Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2024 Apr;9(2):41-50.
doi: 10.1177/24755303231217492. Epub 2023 Nov 21.

Predicting Psoriatic Arthritis in Psoriasis Patients - A Swiss Registry Study

Mia-Louise Nielsen  1 , Troels C Petersen  2 , Lara Valeska Maul  3 , Jacob P Thyssen  1 , Simon F Thomsen  1 , Jashin J Wu  4 , Alexander A Navarini  3 , Thomas Kündig  5   6 , Nikhil Yawalkar  7 , Christoph Schlapbach  7 , Wolf-Henning Boehncke  8 , Curdin Conrad  9 , Antonio Cozzio  10 , Raphael Micheroli  11 , Lars Erik Kristensen  12 , Alexander Egeberg  1   13 , Julia-Tatjana Maul  5   6
Affiliations

Predicting Psoriatic Arthritis in Psoriasis Patients - A Swiss Registry Study

Mia-Louise Nielsen et al. J Psoriasis Psoriatic Arthritis. 2024 Apr.

Abstract

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.

Keywords: classification; machine learning; predictive models; psoriasis; psoriatic arthritis; real word; registry; statistics.

PubMed Disclaimer

Conflict of interest statement

The author(s) declared the following potential conflicts of interest with respect to the research, authorship, and/or publication of this article: Ms. Nielsen has nothing to declare Dr. Petersen has nothing to declare With no relation to the present manuscript Dr. LV Maul has served as advisor and/or received speaking fees and/or participated in clinical trials sponsored by Abbvie, Almirall, Amgen, Eli Lilly, MSD, Novartis, Pierre Fabre, Roche, and Sanofi. Dr. Thomsen has been a speaker or advisor for Sanofi, AbbVie, LEO Pharma, Pfizer, Eli Lilly, Novartis, UCB Pharma, Almirall, and Janssen Pharmaceuticals, and received research support from Sanofi, AbbVie, LEO Pharma, Novartis, UCB Pharma, and Janssen Pharmaceuticals, outside the submitted work. With no relation to the present manuscript, Dr. Schlapbach has received honoraria as adviser for Abbvie, BMS, LEO Pharma, Lilly, Kiowa Kirin, Novartis, and Pfizer and has received research funding from PPM Services. Prof. Kündig has intermittent, project focused consulting and/or advisory relationships with Leo Pharma, Janssen-Cilag, Eli Lilly, Pierre Fabre, Sanofi Genzyme, Abbvie, Biomed AG, Novartis, Almirall, Bristol-Myers Squibb, Galderma, L’Oréal/LaRoche-Posay, Merck-Sharp & Dohme, Zur Rose AG, Allergy Therapeutics AG, Derma2go AG, Oncobit AG, EVAX AG, Saiba Biotechnology AG, Saiba Animal Health AG, AltiBio Corp, Encoded Corp, Mabylon AG, MannKind Corp, XBiotech Corp. With no relation to the present manuscript, Dr. Wu is or has been an investigator, consultant, or speaker for AbbVie, Almirall, Amgen, Arcutis, Aristea Therapeutics, Bausch Health, Bayer, Boehringer Ingelheim, Bristol-Myers Squibb, Codex Labs, Dermavant, DermTech, Dr. Reddy’s Laboratories, Eli Lilly, EPI Health, Galderma, Incyte, Janssen, LEO Pharma, Mindera, Novartis, Pfizer, Regeneron, Samsung Bioepis, Sanofi Genzyme, Solius, Sun Pharmaceutical, UCB, and Zerigo Health. Dr. Cozzio is or has been involved in advisory activities for AbbVie, Eli Lilly, Sanofi, Janssen-Cilag, Leo, Amgen. Dr. Conrad is or has been Scientific adviser and/or clinical study investigator for AbbVie, Actelion, Almirall, Amgen, Boehringer Ingelheim, Bristol-Myers Squibb, Celgene, Eli-Lilly, Galderma, Incyte, Janssen, LEO pharma, MSD, Novartis, Pfizer, Samsung, Sanofi, and UCB With no relation to the present manuscript, Prof. Navarini declares being a consultant and advisor and/or receiving speaking fees and/or grants and/or served as an investigator in clinical trials for AbbVie, Almirall, Amgen, Biomed, BMS, Boehringer Ingelheim, Celgene, Eli Lilly, Galderma, GSK, LEO Pharma, Janssen-Cilag, MSD, Novartis, Pfizer, Pierre Fabre Pharma, Regeneron, Sandoz, Sanofi, and UCB. With no relation to the present manuscript Dr. Thyssen is a full time employee at LEO Pharma and is an advisor for AbbVie, Almirall, Arena Pharmaceuticals, Coloplast, OM Pharma, Aslan Pharmaceuticals, Union Therapeutics, Eli Lilly & Co, LEO Pharma, Pfizer, Regeneron, and Sanofi-Genzyme, a speaker for AbbVie, Almirall, Eli Lilly & Co, LEO Pharma, Pfizer, Regeneron, and Sanofi-Genzyme, and received research grants from Pfizer, Regeneron, and Sanofi-Genzyme. Dr. Boehncke has received honoraria as a speaker and/or advisor from Abbvie, Almirall, Amgen, BMS, Leo, Lilly, Novartis, and UCB. With no relation to the present manuscript Dr. Kristensen reports speakers bureau: Pfizer, AbbVie, Amgen, UCB, Galapagos, Biogen, BMS, MSD, Novartis, Eli Lilly, and Janssen pharmaceuticals & Consultancy for Pfizer, AbbVie, Amgen, UCB, Gilead, Biogen, BMS, MSD, Novartis, Eli Lilly, and Janssen pharmaceuticals. With no relation to the present manuscript Dr. Egeberg has received research funding from Pfizer, Eli Lilly, Novartis, Bristol-Myers Squibb, Boehringer Ingelheim, AbbVie, Janssen Pharmaceuticals, the Danish National Psoriasis Foundation, the Simon Spies Foundation, and the Kgl Hofbundtmager Aage Bang Foundation, and honoraria as consultant and/or speaker from AbbVie, Almirall, Leo Pharma, Zuellig Pharma Ltd., Galápagos NV, Sun Pharmaceuticals, Samsung Bioepis Co., Ltd., Pfizer, Eli Lilly and Company, Novartis, Galderma, Dermavant, UCB, Mylan, Bristol-Myers Squibb, McNeil Consumer Healthcare, Horizon Therapeutics, Boehringer Ingelheim, and Janssen Pharmaceuticals. With no relation to the present manuscript Dr. Maul has served as advisor and/or received speaking fees and/or participated in clinical trials sponsored by AbbVie, Almirall, Amgen, BMS, Celgene, Eli Lilly, LEO Pharma, Janssen-Cilag, MSD, Novartis, Pfizer, Pierre Fabre, Roche, Sanofi, UCB. With no relation to the present manuscript Dr. Yawalkar has served as advisor and/or received speaking fees and/or participated in clinical trials sponsored by AbbVie, Almirall, Amgen, Boehringer Ingelheim, Bristol-Myers Squibb, Celgene, Eli Lilly, Galderma, LEO Pharma, Janssen-Cilag, MSD, Novartis, Pfizer, Sanofi-Genzyme, UCB.

