{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,17]],"date-time":"2026-09-17T23:04:44Z","timestamp":1789686284853,"version":"4.0.1"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T00:00:00Z","timestamp":1764374400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T00:00:00Z","timestamp":1767571200000},"content-version":"vor","delay-in-days":37,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"AbbVie"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Arthritis Res Ther"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The development of personalized approaches in psoriatic arthritis (PsA) is challenging due to unclear patient phenotypes and trajectories. Machine learning (ML) could help to identify homogeneous patient groups. The objective of this analysis was to classify patients with PsA into distinct phenotypes using ML.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A post hoc analysis of PsA patients treated with risankizumab for \u2264\u20094 years (196 weeks) from KEEPsAKE 1 and KEEPsAKE 2. The phenotypes were based on baseline demographics and clinical characteristics using unsupervised ML (a finite mixture model). Response to risankizumab at 4 years was defined as minimal disease activity (MDA) and Disease Activity in PsA (DAPSA) low disease activity (LDA).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>A total of 1119 patients were classified into 5 distinct PsA phenotypes: Moderate to High Disease Activity (40.3% of patients) - characterized by lower tender joint count (TJC) and swollen joint count (SJC), dactylitis, and enthesitis; Enthesitis and Large Joints Dominant (20.8% of patients) - characterized by enthesitis and mainly active large joints; Very High Disease Activity (14.0% of patients) - characterized by high TJC\/SJC, dactylitis, and enthesitis; Hand Dominant (13.8% of patients) - characterized by active joints primarily in the hands; Dactylitis and Feet Dominant (11.1% of patients) - characterized by dactylitis and active joints primarily in the feet. At 4 years, risankizumab demonstrated efficacy across all phenotypes (MDA and DAPSA LDA; range: 42.9% to 58.8% of patients and 66.0% to 82.0% of patients, respectively), with highest responses observed in the Moderate to High Disease Activity and Dactylitis and Feet Dominant phenotypes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>Five distinct PsA phenotypes were identified in patients starting risankizumab. Moderate to High Disease Activity, the most frequent phenotype, showed the highest response, though risankizumab demonstrated efficacy across all phenotypes. These results are a first step toward more personalized medicine for patients with PsA.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Trial registration<\/jats:title>\n                    <jats:p>ClinicalTrials.gov: KEEPsAKE 1, NCT03675308; KEEPsAKE 2, NCT03671148.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s13075-025-03670-0","type":"journal-article","created":{"date-parts":[[2025,11,29]],"date-time":"2025-11-29T08:15:21Z","timestamp":1764404121000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Efficacy of Risankizumab across distinct PsA phenotypes identified with machine learning analytics using data from biologic DMARD-Na\u00efve patients in two phase 3 clinical trials"],"prefix":"10.1186","volume":"28","author":[{"given":"Laure","family":"Gossec","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andra","family":"Balanescu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maria