Moderate-High Disease Activity in Patients with Recent-Onset Psoriatic Arthritis-Multivariable Prediction Model Based on Machine Learning
Queiro, Ruben (Universidad de Oviedo)
Seoane-Mato, Daniel (Sociedad Española de Reumatología)
Laiz, Ana (Hospital de la Santa Creu i Sant Pau (Barcelona, Catalunya))
Galíndez Agirregoikoa, Eva (Hospital de Basurto (Bilbao, Biscaia))
Montilla, Carlos (Hospital Universitario de Salamanca)
Park, Hye S. (Hospital de la Santa Creu i Sant Pau (Barcelona, Catalunya))
Tasende, Jose A. Pinto (Complejo Hospitalario Universitario de A Coruña)
Bethencourt Baute, Juan José (Hospital Universitario de Canarias (La Laguna))
Joven Ibáñez, Beatriz (Hospital Universitario 12 de Octubre (Madrid))
Toniolo, Elide (Hospital Universitari Son Llàtzer (Palma de Mallorca, Balears))
Ramírez, Julio (Hospital Clínic i Provincial de Barcelona)
Montero, Nuria (Sociedad Española de Reumatología)
Pruenza García-Hinojosa, Cristina (Universidad Autónoma de Madrid)
Serrano García, Ana (Universidad Autónoma de Madrid)
Universitat Autònoma de Barcelona

Data:	2023
Resum:	The aim was to identify patient- and disease-related characteristics predicting moderate-to-high disease activity in recent-onset psoriatic arthritis (PsA). We performed a multicenter observational prospective study (2-year follow-up, regular annual visits) in patients aged ≥18 years who fulfilled the CASPAR criteria and had less than 2 years since the onset of symptoms. The moderate-to-high activity of PsA was defined as DAPSA > 14. We trained a logistic regression model and random forest-type and XGBoost machine learning algorithms to analyze the association between the outcome measure and the variables selected in the bivariate analysis. The sample comprised 158 patients. At the first follow-up visit, 20. 8% of the patients who attended the clinic had a moderate-to-severe disease. This percentage rose to 21. 2% on the second visit. The variables predicting moderate-high activity were the PsAID score, tender joint count, level of physical activity, and sex. The mean values of the measures of validity of the machine learning algorithms were all high, especially sensitivity (98%; 95% CI: 86. 89-100. 00). PsAID was the most important variable in the prediction algorithms, reinforcing the convenience of its inclusion in daily clinical practice. Strategies that focus on the needs of women with PsA should be considered.
Drets:	Aquest document està subjecte a una llicència d'ús Creative Commons. Es permet la reproducció total o parcial, la distribució, la comunicació pública de l'obra i la creació d'obres derivades, fins i tot amb finalitats comercials, sempre i quan es reconegui l'autoria de l'obra original.
Llengua:	Anglès
Document:	Article ; recerca ; Versió publicada
Matèria:	Arthritis ; DAPSA ; Disease activity ; Machine learning ; Predictive model ; PsAID ; Psoriatic
Publicat a:	Journal of clinical medicine, Vol. 12 (january 2023) , ISSN 2077-0383

DOI: 10.3390/jcm12030931
PMID: 36769579

12 p, 301.6 KB

El registre apareix a les col·leccions:
Articles > Articles de recerca
Articles > Articles publicats