Lupus & antiphospholipid syndrome

Machine learning improves 10-year prediction of atherosclerotic plaque progression and cardiovascular events in systemic lupus erythematosus

Rheumatology (Oxford)Published prospective 10-year follow-up carotid and femoral ultrasound study

Authors' conclusion

Conventional and SLE-adapted tools underestimate CVD events and atherosclerosis progression risk in SLE. A machine learning-based model incorporating disease-specific and traditional cardiovascular risk factors into QRISK3 improves CVD risk stratification.

Study context

Population
Patients with systemic lupus erythematosus (SLE) without prior cardiovascular disease (CVD) eventspatients with 10-year ultrasonography follow-up (91% female, median age: 43.0 years)
Participants
111 patientsEvents: 53 (47.7%) developed new plaques, and 8 (7.2%) had incident CVD events
Predictors
11 CVD risk scores (7 conventional, 4 SLE-adapted); a machine learning-based gradient boosting model integrating QRISK3 with disease-related risk factors (disease duration, cumulative glucocorticoid dose, DORIS achievement, antiphospholipid antibodies, hydroxychloroquine) and additional traditional CVD risk factors (physical activity, waist circumference)
Predicted outcome
10-year cardiovascular disease (CVD) events and atherosclerotic plaque progression
Methodological detailsmachine learning-based gradient boosting model developed and internally validated, logistic regression and time-to-event analyses
  • Machine learning-based gradient boosting model developed and internally validated
  • Logistic regression and time-to-event analyses

Model performance

As reported in the abstract

All 11 scores: sensitivity

0.00-0.44

All 11 scores: AUC

0.58-0.79

All 11 scores: BS

0.44-0.71

Further findings

Performance of the machine learning-based score

Significantly better performance compared to all evaluated scores

CVD events and/or plaque progression, QRISK3 (multivariable analysis)

QRISK3 HR
1.87
p
P = 0.027
  • QRISK3 was the only tool independently associated with CVD events and/or plaque progression

Original publication

Machine learning improves 10-year prediction of atherosclerotic plaque progression and cardiovascular events in systemic lupus erythematosus. Rheumatology (Oxford). Published 29 October 2026. doi:10.1093/rheumatology/keag607

Composed by AI from the published abstract and checked against it. How Briefs are made →

Get them every week

New studies on this topic in My Week and in your Monday e-mail.

We e-mail you a sign-in link and a code. No password, no spam.