Predicting Psoriatic Arthritis in Psoriasis Patients – A Swiss Registry Study
Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Standard
Predicting Psoriatic Arthritis in Psoriasis Patients – A Swiss Registry Study. / Nielsen, Mia-Louise; Petersen, Troels C.; Maul, Lara Valeska; Thyssen, Jacob P.; Thomsen, Simon F.; Wu, Jashin J.; Navarini, Alexander A.; Kündig, Thomas; Yawalkar, Nikhil; Schlapbach, Christoph; Boehncke, Wolf-Henning; Conrad, Curdin; Cozzio, Antonio; Micheroli, Raphael; Erik Kristensen, Lars; Egeberg, Alexander; Maul, Julia-Tatjana.
I: Journal of Psoriasis and Psoriatic Arthritis, Bind 9, Nr. 2, 2024, s. 41-50.Publikation: Bidrag til tidsskrift › Tidsskriftartikel › Forskning › fagfællebedømt
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Predicting Psoriatic Arthritis in Psoriasis Patients – A Swiss Registry Study
AU - Nielsen, Mia-Louise
AU - Petersen, Troels C.
AU - Maul, Lara Valeska
AU - Thyssen, Jacob P.
AU - Thomsen, Simon F.
AU - Wu, Jashin J.
AU - Navarini, Alexander A.
AU - Kündig, Thomas
AU - Yawalkar, Nikhil
AU - Schlapbach, Christoph
AU - Boehncke, Wolf-Henning
AU - Conrad, Curdin
AU - Cozzio, Antonio
AU - Micheroli, Raphael
AU - Erik Kristensen, Lars
AU - Egeberg, Alexander
AU - Maul, Julia-Tatjana
N1 - Publisher Copyright: © The Author(s) 2023.
PY - 2024
Y1 - 2024
N2 - Background: Psoriatic arthritis (PsA) is a prevalent comorbidity among patients with psoriasis, heavily contributing to their burden of disease, usually diagnosed several years after the diagnosis of psoriasis. Objectives: To investigate the predictability of psoriatic arthritis in patients with psoriasis and to identify important predictors. Methods: Data from the Swiss Dermatology Network on Targeted Therapies (SDNTT) involving patients treated for psoriasis were utilized. A combination of gradient-boosted decision trees and mixed models was used to classify patients based on their diagnosis of PsA or its absence. The variables with the highest predictive power were identified. Time to PsA diagnosis was visualized with the Kaplan-Meier method and the relationship between severity of psoriasis and PsA was explored through quantile regression. Results: A diagnosis of psoriatic arthritis was registered at baseline of 407 (29.5%) treatment series. 516 patients had no registration of PsA, 257 patients had PsA at inclusion, and 91 patients were diagnosed with PsA after inclusion. The model’s AUROCs was up to 73.7%, and variables with the highest discriminatory power were age, PASI, physical well-being, and severity of nail psoriasis. Among patients who developed PsA after inclusion, significantly more first treatment series were classified in the PsA-group, compared to those with no PsA registration. PASI was significantly correlated with the median burden/severity of PsA (P =.01). Conclusions: Distinguishing between patients with and without PsA based on clinical characteristics is feasible and even predicting future diagnoses of PsA is possible. Patients at higher risk can be identified using important predictors of PsA.
AB - Background: Psoriatic arthritis (PsA) is a prevalent comorbidity among patients with psoriasis, heavily contributing to their burden of disease, usually diagnosed several years after the diagnosis of psoriasis. Objectives: To investigate the predictability of psoriatic arthritis in patients with psoriasis and to identify important predictors. Methods: Data from the Swiss Dermatology Network on Targeted Therapies (SDNTT) involving patients treated for psoriasis were utilized. A combination of gradient-boosted decision trees and mixed models was used to classify patients based on their diagnosis of PsA or its absence. The variables with the highest predictive power were identified. Time to PsA diagnosis was visualized with the Kaplan-Meier method and the relationship between severity of psoriasis and PsA was explored through quantile regression. Results: A diagnosis of psoriatic arthritis was registered at baseline of 407 (29.5%) treatment series. 516 patients had no registration of PsA, 257 patients had PsA at inclusion, and 91 patients were diagnosed with PsA after inclusion. The model’s AUROCs was up to 73.7%, and variables with the highest discriminatory power were age, PASI, physical well-being, and severity of nail psoriasis. Among patients who developed PsA after inclusion, significantly more first treatment series were classified in the PsA-group, compared to those with no PsA registration. PASI was significantly correlated with the median burden/severity of PsA (P =.01). Conclusions: Distinguishing between patients with and without PsA based on clinical characteristics is feasible and even predicting future diagnoses of PsA is possible. Patients at higher risk can be identified using important predictors of PsA.
KW - classification
KW - machine learning
KW - predictive models
KW - psoriasis
KW - psoriatic arthritis
KW - real word
KW - registry
KW - statistics
U2 - 10.1177/24755303231217492
DO - 10.1177/24755303231217492
M3 - Journal article
AN - SCOPUS:85177453220
VL - 9
SP - 41
EP - 50
JO - Journal of Psoriasis and Psoriatic Arthritis
JF - Journal of Psoriasis and Psoriatic Arthritis
SN - 2475-5303
IS - 2
ER -
ID: 387824242