Full Papers
Machine-learning derived algorithms for prediction of radiographic progression in early axial spondyloarthritis
R. Garofoli1, M. Resche-Rigon2, C. Roux3, D. Van Der Heijde4, M. Dougados5, A. Moltó6
- ECAMO Team, INSERM U1153: Clinical Epidemiology and Biostatistics, Université de Paris, France. romaingarofoli@gmail.com
- ECSTRRA Team, INSERM U1153: Clinical Epidemiology and Biostatistics, Université de Paris, and SBIM, Saint-Louis Hospital, APHP, Paris, France.
- ECAMO Team, INSERM U1153: Clinical Epidemiology and Biostatistics, Université de Paris, and Rheumatology Department, Cochin Hospital, APHP.5, Paris, France.
- Leiden University Medical Center (LUMC), Leiden, The Netherlands.
- ECAMO Team, INSERM U1153: Clinical Epidemiology and Biostatistics, Université de Paris, and Rheumatology Department, Cochin Hospital, APHP.5, Paris, France.
- ECAMO Team, INSERM U1153: Clinical Epidemiology and Biostatistics, Université de Paris, and Rheumatology Department, Cochin Hospital, APHP.5, Paris, France.
CER15782
2023 Vol.41, N°3
PI 0727, PF 0734
Full Papers
Free to view
(click on article PDF icon to read the article)
PMID: 36200930 [PubMed]
Received: 15/04/2022
Accepted : 27/06/2022
In Press: 04/10/2022
Published: 23/03/2023
Abstract
OBJECTIVES:
To compare machine learning (ML) to traditional models to predict radiographic progression in patients with early axial spondyloarthritis (axSpA).
METHODS:
We carried out a prospective French multicentric DESIR cohort study with 5 years of follow-up that included patients with chronic back pain for <3 years, suggestive of axSpA. Radiographic progression was defined as progression at the spine (increase of at least 1 point of mSASSS scores/2 years) or at the sacroiliac joint (worsening of at least one grade of the mNY score between 2 visits). Statistical analyses were based on patients without any missing data regarding the outcome and variables of interest (295 patients).
Traditional modelling: we performed a multivariate logistic regression model (M1); then variable selection with stepwise selection based on Akaike Information Criterion (stepAIC) method (M2), and Least Absolute Shrinkage and Selection Operator (LASSO) method (M3).
ML modelling: using “SuperLearner” package on R, we modelled radiographic progression with stepAIC, LASSO, random forest, Discrete Bayesian Additive Regression Trees Samplers (DBARTS), Generalized Additive Models (GAM), multivariate adaptive polynomial spline regression (polymars), Recursive Partitioning And Regression Trees (RPART) and Super Learner. Accuracy of these models was compared based on their 10-fold cross-validated AUC (cv-AUC).
RESULTS:
10-fold cv-AUC for traditional models were 0.79 and 0.78 for M2 and M3, respectively. The three best models in the ML algorithms were the GAM, the DBARTS and the Super Learner models, with 10-fold cv-AUC of: 0.77, 0.76 and 0.74, respectively.
CONCLUSIONS:
Two traditional models predicted radiographic progression as good as the eight ML models tested in this population.
