A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning
Objective Published predictive models of disease outcomes in idiopathic inflammatory myopathies (IIMs) are sparse and of limited accuracy due to disease heterogeneity. Computational methods may address this heterogeneity by partitioning patients based on clinical and biological phenotype. Methods To...
Main Authors: | , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2020-03-01
|
Series: | ACR Open Rheumatology |
Online Access: | https://doi.org/10.1002/acr2.11115 |
id |
doaj-9d92f243072c471780161d15beb82080 |
---|---|
record_format |
Article |
spelling |
doaj-9d92f243072c471780161d15beb820802020-11-25T02:28:13ZengWileyACR Open Rheumatology2578-57452020-03-012315816610.1002/acr2.11115A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine LearningSimon W. M. Eng0Jeannette M. Olazagasti1Anna Goldenberg2Cynthia S. Crowson3Chester V. Oddis4Timothy B. Niewold5Rae S. M. Yeung6Ann M. Reed7Hospital for Sick Children (SickKids), University of Toronto Toronto Ontario CanadaMayo Clinic Rochester MinnesotaHospital for Sick Children (SickKids), Vector Institute, University of Toronto Toronto Ontario CanadaMayo Clinic Rochester MinnesotaUniversity of Pittsburgh Pittsburgh PennsylvaniaMayo Clinic Rochester MinnesotaHospital for Sick Children (SickKids), University of Toronto Toronto Ontario CanadaDuke University School of Medicine Durham North CarolinaObjective Published predictive models of disease outcomes in idiopathic inflammatory myopathies (IIMs) are sparse and of limited accuracy due to disease heterogeneity. Computational methods may address this heterogeneity by partitioning patients based on clinical and biological phenotype. Methods To identify new patient groups, we applied similarity network fusion (SNF) to clinical and biological data from 168 patients with myositis (64 adult polymyositis [PM], 65 adult dermatomyositis [DM], and 39 juvenile DM [JDM]) in the Rituximab in Myositis trial. We generated a sparse proof‐of‐concept bedside classifier using multinomial regression and identified characteristics that distinguished these groups. We conducted χ2 tests to link new patient groups with the myositis subtypes. Results SNF identified five patient groups in the discovery cohort that subdivided the myositis subtypes. The sparse multinomial regressor to predict patient group assignments (areas under the receiver operating characteristic curve = [0.78, 0.97]; areas under the precision‐recall curve = [0.55, 0.96]) found that autoantibody enrichment defined four of these groups: anti–Mi‐2, anti–signal recognition peptide (SRP), anti–nuclear matrix protein 2 (NXP2), and anti‐synthetase (Syn). Depletion of immunoglobulin M (IgM) defined the fifth group. Each group was associated with one subtype, with adult DM being associated with anti–Mi‐2 and anti‐Syn autoantibodies, JDM being associated with anti‐NXP2 autoantibodies, and adult PM being associated with IgM depletion and anti‐SRP autoantibodies. These associations enabled us to further resolve the current myositis subtypes. Conclusion Using unsupervised machine learning, we identified clinically and biologically homogeneous groups of patients with IIMs, forming the basis of an integrated disease classification based on both clinical and biological phenotype, thus validating other approaches and what has been previously described.https://doi.org/10.1002/acr2.11115 |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Simon W. M. Eng Jeannette M. Olazagasti Anna Goldenberg Cynthia S. Crowson Chester V. Oddis Timothy B. Niewold Rae S. M. Yeung Ann M. Reed |
spellingShingle |
Simon W. M. Eng Jeannette M. Olazagasti Anna Goldenberg Cynthia S. Crowson Chester V. Oddis Timothy B. Niewold Rae S. M. Yeung Ann M. Reed A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning ACR Open Rheumatology |
author_facet |
Simon W. M. Eng Jeannette M. Olazagasti Anna Goldenberg Cynthia S. Crowson Chester V. Oddis Timothy B. Niewold Rae S. M. Yeung Ann M. Reed |
author_sort |
Simon W. M. Eng |
title |
A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning |
title_short |
A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning |
title_full |
A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning |
title_fullStr |
A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning |
title_full_unstemmed |
A Clinically and Biologically Based Subclassification of the Idiopathic Inflammatory Myopathies Using Machine Learning |
title_sort |
clinically and biologically based subclassification of the idiopathic inflammatory myopathies using machine learning |
publisher |
Wiley |
series |
ACR Open Rheumatology |
issn |
2578-5745 |
publishDate |
2020-03-01 |
description |
Objective Published predictive models of disease outcomes in idiopathic inflammatory myopathies (IIMs) are sparse and of limited accuracy due to disease heterogeneity. Computational methods may address this heterogeneity by partitioning patients based on clinical and biological phenotype. Methods To identify new patient groups, we applied similarity network fusion (SNF) to clinical and biological data from 168 patients with myositis (64 adult polymyositis [PM], 65 adult dermatomyositis [DM], and 39 juvenile DM [JDM]) in the Rituximab in Myositis trial. We generated a sparse proof‐of‐concept bedside classifier using multinomial regression and identified characteristics that distinguished these groups. We conducted χ2 tests to link new patient groups with the myositis subtypes. Results SNF identified five patient groups in the discovery cohort that subdivided the myositis subtypes. The sparse multinomial regressor to predict patient group assignments (areas under the receiver operating characteristic curve = [0.78, 0.97]; areas under the precision‐recall curve = [0.55, 0.96]) found that autoantibody enrichment defined four of these groups: anti–Mi‐2, anti–signal recognition peptide (SRP), anti–nuclear matrix protein 2 (NXP2), and anti‐synthetase (Syn). Depletion of immunoglobulin M (IgM) defined the fifth group. Each group was associated with one subtype, with adult DM being associated with anti–Mi‐2 and anti‐Syn autoantibodies, JDM being associated with anti‐NXP2 autoantibodies, and adult PM being associated with IgM depletion and anti‐SRP autoantibodies. These associations enabled us to further resolve the current myositis subtypes. Conclusion Using unsupervised machine learning, we identified clinically and biologically homogeneous groups of patients with IIMs, forming the basis of an integrated disease classification based on both clinical and biological phenotype, thus validating other approaches and what has been previously described. |
url |
https://doi.org/10.1002/acr2.11115 |
work_keys_str_mv |
AT simonwmeng aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT jeannettemolazagasti aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT annagoldenberg aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT cynthiascrowson aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT chestervoddis aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT timothybniewold aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT raesmyeung aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT annmreed aclinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT simonwmeng clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT jeannettemolazagasti clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT annagoldenberg clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT cynthiascrowson clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT chestervoddis clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT timothybniewold clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT raesmyeung clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning AT annmreed clinicallyandbiologicallybasedsubclassificationoftheidiopathicinflammatorymyopathiesusingmachinelearning |
_version_ |
1724839570265079808 |