Lupus or not? SLE Risk Probability Index (SLERPI): a simple, clinician-friendly machine learning-based model to assist the diagnosis of systemic lupus erythematosus
Open Access
- 10 February 2021
- journal article
- research article
- Published by BMJ in Annals Of The Rheumatic Diseases
- Vol. 80 (6), 758-766
- https://doi.org/10.1136/annrheumdis-2020-219069
Abstract
Objectives Diagnostic reasoning in systemic lupus erythematosus (SLE) is a complex process reflecting the probability of disease at a given timepoint against competing diagnoses. We applied machine learning in well-characterised patient data sets to develop an algorithm that can aid SLE diagnosis. Methods From a discovery cohort of randomly selected 802 adults with SLE or control rheumatologic diseases, clinically selected panels of deconvoluted classification criteria and non-criteria features were analysed. Feature selection and model construction were done with Random Forests and Least Absolute Shrinkage and Selection Operator-logistic regression (LASSO-LR). The best model in 10-fold cross-validation was tested in a validation cohort (512 SLE, 143 disease controls). Results A novel LASSO-LR model had the best performance and included 14 variably weighed features with thrombocytopenia/haemolytic anaemia, malar/maculopapular rash, proteinuria, low C3 and C4, antinuclear antibodies (ANA) and immunologic disorder being the strongest SLE predictors. Our model produced SLE risk probabilities (depending on the combination of features) correlating positively with disease severity and organ damage, and allowing the unbiased classification of a validation cohort into diagnostic certainty levels (unlikely, possible, likely, definitive SLE) based on the likelihood of SLE against other diagnoses. Operating the model as binary (lupus/not-lupus), we noted excellent accuracy (94.8%) for identifying SLE, and high sensitivity for early disease (93.8%), nephritis (97.9%), neuropsychiatric (91.8%) and severe lupus requiring immunosuppressives/biologics (96.4%). This was converted into a scoring system, whereby a score >7 has 94.2% accuracy. Conclusions We have developed and validated an accurate, clinician-friendly algorithm based on classical disease features for early SLE diagnosis and treatment to improve patient outcomes.Keywords
Funding Information
- H2020 European Research Council (742390)
- Foundation for Research in Rheumatology (016BertsiasPrecl)
- Pancretan Health Association
- Hellenic Society of Rheumatology & Professionals Union of Rheumatologists of Greece (644)
This publication has 49 references indexed in Scilit:
- Diagnostic criteria for systemic lupus erythematosus: has the time come?Nature Reviews Rheumatology, 2013
- Derivation and validation of the Systemic Lupus International Collaborating Clinics classification criteria for systemic lupus erythematosusArthritis & Rheumatism, 2012
- Undifferentiated CTD: A wide spectrum of autoimmune diseasesBest Practice & Research Clinical Rheumatology, 2012
- SLE diagnosis and treatment: When early is earlyAutoimmunity Reviews, 2010
- Long‐term mortality and renal outcome in a cohort of 100 patients with Lupus NephritisArthritis Care & Research, 2010
- MALDI-TOF MS combined with magnetic beads for detecting serum protein biomarkers and establishment of boosting decision tree model for diagnosis of systemic lupus erythematosusRheumatology, 2009
- Deterministic versus evidence-based attitude towards clinical diagnosisJournal of Evaluation in Clinical Practice, 2007
- BILAG 2004. Development and initial validation of an updated version of the British Isles Lupus Assessment Group's disease activity index for patients with systemic lupus erythematosusRheumatology, 2005
- Updating the American college of rheumatology revised criteria for the classification of systemic lupus erythematosusArthritis & Rheumatism, 1997
- The development and initial validation of the systemic lupus international collaborating clinics/American college of rheumatology damage index for systemic lupus erythematosusArthritis & Rheumatism, 1996