Figures

Figure 1.
Figure 1.
Kaplan-Meier plot showing the time to PsA diagnosis for patients with at least one follow-up visit (at least two visits in total) who did not have PsA at baseline.
Figure 2.
Figure 2.
(A) Receiver operating curves for individual folds in 10-fold cross validation for model 1 (does not include information on previous number of treatments/biologics) and the average over all folds. (B) Average receiver operating curves for models 1 and 2.
Figure 3.
Figure 3.
SHAP values for model 1 (A) and model 2 (B), indicating the feature importance for each variable included in the models. A higher SHAP value means that the data point (treatment series) contributed more towards a prediction of PsA.
Figure 4.
Figure 4.
(A) Quantile regression lines for three different quantiles. (B) Regression coefficients as a function of the quantile. Baseline data (first treatment) is included for patients with a diagnosis of PsA.
See this image and copyright information in PMC

References

    1. Alinaghi F, Calov M, Kristensen LE, et al. Prevalence of psoriatic arthritis in patients with psoriasis: A systematic review and meta-analysis of observational and clinical studies. J Am Acad Dermatol. 2019;80:251-265.e19. - PubMed
    1. Prey S, Paul C, Bronsard V, et al. Assessment of risk of psoriatic arthritis in patients with plaque psoriasis: A systematic review of the literature. J Eur Acad Dermatol Venereol. 2010;24(Suppl 2):31-35. - PubMed
    1. Bowes J, Ashcroft J, Dand N, et al. Cross-phenotype association mapping of the MHC identifies genetic variants that differentiate psoriatic arthritis from psoriasis. Ann Rheum Dis. 2017;76:1774-1779. - PMC - PubMed
    1. Stuart PE, Nair RP, Tsoi LC, et al. Genome-wide association analysis of psoriatic arthritis and cutaneous psoriasis reveals differences in their genetic architecture. Am J Hum Genet. 2015;97:816-836. - PMC - PubMed
    1. Rahmati S, Li Q, Rahman P, Chandran V. Insights into the pathogenesis of psoriatic arthritis from genetic studies. Semin Immunopathol. 2021;43:221-234. - PubMed