Direct Health Care Costs Differ by SLE Autoantibody Machine Learning Clusters in an International Inception

May Choi¹, Karen Costenbader², Marvin Fritzler¹, Yvan St. Pierre³, Murray Urowitz⁴, John G. Hanly⁵, Caroline Gordon⁶, Sang-Cheol Bae⁷, Juanita Romero-Diaz⁸, Jorge Sanchez-Guerrero⁹, Sasha Bernatsky³, Daniel Wallace¹⁰, David Isenberg¹¹, Anisur Rahman¹², Joan Merrill¹³, Paul R. Fortin¹⁴, Dafna Gladman¹⁵, Ian Bruce¹⁶, Michelle Petri¹⁷, Ellen Ginzler¹⁸, Mary Anne Dooley¹⁹, Rosalind Ramsey-Goldman²⁰, Susan Manzi²¹, Andreas Jonsen²², Graciela S Alarcón²³, Ronald van Vollenhoven²⁴, Cynthia Aranow²⁵, Meggan MacKay²⁵, Guillermo Ruiz-Irastorza²⁶, S. Sam Lim²⁷, Murat Inanc²⁸, Kenneth Kalunian²⁹, Soren Jacobsen³⁰, Christine Peschken³¹, Diane L. Kamen³², Anca Askanase³³, Jill Buyon³⁴ and Ann Clarke³⁵, ¹University of Calgary, Calgary, AB, Canada, ²Brigham and Women's Hospital and Harvard Medical School, Boston, MA, ³Research Institute of the McGill University Health Centre, Montreal, QC, Canada, ⁴Schroeder Arthritis Institute, Krembil Research Institute; University of Toronto Lupus Clinic; Division of Rheumatology, Toronto, ON, Canada, ⁵Dalhousie University, Halifax, NS, Canada, ⁶Institute of Inflammation and Ageing, University of Birmingham, Birmingham, United Kingdom, ⁷Hanyang University Hospital for Rheumatic Diseases and Hanyang University Institute for Rheumatology Research, Department of Rheumatology, Seoul, South Korea, ⁸Instituto Nacional de Ciencias Medicas y Nutricion Salvador Zubiran, Mexico City, Mexico, ⁹University Health Network, Toronto, ON, Canada, ¹⁰Cedars-Sinai Medical Center, Los Angeles, CA, ¹¹University College London, London, United Kingdom, ¹²Centre for Rheumatology, Division of Medicine, University College London, London, United Kingdom, ¹³Oklahoma Medical Research Foundation, Oklahoma City, OK, ¹⁴Centre ARThrite - CHU de Québec - Université Laval, Quebec City, QC, Canada, ¹⁵Schroeder Arthritis Institute, Krembil Research Institute, Toronto Western Hospital, Department of Medicine, University of Toronto, Toronto, ON, Canada, ¹⁶University of Manchester, Manchester, United Kingdom, ¹⁷Department of Medicine, Division of Rheumatology, Johns Hopkins University School of Medicine, Timonium, MD, ¹⁸SUNY Downstate Health Sciences University, Brooklyn, NY, ¹⁹Raleigh Neurology Associates, Chapel Hill, NC, ²⁰Northwestern University, Chicago, IL, ²¹Lupus Center of Excellence, Autoimmunity Institute, Allegheny Health Network, Pittsburgh, PA, ²²Rheumatology, Department of Clinical Sciences, Lund University, Lund, Sweden, ²³Heersink School of Medicine. The University of Alabama at Birmingham, Birmingham, AL, ²⁴Amsterdam University Medical Centers, Amsterdam, Netherlands, ²⁵Feinstein Institutes for Medical Research, Manhasset, NY, ²⁶Hospital Universitario Cruces, Barakaldo, Spain, ²⁷Emory University, Atlanta, GA, ²⁸Division of Rheumatology, Department of Internal Medicine, Istanbul Faculty of Medicine, Istanbul University, Istanbul, Turkey, ²⁹University of California San Diego, La Jolla, CA, ³⁰Rigshospitalet, Copenhagen, Denmark, ³¹University of Manitoba, Winnipeg, MB, Canada, ³²Medical University of South Carolina, Charleston, SC, ³³Columbia University Medical Center, New York, NY, ³⁴NYU Grossman School of Medicine, New York, NY, ³⁵University of Calgary, Division of Rheumatology, Cumming School of Medicine, Calgary, AB, Canada

