Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning
Abstract Background Very few data are available on predictors of minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis (PsA). Such data are crucial, since the therapeutic measures used to change the adverse course of PsA are more likely to succeed if we intervene early. In...
Main Authors: | , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2022-06-01
|
Series: | Arthritis Research & Therapy |
Subjects: | |
Online Access: | https://doi.org/10.1186/s13075-022-02838-2 |
_version_ | 1811334635180785664 |
---|---|
author | Rubén Queiro Daniel Seoane-Mato Ana Laiz Eva Galíndez Agirregoikoa Carlos Montilla Hye-Sang Park Jose A. Pinto-Tasende Juan J. Bethencourt Baute Beatriz Joven Ibáñez Elide Toniolo Julio Ramírez Ana Serrano García on behalf of Proyecto REAPSER Study Group |
author_facet | Rubén Queiro Daniel Seoane-Mato Ana Laiz Eva Galíndez Agirregoikoa Carlos Montilla Hye-Sang Park Jose A. Pinto-Tasende Juan J. Bethencourt Baute Beatriz Joven Ibáñez Elide Toniolo Julio Ramírez Ana Serrano García on behalf of Proyecto REAPSER Study Group |
author_sort | Rubén Queiro |
collection | DOAJ |
description | Abstract Background Very few data are available on predictors of minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis (PsA). Such data are crucial, since the therapeutic measures used to change the adverse course of PsA are more likely to succeed if we intervene early. In the present study, we used predictive models based on machine learning to detect variables associated with achieving MDA in patients with recent-onset PsA. Methods We performed a multicenter observational prospective study (2-year follow-up, regular annual visits). The study population comprised patients aged ≥18 years who fulfilled the CASPAR criteria and less than 2 years since the onset of symptoms. The dataset contained data for the independent variables from the baseline visit and from follow-up visit number 1. These were matched with the outcome measures from follow-up visits 1 and 2, respectively. We trained a random forest–type machine learning algorithm to analyze the association between the outcome measure and the variables selected in the bivariate analysis. In order to understand how the model uses the variables to make its predictions, we applied the SHAP technique. We used a confusion matrix to visualize the performance of the model. Results The sample comprised 158 patients. 55.5% and 58.3% of the patients had MDA at the first and second follow-up visit, respectively. In our model, the variables with the greatest predictive ability were global pain, impact of the disease (PsAID), patient global assessment of disease, and physical function (HAQ-Disability Index). The percentage of hits in the confusion matrix was 85.94%. Conclusions A key objective in the management of PsA should be control of pain, which is not always associated with inflammatory burden, and the establishment of measures to better control the various domains of PsA. |
first_indexed | 2024-04-13T17:11:58Z |
format | Article |
id | doaj.art-86d99bd5578c46aa9fa68022a8a1f678 |
institution | Directory Open Access Journal |
issn | 1478-6362 |
language | English |
last_indexed | 2024-04-13T17:11:58Z |
publishDate | 2022-06-01 |
publisher | BMC |
record_format | Article |
series | Arthritis Research & Therapy |
spelling | doaj.art-86d99bd5578c46aa9fa68022a8a1f6782022-12-22T02:38:15ZengBMCArthritis Research & Therapy1478-63622022-06-012411910.1186/s13075-022-02838-2Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learningRubén Queiro0Daniel Seoane-Mato1Ana Laiz2Eva Galíndez Agirregoikoa3Carlos Montilla4Hye-Sang Park5Jose A. Pinto-Tasende6Juan J. Bethencourt Baute7Beatriz Joven Ibáñez8Elide Toniolo9Julio Ramírez10Ana Serrano García11on behalf of Proyecto REAPSER Study GroupRheumatology Service & the Principality of Asturias Institute for Health Research (ISPA), Faculty of Medicine, Universidad de OviedoResearch Unit, Spanish Society of RheumatologyRheumatology and Autoimmune Disease Department, Hospital Universitari de la Santa Creu i Sant PauRheumatology Service, Hospital Universitario BasurtoRheumatology Service, Hospital Universitario de SalamancaRheumatology and Autoimmune Disease Department, Hospital Universitari de la Santa Creu i Sant PauRheumatology Service-INIBIC, Complexo Hospitalario Universitario de A CoruñaRheumatology Service, Hospital Universitario de CanariasRheumatology Service, Hospital Universitario 12 de OctubreRheumatology Service, Hospital Universitari Son LlàtzerArthritis Unit, Rheumatology Department, Hospital Clínic BarcelonaKnowledge Engineering Institute, Universidad Autónoma de MadridAbstract Background Very few data are available on predictors of minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis (PsA). Such data are crucial, since the therapeutic measures used to change the adverse course of PsA are more likely to succeed if we intervene early. In the present study, we used predictive models based on machine learning to detect variables associated with achieving MDA in patients with recent-onset PsA. Methods We performed a multicenter observational prospective study (2-year follow-up, regular annual visits). The study population comprised patients aged ≥18 years who fulfilled the CASPAR criteria and less than 2 years since the onset of symptoms. The dataset contained data for the independent variables from the baseline visit and from follow-up visit number 1. These were matched with the outcome measures from follow-up visits 1 and 2, respectively. We trained a random forest–type machine learning algorithm to analyze the association between the outcome measure and the variables selected in the bivariate analysis. In order to understand how the model uses the variables to make its predictions, we applied the SHAP technique. We used a confusion matrix to visualize the performance of the model. Results The sample comprised 158 patients. 55.5% and 58.3% of the patients had MDA at the first and second follow-up visit, respectively. In our model, the variables with the greatest predictive ability were global pain, impact of the disease (PsAID), patient global assessment of disease, and physical function (HAQ-Disability Index). The percentage of hits in the confusion matrix was 85.94%. Conclusions A key objective in the management of PsA should be control of pain, which is not always associated with inflammatory burden, and the establishment of measures to better control the various domains of PsA.https://doi.org/10.1186/s13075-022-02838-2Recent-onset psoriatic arthritisMinimal disease activityPredictive modelMachine learning |
spellingShingle | Rubén Queiro Daniel Seoane-Mato Ana Laiz Eva Galíndez Agirregoikoa Carlos Montilla Hye-Sang Park Jose A. Pinto-Tasende Juan J. Bethencourt Baute Beatriz Joven Ibáñez Elide Toniolo Julio Ramírez Ana Serrano García on behalf of Proyecto REAPSER Study Group Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning Arthritis Research & Therapy Recent-onset psoriatic arthritis Minimal disease activity Predictive model Machine learning |
title | Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning |
title_full | Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning |
title_fullStr | Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning |
title_full_unstemmed | Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning |
title_short | Minimal disease activity (MDA) in patients with recent-onset psoriatic arthritis: predictive model based on machine learning |
title_sort | minimal disease activity mda in patients with recent onset psoriatic arthritis predictive model based on machine learning |
topic | Recent-onset psoriatic arthritis Minimal disease activity Predictive model Machine learning |
url | https://doi.org/10.1186/s13075-022-02838-2 |
work_keys_str_mv | AT rubenqueiro minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT danielseoanemato minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT analaiz minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT evagalindezagirregoikoa minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT carlosmontilla minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT hyesangpark minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT joseapintotasende minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT juanjbethencourtbaute minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT beatrizjovenibanez minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT elidetoniolo minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT julioramirez minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT anaserranogarcia minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning AT onbehalfofproyectoreapserstudygroup minimaldiseaseactivitymdainpatientswithrecentonsetpsoriaticarthritispredictivemodelbasedonmachinelearning |