Antonietta","family":"D\u2019Agostino","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alexis","family":"Ogdie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Philipp","family":"Sewerin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Deng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linyu","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yoshiyuki","family":"Sugimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sheng","family":"Zhong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunzhao","family":"Xing","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ralph","family":"Lippe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mitsumasa","family":"Kishimoto","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,29]]},"reference":[{"key":"3670_CR1","doi-asserted-by":"publisher","first-page":"698","DOI":"10.3899\/jrheum.200371","volume":"48","author":"A Ogdie","year":"2021","unstructured":"Ogdie A, Hur P, Liu M, Rebello S, McLean RR, Dube B, et al. Effect of multidomain disease presentations on patients with psoriatic arthritis in the Corrona psoriatic arthritis\/Spondyloarthritis registry. J Rheumatol. 2021;48:698\u2013706.","journal-title":"J Rheumatol"},{"key":"3670_CR2","doi-asserted-by":"publisher","first-page":"i77","DOI":"10.1136\/ard.2010.140582","volume":"70","author":"PJ Mease","year":"2011","unstructured":"Mease PJ. Psoriatic arthritis: update on pathophysiology, assessment and management. Ann Rheum Dis. 2011;70:i77\u201384.","journal-title":"Ann Rheum Dis"},{"key":"3670_CR3","doi-asserted-by":"publisher","first-page":"1759720X2210867","DOI":"10.1177\/1759720X221086710","volume":"14","author":"S Hackett","year":"2022","unstructured":"Hackett S, Ogdie A, Coates LC. Psoriatic arthritis: prospects for the future. Ther Adv Musculoskelet Dis. 2022;14:1759720X221086710.","journal-title":"Ther Adv Musculoskelet Dis"},{"key":"3670_CR4","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1038\/s41584-022-00798-0","volume":"18","author":"LC Coates","year":"2022","unstructured":"Coates LC, Soriano ER, Corp N, Bertheussen H, Duffin KC, Campanholo CB, et al. Group for research and assessment of psoriasis and psoriatic arthritis (GRAPPA): updated treatment recommendations for psoriatic arthritis 2021. Nat Rev Rheumatol. 2022;18:465\u201379.","journal-title":"Nat Rev Rheumatol"},{"key":"3670_CR5","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1161\/CIRCULATIONAHA.114.010637","volume":"131","author":"SJ Shah","year":"2015","unstructured":"Shah SJ, Katz DH, Selvaraj S, Burke MA, Yancy CW, Gheorghiade M, et al. Phenomapping for novel classification of heart failure with preserved ejection fraction. Circulation. 2015;131:269\u201379.","journal-title":"Circulation"},{"key":"3670_CR6","doi-asserted-by":"publisher","first-page":"969","DOI":"10.1002\/mds.23116","volume":"25","author":"SM van Rooden","year":"2010","unstructured":"van Rooden SM, Heiser WJ, Kok JN, Verbaan D, van Hilten JJ, Marinus J. The identification of parkinson\u2019s disease subtypes using cluster analysis: A systematic review. Mov Disord. 2010;25:969\u201378.","journal-title":"Mov Disord"},{"key":"3670_CR7","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1136\/annrheumdis-2019-215694","volume":"79","author":"L Gossec","year":"2020","unstructured":"Gossec L, Kedra J, Servy H, Pandit A, Stones S, Berenbaum F, et al. EULAR points to consider for the use of big data in rheumatic and musculoskeletal diseases. Ann Rheum Dis. 2020;79:69\u201376.","journal-title":"Ann Rheum Dis"},{"key":"3670_CR8","doi-asserted-by":"publisher","first-page":"rkaa005","DOI":"10.1093\/rap\/rkaa005","volume":"4","author":"M H\u00fcgle","year":"2020","unstructured":"H\u00fcgle M, Omoumi P, van Laar JM, Boedecker J, H\u00fcgle T. Applied machine learning and artificial intelligence in rheumatology. Rheumatol Adv Pr. 2020;4:rkaa005.","journal-title":"Rheumatol Adv Pr"},{"key":"3670_CR9","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1136\/annrheumdis-2021-220454","volume":"80","author":"SJW Shoop-Worrall","year":"2021","unstructured":"Shoop-Worrall SJW, Cresswell K, Bolger I, Dillon B, Hyrich KL, Geifman N, et al. Nothing about Us without Us: involving patient collaborators for machine learning applications in rheumatology. Ann Rheum Dis. 2021;80:1505\u201310.","journal-title":"Ann Rheum Dis"},{"key":"3670_CR10","doi-asserted-by":"publisher","first-page":"927","DOI":"10.1136\/ard-2022-223808","volume":"82","author":"MY Choi","year":"2023","unstructured":"Choi MY, Chen I, Clarke AE, Fritzler MJ, Buhler KA, Urowitz M, et al. Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes. Ann Rheum Dis. 2023;82:927\u201336.","journal-title":"Ann Rheum Dis"},{"key":"3670_CR11","doi-asserted-by":"publisher","first-page":"e001845","DOI":"10.1136\/rmdopen-2021-001845","volume":"7","author":"E Pournara","year":"2021","unstructured":"Pournara E, Kormaksson M, Nash P, Ritchlin CT, Kirkham BW, Ligozio G, et al. Clinically relevant patient clusters identified by machine learning from the clinical development programme of Secukinumab in psoriatic arthritis. RMD Open. 2021;7:e001845.","journal-title":"RMD Open"},{"key":"3670_CR12","doi-asserted-by":"crossref","unstructured":"\u00d6st\u00f6r A, Van den Bosch F , Papp K, Asnal C, Blanco R, Aelion J et al. Efficacy and safety of risankizumab for active psoriatic arthritis: 24-week results from the randomised, double-blind, phase 3 KEEPsAKE 2 trial. Ann Rheum Dis. 2022;81:351\u20138.","DOI":"10.1136\/annrheumdis-2021-221048"},{"key":"3670_CR13","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1136\/annrheumdis-2021-221019","volume":"81","author":"LE Kristensen","year":"2022","unstructured":"Kristensen LE, Keiserman M, Papp K, McCasland L, White D, Lu W, et al. Efficacy and safety of Risankizumab for active psoriatic arthritis: 24-week results from the randomised, double-blind, phase 3 keepsake 1 trial. Ann Rheum Dis. 2022;81:225\u201331.","journal-title":"Ann Rheum Dis"},{"key":"3670_CR14","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1007\/s40744-024-00654-5","volume":"11","author":"LE Kristensen","year":"2024","unstructured":"Kristensen LE, Keiserman M, Papp K, McCasland L, White D, Carter K, et al. Efficacy and safety of Risankizumab for active psoriatic arthritis: 100-Week results from the phase 3 keepsake 1 randomized clinical trial. Rheumatol Ther. 2024;11:617\u201332.","journal-title":"Rheumatol Ther"},{"key":"3670_CR15","doi-asserted-by":"publisher","first-page":"633","DOI":"10.1007\/s40744-024-00657-2","volume":"11","author":"A \u00d6st\u00f6r","year":"2024","unstructured":"\u00d6st\u00f6r A, Van den Bosch F , Papp K, Asnal C, Blanco R, Aelion J, et al. Efficacy and safety of Risankizumab for active psoriatic arthritis: 100-Week results from the keepsake 2 randomized clinical trial. Rheumatol Ther. 2024;11:633\u201348.","journal-title":"Rheumatol Ther"},{"key":"3670_CR16","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1146\/annurev-statistics-031017-100325","volume":"6","author":"GJ McLachlan","year":"2019","unstructured":"McLachlan GJ, Lee SX, Rathnayake SI. Finite mixture models. Annu Rev Stat Appl. 2019;6:355\u201378.","journal-title":"Annu Rev Stat Appl"},{"issue":"2","key":"3670_CR17","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1002\/wics.199","volume":"4","author":"AA Neath","year":"2012","unstructured":"Neath AA, Cavanaugh JE. The bayesian information criterion: background, derivation, and applications. WIREs Comp Stats. 2012;4(2):199\u2013203.","journal-title":"WIREs Comp Stats"},{"key":"3670_CR18","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/A:1023949509487","volume":"52","author":"S Monti","year":"2003","unstructured":"Monti S, Tamayo P, Mesirov J, Golub T. Consensus clustering: A Resampling-Based method for class discovery and visualization of gene expression microarray data. Mach Learn. 