Meeting: ACR Convergence 2023

Keywords: Autoantibody(ies), Economics, Health Services Research, Systemic lupus erythematosus (SLE)

Session Information

Date: Tuesday, November 14, 2023

Title: (2257–2325) SLE – Diagnosis, Manifestations, & Outcomes Poster III

Session Type: Poster Session C

Session Time: 9:00AM-11:00AM

Background/Purpose: Using machine learning, we identified 4 patient clusters based on longitudinal autoantibody profiles in an international SLE inception cohort, which were predictive of disease outcomes (Ann Rheum Dis 2023). We now compare direct and indirect costs between these SLE clusters to elucidate healthcare utilization patterns in SLE.

Methods: Patients fulfilling the 1997 Revised ACR SLE Classification Criteria from 33 centres (11 countries) were enrolled within 15 months of diagnosis and clustered by k-means using longitudinal 29 ANA immunofluorescence pattern and 20 autoantibody profiles. Data were collected annually on health care use (i.e., hospitalizations, medications, dialysis, and selected procedures, as well as SLE antibodies, organ involvement, activity [adjusted mean SLEDAI-2K] and medication use), supplemented by data on additional resource use and lost work-force/non-work-force productivity in a patient subset. Multiple imputation was used to predict all missing values for the patients in the full cohort who did not provide direct/indirect costs for all observations. Health care use was costed using 2023 Canadian prices and lost productivity using Statistics Canada age-and-sex specific wages. Average annual costs over follow up were compared between clusters using multivariable regressions, adjusting for significant predictors for direct and indirect costs.

Results: Of 1800+ patients enrolled in the SLICC cohort, 805 subjects were included in the SLE clusters and provided cost data (Table 1). Mean follow-up time for the entire cohort was 12.3 years (range 2.9-21.6 years) and similar across clusters. There were no clear differences in direct and indirect costs and component costs between clusters 1 (high frequency of anti-Sm/anti-U1RNP, predictive of high cumulative disease activity and immunosuppressant/biologic use), 2 (low autoantibody reactivity, predictive of low disease activity and immunosuppressant/biologic use), and 4 (multiple autoantibody reactivities, predictive of high disease activity). Thus, these 3 clusters were combined and compared with cluster 3 (highest frequency of all antiphospholipid antibodies [IgM/IgG anti-cardiolipin, -ß2GP1, -PS/PT, IgG anti-ß2GP1D1, lupus anticoagulant], predictive of seizures and mortality) using multivariable regressions. Cluster 3 had higher total direct costs than clusters 1, 2, and 4 combined ($9288 vs $7061; adj. diff. $2852 [95%CI $196, $5510]), particularly for hospitalizations ($2134 vs $1320; adj. diff. $1158 [95%CI $455, $1860]) (Table 2). Cluster 3 had significantly more hospitalizations for thrombotic/cardiovascular (CVD) events compared to combined clusters (2-sample test of proportions, 22.7% vs. 4.1%, diff. 18.6% [95%CI 6.0%, 31.3%]) (Fig1).

Conclusion: Machine learning based on autoantibodies alone identified a patient cluster with high antiphospholipid antibody frequency who incurred the greatest direct costs, a high proportion driven by hospitalizations due to thrombosis/CVD-related events. Even clusters with severe SLE did not incur such high cost, suggesting thrombotic and antiphospholipid-related complications are important contributors to the economic burden of SLE.

