Novel Multiclass Classification Machine Learning Approach for the Early-stage Classification of Systemic Autoimmune Rheumatic Diseases

Overview

Journal Lupus Sci Med

Specialties Allergy & Immunology
Rheumatology

Date 2024 Feb 1

PMID 38302133

Authors

Yun Wang

Wei Wei

Renren Ouyang

Rujia Chen

Ting Wang

Xu Yuan

Feng Wang

Hongyan Hou

Shiji Wu

Affiliations

Soon will be listed here.

Abstract

Objective: Systemic autoimmune rheumatic diseases (SARDs) encompass a diverse group of complex conditions with overlapping clinical features, making accurate diagnosis challenging. This study aims to develop a multiclass machine learning (ML) model for early-stage SARDs classification using accessible laboratory indicators.

Methods: A total of 925 SARDs patients were included, categorised into SLE, Sjögren's syndrome (SS) and inflammatory myositis (IM). Clinical characteristics and laboratory markers were collected and nine key indicators, including anti-dsDNA, anti-SS-A60, anti-Sm/nRNP, antichromatin, anti-dsDNA (indirect immunofluorescence assay), haemoglobin (Hb), platelet, neutrophil percentage and cytoplasmic patterns (AC-19, AC-20), were selected for model building. Various ML algorithms were used to construct a tripartite classification ML model.

Results: Patients were divided into two cohorts, cohort 1 was used to construct a tripartite classification model. Among models assessed, the random forest (RF) model demonstrated superior performance in distinguishing SLE, IM and SS (with area under curve=0.953, 0.903 and 0.836; accuracy= 0.892, 0.869 and 0.857; sensitivity= 0.890, 0.868 and 0.795; specificity= 0.910, 0.836 and 0.748; positive predictive value=0.922, 0.727 and 0.663; and negative predictive value= 0.854, 0.915 and 0.879). The RF model excelled in classifying SLE (precision=0.930, recall=0.985, F1 score=0.957). For IM and SS, RF model outcomes were (precision=0.793, 0.950; recall=0.920, 0.679; F1 score=0.852, 0.792). Cohort 2 served as an external validation set, achieving an overall accuracy of 87.3%. Individual classification performances for SLE, SS and IM were excellent, with precision, recall and F1 scores specified. SHAP analysis highlighted significant contributions from antibody profiles.

Conclusion: This pioneering multiclass ML model, using basic laboratory indicators, enhances clinical feasibility and demonstrates promising potential for SARDs classification. The collaboration of clinical expertise and ML offers a nuanced approach to SARDs classification, with potential for enhanced patient care.

References

Szekanecz Z, McInnes I, Schett G, Szamosi S, Benko S, Szucs G . Autoinflammation and autoimmunity across rheumatic and musculoskeletal diseases. Nat Rev Rheumatol. 2021; 17(10):585-595. DOI: 10.1038/s41584-021-00652-9. View

Pons-Estel G, Ugarte-Gil M, Harvey G, Wojdyla D, Quintana R, Saurit V . Applying the 2019 EULAR/ACR lupus criteria to patients from an established cohort: a Latin American perspective. RMD Open. 2020; 6(1). PMC: 6999682. DOI: 10.1136/rmdopen-2019-001097. View

Gatto M, Iaccarino L, Ghirardello A, Punzi L, Doria A . Clinical and pathologic considerations of the qualitative and quantitative aspects of lupus nephritogenic autoantibodies: A comprehensive review. J Autoimmun. 2016; 69:1-11. DOI: 10.1016/j.jaut.2016.02.003. View

Giacomelli R, Afeltra A, Alunno A, Baldini C, Bartoloni-Bocci E, Berardicurti O . International consensus: What else can we do to improve diagnosis and therapeutic strategies in patients affected by autoimmune rheumatic diseases (rheumatoid arthritis, spondyloarthritides, systemic sclerosis, systemic lupus erythematosus,.... Autoimmun Rev. 2017; 16(9):911-924. DOI: 10.1016/j.autrev.2017.07.012. View

Choi M, Chen I, Clarke A, Fritzler M, Buhler K, Urowitz M . Machine learning identifies clusters of longitudinal autoantibody profiles predictive of systemic lupus erythematosus disease outcomes. Ann Rheum Dis. 2023; 82(7):927-936. PMC: 11293954. DOI: 10.1136/ard-2022-223808. View

Ehrenstein M, Shipa M . SLE is not a one-size-fits-all disease. J Exp Med. 2023; 220(6). PMC: 10130747. DOI: 10.1084/jem.20230559. View

