Systemic lupus erythematosus (SLE) is a clinically and immunologically heterogeneous autoimmune disease that can be challenging to diagnose, especially in its early stages. Although developed in the context of clinical studies, evidence suggests that existing classification criteria have high sensitivity and specificity for identifying SLE patients in daily practice.^1–3 Under this premise, and using advanced feature selection and machine learning methodologies, we found that a combination of simple, variably weighted clinical and serological features could provide high accuracy for the identification and diagnosis of SLE patients, including those with early, organ-dominant, or severe forms of the disease.⁴ The new tool, SLE Risk Probability Index (SLERPI), can operate both in binary (SLE or not-SLE) and probabilistic formats, enabling the monitoring of individuals at risk for connective tissue disease/SLE.⁴ Subsequent validation studies by various groups in different regions and settings have confirmed the high sensitivity (with sufficient specificity) of SLERPI.^{3 5–7} Such approaches, pending further confirmation and calibration, support the endeavour of ultimately developing diagnostic criteria for SLE.

References

1. Aringer M, Costenbader K, Daikh D, et al. 2019 EUropean League Against Rheumatism/American College of Rheumatology classification criteria for systemic lupus erythematosus. Arthritis Rheumatol. 2019;71(9):1400–12. doi: 10.1002/art.40930.

2. Petri M, Orbai AM, Alarcon GS, et al. Derivation and validation of the Systemic Lupus International Collaborating Clinics classification criteria for systemic lupus erythematosus. Arthritis Rheum. 2012;64(8):2677–86. doi: 10.1002/art.34473.

3. Tan BCH, Tang I, Bonin J, et al. The performance of different classification criteria for systemic lupus erythematosus in a real-world rheumatology department. Rheumatology (Oxford). 2022;61(11):4509–13. doi: 10.1093/rheumatology/keac120.

4. Adamichou C, Genitsaridi I, Nikolopoulos D, et al. 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):758–66. doi: 10.1136/annrheumdis-2020-219069.

5. Castaneda-Gonzalez JP, Mogollon Hurtado SA, Rojas-Villarraga A, et al. Comparison of the SLE Risk Probability Index (SLERPI) scale against the EUropean League Against Rheumatism/American College of Rheumatology (ACR/EULAR) and Systemic Lupus International Collaborating Clinics (SLICC) criteria. Lupus. 2024;33(5):520–24. doi: 10.1177/09612033241238053.

6. Zhang L, Lu W, Yan D, et al. Systemic Lupus Erythematosus Risk Probability Index: ready for routine use? Results from a chinese cohort. Lupus Sci Med. 2023;10(2) doi: 10.1136/lupus-2023-000988.

7. Erden A, Apaydin H, Fanouriakis A, et al. Performance of the Systemic Lupus Erythematosus Risk Probability Index in a cohort of undifferentiated connective tissue disease. Rheumatology (Oxford). 2022;61(9):3606–13. doi: 10.1093/rheumatology/keac005.

Learning Objectives At the end of this presentation participants will be able to:

• Explain the differences between the diagnosis and classification of SLE

• Describe the pros and cons of existing classification criteria for SLE

• Describe the methodology towards the development and validation of the SLERPI

• Discuss SLERPI use in clinical practice: case vignettes and real-world performance