Figure 1. Reasons for Hospitalization Cluster 3 vs. Combined Clusters 1, 2, and 4. There was a higher proportion of hospitalizations for thrombotic events (e.g., myocardial infarction, stroke, pulmonary embolism) for Cluster 3 (*** p<0.001) compared to Combined Clusters 1, 2, and 4.

Disclosures: M. Choi: AbbVie/Abbott, 2, 6, Amgen, 2, 6, AstraZeneca, 2, 6, Bristol-Myers Squibb(BMS), 2, 6, Celgene, 2, 6, Eli Lilly, 2, 6, GlaxoSmithKlein(GSK), 2, Janssen, 2, 6, Mallinckrodt, 2, Merck/MSD, 2, MitogenDx, 2, Organon, 6, Pfizer, 2, 6, Roche, 2, Werfen, 2; K. Costenbader: Amgen, 2, 5, AstraZeneca, 5, Bristol-Myers Squibb(BMS), 2, Cabaletta, 2, Eli Lilly, 2, Exagen Diagnostics, 5, Gilead, 5, GlaxoSmithKlein(GSK), 2, 5, Janssen, 2, 5; M. Fritzler: None; Y. St. Pierre: None; M. Urowitz: None; J. Hanly: None; C. Gordon: AbbVie, 2, Alumis, 2, Amgen, 2, AstraZeneca, 2, Sanofi, 2, UCB Pharma, 2; S. Bae: None; J. Romero-Diaz: None; J. Sanchez-Guerrero: None; S. Bernatsky: None; D. Wallace: None; D. Isenberg: None; A. Rahman: None; J. Merrill: AbbVie, 2, Alexion, 2, Alumis, 2, Amgen, 2, AstraZeneca, 2, 5, Aurinia, 2, Bristol Myers Squibb, 2, 5, EMD Serono, 2, Genentech, 2, Gilead, 2, GlaxoSmithKline, 2, 5, Lilly, 2, Merck, 2, Pfizer, 2, Provention, 2, Remegen, 2, Sanofi, 2, UCB Pharma, 2, Zenas, 2; P. Fortin: AbbVie, 1, AstraZeneca, 1, 6, GlaxoSmithKlein(GSK), 1, 6, Roche-Genentech, 1; D. Gladman: AbbVie, 2, 5, Amgen, 2, 5, Bristol Myers Squibb, 2, Celgene, 2, 5, Eli Lilly, 2, 5, Galapagos, 2, Gilead Sciences, 2, Janssen, 2, 5, Novartis, 2, 5, Pfizer Inc, 2, 5, UCB, 2, 5; I. Bruce: AstraZeneca, 1, 2, 5, 6, Aurinia, 2, GSK, 1, 2, 5, 6, Janssen, 5, 6, Lilly, 1, UCB, 6; M. Petri: Alexion, 1, Amgen, 1, AnaptysBio, 1, Annexon Bio, 1, Argenx, 1, Arhros-Focus Med/Ed, 6, AstraZeneca, 1, 5, Aurinia, 1, 5, 6, Axdev, 1, Biogen, 1, Boxer Capital, 2, Cabaletto Bio, 2, Caribou Biosciences, 2, CVS Health, 1, Eli Lilly, 1, 5, Emergent Biosolutions, 1, Exagen, 5, Exo Therapeutics, 2, Gilead Biosciences, 2, GlaxoSmithKlein(GSK), 1, 5, 6, Horizon Therapeutics, 2, Idorsia Pharmaceuticals, 2, IQVIA, 1, Janssen, 1, 5, Kira Pharmaceuticals, 2, MedShr, 6, Merck/EMD Serono, 1, Momenta Pharmaceuticals, 2, Nexstone Immunology, 2, Nimbus Lakshmi, 2, Proviant, 2, Sanofi, 2, Sinomab Biosciences, 2, Thermofisher, 5, UCB, 2; E. Ginzler: None; M. Dooley: None; R. Ramsey-Goldman: Ampel Solutions, 2, Calabetta, 2, Exagen, 2, Immunocor, 