Agmon-Levin N, Damoiseaux J, Kallenberg C, Sack U, Witte T, Herold M . International recommendations for the assessment of autoantibodies to cellular antigens referred to as anti-nuclear antibodies. Ann Rheum Dis. 2013; 73(1):17-23. DOI: 10.1136/annrheumdis-2013-203863. View

Hochberg M . Updating the American College of Rheumatology revised criteria for the classification of systemic lupus erythematosus. Arthritis Rheum. 1997; 40(9):1725. DOI: 10.1002/art.1780400928. View

Li J, Liu K, Ji Z, Wang Y, Yin T, Long T . Serum untargeted metabolomics reveal metabolic alteration of non-small cell lung cancer and refine disease detection. Cancer Sci. 2022; 114(2):680-689. PMC: 9899604. DOI: 10.1111/cas.15629. View

10.

Pinal-Fernandez I, Casal-Dominguez M, Derfoul A, Pak K, Miller F, Milisenda J . Machine learning algorithms reveal unique gene expression profiles in muscle biopsies from patients with different types of myositis. Ann Rheum Dis. 2020; 79(9):1234-1242. PMC: 10461844. DOI: 10.1136/annrheumdis-2019-216599. View

11.

Burlina P, Billings S, Joshi N, Albayda J . Automated diagnosis of myositis from muscle ultrasound: Exploring the use of machine learning and deep learning methods. PLoS One. 2017; 12(8):e0184059. PMC: 5576677. DOI: 10.1371/journal.pone.0184059. View

12.

Lisnevskaia L, Murphy G, Isenberg D . Systemic lupus erythematosus. Lancet. 2014; 384(9957):1878-1888. DOI: 10.1016/S0140-6736(14)60128-8. View

13.

Kedra J, Davergne T, Braithwaite B, Servy H, Gossec L . Machine learning approaches to improve disease management of patients with rheumatoid arthritis: review and future directions. Expert Rev Clin Immunol. 2021; 17(12):1311-1321. DOI: 10.1080/1744666X.2022.2017773. View

14.

Bertsias G, Pamfil C, Fanouriakis A, Boumpas D . Diagnostic criteria for systemic lupus erythematosus: has the time come?. Nat Rev Rheumatol. 2013; 9(11):687-94. DOI: 10.1038/nrrheum.2013.103. View

15.

Bellando-Randone S, Matucci-Cerinic M . Very early systemic sclerosis. Best Pract Res Clin Rheumatol. 2019; 33(4):101428. DOI: 10.1016/j.berh.2019.101428. View

16.

Ines L, Silva C, Galindo M, Lopez-Longo F, Terroso G, Romao V . Classification of Systemic Lupus Erythematosus: Systemic Lupus International Collaborating Clinics Versus American College of Rheumatology Criteria. A Comparative Study of 2,055 Patients From a Real-Life, International Systemic Lupus Erythematosus.... Arthritis Care Res (Hoboken). 2015; 67(8):1180-5. DOI: 10.1002/acr.22539. View

17.

Adamichou C, Genitsaridi I, Nikolopoulos D, Nikoloudaki M, Repa A, Bortoluzzi A . Lupus or not? SLE Risk Probability Index (SLERPI): a simple, clinician-friendly machine learning-based model to assist the diagnosis of systemic lupus erythematosus. Ann Rheum Dis. 2021; 80(6):758-766. PMC: 8142436. DOI: 10.1136/annrheumdis-2020-219069. View

18.

Obermeyer Z, Emanuel E . Predicting the Future - Big Data, Machine Learning, and Clinical Medicine. N Engl J Med. 2016; 375(13):1216-9. PMC: 5070532. DOI: 10.1056/NEJMp1606181. View

19.

Damoiseaux J, Andrade L, Carballo O, Conrad K, Francescantonio P, Fritzler M . Clinical relevance of HEp-2 indirect immunofluorescent patterns: the International Consensus on ANA patterns (ICAP) perspective. Ann Rheum Dis. 2019; 78(7):879-889. PMC: 6585284. DOI: 10.1136/annrheumdis-2018-214436. View

20.

Soret P, Le Dantec C, Desvaux E, Foulquier N, Chassagnol B, Hubert S . A new molecular classification to drive precision treatment strategies in primary Sjögren's syndrome. Nat Commun. 2021; 12(1):3523. PMC: 8192578. DOI: 10.1038/s41467-021-23472-7. View