2003;52:91\u2013118.","journal-title":"Mach Learn"},{"key":"3670_CR19","doi-asserted-by":"publisher","first-page":"5079","DOI":"10.1200\/JCO.2005.05.1748","volume":"24","author":"DN Hayes","year":"2006","unstructured":"Hayes DN, Monti S, Parmigiani G, Gilks CB, Naoki K, Bhattacharjee A, et al. Gene expression profiling reveals reproducible human lung adenocarcinoma subtypes in multiple independent patient cohorts. J Clin Oncol. 2006;24:5079\u201390.","journal-title":"J Clin Oncol"},{"key":"3670_CR20","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1016\/j.ccr.2009.12.020","volume":"17","author":"RGW Verhaak","year":"2010","unstructured":"Verhaak RGW, Hoadley KA, Purdom E, Wang V, Qi Y, Wilkerson MD, et al. Integrated genomic analysis identifies clinically relevant subtypes of glioblastoma characterized by abnormalities in PDGFRA, IDH1, EGFR, and NF1. Cancer Cell. 2010;17:98\u2013110.","journal-title":"Cancer Cell"},{"issue":"8","key":"3670_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.18637\/jss.v011.i08","volume":"11","author":"F Leisch","year":"2004","unstructured":"Leisch F, Flexmix. A general framework for finite mixture models and latent glass regression in R. J Stat Softw. 2004;11(8):1\u201318.","journal-title":"J Stat Softw"},{"key":"3670_CR22","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1136\/svn-2017-000101","volume":"2","author":"F Jiang","year":"2017","unstructured":"Jiang F, Jiang Y, Zhi H, Dong Y, Li H, Ma S, et al. Artificial intelligence in healthcare: past, present and future. Stroke Vasc Neurol. 2017;2:230\u201343.","journal-title":"Stroke Vasc Neurol"},{"key":"3670_CR23","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1038\/s41551-018-0305-z","volume":"2","author":"K-H Yu","year":"2018","unstructured":"Yu K-H, Beam AL, Kohane IS. Artificial intelligence in healthcare. Nat Biomed Eng. 2018;2:719\u201331.","journal-title":"Nat Biomed Eng"},{"key":"3670_CR24","first-page":"696","volume":"42","author":"X Baraliakos","year":"2023","unstructured":"Baraliakos X, Pournara E, Coates LC, Mease PJ, Jahandideh SS, Gladman DD. Patient clusters identified by machine learning from a pooled analysis of the clinical development programme of Secukinumab in psoriatic arthritis, ankylosing spondylitis and psoriatic arthritis with axial manifestations. Clin Exp Rheumatol. 2023;42:696\u2013701.","journal-title":"Clin Exp Rheumatol"},{"key":"3670_CR25","doi-asserted-by":"publisher","first-page":"e002934","DOI":"10.1136\/rmdopen-2022-002934","volume":"9","author":"P Richette","year":"2023","unstructured":"Richette P, Vis M, Ohrndorf S, Tillett W, Ram\u00edrez J, Neuhold M, et al. Identification of PsA phenotypes with machine learning analytics using data from two phase III clinical trials of Guselkumab in a bio-na\u00efve population of patients with PsA. RMD Open. 2023;9:e002934.","journal-title":"RMD Open"},{"key":"3670_CR26","first-page":"138","volume":"52","author":"G Alle","year":"2025","unstructured":"Alle G, Lopez-Medina C, Siebert S, Lavie F, Noel W, Smolen JS, et al. Patient profiles in randomized controlled trials versus a Real-World study in psoriatic arthritis: scoping review and metaanalysis. J Rheumatol. 2025;52:138\u201344.","journal-title":"J Rheumatol"},{"key":"3670_CR27","doi-asserted-by":"crossref","unstructured":"Gossec L, Balanescu A, D\u2019Agostino M, Ogdie A, Sewerin P, Deng Y et al. Efficacy of Risankizumab across distinct PsA phenotypes identified with machine learning analytics using data from biologic DMARD-Naive patients in two phase 3 clinical trials [abstract]. Arthritis Rheumatol. 