6; S. Manzi: AbbVie, 5, Allegheny Singer Research Institute, 10, AstraZeneca, 2, 5, Exagen Diagnostics, Inc, 2, 9, 10, GSK, 2, 5, Lilly, 2, Lupus Foundation of America, 4, Novartis, 2, UCB Advisory Board, 2, Univiersity of Pittsburgh, 10; A. Jonsen: None; G. Alarcón: None; R. van Vollenhoven: AbbVie, 2, 6, AstraZeneca, 2, 5, 6, Biogen, 6, Bristol-Myers Squibb(BMS), 2, 5, 6, Galapagos, 2, 5, 6, GlaxoSmithKline, 6, Janssen, 2, 6, MSD/Merck Sharp and Dohme, 5, Novartis, 5, Pfizer, 2, 5, 6, RemeGen, 2, Roche, 5, Sanofi, 5, UCB, 2, 5, 6; C. Aranow: AstraZeneca, 2, Bristol-Myers Squibb(BMS), 2, GlaxoSmithKlein(GSK), 2, 5, kezar Inc, 2; M. MacKay: None; G. Ruiz-Irastorza: None; S. Lim: None; M. Inanc: None; K. Kalunian: AbbVie/Abbott, 2, Amgen, 5, AstraZeneca, 2, Aurinia, 2, Bristol-Myers Squibb(BMS), 2, Eli Lilly, 2, EquilliumBio, 2, Genentech, 2, Gilead, 2, Janssen, 2, KezarBio, 1, Merck/MSD, 2, Novartis, 2, Pfizer, 2, Remegene, 2, Roche, 2, UCB, 5; S. Jacobsen: None; C. Peschken: AstraZeneca, 2, 5, GSK, 2, 5, Roche, 1, 2; D. Kamen: None; A. Askanase: AbbVie, 2, Amgen, 2, AstraZeneca, 2, Aurinia, 2, Bristol-Myers Squibb, 2, Celgene, 2, Eli Lilly, 2, Genentech, 2, GSK, 2, Idorsia, 2, Janssen, 2, Mallinckrodt, 2, Pfizer, 2, UCB Pharma, 2; J. Buyon: Bristol-Myers Squibb(BMS), 2, GlaxoSmithKlein(GSK), 2, Related Sciences, 1; A. Clarke: AstraZeneca, 2, Bristol-Myers Squibb(BMS), 2, GlaxoSmithKlein(GSK), 2, 5, Otsuka, 2, Roche, 2.

To cite this abstract in AMA style:

Choi M, Costenbader K, Fritzler M, St. Pierre Y, Urowitz M, Hanly J, Gordon C, Bae S, Romero-Diaz J, Sanchez-Guerrero J, Bernatsky S, Wallace D, Isenberg D, Rahman A, Merrill J, Fortin P, Gladman D, Bruce I, Petri M, Ginzler E, Dooley M, Ramsey-Goldman R, Manzi S, Jonsen A, Alarcón G, van Vollenhoven R, Aranow C, MacKay M, Ruiz-Irastorza G, Lim S, Inanc M, Kalunian K, Jacobsen S, Peschken C, Kamen D, Askanase A, Buyon J, Clarke A. Direct Health Care Costs Differ by SLE Autoantibody Machine Learning Clusters in an International Inception [abstract]. Arthritis Rheumatol. 2023; 75 (suppl 9). https://acrabstracts.org/abstract/direct-health-care-costs-differ-by-sle-autoantibody-machine-learning-clusters-in-an-international-inception/. Accessed .

« Back to ACR Convergence 2023

ACR Meeting Abstracts - https://acrabstracts.org/abstract/direct-health-care-costs-differ-by-sle-autoantibody-machine-learning-clusters-in-an-international-inception/