was estimated using nested cross-validation as the area under the receiver operating curve (AUROC). Predictor importance was estimated using the permutation importance approach. Results Data of 135 visits from 41 patients were included. A model selection approach based on nested cross-validation was implemented to find the most suitable modeling formalism for the flare prediction task as well as the optimal model hyper-parameters. Moreover, an approach based on stacking different classifiers was successfully applied to create a powerful and flexible prediction model with the final measured AUROC of 0.81 (95%CI 0.73–0.89). The percent dose change of bDMARDs, clinical disease activity (DAS-28 ESR), disease duration, and inflammatory markers were the most important predictors of a flare. Conclusion Machine learning methods were deemed feasible to predict flares after tapering bDMARDs in RA patients in sustained remission. |
topic |
Rheumatoid arthritis Machine learning Flare prediction |
url |
https://doi.org/10.1186/s13075-021-02439-5 |
work_keys_str_mv |
AT asmirvodencarevic advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT koraytascilar advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT fabianhartmann advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT michaelareiser advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT axeljhueber advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT judithhaschka advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT sarabayat advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT timomeinderink advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT johannesknitza advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT larissamendez advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT melaniehagen advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT gerhardkronke advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT jurgenrech advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT bernhardmanger advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT arndkleyer advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT marcuszimmermannrittereiser advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT georgschett advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT davidsimon advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs AT onbehalfoftheretrostudygroup advancedmachinelearningforpredictingindividualriskofflaresinrheumatoidarthritispatientstaperingbiologicdrugs |
_version_ |
1724223910990315520 |
spelling |
doaj-433cd7a561c442faa840fe6bb87c25c82021-03-11T12:52:52ZengBMCArthritis Research & Therapy1478-63622021-02-012311810.1186/s13075-021-02439-5Advanced machine learning for predicting individual risk of flares in rheumatoid arthritis patients tapering biologic drugsAsmir Vodencarevic0Koray Tascilar1Fabian Hartmann2Michaela Reiser3Axel J. Hueber4Judith Haschka5Sara Bayat6Timo Meinderink7Johannes Knitza8Larissa Mendez9Melanie Hagen10Gerhard Krönke11Jürgen Rech12Bernhard Manger13Arnd Kleyer14Marcus Zimmermann-Rittereiser15Georg Schett16David Simon17on behalf of the RETRO study groupDigital Health, Siemens Healthcare GmbHDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDigital Health, Siemens Healthcare GmbHDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenDepartment of Internal Medicine 3 - Rheumatology and Immunology, Friedrich-Alexander University (FAU) Erlangen-Nürnberg and Universitätsklinikum ErlangenAbstract Background Biological disease-modifying anti-rheumatic drugs (bDMARDs) can be tapered in some rheumatoid arthritis (RA) patients in sustained remission. The purpose of this study was to assess the feasibility of building a model to estimate the individual flare probability in RA patients tapering bDMARDs using machine learning methods. Methods Longitudinal clinical data of RA patients on bDMARDs from a randomized controlled trial of treatment withdrawal (RETRO) were used to build a predictive model to estimate the probability of a flare. Four basic machine learning models were trained, and their predictions were additionally combined to train an ensemble learning method, a stacking meta-classifier model to predict the individual flare probability within 14 weeks after each visit. Prediction performance was estimated using nested cross-validation as the area under the receiver operating curve (AUROC). Predictor importance was estimated using the permutation importance approach. Results Data of 135 visits from 41 patients were included. A model selection approach based on nested cross-validation was implemented to find the most suitable modeling formalism for the flare prediction task as well as the optimal model hyper-parameters. Moreover, an approach based on stacking different classifiers was successfully applied to create a powerful and flexible prediction model with the final measured AUROC of 0.81 (95%CI 0.73–0.89). The percent dose change of bDMARDs, clinical disease activity (DAS-28 ESR), disease duration, and inflammatory markers were the most important predictors of a flare. Conclusion Machine learning methods were deemed feasible to predict flares after tapering bDMARDs in RA patients in sustained remission.https://doi.org/10.1186/s13075-021-02439-5Rheumatoid arthritisMachine learningFlare prediction |