2024;76 (suppl 9).","DOI":"10.1186\/s13075-025-03670-0"}],"container-title":["Arthritis Research &amp; Therapy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13075-025-03670-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13075-025-03670-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13075-025-03670-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:37:20Z","timestamp":1767627440000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13075-025-03670-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,29]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["3670"],"URL":"https:\/\/doi.org\/10.1186\/s13075-025-03670-0","relation":{},"ISSN":["1478-6362"],"issn-type":[{"value":"1478-6362","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,29]]},"assertion":[{"value":"18 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The KEEPsAKE 1 (NCT03675308) and KEEPsAKE 2 (NCT03671148) trials were conducted in accordance with the International Council for Harmonisation of Technical Requirements for Pharmaceuticals for Human Use (ICH) guidelines, applicable regulations governing clinical trial conduct, and the Declaration of Helsinki 1964 and its later amendments. The trial protocols were approved by an independent ethics committee (IEC)\/institutional review board (IRB) at each study site per Good Clinical Practice (GCP). All patients provided written informed consent prior to screening.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"Financial arrangements of the authors with companies whose products may be related to the present manuscript are listed, as declared by the authors. LG has received research grants from AbbVie, Eli Lilly, Novartis, and UCB, and has received consulting fees from AbbVie, Alfasigma, Amgen, Bristol Myers Squibb, Celltrion, J&J, Eli Lilly, Moonlake, Novartis, Pfizer, STADA, and UCB, and has received non-financial support from AbbVie, Amgen, Biogen, Celltrion, Janssen, Pfizer, and UCB. AB has received speaker and consulting fees from AbbVie, Alphasigma, Angelini, Amgen, AstraZeneca, Berlin-Chemie, Biogen, Bristol Myers Squibb, Janssen, Eli Lilly, MSD, Novartis, Pfizer, Roche, Sandoz, Teva, UCB, and Zentiva, and she was an investigator in clinical trials sponsored by Akros, AstraZeneca, Bristol Myers Squibb, GlaxoSmithKline, MSD, Novartis, Roche, Sandoz, Sanofi, Pfizer, and UCB. MADA has received consulting fees from AbbVie, Novartis, Amgen, Eli Lilly, Janssen, Bristol Myers Squibb, Galapagos, and Pfizer, and has received honoraria from AbbVie, Novartis, Amgen, Eli Lilly, Janssen, Bristol Myers Squibb, Galapagos, and Pfizer. AO has received consulting fees from AbbVie, Amgen, Bristol Myers Squibb, Celgene, CorEvitas, Gilead, GSK, Janssen, Eli Lilly, Merck, Novartis, Takeda, Treg, Spyre, Pfizer, and UCB, and has received grants\/research support from AbbVie, Amgen, Bristol Myers Squibb, Janssen, Novartis, Pfizer, UCB, Forward\u2013The National Databank for Rheumatic Diseases, and NIH NIAMS. PS has received grants and research support from AbbVie, Celgene, Chugai, Janssen-Cilag, Eli Lilly, Novartis, Pfizer, and UCB, and has received consulting fees from AbbVie, Biogen, Bristol Myers Squibb, Celgene, Chugai, Hexal, Janssen-Cilag, Eli Lilly, Novartis, Pfizer, Roche, Sanofi-Genzyme, Swedish Orphan Biovitrum, and UCB, and has received speaker fees from AbbVie, Biogen, Bristol Myers Squibb, Celgene, Chugai, Hexal, Janssen-Cilag, Eli Lilly, Novartis, Pfizer, Roche, Sanofi-Genzyme, Swedish Orphan Biovitrum, and UCB. YD, LS, YS, SZ, YX, and RL are full-time employees of AbbVie and may hold AbbVie stock and\/or stock options; MK has received speaker fees from AbbVie, Amgen K.K., Asahi Kasei, AYUMI Pharmaceutical Corporation, Bristol Myers Squibb, Chugai, Daiichi Sankyo, Eisai, Eli Lilly, Gilead Sciences, Janssen, Mitsubishi-Tanabe, Novartis, and UCB.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"2"}}